Internet Engineering Task Force (IETF) R. Krishna
Request for Comments: 9699
Category: Informational A. Rahman
ISSN: 2070-1721 Ericsson
December 2024
Media Operations Use Case for an Extended Reality Application on Edge
Computing Infrastructure
Abstract
This document explores the issues involved in the use of Edge
Computing edge
computing resources to operationalize a media use cases case that involve involves
an Extended Reality (XR) applications. application. In particular, this document
discusses an XR applications application that can run on devices having different
form factors (such as different physical sizes and shapes) and need Edge needs
edge computing resources to mitigate the effect of problems such as
the need to support interactive communication requiring low latency,
limited battery power, and heat dissipation from those devices.
Network operators who are interested in providing edge computing
resources to operationalize the requirements of such applications are
the intended audience for this document. This
document also discusses the expected behavior of XR applications,
which can be used to manage traffic, and the service requirements for
XR applications to be able to run on the network. Network operators
who are interested in providing edge computing resources to
operationalize the requirements of such applications are the intended
audience for this document.
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 Engineering Task Force
(IETF). It represents the consensus of the IETF community. It has
received public review and has been approved for publication by the
Internet Engineering Steering Group (IESG). Not all documents
approved by the IESG are 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/rfc9699.
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. Code Components extracted from this document must
include Revised BSD License text as described in Section 4.e of the
Trust Legal Provisions and are provided without warranty as described
in the Revised BSD License.
Table of Contents
1. Introduction
2. Use Case
2.1. Processing of Scenes
2.2. Generation of Images
3. Technical Challenges and Solutions
4. XR Network Traffic
4.1. Traffic Workload
4.2. Traffic Performance Metrics
5. Conclusion
6. IANA Considerations
7. Security Considerations
8. Informative References
Acknowledgements
Authors' Addresses
1. Introduction
Extended Reality (XR) is a term that includes Augmented Reality (AR),
Virtual Reality (VR), and Mixed Reality (MR) [XR]. AR combines the
real and virtual, is interactive, and is aligned to the physical
world of the user [AUGMENTED_2]. On the other hand, VR places the
user inside a virtual environment generated by a computer
[AUGMENTED]. MR merges the real and virtual along a continuum that
connects a completely real environment at one end to a completely
virtual environment at the other end. In this continuum, all
combinations of the real and virtual are captured [AUGMENTED].
XR applications have several requirements for the network and the
mobile devices running these applications. Some XR applications such
(such as AR applications) require real-time processing of video
streams to recognize specific objects. This processing is then used
to overlay information on the video being displayed to the user. In
addition, other XR applications such (such as AR and VR will applications) also
require generation of new video frames to be played to the user.
Both the real-time processing of video streams and the generation of
overlay information are computationally intensive tasks that generate
heat [DEV_HEAT_1] [DEV_HEAT_2] and drain battery power [BATT_DRAIN]
on the mobile device running the XR application. Consequently, in
order to run applications with XR characteristics on mobile devices,
computationally intensive tasks need to be offloaded to resources
provided by edge computing.
Edge Computing.
Edge Computing computing is an emerging paradigm where, for the purpose of this
document, computing resources and storage are made available in close
network proximity at the edge of the Internet to mobile devices and
sensors [EDGE_1] [EDGE_2]. A computing resource or storage is in
close network proximity to a mobile device or sensor if there is a
short and high-capacity network path to it such that the latency and
bandwidth requirements of applications running on those mobile
devices or sensors can be met. These edge computing devices use
cloud technologies that enable them to support offloaded XR
applications. In particular, cloud implementation techniques
[EDGE_3] such as the following can be deployed:
Disaggregation: Using Software-Defined Networking (SDN) to break
vertically integrated systems into independent components. These
components can have open interfaces that are standard, well
documented, and non-proprietary.
Virtualization: Being able to run multiple independent copies of
those components, such as SDN Controller applications and Virtual
Network Functions, on a common hardware platform.
Commoditization: Being able to elastically scale those virtual
components across commodity hardware as the workload dictates.
Such techniques enable XR applications that require low latency and
high bandwidth to be delivered by proximate edge devices. This is
because the disaggregated components can run on proximate edge
devices rather than on a remote cloud several hops away and deliver
low-latency, high-bandwidth service to offloaded applications
[EDGE_2].
