Dynamic Offloading Strategies within the Internet of Vehicles (IoV) represent a pivotal response to the challenges encountered in Vehicle Edge Computing (VEC). VEC, positioned at the nexus of edge computing and vehicular networks, aims to enhance vehicular systems’ intelligence and efficacy by integrating computational capabilities into vehicles and roadside infrastructure. Leveraging proximity to the network edge, VEC optimizes data processing and task execution, mitigating latency and enabling real-time decision-making for demanding applications such as autonomous driving and bandwidth-intensive functionalities like augmented reality (AR).Addressing the constraints posed by onboard computational limitations, dynamic network conditions, and the need for rapid decision-making in dynamic vehicular environments, Dynamic Offloading Strategies emerge as a pivotal solution. These strategies dynamically allocate computational tasks between vehicular systems and edge resources, optimizing resource utilization. By mitigating challenges related to latency, energy consumption, and computational constraints, these strategies foster a responsive vehicular ecosystem. Adapting dynamically to fluctuating network conditions and computational demands, they enhance VEC systems’ efficiency and performance, addressing resource constraints and uncertainties inherent in vehicular environments.
Dynamic Offloading Strategies in Internet of Vehicles to Address VEC Challenges
Communic.Comp.Inf.Science
International Conference on Information Processing and Network Provisioning ; 2024 ; Beijing, China June 14, 2024 - June 16, 2024
22.07.2025
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Internet of Vehicles (IoV) , Dynamic Offloading Strategies , Vehicle Edge Computing (VEC) , Vehicular Networks , Edge Computing Signal, Image and Speech Processing , Computer Systems Organization and Communication Networks , Computer Science , Cyber-physical systems, IoT , Computer Communication Networks , Mobile and Network Security , Professional Computing