Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Queen's University

$50,000.00

Constrained Online Learning for Wireless Computing Networks

EF 2024-25

Résumé
Due to the emergence of big data and artificial intelligence (AI) and the ever-increasing computing capabilities of devices, next generation wireless networks are shifting from a pure communication network to a distributed computing platform, representing a convergence of wireless networking and computing. Such convergence leads to a growing research interest in wireless computing networks that are expected to be the foundation for Internet of Things, edge computing, and 6G and beyond. Wireless computing networks are required to operate in a highly dynamic wireless environment and under heterogeneity of resources, which significantly complicates the design of scheduling, routing, and resource allocation. Recently, online learning paradigms have been widely applied to cope with uncertainty and complexity. However, the design of online learning solutions should consider various practical constraints such as storage capacity, energy consumption, bandwidth, service fulfillment, etc. The overarching goal of this research program is to establish efficient online learning frameworks to cope with uncertainty and complexity of wireless computing networks by considering various engineering constraints. The emphasis lies on leveraging, improving, and creating new learning techniques to determine and optimize scheduling and control policies for network/computing resource management. Specifically, the proposed research will advance the convergence of wireless networking and computing on multiple fronts including (i) development of constrained bandit learning schemes to tackle the fundamental service function placement problem; (ii) development of efficient algorithms for solving constrained online convex optimization of joint network/computing resource allocation; and (iii) development of constrained reinforcement learning frameworks for network utility maximization in a mobile and power-constrained computing network. This research program seeks to advance the state of the art of machine intelligence required in designing wireless computing networks. Ultimately, this will lead to more efficient use of network/computing resources, more intelligent service management, and enhanced service performance, and therefore promote the smart and agile deployment of next-generation distributed computing networks for building smart and connected infrastructure/services. The learning techniques developed in this research program will also enrich the online learning theory and the associated analytic tools with great potential to be applied in broader application domains. During the funding period, 3 PhD, 4 MSc and 5 undergraduate students will be trained as future engineers with expertise in machine learning, wireless networking, and distributed and mobile computing. There is a strong demand for HQP with knowledge in these areas and their future employment will accelerate the translation of next-generation network and computing technologies to the Canadian industry.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2023-04548
Name nom
Lu, Ning
Department département
Electrical and Computer Engineering - Electrical and Computer Engineering
Organization id
29
Institution établissement
Queen's University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
50000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
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
2508
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Communications networks
Research subject fr
Réseaux de télécommunications
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Constrained Online Learning for Wireless Computing Networks
Keywords
wireless computing network; edge computing; constrained learning; multi-armed bandit; reinforcement learning; online convex optimization; edge computing; network utility maximization; wireless scheduling
Application summary
Due to the emergence of big data and artificial intelligence (AI) and the ever-increasing computing capabilities of devices, next generation wireless networks are shifting from a pure communication network to a distributed computing platform, representing a convergence of wireless networking and computing. Such convergence leads to a growing research interest in wireless computing networks that are expected to be the foundation for Internet of Things, edge computing, and 6G and beyond. Wireless computing networks are required to operate in a highly dynamic wireless environment and under heterogeneity of resources, which significantly complicates the design of scheduling, routing, and resource allocation. Recently, online learning paradigms have been widely applied to cope with uncertainty and complexity. However, the design of online learning solutions should consider various practical constraints such as storage capacity, energy consumption, bandwidth, service fulfillment, etc. The overarching goal of this research program is to establish efficient online learning frameworks to cope with uncertainty and complexity of wireless computing networks by considering various engineering constraints. The emphasis lies on leveraging, improving, and creating new learning techniques to determine and optimize scheduling and control policies for network/computing resource management. Specifically, the proposed research will advance the convergence of wireless networking and computing on multiple fronts including (i) development of constrained bandit learning schemes to tackle the fundamental service function placement problem; (ii) development of efficient algorithms for solving constrained online convex optimization of joint network/computing resource allocation; and (iii) development of constrained reinforcement learning frameworks for network utility maximization in a mobile and power-constrained computing network. This research program seeks to advance the state of the art of machine intelligence required in designing wireless computing networks. Ultimately, this will lead to more efficient use of network/computing resources, more intelligent service management, and enhanced service performance, and therefore promote the smart and agile deployment of next-generation distributed computing networks for building smart and connected infrastructure/services. The learning techniques developed in this research program will also enrich the online learning theory and the associated analytic tools with great potential to be applied in broader application domains. During the funding period, 3 PhD, 4 MSc and 5 undergraduate students will be trained as future engineers with expertise in machine learning, wireless networking, and distributed and mobile computing. There is a strong demand for HQP with knowledge in these areas and their future employment will accelerate the translation of next-generation network and computing technologies to the Canadian industry.