This document discusses the issues involved when edge computing
resources are offered by network operators to operationalize the
requirements of XR applications running on devices with various form
factors. For the purpose of this document, a network operator is any
organization or individual that manages or operates the computing
resources or storage in close network proximity to a mobile device or
sensor. Examples of form factors include head-mounted the following: 1) head-
mounted displays (HMDs), such as optical see-through HMDs and video
see-through HMDs,
and 2) hand-held displays. Smartphones displays, and 3) smartphones with
video cameras and location-
sensing location-sensing capabilities using systems such as
a global navigation satellite system (GNSS) are another example of such devices. (GNSS). These devices have
limited battery capacity and dissipate heat when running. Also, as
the user of these devices moves around as they run the XR
application, the wireless latency and bandwidth available to the
devices fluctuates, and the communication link itself might fail. As
a result, algorithms such as those based on Adaptive Bitrate (ABR)
techniques that base their policy on heuristics or models of
deployment perform sub-optimally in such dynamic environments
[ABR_1]. In addition, network operators can expect that the
parameters that characterize the expected behavior of XR applications
are heavy-tailed. Heaviness of tails is defined as the difference
from the normal distribution in the proportion of the values that
fall a long way from the mean [HEAVY_TAIL_3]. Such workloads require
appropriate resource management policies to be used on the Edge. edge. The
service requirements of XR applications are also challenging when
compared to current video applications. In particular, several
Quality-of-Experience (QoE) factors such as motion sickness are
unique to XR applications and must be considered when
operationalizing a network. This document motivates examines these issues with a
the use case that is presented in the following section.
2. Use Case
This use case involves an application with characteristics of an XR
system. application running on a mobile device.
Consider a group of tourists who are taking a tour around the
historical site of the Tower of London. As they move around the site
and within the historical buildings, they can watch and listen to
historical scenes in 3D that are generated by the XR application and
then overlaid by their XR headsets onto their real-world view. The
headset continuously updates their view as they move around.
The XR application first processes the scene that the walking tourist
is watching in real time and identifies objects that will be targeted
for overlay of high-resolution videos. It then generates high-
resolution 3D images of historical scenes related to the perspective
of the tourist in real time. These generated video images are then
overlaid on the view of the real world as seen by the tourist.
This processing of scenes and generation of high-resolution images
are discussed in greater detail below.
2.1. Processing of Scenes
The task of processing a scene can be broken down into a pipeline of
three consecutive subtasks: tracking, acquisition of a model of the
real world, and registration [AUGMENTED].
Tracking: The XR application that runs on the mobile device needs to
track the six-dimensional pose (translational in the three
perpendicular axes and rotational about those three axes) of the
user's head, eyes, and objects that are in view [AUGMENTED]. This
requires tracking natural features (for example, points or edges
of objects) that are then used in the next stage of the pipeline.
Acquisition of a model of the real world: The tracked natural
features are used to develop a model of the real world. One of
the ways this is done is to develop a model based on an annotated
point cloud (a set of points in space that are annotated with
descriptors) that is then stored in a database. To ensure that
this database can be scaled up, techniques such as combining
client-side simultaneous tracking and mapping with server-side
localization are used to construct a model of the real world
[SLAM_1] [SLAM_2] [SLAM_3] [SLAM_4]. Another model that can be
built is based on a polygon mesh and texture mapping technique.
The polygon mesh encodes a 3D object's shape, which is expressed
as a collection of small flat surfaces that are polygons. In
texture mapping, color patterns are mapped onto an object's
surface. A third modeling technique uses a 2D lightfield that
describes the intensity or color of the light rays arriving at a
single point from arbitrary directions. Such a 2D lightfield is
stored as a two-dimensional table. Assuming distant light
sources, the single point is approximately valid for small scenes.
For larger scenes, many 3D positions are additionally stored,
making the table 5D. A set of all such points (either a 2D or 5D
lightfield) can then be used to construct a model of the real
world [AUGMENTED].
Registration: The coordinate systems, brightness, and color of
virtual and real objects need to be aligned with each other; this
process is called "registration" [REG]. Once the natural features
are tracked as discussed above, virtual objects are geometrically
aligned with those features by geometric registration. This is
followed by resolving occlusion that can occur between virtual and
real objects [OCCL_1] [OCCL_2]. The XR application also applies
photometric registration [PHOTO_REG] by aligning brightness and
color between the virtual and real objects. Additionally,
algorithms that calculate global illumination of both the virtual
and real objects [GLB_ILLUM_1] [GLB_ILLUM_2] are executed.
Various algorithms are also required to deal with artifacts
generated by lens distortion [LENS_DIST], blur [BLUR], noise
[NOISE], etc.
2.2. Generation of Images
The XR application must generate a high-quality video that has the
properties described in the previous step above and overlay the video on the XR device's
display. This step is called "situated visualization". A situated
visualization is a visualization in which the virtual objects that
need to be seen by the XR user are overlaid correctly on the real
world. This entails dealing with registration errors that may arise,
ensuring that there is no visual interference [VIS_INTERFERE], and
finally maintaining temporal coherence by adapting to the movement of
user's eyes and head.
3. Technical Challenges and Solutions
As discussed in Section 2, the components of XR applications perform
tasks that are computationally intensive, such as real-time
generation and processing of high-quality video content. This
section discusses the challenges such applications can face as a
consequence.
consequence and offers some solutions.
As a result of performing computationally intensive tasks on XR
devices such as XR glasses, excessive heat is generated by the
chipsets that are involved in the computation [DEV_HEAT_1]
[DEV_HEAT_2]. Additionally, the battery on such devices discharges
quickly when running such applications [BATT_DRAIN].
