Internet Research Task Force (IRTF) J. Hong

Internet Research Task Force (IRTF) J. Hong
Request for Comments: 9556 ETRI
Category: Informational Y-G. Hong
ISSN: 2070-1721 Daejeon University
X. de Foy
InterDigital Communications, LLC
M. Kovatsch
Huawei Technologies Duesseldorf GmbH
E. Schooler
University of Oxford
D. Kutscher
HKUST(GZ)
April 2024

Internet of Things (IoT) Edge Challenges and Functions

Abstract

Many Internet of Things (IoT) applications have requirements that
cannot be satisfied by centralized cloud-based systems (i.e., cloud
computing). These include time sensitivity, data volume,
connectivity cost, operation in the face of intermittent services,
privacy, and security. As a result, IoT is driving the Internet
toward edge computing. This document outlines the requirements of
the emerging IoT edge and its challenges. It presents a general
model and major components of the IoT edge to provide a common basis
for future discussions in the Thing-to-Thing Research Group (T2TRG)
and other IRTF and IETF groups. This document is a product of the
IRTF T2TRG.

Status of This Memo

This document is not an Internet Standards Track specification; it is
published for informational purposes.

This document is a product of the Internet Research Task Force
(IRTF). The IRTF publishes the results of Internet-related research
and development activities. These results might not be suitable for
deployment. This RFC represents the consensus of the Thing-to-Thing
Research Group of the Internet Research Task Force (IRTF). Documents
approved for publication by the IRSG are not candidates for any level
of Internet Standard; see Section 2 of RFC 7841.

Information about the current status of this document, any errata,
and how to provide feedback on it may be obtained at
https://www.rfc-editor.org/info/rfc9556.

Copyright Notice

Copyright (c) 2024 IETF Trust and the persons identified as the
document authors. All rights reserved.

This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents
(https://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents
carefully, as they describe your rights and restrictions with respect
to this document.

Table of Contents

1. Introduction
2. Background
2.1. Internet of Things (IoT)
2.2. Cloud Computing
2.3. Edge Computing
2.4. Examples of IoT Edge Computing Use Cases
3. IoT Challenges Leading toward Edge Computing
3.1. Time Sensitivity
3.2. Connectivity Cost
3.3. Resilience to Intermittent Services
3.4. Privacy and Security
4. IoT Edge Computing Functions
4.1. Overview of IoT Edge Computing
4.2. General Model
4.3. OAM Components
4.3.1. Resource Discovery and Authentication
4.3.2. Edge Organization and Federation
4.3.3. Multi-Tenancy and Isolation
4.4. Functional Components
4.4.1. In-Network Computation
4.4.2. Edge Storage and Caching
4.4.3. Communication
4.5. Application Components
4.5.1. IoT Device Management
4.5.2. Data Management and Analytics
4.6. Simulation and Emulation Environments
5. Security Considerations
6. Conclusion
7. IANA Considerations
8. Informative References
Acknowledgements
Authors' Addresses

1. Introduction

At the time of writing, many IoT services leverage cloud computing
platforms because they provide virtually unlimited storage and
processing power. The reliance of IoT on back-end cloud computing
provides additional advantages, such as scalability and efficiency.
At the time of writing, IoT systems are fairly static with respect to
integrating and supporting computation. It is not that there is no
computation, but that systems are often limited to static
configurations (edge gateways and cloud services).

However, IoT devices generate large amounts of data at the edges of
the network. To meet IoT use case requirements, data is increasingly
being stored, processed, analyzed, and acted upon close to the data
sources. These requirements include time sensitivity, data volume,
connectivity cost, and resiliency in the presence of intermittent
connectivity, privacy, and security, which cannot be addressed by
centralized cloud computing. A more flexible approach is necessary
to address these needs effectively. This involves distributing
computing (and storage) and seamlessly integrating it into the edge-
cloud continuum. We refer to this integration of edge computing and
IoT as "IoT edge computing". This document describes the related
background, use cases, challenges, system models, and functional
components.

Owing to the dynamic nature of the IoT edge computing landscape, this
document does not list existing projects in this field. Section 4.1
presents a high-level overview of the field based on a limited review
of standards, research, and open-source and proprietary products in
[EDGE-COMPUTING-BACKGROUND].

This document represents the consensus of the Thing-to-Thing Research
Group (T2TRG). It has been reviewed extensively by the research
group members who are actively involved in the research and
development of the technology covered by this document. It is not an
IETF product and is not a standard.

2. Background

2.1. Internet of Things (IoT)

Since the term "Internet of Things" was coined by Kevin Ashton in
1999 while working on Radio-Frequency Identification (RFID)
technology [Ashton], the concept of IoT has evolved. At the time of
writing, it reflects a vision of connecting the physical world to the
virtual world of computers using (often wireless) networks over which
things can send and receive information without human intervention.
Recently, the term has become more literal by connecting things to
the Internet and converging on Internet and web technologies.

A "Thing" is a physical item made available in the IoT, thereby
enabling digital interaction with the physical world for humans,
services, and/or other Things [REST-IOT]. In this document, we will
use the term "IoT device" to designate the embedded system attached
to the Thing.

Resource-constrained Things, such as sensors, home appliances, and
wearable devices, often have limited storage and processing power,
which can create challenges with respect to reliability, performance,
energy consumption, security, and privacy [Lin]. Some, less-
resource-constrained Things, can generate a voluminous amount of
data. This range of factors led to IoT designs that integrate Things
into larger distributed systems, for example, edge or cloud computing
systems.

2.2. Cloud Computing

Cloud computing has been defined in [NIST]:

| Cloud computing is a model for enabling ubiquitous, convenient,
| on-demand network access to a shared pool of configurable
| computing resources (e.g., networks, servers, storage,
| applications, and services) that can be rapidly provisioned and
| released with minimal management effort or service provider
| interaction.

The low cost and massive availability of storage and processing power
enabled the realization of another computing model in which
virtualized resources can be leased in an on-demand fashion and
provided as general utilities. Platform-as-a-Service (PaaS) and
cloud computing platforms widely adopted this paradigm for delivering
services over the Internet, gaining both economical and technical
benefits [Botta].

At the time of writing, an unprecedented volume and variety of data
is generated by Things, and applications deployed at the network edge
consume this data. In this context, cloud-based service models are
not suitable for some classes of applications that require very short
response times, require access to local personal data, or generate
vast amounts of data. These applications may instead leverage edge
computing.

2.3. Edge Computing

Edge computing, also referred to as "fog computing" in some settings,
is a new paradigm in which substantial computing and storage
resources are placed at the edge of the Internet, close to mobile
devices, sensors, actuators, or machines. Edge computing happens
near data sources [Mahadev] as well as close to where decisions are
made or where interactions with the physical world take place
("close" here can refer to a distance that is topological, physical,
latency-based, etc.). It processes both downstream data (originating
from cloud services) and upstream data (originating from end devices
or network elements). The term "fog computing" usually represents
the notion of multi-tiered edge computing, that is, several layers of
compute infrastructure between end devices and cloud services.

An edge device is any computing or networking resource residing
between end-device data sources and cloud-based data centers. In
edge computing, end devices consume and produce data. At the network
edge, devices not only request services and information from the
cloud but also handle computing tasks including processing, storing,
caching, and load balancing on data sent to and from the cloud [Shi].
This does not preclude end devices from hosting computation
themselves, when possible, independently or as part of a distributed
edge computing platform.

Several Standards Developing Organizations (SDOs) and industry forums
have provided definitions of edge and fog computing:

* ISO defines edge computing as a "form of distributed computing in
which significant processing and data storage takes place on nodes
which are at the edge of the network" [ISO_TR].

* ETSI defines multi-access edge computing as a "system which
provides an IT service environment and cloud-computing
capabilities at the edge of an access network which contains one
or more type of access technology, and in close proximity to its
users" [ETSI_MEC_01].

* The Industry IoT Consortium (IIC) (now incorporating what was
formerly OpenFog) defines fog computing as "a horizontal, system-
level architecture that distributes computing, storage, control
and networking functions closer to the users along a cloud-to-
thing continuum" [OpenFog].

Based on these definitions, we can summarize a general philosophy of
edge computing as distributing the required functions close to users
and data, while the difference to classic local systems is the usage
of management and orchestration features adopted from cloud
computing.

Actors from various industries approach edge computing using
different terms and reference models, although, in practice, these
approaches are not incompatible and may integrate with each other:

* The telecommunication industry tends to use a model where edge
computing services are deployed over a Network Function
Virtualization (NFV) infrastructure, at aggregation points, or in
proximity to the user equipment (e.g., gNodeBs) [ETSI_MEC_03].

* Enterprise and campus solutions often interpret edge computing as
an "edge cloud", that is, a smaller data center directly connected
to the local network (often referred to as "on-premise").

* The automation industry defines the edge as the connection point
between IT and Operational Technology (OT). Hence, edge computing
sometimes refers to applying IT solutions to OT problems, such as
analytics, more-flexible user interfaces, or simply having more
computing power than an automation controller.

2.4. Examples of IoT Edge Computing Use Cases

IoT edge computing can be used in home, industry, grid, healthcare,
city, transportation, agriculture, and/or educational scenarios.
Here, we discuss only a few examples of such use cases to identify
differentiating requirements, providing references to other use
cases.

