Grant: Discovery Grants Program - Individual
University of Calgary
$24,000.00
Robust Intelligence for Beyond-5G Networks and Applications
EF 2021-22
Résumé
The recent advances in wireless networks standardization are laying the foundations to support high throughput, high reliability, and ultra-low latency applications - and to do so simultaneously. This will open the door to exciting services such as multi-drone surveillance for precision farming and rescue operations, connected factories, autonomous vehicle communications, and extended reality (XR). However, a major hindrance toward the widespread introduction of such applications by service providers is the inability to support these services at scale and with reasonable deployment costs. To tackle this, the academic and industrial research communities have, and continue to, demonstrate how intelligence and adaptability in network functions and architecture can provide a path toward scalable and cost-efficient deployments of 5G services. While there has been notable progress in this research, the practical adoption of network intelligence methodologies is strongly limited. This is due to their inability to: 1) perform consistently well under generic traffic and network conditions and, 2) guarantee stability and performance bounds while exploring the optimal network configurations. In order to address the aforementioned limitations and drive the practical adoption of network intelligence, it is paramount to introduce robustness in the intelligence approaches. For instance, a congestion control mechanism that uses reinforcement learning techniques to control the queuing delay based on temporal traffic and network state may work exceptionally well once converged. During convergence however, the reinforcement learning agent will likely introduce unacceptable delay and reliability performance that both violates service level agreements (SLAs) and may cause physical harm given the nature of machine-type Beyond-5G applications. Therefore, in order to facilitate industrial adoption, robust intelligence methods that control the behavior of learning itself need to be developed. This is the overarching research goal of this Discovery Grant (DG) Application. This objective of this DG research program is to design robust, practical intelligence in future networks with an emphasis on enabling ubiquitous B5G/6G applications. The research will take a holistic view of end-to-end solutions that incorporate the details of application traffic, cross-layer interactions, and telecom standards. The anticipated end result is networking innovations that are patented and incorporated in commercial networks to improve the quality of life through new experiences, industrial automation, and ubiquitous telepresence. The program will train 8 HQP, where trainees will benefit from an interdisciplinary collaborative environment spanning networking, intelligence, extended reality, and cyber-physical systems. The implemented simulation platforms, source code, and demos will be made publicly available to researchers to further advance and foster innovations in the B5G/6G era.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2021-04050
Name nom
Abou-Zeid, Hatem
Department département
Electrical and Software Engineering - Electrical and Software Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2021
Competition year année de concours
2021
Award amount
24000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2525
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Wireless communication systems
Research subject fr
Systèmes de télécommunications sans fil
Installment
inst:1
Partie
1
Nb partie
5
Application title
Robust Intelligence for Beyond-5G Networks and Applications
Keyword
NSERC
Application summary
The recent advances in wireless networks standardization are laying the foundations to support high throughput, high reliability, and ultra-low latency applications - and to do so simultaneously. This will open the door to exciting services such as multi-drone surveillance for precision farming and rescue operations, connected factories, autonomous vehicle communications, and extended reality (XR). However, a major hindrance toward the widespread introduction of such applications by service providers is the inability to support these services at scale and with reasonable deployment costs. To tackle this, the academic and industrial research communities have, and continue to, demonstrate how intelligence and adaptability in network functions and architecture can provide a path toward scalable and cost-efficient deployments of 5G services. While there has been notable progress in this research, the practical adoption of network intelligence methodologies is strongly limited. This is due to their inability to: 1) perform consistently well under generic traffic and network conditions and, 2) guarantee stability and performance bounds while exploring the optimal network configurations. In order to address the aforementioned limitations and drive the practical adoption of network intelligence, it is paramount to introduce robustness in the intelligence approaches. For instance, a congestion control mechanism that uses reinforcement learning techniques to control the queuing delay based on temporal traffic and network state may work exceptionally well once converged. During convergence however, the reinforcement learning agent will likely introduce unacceptable delay and reliability performance that both violates service level agreements (SLAs) and may cause physical harm given the nature of machine-type Beyond-5G applications. Therefore, in order to facilitate industrial adoption, robust intelligence methods that control the behavior of learning itself need to be developed. This is the overarching research goal of this Discovery Grant (DG) Application. This objective of this DG research program is to design robust, practical intelligence in future networks with an emphasis on enabling ubiquitous B5G/6G applications. The research will take a holistic view of end-to-end solutions that incorporate the details of application traffic, cross-layer interactions, and telecom standards. The anticipated end result is networking innovations that are patented and incorporated in commercial networks to improve the quality of life through new experiences, industrial automation, and ubiquitous telepresence. The program will train 8 HQP, where trainees will benefit from an interdisciplinary collaborative environment spanning networking, intelligence, extended reality, and cyber-physical systems. The implemented simulation platforms, source code, and demos will be made publicly available to researchers to further advance and foster innovations in the B5G/6G era.