A solution to problem of heat dissipation and battery drainage is to
offload the processing and video generation tasks to the remote
cloud. However, running such tasks on the cloud is not feasible as
the end-to-end delays must be within the order of a few milliseconds.
Additionally, such applications require high bandwidth and low jitter
to provide a high QoE to the user. In order to achieve such hard
timing constraints, computationally intensive tasks can be offloaded
to Edge edge devices.
Another requirement for our use case and similar applications, such
as 360-degree streaming (streaming of video that represents a view in
every direction in 3D space), is that the display on the XR device
should synchronize the visual input with the way the user is moving
their head. This synchronization is necessary to avoid motion
sickness that results from a time lag between when the user moves
their head and when the appropriate video scene is rendered. This
time lag is often called "motion-to-photon delay". Studies have
shown that this delay can be at most 20 ms and preferably between
7-15 ms in order to avoid motion sickness [PER_SENSE] [XR] [OCCL_3].
Out of these 20 ms, display techniques including the refresh rate of
write displays and pixel switching take 12-13 ms [OCCL_3] [CLOUD].
This leaves 7-8 ms for the processing of motion sensor inputs,
graphic rendering, and round-trip time (RTT) between the XR device
and the Edge. edge. The use of predictive techniques to mask latencies has
been considered as a mitigating strategy to reduce motion sickness
[PREDICT]. In addition, Edge Devices edge devices that are proximate to the user
might be used to offload these computationally intensive tasks.
Towards this end, a 3GPP study indicates suggests an Ultra-Reliable Low Latency
of 0.1 to 1 ms for communication between an Edge edge server and User
Equipment (UE) [URLLC].
Note that the Edge edge device providing the computation and storage is
itself limited in such resources compared to the cloud. For example,
a sudden surge in demand from a large group of tourists can overwhelm
the device. This will result in a degraded user experience as their
XR device experiences delays in receiving the video frames. In order
to deal with this problem, the client XR applications will need to
use ABR algorithms that choose bitrate policies tailored in a fine-
grained manner to the resource demands and play back the videos with
appropriate QoE metrics as the user moves around with the group of
tourists.
However, the heavy-tailed nature of several operational parameters
(e.g., buffer occupancy, throughput, client-server latency, and
variable transmission times) makes prediction-based adaptation by ABR
algorithms sub-optimal [ABR_2]. This is because with such
distributions, the law of large numbers (how long it takes for the
sample mean to stabilize) works too slowly [HEAVY_TAIL_2] and the
mean of sample does not equal the mean of distribution
[HEAVY_TAIL_2]; as a result, standard deviation and variance are
unsuitable as metrics for such operational parameters [HEAVY_TAIL_1].
Other subtle issues with these distributions include the "expectation
paradox" [HEAVY_TAIL_1] (the longer the wait for an event, the longer
a further need to wait) and the mismatch between the size and count
of events [HEAVY_TAIL_1].
This makes These issues make designing an algorithm
for adaptation error-prone and challenging. Such operational parameters include but are not limited
to buffer occupancy, throughput, client-server latency, and variable
transmission times. In addition, edge
devices and communication links may fail, and logical communication
relationships between various software components change frequently
as the user moves around with their XR device [UBICOMP].
4. XR Network Traffic
4.1. Traffic Workload
As discussed earlier, in Sections 1 and 3, the parameters that capture the
characteristics of XR application behavior are heavy-tailed.
Examples of such parameters include the distribution of arrival times
between XR application invocation, invocations, the amount of data transferred,
and the inter-arrival times of packets within a session. As a
result, any traffic model based on such parameters is also heavy-tailed. heavy-
tailed. Using these models to predict performance under alternative
resource allocations by the network operator is challenging. For
example, both uplink and downlink traffic to a user device has
parameters such as volume of XR data, burst time, and idle time that
are heavy-
tailed. heavy-tailed.
Table 1 below shows various streaming video applications and their
associated throughput requirements [METRICS_1]. Since our use case
envisages a 6 degrees of freedom (6DoF) video or point cloud, the
table indicates that it will require 200 to 1000 Mbps of bandwidth.
Also, the table shows that XR applications, such as the one in our
use case, transmit a larger amount of data per unit time as compared
to traditional regular video applications. As a result, issues arising from
heavy-tailed parameters, such as long-range dependent traffic
[METRICS_2] and self-similar traffic [METRICS_3], would be
experienced at timescales of milliseconds and microseconds rather
than hours or seconds. Additionally, burstiness at the timescale of
tens of milliseconds due to the multi-fractal spectrum of traffic
will be experienced [METRICS_4]. Long-range dependent traffic can
have long bursts, and various traffic parameters from widely
separated times can show correlation [HEAVY_TAIL_1]. Self-similar
traffic contains bursts at a wide range of timescales [HEAVY_TAIL_1].