*Smart Factory*
As part of the Fourth Industrial Revolution, smart factories run
real-time processes based on IT technologies, such as artificial
intelligence and big data. Even a very small environmental change
in a smart factory can lead to a situation in which production
efficiency decreases or product quality problems occur.
Therefore, simple but time-sensitive processing can be performed
at the edge, for example, controlling the temperature and humidity
in the factory or operating machines based on the real-time
collection of the operational status of each machine. However,
data requiring highly precise analysis, such as machine life-cycle
management or accident risk prediction, can be transferred to a
central data center for processing.

The use of edge computing in a smart factory [Argungu] can reduce
the cost of network and storage resources by reducing the
communication load to the central data center or server. It is
also possible to improve process efficiency and facility asset
productivity through real-time prediction of failures and to
reduce the cost of failure through preliminary measures. In the
existing manufacturing field, production facilities are manually
run according to a program entered in advance; however, edge
computing in a smart factory enables tailoring solutions by
analyzing data at each production facility and machine level.
Digital twins [Jones] of IoT devices have been jointly used with
edge computing in industrial IoT scenarios [Chen].

*Smart Grid*
In future smart-city scenarios, the smart grid will be critical in
ensuring highly available and efficient energy control in city-
wide electricity management [Mehmood]. Edge computing is expected
to play a significant role in these systems to improve the
transmission efficiency of electricity, to react to and restore
power after a disturbance, to reduce operation costs, and to reuse
energy effectively since these operations involve local decision-
making. In addition, edge computing can help monitor power
generation and power demand and make local electrical energy
storage decisions in smart grid systems.

*Smart Agriculture*
Smart agriculture integrates information and communication
technologies with farming technology. Intelligent farms use IoT
technology to measure and analyze parameters, such as the
temperature, humidity, sunlight, carbon dioxide, and soil quality,
in crop cultivation facilities. Depending on the analysis
results, control devices are used to set the environmental
parameters to an appropriate state. Remote management is also
possible through mobile devices, such as smartphones.

In existing farms, simple systems, such as management according to
temperature and humidity, can be easily and inexpensively
implemented using IoT technology [Tanveer]. Field sensors gather
data on field and crop condition. This data is then transmitted
to cloud servers that process data and recommend actions. The use
of edge computing can reduce the volume of back-and-forth data
transmissions significantly, resulting in cost and bandwidth
savings. Locally generated data can be processed at the edge, and
local computing and analytics can drive local actions. With edge
computing, it is easy for farmers to select large amounts of data
for processing, and data can be analyzed even in remote areas with
poor access conditions. Other applications include enabling
dashboarding, for example, to visualize the farm status, as well
as enhancing Extended Reality (XR) applications that require edge
audio and/or video processing. As the number of people working on
farming has been decreasing over time, increasing automation
enabled by edge computing can be a driving force for future smart
agriculture [OGrady].

*Smart Construction*
Safety is critical at construction sites. Every year, many
construction workers lose their lives because of falls,
collisions, electric shocks, and other accidents [BigRentz].
Therefore, solutions have been developed to improve construction
site safety, including the real-time identification of workers,
monitoring of equipment location, and predictive accident
prevention. To deploy these solutions, many cameras and IoT
sensors have been installed on construction sites to measure
noise, vibration, gas concentration, etc. Typically, the data
generated from these measurements is collected in on-site gateways
and sent to remote cloud servers for storage and analysis. Thus,
an inspector can check the information stored on the cloud server
to investigate an incident. However, this approach can be
expensive because of transmission costs (for example, of video
streams over a mobile network connection) and because usage fees
of private cloud services.

Using edge computing [Yue], data generated at the construction
site can be processed and analyzed on an edge server located
within or near the site. Only the result of this processing needs
to be transferred to a cloud server, thus reducing transmission
costs. It is also possible to locally generate warnings to
prevent accidents in real time.

*Self-Driving Car*
Edge computing plays a crucial role in safety-focused self-driving
car systems [Badjie]. With a multitude of sensors, such as high-
resolution cameras, radars, Light Detection and Ranging (LiDAR)
systems, sonar sensors, and GPS systems, autonomous vehicles
generate vast amounts of real-time data. Local processing
utilizing edge computing nodes allows for efficient collection and
analysis of this data to monitor vehicle distances and road
conditions and respond promptly to unexpected situations.
Roadside computing nodes can also be leveraged to offload tasks
when necessary, for example, when the local processing capacity of
the car is insufficient because of hardware constraints or a large
data volume.

For instance, when the car ahead slows, a self-driving car adjusts
its speed to maintain a safe distance, or when a roadside signal
changes, it adapts its behavior accordingly. In another example,
cars equipped with self-parking features utilize local processing
to analyze sensor data, determine suitable parking spots, and
execute precise parking maneuvers without relying on external
processing or connectivity. It is also possible to use in-cabin
cameras coupled with local processing to monitor the driver's
attention level and detect signs of drowsiness or distraction.
The system can issue warnings or implement preventive measures to
ensure driver safety.

Edge computing empowers self-driving cars by enabling real-time
processing, reducing latency, enhancing data privacy, and
optimizing bandwidth usage. By leveraging local processing
capabilities, self-driving cars can make rapid decisions, adapt to
changing environments, and ensure safer and more efficient
autonomous driving experiences.

*Digital Twin*
A digital twin can simulate different scenarios and predict
outcomes based on real-time data collected from the physical
environment. This simulation capability empowers proactive
maintenance, optimization of operations, and the prediction of
potential issues or failures. Decision makers can use digital
twins to test and validate different strategies, identify
inefficiencies, and optimize performance [CertMagic].

With edge computing, real-time data is collected, processed, and
analyzed directly at the edge, allowing for the accurate
monitoring and simulation of physical assets. Moreover, edge
computing effectively minimizes latency, enabling rapid responses
to dynamic conditions as computational resources are brought
closer to the physical object. Running digital twin processing at
the edge enables organizations to obtain timely insights and make
informed decisions that maximize efficiency and performance.

*Other Use Cases*
Artificial intelligence (AI) and machine learning (ML) systems at
the edge empower real-time analysis, faster decision-making,
reduced latency, improved operational efficiency, and personalized
experiences across various industries by bringing AI and ML
capabilities closer to edge devices.

In addition, oneM2M has studied several IoT edge computing use
cases, which are documented in [oneM2M-TR0001], [oneM2M-TR0018],
and [oneM2M-TR0026]. The edge-computing-related requirements
raised through the analysis of these use cases are captured in
[oneM2M-TS0002].

3. IoT Challenges Leading toward Edge Computing

This section describes the challenges faced by the IoT that are
motivating the adoption of edge computing. These are distinct from
the research challenges applicable to IoT edge computing, some of
which are mentioned in Section 4.

IoT technology is used with increasingly demanding applications in
domains such as industrial, automotive, and healthcare, which leads
to new challenges. For example, industrial machines, such as laser
cutters, produce over 1 terabyte of data per hour, and similar
amounts can be generated in autonomous cars [NVIDIA]. 90% of IoT
data is expected to be stored, processed, analyzed, and acted upon
close to the source [Kelly], as cloud computing models alone cannot
address these new challenges [Chiang].

Below, we discuss IoT use case requirements that are moving cloud
capabilities to be more proximate, distributed, and disaggregated.

3.1. Time Sensitivity

Often, many industrial control systems, such as manufacturing
systems, smart grids, and oil and gas systems, require stringent end-
to-end latency between the sensor and control nodes. While some IoT
applications may require latency below a few tens of milliseconds
[Weiner], industrial robots and motion control systems have use cases
for cycle times in the order of microseconds [IEC_IEEE_60802]. In
some cases, speed-of-light limitations may simply prevent cloud-based
solutions; however, this is not the only challenge relative to time
sensitivity. Guarantees for bounded latency and jitter ([RFC8578],
Section 7) are also important for industrial IoT applications. This
means that control packets must arrive with as little variation as
possible and within a strict deadline. Given the best-effort
characteristics of the Internet, this challenge is virtually
impossible to address without using end-to-end guarantees for
individual message delivery and continuous data flows.

3.2. Connectivity Cost

Some IoT deployments may not face bandwidth constraints when
uploading data to the cloud. Theoretically, both 5G and Wi-Fi 6
networks top out at 10 gigabits per second (i.e., 4.5 terabytes per
hour), allowing the transfer of large amounts of uplink data.
However, the cost of maintaining continuous high-bandwidth
connectivity for such usage is unjustifiable and impractical for most
IoT applications. In some settings, for example, in aeronautical
communication, higher communication costs reduce the amount of data
that can be practically uploaded even further. Therefore, minimizing
reliance on high-bandwidth connectivity is a requirement; this can be
done, for example, by processing data at the edge and deriving
summarized or actionable insights that can be transmitted to the
cloud.

3.3. Resilience to Intermittent Services

Many IoT devices, such as sensors, actuators, and controllers, have
very limited hardware resources and cannot rely solely on their own
resources to meet their computing and/or storage needs. They require
reliable, uninterrupted, or resilient services to augment their
capabilities to fulfill their application tasks. This is difficult
and partly impossible to achieve using cloud services for systems
such as vehicles, drones, or oil rigs that have intermittent network
connectivity. Conversely, a cloud backend might want to access
device data even if the device is currently asleep.

