Grant: Discovery Grants Program - Individual
École de technologie supérieure
$32,000.00
SAGIN4AI: Enabling Future AI-based Services on Space-Air-Ground Integrated Networks
FY 2024-25
Summary
Given the unprecedented growth of mobile traffic demands, mainly due to the accelerated development of artificial intelligence (AI)-native applications such as traffic surveillance, remote health monitoring, and battlefield assessment, a paradigm shift in edge computing has been observed recently; from terrestrial edge computing towards non-terrestrial edge computing, aiming to satisfy compute-intensive services anywhere, anytime. This paradigm shift is identified as the space-air-ground integrated network, a.k.a., SAGIN. The development of SAGIN is still in its infancy and involves novel non-terrestrial nodes, such as unmanned aerial vehicles (UAVs), high altitude platform stations (HAPS), and low-Earth orbit (LEO) satellites. However, these nodes have different intrinsic characteristics and capabilities, which makes their utilization for compute-intensive (e.g., AI-based) applications very complex. This is seen as a critical challenge to unleash the full potential of SAGIN in supporting critical and non-critical compute-intensive services around the globe.
The long-term vision of my research work consists on developing and validating an efficient and practical SAGIN framework, aiming to enable seamless handling of a plethora of AI-based services with heterogeneous and stringent quality-of-service (QoS) requirements. Specifically, my program will tackle this problem from two perspectives, namely the networking and the AI application design perspectives. In the first perspective, I propose studying the combined communication, computing, and spatial resource allocation problem, owing to the SAGIN's uncertain environment conditions, due, for instance, to the nodes' mobility, meteorological conditions, etc. Subsequently, the focus will shift to the mobility and handover management problems in SAGIN. Indeed, I plan to develop smart and energy-efficient mobility and handover management strategies that can rapidly adapt to the behavioural patterns and predictions of both users and SAGIN nodes. In the second perspective, I propose AI-based applications' design to support their seamless execution within the computing-enabled SAGIN. In particular, I intend to exploit conventional neural network procedures, e.g., pruning and low-level quantization, with recent tiny machine learning (tinyML) and neural network segmentation approaches in order to reduce the communication, computing, and storage burden within the SAGIN's nodes.
The outcomes of my research program are of paramount importance to the scientific community, industry practitioners and society. Specifically, they will contribute to the development of the 6th generation (6G) wireless networks, in particular SAGIN features and functionalities, bring valuable insights into the latter's capability to support compute-intensive applications with stringent QoS requirements, enable business developments to bridge the digital divide around the globe, and finally create novel 6G-based services.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-03757
Name nom
Jaafar, Wael
Department département
Software and IT Engineering
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
32000
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
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
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
SAGIN4AI: Enabling Future AI-based Services on Space-Air-Ground Integrated Networks
Keywords
space-air-ground integrated network; internet-of-things; unmanned aerial vehicle; high altitude platform station; satellite; edge computing; resource allocation; task offloading; optimization
Application summary
Given the unprecedented growth of mobile traffic demands, mainly due to the accelerated development of artificial intelligence (AI)-native applications such as traffic surveillance, remote health monitoring, and battlefield assessment, a paradigm shift in edge computing has been observed recently; from terrestrial edge computing towards non-terrestrial edge computing, aiming to satisfy compute-intensive services anywhere, anytime. This paradigm shift is identified as the space-air-ground integrated network, a.k.a., SAGIN. The development of SAGIN is still in its infancy and involves novel non-terrestrial nodes, such as unmanned aerial vehicles (UAVs), high altitude platform stations (HAPS), and low-Earth orbit (LEO) satellites. However, these nodes have different intrinsic characteristics and capabilities, which makes their utilization for compute-intensive (e.g., AI-based) applications very complex. This is seen as a critical challenge to unleash the full potential of SAGIN in supporting critical and non-critical compute-intensive services around the globe.
The long-term vision of my research work consists on developing and validating an efficient and practical SAGIN framework, aiming to enable seamless handling of a plethora of AI-based services with heterogeneous and stringent quality-of-service (QoS) requirements. Specifically, my program will tackle this problem from two perspectives, namely the networking and the AI application design perspectives. In the first perspective, I propose studying the combined communication, computing, and spatial resource allocation problem, owing to the SAGIN's uncertain environment conditions, due, for instance, to the nodes' mobility, meteorological conditions, etc. Subsequently, the focus will shift to the mobility and handover management problems in SAGIN. Indeed, I plan to develop smart and energy-efficient mobility and handover management strategies that can rapidly adapt to the behavioural patterns and predictions of both users and SAGIN nodes. In the second perspective, I propose AI-based applications' design to support their seamless execution within the computing-enabled SAGIN. In particular, I intend to exploit conventional neural network procedures, e.g., pruning and low-level quantization, with recent tiny machine learning (tinyML) and neural network segmentation approaches in order to reduce the communication, computing, and storage burden within the SAGIN's nodes.
The outcomes of my research program are of paramount importance to the scientific community, industry practitioners and society. Specifically, they will contribute to the development of the 6th generation (6G) wireless networks, in particular SAGIN features and functionalities, bring valuable insights into the latter's capability to support compute-intensive applications with stringent QoS requirements, enable business developments to bridge the digital divide around the globe, and finally create novel 6G-based services.