Multi-fractal spectrum bursts for traffic summarize the statistical
distribution of local scaling exponents found in a traffic trace
[HEAVY_TAIL_1]. The operational consequence of XR traffic having
characteristics such as long-range dependency and self-similarity is
that the edge servers to which multiple XR devices are connected
wirelessly could face long bursts of traffic [METRICS_2] [METRICS_3].
In addition, multi-fractal spectrum burstiness at the scale of
milliseconds could induce jitter contributing to motion sickness
[METRICS_4]. This is because bursty traffic combined with variable
queueing delays leads to large delay jitter [METRICS_4]. The
operators of edge servers will need to run a "managed edge cloud
service" [METRICS_5] to deal with the above problems.
Functionalities that such a managed edge cloud service could
operationally provide include dynamic placement of XR servers,
mobility support, and energy management [METRICS_6]. Providing Edge
server
support for the edge servers in techniques being developed at the DETNET
Working Group such as those described in the IETF [RFC8939] [RFC9023]
[RFC8939], [RFC9023], and [RFC9450] could guarantee performance of XR
applications. For example, these techniques could be used for the
link between the XR device and the edge as well as within the managed
edge cloud service. Another option for network operators would could be to
deploy equipment that supports differentiated services [RFC2475] or
per-connection Quality-
of-Service Quality-of-Service (QoS) guarantees using RSVP
[RFC2210].
Thus, the provisioning of edge servers (in terms of the number of
servers, the topology, the placement of servers, the assignment of
link capacity, CPUs, and Graphics Processing Units (GPUs)) should be
performed with the above factors in mind.
+===============================================+============+
| Application | Throughput |
| | Required |
+===============================================+============+
| Real-world objects annotated with text and | 1 Mbps |
| images for workflow assistance (e.g., repair) | |
+-----------------------------------------------+------------+
| Video conferencing | 2 Mbps |
+-----------------------------------------------+------------+
| 3D model and data visualization | 2 to 20 |
| | Mbps |
+-----------------------------------------------+------------+
| Two-way 3D telepresence | 5 to 25 |
| | Mbps |
+-----------------------------------------------+------------+
| Current-Gen 360-degree video (4K) | 10 to 50 |
| | Mbps |
+-----------------------------------------------+------------+
| Next-Gen 360-degree video (8K, 90+ frames per | 50 to 200 |
| second, high dynamic range, stereoscopic) | Mbps |
+-----------------------------------------------+------------+
| 6DoF video or point cloud | 200 to |
| | 1000 Mbps |
+-----------------------------------------------+------------+
Table 1: Throughput Requirements for Streaming Video
Applications
Thus, the provisioning of edge servers (in terms of the number of
servers, the topology, the placement of servers, the assignment of
link capacity, CPUs, and Graphics Processing Units (GPUs)) should be
performed with the above factors in mind.
4.2. Traffic Performance Metrics
The performance requirements for XR traffic have characteristics that
need to be considered when operationalizing a network. These
characteristics are discussed in this section.
The bandwidth requirements of XR applications are substantially
higher than those of video-based applications.
The latency requirements of XR applications have been studied
recently [XR_TRAFFIC]. The following characteristics were
identified:
* The uploading of data from an XR device to a remote server for
processing dominates the end-to-end latency.
* A lack of visual features in the grid environment can cause
increased latencies as the XR device uploads additional visual
data for processing to the remote server.
* XR applications tend to have large bursts that are separated by
significant time gaps.
Additionally, XR applications interact with each other on a timescale
of an RTT propagation, and this must be considered when
operationalizing a network.
Table 2 [METRICS_6] shows a taxonomy of applications with their
associated required response times and bandwidths. Response times
can be defined as the time interval between the end of a request
submission and the end of the corresponding response from a system.
If the XR device offloads a task to an edge server, the response time
of the server is the RTT from when a data packet is sent from the XR
device until a response is received. Note that the required response
time provides an upper bound for the sum of the time taken by
computational tasks (such as processing of scenes and generation of
images) and the RTT. This response time depends only on the QoS
required by an application. The response time is therefore
independent of the underlying technology of the network and the time
taken by the computational tasks.
Our use case requires a response time of 20 ms at most and preferably
between 7-15 ms, as discussed earlier. This requirement for response
time is similar to the first two entries in Table 2. Additionally,
the required bandwidth for our use case is 200 to 1000 Mbps (see
Section 4.1). Since our use case envisages multiple users running
the XR application on their devices and connecting to the edge server
that is closest to them, these latency and bandwidth connections will
grow linearly with the number of users. The operators should match
the network provisioning to the maximum number of tourists that can
be supported by a link to an edge server.