3.4. Privacy and Security

When IoT services are deployed at home, personal information can be
learned from detected usage data. For example, one can extract
information about employment, family status, age, and income by
analyzing smart meter data [ENERGY]. Policy makers have begun to
provide frameworks that limit the usage of personal data and impose
strict requirements on data controllers and processors. Data stored
indefinitely in the cloud also increases the risk of data leakage,
for instance, through attacks on rich targets.

It is often argued that industrial systems do not provide privacy
implications, as no personal data is gathered. However, data from
such systems is often highly sensitive, as one might be able to infer
trade secrets, such as the setup of production lines. Hence, owners
of these systems are generally reluctant to upload IoT data to the
cloud.

Furthermore, passive observers can perform traffic analysis on
device-to-cloud paths. Therefore, hiding traffic patterns associated
with sensor networks can be another requirement for edge computing.

4. IoT Edge Computing Functions

We first look at the current state of IoT edge computing
(Section 4.1) and then define a general system model (Section 4.2).
This provides a context for IoT edge computing functions, which are
listed in Sections 4.3, 4.4, and 4.5.

4.1. Overview of IoT Edge Computing

This section provides an overview of the current (at the time of
writing) IoT edge computing field based on a limited review of
standards, research, and open-source and proprietary products in
[EDGE-COMPUTING-BACKGROUND].

IoT gateways, both open-source (such as EdgeX Foundry or Home Edge)
and proprietary products, represent a common class of IoT edge
computing products, where the gateway provides a local service on
customer premises and is remotely managed through a cloud service.
IoT communication protocols are typically used between IoT devices
and the gateway, including a Constrained Application Protocol (CoAP)
[RFC7252], Message Queuing Telemetry Transport (MQTT) [MQTT5], and
many specialized IoT protocols (such as Open Platform Communications
Unified Architecture (OPC UA) and Data Distribution Service (DDS) in
the industrial IoT space), while the gateway communicates with the
distant cloud typically using HTTPS. Virtualization platforms enable
the deployment of virtual edge computing functions (using Virtual
Machines (VMs) and application containers), including IoT gateway
software, on servers in the mobile network infrastructure (at base
stations and concentration points), edge data centers (in central
offices), and regional data centers located near central offices.
End devices are envisioned to become computing devices in forward-
looking projects but are not commonly used at the time of writing.

In addition to open-source and proprietary solutions, a horizontal
IoT service layer is standardized by the oneM2M standards body to
reduce fragmentation, increase interoperability, and promote reuse in
the IoT ecosystem. Furthermore, ETSI Multi-access Edge Computing
(MEC) developed an IoT API [ETSI_MEC_33] that enables the deployment
of heterogeneous IoT platforms and provides a means to configure the
various components of an IoT system.

Physical or virtual IoT gateways can host application programs that
are typically built using an SDK to access local services through a
programmatic API. Edge cloud system operators host their customers'
application VMs or containers on servers located in or near access
networks that can implement local edge services. For example, mobile
networks can provide edge services for radio network information,
location, and bandwidth management.

Resilience in the IoT can entail the ability to operate autonomously
in periods of disconnectedness to preserve the integrity and safety
of the controlled system, possibly in a degraded mode. IoT devices
and gateways are often expected to operate in always-on and
unattended modes, using fault detection and unassisted recovery
functions.

The life-cycle management of services and applications on physical
IoT gateways is generally cloud based. Edge cloud management
platforms and products (such as StarlingX, Akraino Edge Stack, or
proprietary products from major cloud providers) adapt cloud
management technologies (e.g., Kubernetes) to the edge cloud, that
is, to smaller, distributed computing devices running outside a
controlled data center. Typically, the service and application life
cycle is using an NFV-like management and orchestration model.

The platform generally enables advertising or consuming services
hosted on the platform (e.g., the Mp1 interface in ETSI MEC supports
service discovery and communication), and enables communication with
local and remote endpoints (e.g., message routing function in IoT
gateways). The platform is usually extensible to edge applications
because it can advertise a service that other edge applications can
consume. The IoT communication services include protocol
translation, analytics, and transcoding. Communication between edge
computing devices is enabled in tiered or distributed deployments.

An edge cloud platform may enable pass-through without storage or
local storage (e.g., on IoT gateways). Some edge cloud platforms use
distributed storage such as that provided by a distributed storage
platform (e.g., EdgeFS and Ceph) or, in more experimental settings,
by an Information-Centric Networking (ICN) network, for example,
systems such as Chipmunk [Chipmunk] and Kua [Kua] have been proposed
as distributed information-centric objects stores. External storage,
for example, on databases in a distant or local IT cloud, is
typically used for filtered data deemed worthy of long-term storage;
although, in some cases, it may be for all data, for example, when
required for regulatory reasons.

Stateful computing is the default on most systems, VMs, and
containers. Stateless computing is supported on platforms providing
a "serverless computing" service (also known as function-as-
a-service, e.g., using stateless containers) or on systems based on
named function networking.

In many IoT use cases, a typical network usage pattern is a high-
volume uplink with some form of traffic reduction enabled by
processing over edge computing devices. Alternatives to traffic
reduction include deferred transmission (to off-peak hours or using
physical shipping). Downlink traffic includes application control
and software updates. Downlink-heavy traffic patterns are not
excluded but are more often associated with non-IoT usage (e.g.,
video Content Delivery Networks (CDNs)).

4.2. General Model

Edge computing is expected to play an important role in deploying new
IoT services integrated with big data and AI enabled by flexible in-
network computing platforms. Although there are many approaches to
edge computing, this section lays out an attempt at a general model
and lists associated logical functions. In practice, this model can
be mapped to different architectures, such as:

* A single IoT gateway, or a hierarchy of IoT gateways, typically
connected to the cloud (e.g., to extend the centralized cloud-
based management of IoT devices and data to the edge). The IoT
gateway plays a common role in providing access to a heterogeneous
set of IoT devices and sensors, handling IoT data, and delivering
IoT data to its final destination in a cloud network. An IoT
gateway requires interactions with the cloud; however, it can also
operate independently in a disconnected mode.

* A set of distributed computing nodes, for example, embedded in
switches, routers, edge cloud servers, or mobile devices. Some
IoT devices have sufficient computing capabilities to participate
in such distributed systems owing to advances in hardware
technology. In this model, edge computing nodes can collaborate
to share resources.

* A hybrid system involving both IoT gateways and supporting
functions in distributed computing nodes.

In the general model described in Figure 1, the edge computing domain
is interconnected with IoT devices (southbound connectivity),
possibly with a remote (e.g., cloud) network (northbound
connectivity), and with a service operator's system. Edge computing
nodes provide multiple logical functions or components that may not
be present in a given system. They may be implemented in a
centralized or distributed fashion, at the network edge, or through
interworking between the edge network and remote cloud networks.

+---------------------+
| Remote Network | +---------------+
|(e.g., cloud network)| | Service |
+-----------+---------+ | Operator |
| +------+--------+
| |
+--------------+-------------------+-----------+
| Edge Computing Domain |
| |
| One or more computing nodes |
| (IoT gateway, end devices, switches, |
| routers, mini/micro-data centers, etc.) |
| |
| OAM Components |
| - Resource Discovery and Authentication |
| - Edge Organization and Federation |
| - Multi-Tenancy and Isolation |
| - ... |
| |
| Functional Components |
| - In-Network Computation |
| - Edge Caching |
| - Communication |
| - Other Services |
| - ... |
| |
| Application Components |
| - IoT Devices Management |
| - Data Management and Analytics |
| - ... |
| |
+------+--------------+-------- - - - -+- - - -+
| | | | |
| | +-----+--+
+----+---+ +-----+--+ | |Compute | |
| End | | End | ... |Node/End|
|Device 1| |Device 2| ...| |Device n| |
+--------+ +--------+ +--------+
+ - - - - - - - -+

Figure 1: Model of IoT Edge Computing

In the distributed model described in Figure 2, the edge computing
domain is composed of IoT edge gateways and IoT devices that are also
used as computing nodes. Edge computing domains are connected to a
remote (e.g., cloud) network and their respective service operator's
system. The computing nodes provide logical functions, for example,
as part of distributed machine learning or distributed image
processing applications. The processing capabilities in IoT devices
are limited; they require the support of other nodes. In a
distributed machine learning application, the training process for AI
services can be executed at IoT edge gateways or cloud networks, and
the prediction (inference) service is executed in the IoT devices.
Similarly, in a distributed image processing application, some image
processing functions can be executed at the edge or in the cloud. To
limit the amount of data to be uploaded to central cloud functions,
IoT edge devices may pre-process data.