+===================+==============+==========+=====================+
| Application | Required | Expected | Possible |
| | Response | Data | Implementations/ |
| | Time | Capacity | Examples |
+===================+==============+==========+=====================+
| Mobile XR-based | Less than 10 | Greater | Assisting |
| remote assistance | milliseconds | than 7.5 | maintenance |
| with uncompressed | | Gbps | technicians, |
| 4K (1920x1080 | | | Industry 4.0 |
| pixels) 120 fps | | | remote |
| HDR 10-bit real- | | | maintenance, |
| time video stream | | | remote assistance |
| | | | in robotics |
| | | | industry |
+-------------------+--------------+----------+---------------------+
| Indoor and | Less than 20 | 50 to | Guidance in theme |
| localized outdoor | milliseconds | 200 Mbps | parks, shopping |
| navigation | | | malls, |
| | | | archaeological |
| | | | sites, and |
| | | | museums |
+-------------------+--------------+----------+---------------------+
| Cloud-based | Less than 50 | 50 to | Google Live View, |
| mobile XR | milliseconds | 100 Mbps | XR-enhanced |
| applications | | | Google Translate |
+-------------------+--------------+----------+---------------------+
Table 2: Traffic Performance Metrics of Selected XR Applications
5. Conclusion
In order to operationalize a use case such as the one presented in
this document, a network operator could dimension their network to
provide a short and high-capacity network path from the edge
computing resources or storage to the mobile devices running the XR
application. This is required to ensure a response time of 20 ms at
most and preferably between 7-15 ms. Additionally, a bandwidth of
200 to 1000 Mbps is required by such applications. To deal with the
characteristics of XR traffic as discussed in this document, network
operators could deploy a managed edge cloud service that
operationally provides dynamic placement of XR servers, mobility
support, and energy management. Although the use case is technically
feasible, economic viability is an important factor that must be
considered.
6. IANA Considerations
This document has no IANA actions.
7. Security Considerations
The security issues for the presented use case are similar to other
streaming applications [DIST] [NIST1] [CWE] those
described in [DIST], [NIST1], [CWE], and [NIST2]. This document does
not introduce any new security issues.
8. Informative References
[ABR_1] Mao, H., Netravali, R., and M. Alizadeh, "Neural Adaptive
Video Streaming with Pensieve", SIGCOMM '17: Proceedings
of the Conference of the ACM Special Interest Group on
Data Communication, pp. 197-210,
DOI 10.1145/3098822.3098843, 2017,
<https://dl.acm.org/doi/10.1145/3098822.3098843>.
[ABR_2] Yan, F., Ayers, H., Zhu, C., Fouladi, S., Hong, J., Zhang,
K., Levis, P., and K. Winstein, "Learning in situ: a
randomized experiment in video streaming", 17th USENIX
Symposium on Networked Systems Design and Implementation
(NSDI '20), pp. 495-511, February 2020,
<https://www.usenix.org/conference/nsdi20/presentation/
yan>.
[AUGMENTED]
Schmalstieg, D. and T. Höllerer, "Augmented Reality:
Principles and Practice", Addison-Wesley Professional,
2016, <https://www.oreilly.com/library/view/augmented-
reality-principles/9780133153217/>.
[AUGMENTED_2]
Azuma, R.T., "A Survey of Augmented Reality", Presence:
Teleoperators and Virtual Environments, vol. 6, no. 4, pp.
355-385, DOI 10.1162/pres.1997.6.4.355, August 1997,
<https://direct.mit.edu/pvar/article-
abstract/6/4/355/18336/A-Survey-of-Augmented-
Reality?redirectedFrom=fulltext>.
[BATT_DRAIN]
Seneviratne, S., Hu, Y., Nguyen, T., Lan, G., Khalifa, S.,
Thilakarathna, K., Hassan, M., and A. Seneviratne, "A
Survey of Wearable Devices and Challenges", IEEE
Communication Surveys and Tutorials, vol. 19 no. 4, pp.
2573-2620, DOI 10.1109/COMST.2017.2731979, 2017,
<https://ieeexplore.ieee.org/document/7993011>.
[BLUR] Kan, P. and H. Kaufmann, "Physically-Based Depth of Field
in Augmented Reality", Eurographics 2012 - Short Papers,
pp. 89-92, DOI 10.2312/conf/EG2012/short/089-092, 2012,
<https://diglib.eg.org/items/6954bf7e-5852-44cf-
8155-4ba269dc4cee>.
[CLOUD] Corneo, L., Eder, M., Mohan, N., Zavodovski, A., Bayhan,
S., Wong, W., Gunningberg, P., Kangasharju, J., and J.
Ott, "Surrounded by the Clouds: A Comprehensive Cloud
Reachability Study", WWW '21: Proceedings of the Web
Conference 2021, pp. 295-304, DOI 10.1145/3442381.3449854,
2021, <https://dl.acm.org/doi/10.1145/3442381.3449854>.
[CWE] SANS Institute, "CWE/SANS TOP 25 Most Dangerous Software
Errors", <https://www.sans.org/top25-software-errors/>.
[DEV_HEAT_1]
LiKamWa, R., Wang, Z., Carroll, A., Lin, F., and L. Zhong,
"Draining our glass: an energy and heat characterization
of Google Glass", APSys '14: 5th Asia-Pacific Workshop on
Systems, pp. 1-7, DOI 10.1145/2637166.2637230, 2014,
<https://dl.acm.org/doi/10.1145/2637166.2637230>.