+----------------------------------------------+
| Edge Computing Domain |
| |
| +--------+ +--------+ +--------+ |
| |Compute | |Compute | |Compute | |
| |Node/End| |Node/End| .... |Node/End| |
| |Device 1| |Device 2| .... |Device m| |
| +----+---+ +----+---+ +----+---+ |
| | | | |
| +---+-------------+-----------------+--+ |
| | IoT Edge Gateway | |
| +-----------+-------------------+------+ |
| | | |
+--------------+-------------------+-----------+
| |
+-----------+---------+ +------+-------+
| Remote Network | | Service |
|(e.g., cloud network)| | Operator(s) |
+-----------+---------+ +------+-------+
| |
+--------------+-------------------+-----------+
| | | |
| +-----------+-------------------+------+ |
| | IoT Edge Gateway | |
| +---+-------------+-----------------+--+ |
| | | | |
| +----+---+ +----+---+ +----+---+ |
| |Compute | |Compute | |Compute | |
| |Node/End| |Node/End| .... |Node/End| |
| |Device 1| |Device 2| .... |Device n| |
| +--------+ +--------+ +--------+ |
| |
| Edge Computing Domain |
+----------------------------------------------+

Figure 2: Example of Machine Learning over a Distributed IoT Edge
Computing System

In the following, we enumerate major edge computing domain
components. Here, they are loosely organized into Operations,
Administration, and Maintenance (OAM); functional; and application
components, with the understanding that the distinction between these
classes may not always be clear, depending on actual system
architectures. Some representative research challenges are
associated with those functions. We used input from coauthors,
participants of T2TRG meetings, and some comprehensive reviews of the
field ([Yousefpour], [Zhang2], and [Khan]).

4.3. OAM Components

Edge computing OAM extends beyond the network-related OAM functions
listed in [RFC6291]. In addition to infrastructure (network,
storage, and computing resources), edge computing systems can also
include computing environments (for VMs, software containers, and
functions), IoT devices, data, and code.

Operation-related functions include performance monitoring for
Service Level Agreement (SLA) measurements, fault management, and
provisioning for links, nodes, compute and storage resources,
platforms, and services. Administration covers network/compute/
storage resources, platform and service discovery, configuration, and
planning. Discovery during normal operation (e.g., discovery of
compute or storage nodes by endpoints) is typically not included in
OAM; however, in this document, we do not address it separately.
Management covers the monitoring and diagnostics of failures, as well
as means to minimize their occurrence and take corrective actions.
This may include software update management and high service
availability through redundancy and multipath communication.
Centralized (e.g., Software-Defined Networking (SDN)) and
decentralized management systems can be used. Finally, we
arbitrarily chose to address data management as an application
component; however, in some systems, data management may be
considered similar to a network management function.

We further detail a few relevant OAM components.

4.3.1. Resource Discovery and Authentication

Discovery and authentication may target platforms and infrastructure
resources, such as computing, networking, and storage, as well as
other resources, such as IoT devices, sensors, data, code units,
services, applications, and users interacting with the system. In a
broker-based system, an IoT gateway can act as a broker to discover
IoT resources. More decentralized solutions can also be used in
replacement of or in complement to the broker-based solutions; for
example, CoAP enables multicast discovery of an IoT device and CoAP
service discovery enables one to obtain a list of resources made
available by this device [RFC7252]. For device authentication,
current centralized gateway-based systems rely on the installation of
a secret on IoT devices and computing devices (e.g., a device
certificate stored in a hardware security module or a combination of
code and data stored in a trusted execution environment).

Related challenges include:

* Discovery, authentication, and trust establishment between IoT
devices, compute nodes, and platforms, with regard to concerns
such as mobility, heterogeneous devices and networks, scale,
multiple trust domains, constrained devices, anonymity, and
traceability.

* Intermittent connectivity to the Internet, removing the need to
rely on a third-party authority [Echeverria].

* Resiliency to failure [Harchol], denial-of-service attacks, and
easier physical access for attackers.

4.3.2. Edge Organization and Federation

In a distributed system context, once edge devices have discovered
and authenticated each other, they can be organized or self-organized
into hierarchies or clusters. The organizational structure may range
from centralized to peer-to-peer, or it may be closely tied to other
systems. Such groups can also form federations with other edges or
with remote clouds.

Related challenges include:

* Support for scaling and enabling fault tolerance or self-healing
[Jeong]. In addition to using a hierarchical organization to cope
with scaling, another available and possibly complementary
mechanism is multicast [RFC7390] [CORE-GROUPCOMM-BIS]. Other
approaches include relying on blockchains [Ali].

* Integration of edge computing with virtualized Radio Access
Networks (Fog RAN) [SFC-FOG-RAN] and 5G access networks.

* Sharing resources in multi-vendor and multi-operator scenarios to
optimize criteria such as profit [Anglano], resource usage,
latency, and energy consumption.

* Capacity planning, placement of infrastructure nodes to minimize
delay [Fan], cost, energy, etc.

* Incentives for participation, for example, in peer-to-peer
federation schemes.

* Design of federated AI over IoT edge computing systems [Brecko],
for example, for anomaly detection.

4.3.3. Multi-Tenancy and Isolation

Some IoT edge computing systems make use of virtualized (compute,
storage, and networking) resources to address the need for secure
multi-tenancy at the edge. This leads to "edge clouds" that share
properties with remote clouds and can reuse some of their ecosystems.
Virtualization function management is largely covered by ETSI NFV and
MEC standards and recommendations. Projects such as [LFEDGE-EVE]
further cover virtualization and its management in distributed edge
computing settings.

Related challenges include:

* Adapting cloud management platforms to the edge to account for its
distributed nature, heterogeneity, need for customization, and
limited resources (for example, using Conflict-free Replicated
Data Types (CRDTs) [Jeffery] or intent-based management mechanisms
[Cao]).

* Minimizing virtual function instantiation time and resource usage.

4.4. Functional Components

4.4.1. In-Network Computation

A core function of IoT edge computing is to enable local computation
on a node at the network edge, typically for application-layer
processing, such as processing input data from sensors, making local
decisions, preprocessing data, and offloading computation on behalf
of a device, service, or user. Related functions include
orchestrating computation (in a centralized or distributed manner)
and managing application life cycles. Support for in-network
computation may vary in terms of capability; for example, computing
nodes can host virtual machines, software containers, software
actors, unikernels running stateful or stateless code, or a rule
engine providing an API to register actions in response to conditions
(such as an IoT device ID, sensor values to check, thresholds, etc.).

Edge offloading includes offloading to and from an IoT device and to
and from a network node. [Cloudlets] describes an example of
offloading computation from an end device to a network node. In
contrast, oneM2M is an example of a system that allows a cloud-based
IoT platform to transfer resources and tasks to a target edge node
[oneM2M-TR0052]. Once transferred, the edge node can directly
support IoT devices that it serves with the service offloaded by the
cloud (e.g., group management, location management, etc.).

QoS can be provided in some systems through the combination of
network QoS (e.g., traffic engineering or wireless resource
scheduling) and compute and storage resource allocations. For
example, in some systems, a bandwidth manager service can be exposed
to enable allocation of the bandwidth to or from an edge computing
application instance.

In-network computation can leverage the underlying services provided
using data generated by IoT devices and access networks. Such
services include IoT device location, radio network information,
bandwidth management, and congestion management (e.g., the congestion
management feature of oneM2M [oneM2M-TR0052]).

Related challenges include:

* Computation placement: in a centralized or distributed (e.g.,
peer-to-peer) manner, selecting an appropriate compute device.
The selection is based on available resources, location of data
input and data sinks, compute node properties, etc. with varying
goals. These goals include end-to-end latency, privacy, high
availability, energy conservation, or network efficiency (for
example, using load-balancing techniques to avoid congestion).

* Onboarding code on a platform or computing device and invoking
remote code execution, possibly as part of a distributed
programming model and with respect to similar concerns of latency,
privacy, etc. For example, offloading can be included in a
vehicular scenario [Grewe]. These operations should deal with
heterogeneous compute nodes [Schafer] and may also support end
devices, including IoT devices, as compute nodes [Larrea].

* Adapting Quality of Results (QoR) for applications where a perfect
result is not necessary [Li].

* Assisted or automatic partitioning of code. For example, for
application programs [COIN-APPCENTRES] or network programs
[REQS-P4COMP].

* Supporting computation across trust domains. For example,
verifying computation results.

* Supporting computation mobility: relocating an instance from one
compute node to another while maintaining a given service level;
session continuity when communicating with end devices that are
mobile, possibly at high speed (e.g., in vehicular scenarios);
defining lightweight execution environments for secure code
mobility, for example, using WebAssembly [Nieke].

* Defining, managing, and verifying SLAs for edge computing systems;
pricing is a challenging task.

4.4.2. Edge Storage and Caching

Local storage or caching enables local data processing (e.g.,
preprocessing or analysis) as well as delayed data transfer to the
cloud or delayed physical shipping. An edge node may offer local
data storage (in which persistence is subject to retention policies),
caching, or both. Generally, "caching" refers to temporary storage
to improve performance without persistence guarantees. An edge-
caching component manages data persistence; for example, it schedules
the removal of data when it is no longer needed. Other related
aspects include the authentication and encryption of data. Edge
storage and caching can take the form of a distributed storage
system.

Related challenges include:

* Cache and data placement: using cache positioning and data
placement strategies to minimize data retrieval delay [Liu] and
energy consumption. Caches may be positioned in the access-
network infrastructure or on end devices.

* Maintaining consistency, freshness, reliability, and privacy of
data stored or cached in systems that are distributed,
constrained, and dynamic (e.g., due to node mobility, energy-
saving regimes, and disruptions) and which can have additional
data governance constraints on data storage location. For
example, [Mortazavi] describes leveraging a hierarchical storage
organization. Freshness-related metrics include the age of
information [Yates] that captures the timeliness of information
received from a sender (e.g., an IoT device).

4.4.3. Communication

An edge cloud may provide a northbound data plane or management plane
interface to a remote network, such as a cloud, home, or enterprise
network. This interface does not exist in stand-alone (local-only)
scenarios. To support such an interface when it exists, an edge
computing component needs to expose an API, deal with authentication
and authorization, and support secure communication.

An edge cloud may provide an API or interface to local or mobile
users, for example, to provide access to services and applications or
to manage data published by local or mobile devices.

Edge computing nodes communicate with IoT devices over a southbound
interface, typically for data acquisition and IoT device management.

Communication brokering is a typical function of IoT edge computing
that facilitates communication with IoT devices, enables clients to
register as recipients for data from devices, forwards traffic to or
from IoT devices, enables various data discovery and redistribution
patterns (for example, north-south with clouds and east-west with
other edge devices [EDGE-DATA-DISCOVERY-OVERVIEW]). Another related
aspect is dispatching alerts and notifications to interested
consumers both inside and outside the edge computing domain.
Protocol translation, analytics, and video transcoding can also be
performed when necessary. Communication brokering may be centralized
in some systems, for example, using a hub-and-spoke message broker or
distributed with message buses, possibly in a layered bus approach.
Distributed systems can leverage direct communication between end
devices over device-to-device links. A broker can ensure
communication reliability and traceability and, in some cases,
transaction management.

Related challenges include:

* Defining edge computing abstractions, such as PaaS [Yangui],
suitable for users and cloud systems to interact with edge
computing systems and dealing with interoperability issues, such
as data-model heterogeneity.

* Enabling secure and resilient communication between IoT devices
and a remote cloud, for example, through multipath support.

4.5. Application Components

IoT edge computing can host applications, such as those mentioned in
Section 2.4. While describing the components of individual
applications is out of our scope, some of those applications share
similar functions, such as IoT device management and data management,
as described below.

4.5.1. IoT Device Management

IoT device management includes managing information regarding IoT
devices, including their sensors and how to communicate with them.
Edge computing addresses the scalability challenges of a large number
of IoT devices by separating the scalability domain into local (e.g.,
edge) networks and remote networks. For example, in the context of
the oneM2M standard, a device management functionality (called
"software campaign" in oneM2M) enables the installation, deletion,
activation, and deactivation of software functions and services on a
potentially large number of edge nodes [oneM2M-TR0052]. Using a
dashboard or management software, a service provider issues these
requests through an IoT cloud platform supporting the software
campaign functionality.

The challenges listed in Section 4.3.1 may be applicable to IoT
device management as well.

4.5.2. Data Management and Analytics

Data storage and processing at the edge are major aspects of IoT edge
computing, directly addressing the high-level IoT challenges listed
in Section 3. Data analysis, for example, through AI/ML tasks
performed at the edge, may benefit from specialized hardware support
on the computing nodes.

Related challenges include:

* Addressing concerns regarding resource usage, security, and
privacy when sharing, processing, discovering, or managing data:
for example, presenting data in views composed of an aggregation
of related data [Zhang], protecting data communication between
authenticated peers [Basudan], classifying data (e.g., in terms of
privacy, importance, and validity), and compressing and encrypting
data, for example, using homomorphic encryption to directly
process encrypted data [Stanciu].

* Other concerns regarding edge data discovery (e.g., streaming
data, metadata, and events) include siloization and lack of
standards in edge environments that can be dynamic (e.g.,
vehicular networks) and heterogeneous
[EDGE-DATA-DISCOVERY-OVERVIEW].

* Data-driven programming models [Renart], for example, those that
are event based, including handling naming and data abstractions.

* Data integration in an environment without data standardization or
where different sources use different ontologies
[Farnbauer-Schmidt].

* Addressing concerns such as limited resources, privacy, and
dynamic and heterogeneous environments to deploy machine learning
at the edge: for example, making machine learning more lightweight
and distributed (e.g., enabling distributed inference at the
edge), supporting shorter training times and simplified models,
and supporting models that can be compressed for efficient
communication [Murshed].

* Although edge computing can support IoT services independently of
cloud computing, it can also be connected to cloud computing.
Thus, the relationship between IoT edge computing and cloud
computing, with regard to data management, is another potential
challenge [ISO_TR].

4.6. Simulation and Emulation Environments

IoT edge computing introduces new challenges to the simulation and
emulation tools used by researchers and developers. A varied set of
applications, networks, and computing technologies can coexist in a
distributed system, making modeling difficult. Scale, mobility, and
resource management are additional challenges [SimulatingFog].

Tools include simulators, where simplified application logic runs on
top of a fog network model, and emulators, where actual applications
can be deployed, typically in software containers, over a cloud
infrastructure (e.g., Docker and Kubernetes) running over a network
emulating network edge conditions, such as variable delays,
throughput, and mobility events. To gain in scale, emulated and
simulated systems can be used together in hybrid federation-based
approaches [PseudoDynamicTesting]; whereas to gain in realism,
physical devices can be interconnected with emulated systems.
Examples of related work and platforms include the publicly
accessible MEC sandbox work recently initiated in ETSI [ETSI_Sandbox]
and open-source simulators and emulators ([AdvantEDGE] emulator and
tools cited in [SimulatingFog]). EdgeNet [Senel] is a globally
distributed edge cloud for Internet researchers, which uses nodes
contributed by institutions and which is based on Docker for
containerization and Kubernetes for deployment and node management.

Digital twins are virtual instances of a physical system (twin) that
are continually updated with the latter's performance, maintenance,
and health status data throughout the life cycle of the physical
system [Madni]. In contrast to an emulation or simulated
environment, digital twins, once generated, are maintained in sync by
their physical twin, which can be, among many other instances, an IoT
device, edge device, or an edge network. The benefits of digital
twins go beyond those of emulation and include accelerated business
processes, enhanced productivity, and faster innovation with reduced
costs [NETWORK-DIGITAL-TWIN-ARCH].

5. Security Considerations

Privacy and security are drivers of the adoption of edge computing
for the IoT (Section 3.4). As discussed in Section 4.3.1,
authentication and trust (among computing nodes, management nodes,
and end devices) can be challenging as scale, mobility, and
heterogeneity increase. The sometimes disconnected nature of edge
resources can avoid reliance on third-party authorities. Distributed
edge computing is exposed to reliability and denial-of-service
attacks. A personal or proprietary IoT data leakage is also a major
threat, particularly because of the distributed nature of the systems
(Section 4.5.2). Furthermore, blockchain-based distributed IoT edge
computing must be designed for privacy, since public blockchain
addressing does not guarantee absolute anonymity [Ali].

However, edge computing also offers solutions in the security space:
maintaining privacy by computing sensitive data closer to data
generators is a major use case for IoT edge computing. An edge cloud
can be used to perform actions based on sensitive data or to
anonymize or aggregate data prior to transmission to a remote cloud
server. Edge computing communication brokering functions can also be
used to secure communication between edge and cloud networks.

6. Conclusion

IoT edge computing plays an essential role, complementary to the
cloud, in enabling IoT systems in certain situations. In this
document, we presented use cases and listed the core challenges faced
by the IoT that drive the need for IoT edge computing. Therefore,
the first part of this document may help focus future research
efforts on the aspects of IoT edge computing where it is most useful.
The second part of this document presents a general system model and
structured overview of the associated research challenges and related
work. The structure, based on the system model, is not meant to be
restrictive and exists for the purpose of having a link between
individual research areas and where they are applicable in an IoT
edge computing system.

7. IANA Considerations

This document has no IANA actions.

8. Informative References

[AdvantEDGE]
"AdvantEDGE, Mobile Edge Emulation Platform", commit
8f6edbe, May 2023,
<https://github.com/InterDigitalInc/AdvantEDGE>.

[Ali] Ali, M., Vecchio, M., and F. Antonelli, "Enabling a
Blockchain-Based IoT Edge", IEEE Internet of Things
Magazine, vol. 1, no.2, pp. 24-29,
DOI 10.1109/IOTM.2019.1800024, December 2018,
<https://doi.org/10.1109/IOTM.2019.1800024>.

[Anglano] Anglano, C., Canonico, M., Castagno, P., Guazzone, M., and
M. Sereno, "A game-theoretic approach to coalition
formation in fog provider federations", 2018 Third
International Conference on Fog and Mobile Edge Computing
(FMEC), DOI 10.1109/fmec.2018.8364054, April 2018,
<https://doi.org/10.1109/fmec.2018.8364054>.

[Argungu] Argungu, J., Idina, M., Chalawa, U., Ummar, M., Bello, S.,
Arzika, I., and B. Mala, "A Survey of Edge Computing
Approaches in Smart Factory", International Journal of
Advanced Research in Computer and Communication
Engineering, Vol. 12, Issue 9, September 2023.

[Ashton] Ashton, K., "That 'Internet of Things' Thing", RFID
Journal, vol. 22, no. 7, pp. 97-114, June 2009,
<http://www.itrco.jp/libraries/RFIDjournal-
That%20Internet%20of%20Things%20Thing.pdf>.