[DEV_HEAT_2]
Matsuhashi, K., Kanamoto, T., and A. Kurokawa, "Thermal
Model and Countermeasures for Future Smart Glasses",
Sensors, vol. 20, no. 5, p. 1446, DOI 10.3390/s20051446,
2020, <https://www.mdpi.com/1424-8220/20/5/1446>.
[DIST] Coulouris, G., Dollimore, J., Kindberg, T., and G. Blair,
"Distributed Systems: Concepts and Design", Addison-
Wesley, 2011, <https://dl.acm.org/doi/10.5555/2029110>.
[EDGE_1] Satyanarayanan, M., "The Emergence of Edge Computing",
Computer, vol. 50, no. 1, pp. 30-39,
DOI 10.1109/MC.2017.9, 2017,
<https://ieeexplore.ieee.org/document/7807196>.
[EDGE_2] Satyanarayanan, M., Klas, G., Silva, M., and S. Mangiante,
"The Seminal Role of Edge-Native Applications", 2019 IEEE
International Conference on Edge Computing (EDGE), pp.
33-40, DOI 10.1109/EDGE.2019.00022, 2019,
<https://ieeexplore.ieee.org/document/8812200>.
[EDGE_3] Peterson, L. and O. Sunay, "5G Mobile Networks: A Systems
Approach", Synthesis Lectures on Network Systems,
DOI 10.1007/978-3-031-79733-0, 2020,
<https://link.springer.com/
book/10.1007/978-3-031-79733-0>.
[GLB_ILLUM_1]
Kan, P. and H. Kaufmann, "Differential Irradiance Caching
for fast high-quality light transport between virtual and
real worlds", 2013 IEEE International Symposium on Mixed
and Augmented Reality (ISMAR), pp. 133-141,
DOI 10.1109/ISMAR.2013.6671773, 2013,
<https://ieeexplore.ieee.org/document/6671773>.
[GLB_ILLUM_2]
Franke, T., "Delta Voxel Cone Tracing", 2014 IEEE
International Symposium on Mixed and Augmented Reality
(ISMAR), pp. 39-44, DOI 10.1109/ISMAR.2014.6948407, 2014,
<https://ieeexplore.ieee.org/document/6948407>.
[HEAVY_TAIL_1]
Crovella, M. and B. Krishnamurthy, "Internet Measurement:
Infrastructure, Traffic and Applications", John Wiley and
Sons, 2006, <https://www.wiley.com/en-us/Internet+Measurem
ent%3A+Infrastructure%2C+Traffic+and+Applications-
p-9780470014615>.
[HEAVY_TAIL_2]
Taleb, N., "Statistical Consequences of Fat Tails: Real
World Preasymptotics, Epistemology, and Applications",
Revised Edition, STEM Academic Press, 2022,
<https://arxiv.org/pdf/2001.10488>.
[HEAVY_TAIL_3]
Ehrenberg, A., "A Primer in Data Reduction: An
Introductory Statistics Textbook", John Wiley and Sons,
2007, <https://www.wiley.com/en-us/A+Primer+in+Data+Reduct
ion%3A+An+Introductory+Statistics+Textbook-
p-9780471101352>.
[LENS_DIST]
Fuhrmann, A., Schmalstieg, D., and W. Purgathofer,
"Practical Calibration Procedures for Augmented Reality",
Virtual Environments 2000, pp. 3-12,
DOI 10.1007/978-3-7091-6785-4_2, 2000,
<https://link.springer.com/
chapter/10.1007/978-3-7091-6785-4_2>.
[METRICS_1]
ABI Research, "Augmented and Virtual Reality: The first
Wave of Killer Apps: Qualcomm - ABI Research", April 2017,
<https://gsacom.com/paper/augmented-virtual-reality-first-
wave-5g-killer-apps-qualcomm-abi-research/>.
[METRICS_2]
Paxon, V. and S. Floyd, "Wide area traffic: the failure of
Poisson modeling", IEEE/ACM Transactions on Networking,
vol. 3, no. 3, pp. 226-244, DOI 10.1109/90.392383, June
1995, <https://ieeexplore.ieee.org/document/392383>.
[METRICS_3]
Willinger, W., Taqqu, M.S., Sherman, R., and D.V. Wilson,
"Self-similarity through high variability: statistical
analysis and Ethernet LAN traffic at source level", IEEE/
ACM Transactions on Networking, vol. 5, no. 1, pp. 71-86,
DOI 10.1109/90.554723, February 1997,
<https://ieeexplore.ieee.org/abstract/document/554723>.
[METRICS_4]
Gilbert, A.C., "Multiscale Analysis and Data Networks",
Applied and Computational Harmonic Analysis, vol. 10, no.
3, pp. 185-202, DOI 10.1006/acha.2000.0342, May 2001,
<https://www.sciencedirect.com/science/article/pii/
S1063520300903427>.
[METRICS_5]
Beyer, B., Ed., Jones, C., Ed., Petoff, J., Ed., and N.R.