[Badjie] Badjie, B., "The Future of Autonomous Driving Systems with
Edge Computing", September 2023,
<https://medium.com/@bakarykumba1996/the-future-of-
autonomous-driving-systems-with-edge-computing-
8c919597c4ee>.

[Basudan] Basudan, S., Lin, X., and K. Sankaranarayanan, "A Privacy-
Preserving Vehicular Crowdsensing-Based Road Surface
Condition Monitoring System Using Fog Computing", IEEE
Internet of Things Journal, vol. 4, no. 3, pp. 772-782,
DOI 10.1109/jiot.2017.2666783, June 2017,
<https://doi.org/10.1109/jiot.2017.2666783>.

[BigRentz] BigRentz, "41 Construction Safety Statistics for 2024",
February 2024, <https://www.bigrentz.com/blog/
construction-safety-statistics>.

[Botta] Botta, A., de Donato, W., Persico, V., and A. Pescapé,
"Integration of Cloud computing and Internet of Things: A
survey", Future Generation Computer Systems, vol. 56, pp.
684-700, DOI 10.1016/j.future.2015.09.021, March 2016,
<https://doi.org/10.1016/j.future.2015.09.021>.

[Brecko] Brecko, A., Kajáti, E., Koziorek, J., and I. Zolotová,
"Federated Learning for Edge Computing: A Survey", Applied
Sciences 12(18):9124, DOI 10.3390/app12189124, September
2022, <https://doi.org/10.3390/app12189124>.

[Cao] Cao, L., Merican, A., Tootaghaj, D., Ahmed, F., Sharma,
P., and V. Saxena, "eCaaS: A Management Framework of Edge
Container as a Service for Business Workload", Proceedings
of the 4th International Workshop on Edge Systems,
Analytics and Networking, DOI 10.1145/3434770.3459741,
April 2021, <https://doi.org/10.1145/3434770.3459741>.

[CertMagic]
CertMagic, "Digital Twin Technology: Simulating Real-World
Scenarios for Enhanced Decision Making", May 2023,
<https://certmagic.medium.com/digital-twin-technology-
simulating-real-world-scenarios-for-enhanced-decision-
making-8844c51e856d>.

[Chen] Chen, B., Wan, J., Celesti, A., Li, D., Abbas, H., and Q.
Zhang, "Edge Computing in IoT-Based Manufacturing", IEEE
Communications Magazine, vol. 56, no. 9, pp. 103-109,
DOI 10.1109/mcom.2018.1701231, September 2018,
<https://doi.org/10.1109/mcom.2018.1701231>.

[Chiang] Chiang, M. and T. Zhang, "Fog and IoT: An Overview of
Research Opportunities", IEEE Internet of Things Journal,
vol. 3, no. 6, pp. 854-864, DOI 10.1109/jiot.2016.2584538,
December 2016,
<https://doi.org/10.1109/jiot.2016.2584538>.

[Chipmunk] Shin, Y., Park, S., Ko, N., and A. Jeong, "Chipmunk:
Distributed Object Storage for NDN", Proceedings of the
7th ACM Conference on Information-Centric Networking, ACM,
DOI 10.1145/3405656.3420231, September 2020,
<https://doi.org/10.1145/3405656.3420231>.

[Cloudlets]
Satyanarayanan, M., Bahl, P., Caceres, R., and N. Davies,
"The Case for VM-Based Cloudlets in Mobile Computing",
IEEE Pervasive Computing, vol. 8, no. 4, pp. 14-23,
DOI 10.1109/mprv.2009.82, October 2009,
<https://doi.org/10.1109/mprv.2009.82>.

[COIN-APPCENTRES]
Trossen, D., Sarathchandra, C., and M. Boniface, "In-
Network Computing for App-Centric Micro-Services", Work in
Progress, Internet-Draft, draft-sarathchandra-coin-
appcentres-04, 26 January 2021,
<https://datatracker.ietf.org/doc/html/draft-
sarathchandra-coin-appcentres-04>.

[CORE-GROUPCOMM-BIS]
Dijk, E., Wang, C., and M. Tiloca, "Group Communication
for the Constrained Application Protocol (CoAP)", Work in
Progress, Internet-Draft, draft-ietf-core-groupcomm-bis-
10, 23 October 2023,
<https://datatracker.ietf.org/doc/html/draft-ietf-core-
groupcomm-bis-10>.

[Echeverria]
Echeverría, S., Klinedinst, D., Williams, K., and G.
Lewis, "Establishing Trusted Identities in Disconnected
Edge Environments", 2016 IEEE/ACM Symposium on Edge
Computing (SEC), DOI 10.1109/sec.2016.27, October 2016,
<https://doi.org/10.1109/sec.2016.27>.

[EDGE-COMPUTING-BACKGROUND]
de Foy, X., Hong, J., Hong, Y., Kovatsch, M., Schooler,
E., and D. Kutscher, "IoT Edge Computing: Initiatives,
Projects and Products", Work in Progress, Internet-Draft,
draft-defoy-t2trg-iot-edge-computing-background-00, 25 May
2020, <https://datatracker.ietf.org/doc/html/draft-defoy-
t2trg-iot-edge-computing-background-00>.

[EDGE-DATA-DISCOVERY-OVERVIEW]
McBride, M., Kutscher, D., Schooler, E., Bernardos, C. J.,
Lopez, D., and X. de Foy, "Edge Data Discovery for COIN",
Work in Progress, Internet-Draft, draft-mcbride-edge-data-
discovery-overview-05, 1 November 2020,
<https://datatracker.ietf.org/doc/html/draft-mcbride-edge-
data-discovery-overview-05>.

[ENERGY] Beckel, C., Sadamori, L., Staake, T., and S. Santini,
"Revealing household characteristics from smart meter
data", Energy, vol. 78, pp. 397-410,
DOI 10.1016/j.energy.2014.10.025, December 2014,
<https://doi.org/10.1016/j.energy.2014.10.025>.

[ETSI_MEC_01]
ETSI, "Multi-access Edge Computing (MEC); Terminology",
V2.1.1, ETSI GS MEC 001, January 2019,
<https://www.etsi.org/deliver/etsi_gs/
MEC/001_099/001/02.01.01_60/gs_MEC001v020101p.pdf>.

[ETSI_MEC_03]
ETSI, "Multi-access Edge Computing (MEC); Framework and
Reference Architecture", V2.1.1, ETSI GS MEC 003, January
2019, <https://www.etsi.org/deliver/etsi_gs/
MEC/001_099/003/02.01.01_60/gs_MEC003v020101p.pdf>.

[ETSI_MEC_33]
ETSI, "Multi-access Edge Computing (MEC); IoT API",
V3.1.1, ETSI GS MEC 033, December 2022,
<https://www.etsi.org/deliver/etsi_gs/
MEC/001_099/033/03.01.01_60/gs_MEC033v030101p.pdf>.

[ETSI_Sandbox]
ETSI, "Multi-access Edge Computing (MEC) MEC Sandbox",
Portal, September 2023,
<https://portal.etsi.org/webapp/WorkProgram/
Report_WorkItem.asp?WKI_ID=57671>.

[Fan] Fan, Q. and N. Ansari, "Cost Aware cloudlet Placement for
big data processing at the edge", 2017 IEEE International
Conference on Communications (ICC),
DOI 10.1109/icc.2017.7996722, May 2017,
<https://doi.org/10.1109/icc.2017.7996722>.

[Farnbauer-Schmidt]
Farnbauer-Schmidt, M., Lindner, J., Kaffenberger, C., and
J. Albrecht, "Combining the Concepts of Semantic Data
Integration and Edge Computing", INFORMATIK 2019: 50 Jahre
Gesellschaft für Informatik - Informatik für Gesellschaf,
pp. 139-152, DOI 10.18420/inf2019_19, September 2019,
<https://doi.org/10.18420/inf2019_19>.

[Grewe] Grewe, D., Wagner, M., Arumaithurai, M., Psaras, I., and
D. Kutscher, "Information-Centric Mobile Edge Computing
for Connected Vehicle Environments: Challenges and
Research Directions", Proceedings of the Workshop on
Mobile Edge Communications, pp. 7-12,
DOI 10.1145/3098208.3098210, August 2017,
<https://doi.org/10.1145/3098208.3098210>.

[Harchol] Harchol, Y., Mushtaq, A., McCauley, J., Panda, A., and S.
Shenker, "CESSNA: Resilient Edge-Computing", Proceedings
of the 2018 Workshop on Mobile Edge Communications,
DOI 10.1145/3229556.3229558, August 2018,
<https://doi.org/10.1145/3229556.3229558>.

[IEC_IEEE_60802]
IEC/IEEE, "Use Cases IEC/IEEE 60802", V1.3, IEC/
IEEE 60802, September 2018,
<https://grouper.ieee.org/groups/802/1/files/public/
docs2018/60802-industrial-use-cases-0918-v13.pdf>.

[ISO_TR] "Internet of things (IoT) - Edge computing", ISO/IEC TR
30164:2020, April 2020,
<https://www.iso.org/standard/53284.html>.

[Jeffery] Jeffery, A., Howard, H., and R. Mortier, "Rearchitecting
Kubernetes for the Edge", Proceedings of the 4th
International Workshop on Edge Systems, Analytics and
Networking, DOI 10.1145/3434770.3459730, April 2021,
<https://doi.org/10.1145/3434770.3459730>.

[Jeong] Jeong, T., Chung, J., Hong, J., and S. Ha, "Towards a
distributed computing framework for Fog", 2017 IEEE Fog
World Congress (FWC), DOI 10.1109/fwc.2017.8368528,
October 2017, <https://doi.org/10.1109/fwc.2017.8368528>.

[Jones] Jones, D., Snider, C., Nassehi, A., Yon, J., and B. Hicks,
"Characterising the Digital Twin: A systematic literature
review", CIRP Journal of Manufacturing Science and
Technology, vol. 29, pp. 36-52,
DOI 10.1016/j.cirpj.2020.02.002, May 2020,
<https://doi.org/10.1016/j.cirpj.2020.02.002>.

[Kelly] Kelly, R., "Internet of Things Data to Top 1.6 Zettabytes
by 2020", April 2015,
<https://campustechnology.com/articles/2015/04/15/
internet-of-things-data-to-top-1-6-zettabytes-by-
2020.aspx>. Retrieved on 2022-05-24.

[Khan] Khan, L., Yaqoob, I., Tran, N., Kazmi, S., Dang, T., and
C. Hong, "Edge-Computing-Enabled Smart Cities: A
Comprehensive Survey", IEEE Internet of Things Journal,
vol. 7, no. 10, pp. 10200-10232,
DOI 10.1109/jiot.2020.2987070, October 2020,
<https://doi.org/10.1109/jiot.2020.2987070>.

[Kua] Patil, V., Desai, H., and L. Zhang, "Kua: a distributed
object store over named data networking", Proceedings of
the 9th ACM Conference on Information-Centric Networking,
DOI 10.1145/3517212.3558083, September 2022,
<https://doi.org/10.1145/3517212.3558083>.

[Larrea] Larrea, J. and A. Barbalace, "The serverkernel operating
system", Proceedings of the Third ACM International
Workshop on Edge Systems, Analytics and Networking,
DOI 10.1145/3378679.3394537, May 2020,
<https://doi.org/10.1145/3378679.3394537>.

[LFEDGE-EVE]
Linux Foundation, "Project Edge Virtualization Engine
(EVE)", Portal, <https://www.lfedge.org/projects/eve>.
Retrieved on 2022-05-24.

[Li] Li, Y., Chen, Y., Lan, T., and G. Venkataramani, "MobiQoR:
Pushing the Envelope of Mobile Edge Computing Via Quality-
of-Result Optimization", 2017 IEEE 37th International
Conference on Distributed Computing Systems (ICDCS),
DOI 10.1109/icdcs.2017.54, June 2017,
<https://doi.org/10.1109/icdcs.2017.54>.

[Lin] Lin, J., Yu, W., Zhang, N., Yang, X., Zhang, H., and W.
Zhao, "A Survey on Internet of Things: Architecture,
Enabling Technologies, Security and Privacy, and
Applications", IEEE Internet of Things Journal, vol. 4,
no. 5, pp. 1125-1142, DOI 10.1109/jiot.2017.2683200,
October 2017, <https://doi.org/10.1109/jiot.2017.2683200>.

[Liu] Liu, J., Bai, B., Zhang, J., and K. Letaief, "Cache
Placement in Fog-RANs: From Centralized to Distributed
Algorithms", IEEE Transactions on Wireless Communications,
vol. 16, no. 11, pp. 7039-7051,
DOI 10.1109/twc.2017.2737015, November 2017,
<https://doi.org/10.1109/twc.2017.2737015>.

[Madni] Madni, A., Madni, C., and S. Lucero, "Leveraging Digital
Twin Technology in Model-Based Systems Engineering",
Systems 7(1):7, DOI 10.3390/systems7010007, January 2019,
<https://doi.org/10.3390/systems7010007>.

[Mahadev] Satyanarayanan, M., "The Emergence of Edge Computing",
Computer, vol. 50, no. 1, pp. 30-39,
DOI 10.1109/mc.2017.9, January 2017,
<https://doi.org/10.1109/mc.2017.9>.

[Mehmood] Mehmood, M., Oad, A., Abrar, M., Munir, H., Hasan, S.,
Muqeet, H., and N. Golilarz, "Edge Computing for IoT-
Enabled Smart Grid", Security and Communication Networks,
Vol. 2021, Article ID 5524025, DOI 10.1155/2021/5524025,
July 2021, <https://doi.org/10.1155/2021/5524025>.

[Mortazavi]
Mortazavi, S., Balasubramanian, B., de Lara, E., and S.
Narayanan, "Toward Session Consistency for the Edge",
USENIX Workshop on Hot Topics in Edge Computing (HotEdge
18), 2018,
<https://www.usenix.org/conference/hotedge18/presentation/
mortazavi>.

[MQTT5] Banks, A., Ed., Briggs, E., Ed., Borgendale, K., Ed., and
R. Gupta, Ed., "MQTT Version 5.0", OASIS Standard, March
2019, <https://docs.oasis-open.org/mqtt/mqtt/v5.0/mqtt-
v5.0.html>.

[Murshed] Murshed, M., Murphy, C., Hou, D., Khan, N.,
Ananthanarayanan, G., and F. Hussain, "Machine Learning at
the Network Edge: A Survey", ACM Computing Surveys, vol.
54, no. 8, pp. 1-37, DOI 10.1145/3469029, October 2021,
<https://doi.org/10.1145/3469029>.

[NETWORK-DIGITAL-TWIN-ARCH]
Zhou, C., Yang, H., Duan, X., Lopez, D., Pastor, A., Wu,
Q., Boucadair, M., and C. Jacquenet, "Network Digital
Twin: Concepts and Reference Architecture", Work in
Progress, Internet-Draft, draft-irtf-nmrg-network-digital-
twin-arch-05, 4 March 2024,
<https://datatracker.ietf.org/doc/html/draft-irtf-nmrg-
network-digital-twin-arch-05>.

[Nieke] Nieke, M., Almstedt, L., and R. Kapitza, "Edgedancer:
Secure Mobile WebAssembly Services on the Edge",
Proceedings of the 4th International Workshop on Edge
Systems, Analytics and Networking,
DOI 10.1145/3434770.3459731, April 2021,
<https://doi.org/10.1145/3434770.3459731>.

[NIST] Mell, P. and T. Grance, "The NIST Definition of Cloud
Computing", NIST Special Publication 800-145,
DOI 10.6028/nist.sp.800-145, September 2011,
<https://doi.org/10.6028/nist.sp.800-145>.

[NVIDIA] Grzywaczewski, A., "Training AI for Self-Driving Vehicles:
the Challenge of Scale", NVIDIA Developer Blog, October
2017, <https://devblogs.nvidia.com/training-self-driving-
vehicles-challenge-scale/>. Retrieved on 2022-05-24.

[OGrady] O'Grady, M., Langton, D., and G. O'Hare, "Edge computing:
A tractable model for smart agriculture?", Artificial
Intelligence in Agriculture, Vol. 3, Pages 42-51,
DOI 10.1016/j.aiia.2019.12.001, September 2019,
<https://doi.org/10.1016/j.aiia.2019.12.001>.

[oneM2M-TR0001]
Mladin, C., "Use Cases Collection", oneM2M, v4.2.0,
TR 0001, October 2018,
<https://member.onem2m.org/Application/documentapp/
downloadLatestRevision/default.aspx?docID=28153>.

[oneM2M-TR0018]
Lu, C. and M. Jiang, "Industrial Domain Enablement",
oneM2M, v2.5.2, TR 0018, February 2019,
<https://member.onem2m.org/Application/documentapp/
downloadLatestRevision/default.aspx?docID=29334>.

[oneM2M-TR0026]
Yamamoto, K., Mladin, C., and V. Kueh, "Vehicular Domain
Enablement", oneM2M, TR 0026, January 2020,
<https://member.onem2m.org/Application/documentapp/
downloadLatestRevision/default.aspx?docID=31410>.

[oneM2M-TR0052]
Yamamoto, K. and C. Mladin, "Study on Edge and Fog
Computing in oneM2M systems", oneM2M, TR 0052, September
2020, <https://member.onem2m.org/Application/documentapp/
downloadLatestRevision/default.aspx?docID=32633>.

[oneM2M-TS0002]
He, S., "TS 0002, Requirements", oneM2M, TS 0002, February
2019, <https://member.onem2m.org/Application/documentapp/
downloadLatestRevision/default.aspx?docID=29274>.

[OpenFog] OpenFog Consortium, "OpenFog Reference Architecture for
Fog Computing", February 2017,
<https://iiconsortium.org/pdf/
OpenFog_Reference_Architecture_2_09_17.pdf>.

[PseudoDynamicTesting]
Ficco, M., Esposito, C., Xiang, Y., and F. Palmieri,
"Pseudo-Dynamic Testing of Realistic Edge-Fog Cloud
Ecosystems", IEEE Communications Magazine, vol. 55, no.
11, pp. 98-104, DOI 10.1109/mcom.2017.1700328, November
2017, <https://doi.org/10.1109/mcom.2017.1700328>.