Murphy, Ed., "Site Reliability Engineering: How Google
Runs Production Systems", O'Reilly Media, Inc., 2016,
<https://research.google/pubs/site-reliability-
engineering-how-google-runs-production-systems/>.
[METRICS_6]
Siriwardhana, Y., Porambage, P., Liyanage, M., and M.
Ylianttila, "A Survey on Mobile Augmented Reality With 5G
Mobile Edge Computing: Architectures, Applications, and
Technical Aspects", IEEE Communications Surveys and
Tutorials, vol. 23, no. 2, pp. 1160-1192,
DOI 10.1109/COMST.2021.3061981, 2021,
<https://ieeexplore.ieee.org/document/9363323>.
[NIST1] NIST, "Cloud Computing Synopsis and Recommendations", NIST
SP 800-146, DOI 10.6028/NIST.SP.800-146, May 2012,
<https://csrc.nist.gov/pubs/sp/800/146/final>.
[NIST2] NIST, "Guide to General Server Security", NIST SP 800-123,
DOI 10.6028/NIST.SP.800-123, July 2008,
<https://csrc.nist.gov/pubs/sp/800/123/final>.
[NOISE] Fischer, J., Bartz, D., and W. Strasser, "Enhanced visual
realism by incorporating camera image effects", 2006 IEEE/
ACM International Symposium on Mixed and Augmented
Reality, pp. 205-208, DOI 10.1109/ISMAR.2006.297815, 2006,
<https://ieeexplore.ieee.org/document/4079277>.
[OCCL_1] Breen, D.E., Whitaker, R.T., Rose, E., and M. Tuceryan,
"Interactive Occlusion and Automatic Object Placement for
Augmented Reality", Computer Graphics Forum, vol. 15, no.
3, pp. 11-22, DOI 10.1111/1467-8659.1530011, August 1996,
<https://onlinelibrary.wiley.com/
doi/10.1111/1467-8659.1530011>.
[OCCL_2] Zheng, F., Schmalstieg, D., and G. Welch, "Pixel-wise
closed-loop registration in video-based augmented
reality", 2014 IEEE International Symposium on Mixed and
Augmented Reality (ISMAR), pp. 135-143,
DOI 10.1109/ISMAR.2014.6948419, 2014,
<https://ieeexplore.ieee.org/document/6948419>.
[OCCL_3] Lang, B., "Oculus Shares 5 Key Ingredients for Presence in
Virtual Reality", Road to VR, 24 September 2014,
<https://www.roadtovr.com/oculus-shares-5-key-ingredients-
for-presence-in-virtual-reality/>.
[PER_SENSE]
Mania, K., Adelstein, B.D., Ellis, S.R., and M.I. Hill,
"Perceptual sensitivity to head tracking latency in
virtual environments with varying degrees of scene
complexity.", APGV '04: Proceedings of the 1st Symposium
on Applied perception in graphics and visualization, pp.
39-47, DOI 10.1145/1012551.1012559, 2004,
<https://dl.acm.org/doi/10.1145/1012551.1012559>.
[PHOTO_REG]
Liu, Y. and X. Granier, "Online Tracking of Outdoor
Lighting Variations for Augmented Reality with Moving
Cameras", IEEE Transactions on Visualization and Computer
Graphics, vol. 18, no. 4, pp. 573-580,
DOI 10.1109/TVCG.2012.53, 2012,
<https://ieeexplore.ieee.org/document/6165138>.
[PREDICT] Buker, T.J., Vincenzi, D.A., and J.E. Deaton, "The effect
of apparent latency on simulator sickness while using a
see-through helmet-mounted display: reducing apparent
latency with predictive compensation", Human Factors, vol.
54, no. 2, pp. 235-249, DOI 10.1177/0018720811428734,
April 2012, <https://pubmed.ncbi.nlm.nih.gov/22624290/>.
[REG] Holloway, R.L., "Registration Error Analysis for Augmented
Reality", Presence: Teleoperators and Virtual
Environments, vol. 6, no. 4, pp. 413-432,
DOI 10.1162/pres.1997.6.4.413, August 1997,
<https://direct.mit.edu/pvar/article-
abstract/6/4/413/18334/Registration-Error-Analysis-for-
Augmented-Reality?redirectedFrom=fulltext>.
[RFC2210] Wroclawski, J., "The Use of RSVP with IETF Integrated
Services", RFC 2210, DOI 10.17487/RFC2210, September 1997,
<https://www.rfc-editor.org/info/rfc2210>.
[RFC2475] Blake, S., Black, D., Carlson, M., Davies, E., Wang, Z.,
and W. Weiss, "An Architecture for Differentiated
Services", RFC 2475, DOI 10.17487/RFC2475, December 1998,
<https://www.rfc-editor.org/info/rfc2475>.
[RFC8939] Varga, B., Ed., Farkas, J., Berger, L., Fedyk, D., and S.