[Renart] Renart, E., Diaz-Montes, J., and M. Parashar, "Data-Driven
Stream Processing at the Edge", 2017 IEEE 1st
International Conference on Fog and Edge Computing
(ICFEC), DOI 10.1109/icfec.2017.18, May 2017,
<https://doi.org/10.1109/icfec.2017.18>.

[REQS-P4COMP]
Singh, H. and M. Montpetit, "Requirements for P4 Program
Splitting for Heterogeneous Network Nodes", Work in
Progress, Internet-Draft, draft-hsingh-coinrg-reqs-p4comp-
03, 18 February 2021,
<https://datatracker.ietf.org/doc/html/draft-hsingh-
coinrg-reqs-p4comp-03>.

[REST-IOT] Keränen, A., Kovatsch, M., and K. Hartke, "Guidance on
RESTful Design for Internet of Things Systems", Work in
Progress, Internet-Draft, draft-irtf-t2trg-rest-iot-13, 25
January 2024, <https://datatracker.ietf.org/doc/html/
draft-irtf-t2trg-rest-iot-13>.

[RFC6291] Andersson, L., van Helvoort, H., Bonica, R., Romascanu,
D., and S. Mansfield, "Guidelines for the Use of the "OAM"
Acronym in the IETF", BCP 161, RFC 6291,
DOI 10.17487/RFC6291, June 2011,
<https://www.rfc-editor.org/info/rfc6291>.

[RFC7252] Shelby, Z., Hartke, K., and C. Bormann, "The Constrained
Application Protocol (CoAP)", RFC 7252,
DOI 10.17487/RFC7252, June 2014,
<https://www.rfc-editor.org/info/rfc7252>.

[RFC7390] Rahman, A., Ed. and E. Dijk, Ed., "Group Communication for
the Constrained Application Protocol (CoAP)", RFC 7390,
DOI 10.17487/RFC7390, October 2014,
<https://www.rfc-editor.org/info/rfc7390>.

[RFC8578] Grossman, E., Ed., "Deterministic Networking Use Cases",
RFC 8578, DOI 10.17487/RFC8578, May 2019,
<https://www.rfc-editor.org/info/rfc8578>.

[Schafer] Schäfer, D., Edinger, J., VanSyckel, S., Paluska, J., and
C. Becker, "Tasklets: Overcoming Heterogeneity in
Distributed Computing Systems", 2016 IEEE 36th
International Conference on Distributed Computing Systems
Workshops (ICDCSW), DOI 10.1109/icdcsw.2016.22, June 2016,
<https://doi.org/10.1109/icdcsw.2016.22>.

[Senel] Şenel, B., Mouchet, M., Cappos, J., Fourmaux, O.,
Friedman, T., and R. McGeer, "EdgeNet: A Multi-Tenant and
Multi-Provider Edge Cloud", Proceedings of the 4th
International Workshop on Edge Systems, Analytics and
Networking, DOI 10.1145/3434770.3459737, April 2021,
<https://doi.org/10.1145/3434770.3459737>.

[SFC-FOG-RAN]
Bernardos, C. J. and A. Mourad, "Service Function Chaining
Use Cases in Fog RAN", Work in Progress, Internet-Draft,
draft-bernardos-sfc-fog-ran-10, 22 October 2021,
<https://datatracker.ietf.org/doc/html/draft-bernardos-
sfc-fog-ran-10>.

[Shi] Shi, W., Cao, J., Zhang, Q., Li, Y., and L. Xu, "Edge
Computing: Vision and Challenges", IEEE Internet of Things
Journal, vol. 3, no. 5, pp. 637-646,
DOI 10.1109/jiot.2016.2579198, October 2016,
<https://doi.org/10.1109/jiot.2016.2579198>.

[SimulatingFog]
Svorobej, S., Takako Endo, P., Bendechache, M., Filelis-
Papadopoulos, C., Giannoutakis, K., Gravvanis, G.,
Tzovaras, D., Byrne, J., and T. Lynn, "Simulating Fog and
Edge Computing Scenarios: An Overview and Research
Challenges", Future Internet, vol. 11, no. 3, pp. 55,
DOI 10.3390/fi11030055, February 2019,
<https://doi.org/10.3390/fi11030055>.

[Stanciu] Stanciu, V., Steen, M., Dobre, C., and A. Peter, "Privacy-
Preserving Crowd-Monitoring Using Bloom Filters and
Homomorphic Encryption", Proceedings of the 4th
International Workshop on Edge Systems, Analytics and
Networking, DOI 10.1145/3434770.3459735, April 2021,
<https://doi.org/10.1145/3434770.3459735>.

[Tanveer] Tanveer, S., Sree, N., Bhavana, B., and D. Varsha, "Smart
Agriculture System using IoT", 2022 IEEE World Conference
on Applied Intelligence and Computing (AIC), Sonbhadra,
India, pp. 482-486, DOI 10.1109/AIC55036.2022.9848948,
August 2022,
<https://doi.org/10.1109/AIC55036.2022.9848948>.

[Weiner] Weiner, M., Jorgovanovic, M., Sahai, A., and B. Nikolie,
"Design of a low-latency, high-reliability wireless
communication system for control applications", 2014 IEEE
International Conference on Communications (ICC),
DOI 10.1109/icc.2014.6883918, June 2014,
<https://doi.org/10.1109/icc.2014.6883918>.

[Yangui] Yangui, S., Ravindran, P., Bibani, O., Glitho, R., Ben
Hadj-Alouane, N., Morrow, M., and P. Polakos, "A platform
as-a-service for hybrid cloud/fog environments", 2016 IEEE
International Symposium on Local and Metropolitan Area
Networks (LANMAN), DOI 10.1109/lanman.2016.7548853, June
2016, <https://doi.org/10.1109/lanman.2016.7548853>.

[Yates] Yates, R. and S. Kaul, "The Age of Information: Real-Time
Status Updating by Multiple Sources", IEEE Transactions on
Information Theory, vol. 65, no. 3, pp. 1807-1827,
DOI 10.1109/tit.2018.2871079, March 2019,
<https://doi.org/10.1109/tit.2018.2871079>.

[Yousefpour]
Yousefpour, A., Fung, C., Nguyen, T., Kadiyala, K.,
Jalali, F., Niakanlahiji, A., Kong, J., and J. Jue, "All
one needs to know about fog computing and related edge
computing paradigms: A complete survey", Journal of
Systems Architecture, vol. 98, pp. 289-330,
DOI 10.1016/j.sysarc.2019.02.009, September 2019,
<https://doi.org/10.1016/j.sysarc.2019.02.009>.

[Yue] Yue, Q., Mu, S., Zhang, L., Wang, Z., Zhang, Z., Zhang,
X., Wang, Y., and Z. Miao, "Assisting Smart Construction
With Reliable Edge Computing Technology", Frontiers in
Energy Research, Sec. Smart Grids, Vol. 10,
DOI 10.3389/fenrg.2022.900298, May 2022,
<https://doi.org/10.3389/fenrg.2022.900298>.

[Zhang] Zhang, Q., Zhang, X., Zhang, Q., Shi, W., and H. Zhong,
"Firework: Big Data Sharing and Processing in
Collaborative Edge Environment", 2016 Fourth IEEE Workshop
on Hot Topics in Web Systems and Technologies (HotWeb),
DOI 10.1109/hotweb.2016.12, October 2016,
<https://doi.org/10.1109/hotweb.2016.12>.

[Zhang2] Zhang, J., Chen, B., Zhao, Y., Cheng, X., and F. Hu, "Data
Security and Privacy-Preserving in Edge Computing
Paradigm: Survey and Open Issues", IEEE Access, vol. 6,
pp. 18209-18237, DOI 10.1109/access.2018.2820162, March
2018, <https://doi.org/10.1109/access.2018.2820162>.

Acknowledgements

The authors would like to thank Joo-Sang Youn, Akbar Rahman, Michel
Roy, Robert Gazda, Rute Sofia, Thomas Fossati, Chonggang Wang, Marie-
José Montpetit, Carlos J. Bernardos, Milan Milenkovic, Dale Seed,
JaeSeung Song, Roberto Morabito, Carsten Bormann, and Ari Keränen for
their valuable comments and suggestions on this document.

Authors' Addresses

Jungha Hong
ETRI
218 Gajeong-ro, Yuseung-Gu
Daejeon
34129
Republic of Korea
Email: [email protected]

Yong-Geun Hong
Daejeon University
62 Daehak-ro, Dong-gu
Daejeon
300716
Republic of Korea
Email: [email protected]

Xavier de Foy
InterDigital Communications, LLC
1000 Sherbrooke West
Montreal H3A 3G4
Canada
Email: [email protected]

Matthias Kovatsch
Huawei Technologies Duesseldorf GmbH
Riesstr. 25 C // 3.OG
80992 Munich
Germany
Email: [email protected]

Eve Schooler
University of Oxford
Parks Road
Oxford
OX1 3PJ
United Kingdom
Email: [email protected]

Dirk Kutscher
Hong Kong University of Science and Technology (Guangzhou)
No.1 Du Xue Rd
Guangzhou
China
Email: [email protected]