Bryant, "Deterministic Networking (DetNet) Data Plane:
IP", RFC 8939, DOI 10.17487/RFC8939, November 2020,
<https://www.rfc-editor.org/info/rfc8939>.
[RFC9023] Varga, B., Ed., Farkas, J., Malis, A., and S. Bryant,
"Deterministic Networking (DetNet) Data Plane: IP over
IEEE 802.1 Time-Sensitive Networking (TSN)", RFC 9023,
DOI 10.17487/RFC9023, June 2021,
<https://www.rfc-editor.org/info/rfc9023>.
[RFC9450] Bernardos, CJ., Ed., Papadopoulos, G., Thubert, P., and F.
Theoleyre, "Reliable and Available Wireless (RAW) Use
Cases", RFC 9450, DOI 10.17487/RFC9450, August 2023,
<https://www.rfc-editor.org/info/rfc9450>.
[SLAM_1] Ventura, J., Arth, C., Reitmayr, G., and D. Schmalstieg,
"A Minimal Solution to the Generalized Pose-and-Scale
Problem", 2014 IEEE Conference on Computer Vision and
Pattern Recognition, pp. 422-429,
DOI 10.1109/CVPR.2014.61, 2014,
<https://ieeexplore.ieee.org/document/6909455>.
[SLAM_2] Sweeny, C., Fragoso, V., Höllerer, T., and M. Turk, "gDLS:
A Scalable Solution to the Generalized Pose and Scale
Problem", Computer Vision - ECCV 2014, pp. 16-31,
DOI 10.1007/978-3-319-10593-2_2, 2014,
<https://link.springer.com/
chapter/10.1007/978-3-319-10593-2_2>.
[SLAM_3] Gauglitz, S., Sweeney, C., Ventura, J., Turk, M., and T.
Höllerer, "Model Estimation and Selection towards
Unconstrained Real-Time Tracking and Mapping", IEEE
Transactions on Visualization and Computer Graphics, vol.
20, no. 6, pp. 825-838, DOI 10.1109/TVCG.2013.243, 2014,
<https://ieeexplore.ieee.org/document/6636302>.
[SLAM_4] Pirchheim, C., Schmalstieg, D., and G. Reitmayr, "Handling
pure camera rotation in keyframe-based SLAM", 2013 IEEE
International Symposium on Mixed and Augmented Reality
(ISMAR), pp. 229-238, DOI 10.1109/ISMAR.2013.6671783,
2013, <https://ieeexplore.ieee.org/document/6671783>.
[UBICOMP] Bardram, J. and A. Friday, "Ubiquitous Computing Systems",
Ubiquitous Computing Fundamentals, 1st Edition, Chapman
and Hall/CRC Press, pp. 37-94, 2009,
<https://www.taylorfrancis.com/chapters/
edit/10.1201/9781420093612-6/ubiquitous-computing-systems-
jakob-bardram-adrian-friday>.
[URLLC] 3GPP, "Study on enhancement of Ultra-Reliable Low-Latency
Communication (URLLC) support in the 5G Core network
(5GC)", 3GPP TR 23.725, 2019,
<https://portal.3gpp.org/desktopmodules/Specifications/
SpecificationDetails.aspx?specificationId=3453>.
[VIS_INTERFERE]
Kalkofen, D., Mendez, E., and D. Schmalstieg, "Interactive
Focus and Context Visualization for Augmented Reality",
2007 6th IEEE and ACM International Symposium on Mixed and
Augmented Reality, pp. 191-201,
DOI 10.1109/ISMAR.2007.4538846, 2007,
<https://ieeexplore.ieee.org/document/4538846>.
[XR] 3GPP, "Extended Reality (XR) in 5G", 3GPP TR 26.928, 2020,
<https://portal.3gpp.org/desktopmodules/Specifications/
SpecificationDetails.aspx?specificationId=3534>.
[XR_TRAFFIC]
Apicharttrisorn, K., Balasubramanian, B., Chen, J.,
Sivaraj, R., Tsai, Y., Jana, R., Krishnamurthy, S., Tran,
T., and Y. Zhou, "Characterization of Multi-User Augmented
Reality over Cellular Networks", 2020 17th Annual IEEE
International Conference on Sensing, Communication, and
Networking (SECON), pp. 1-9,
DOI 10.1109/SECON48991.2020.9158434, 2020,
<https://ieeexplore.ieee.org/document/9158434>.
Acknowledgements
Many thanks to Spencer Dawkins, Rohit Abhishek, Jake Holland, Kiran
Makhijani, Ali Begen, Cullen Jennings, Stephan Wenger, Eric Vyncke,
Wesley Eddy, Paul Kyzivat, Jim Guichard, Roman Danyliw, Warren
Kumari, and Zaheduzzaman Sarker for providing helpful feedback,
suggestions, and comments.
Authors' Addresses
Renan Krishna
United Kingdom
Email: renan.krishna@gmail.com
Akbar Rahman
Ericsson
349 Terry Fox Drive
Ottawa Ontario K2K 2V6
Canada
Email: Akbar.Rahman@ericsson.com