Energy Efficiency Optimisation of Joint Computational Task Offloading and Resource Allocation Using Particle Swarm Optimisation Approach in Vehicular Edge Networks

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 10; p. 3001
• Main Authors: Alam, Amjad, Shah, Purav, Trestian, Ramona, Ali, Kamran, Mapp, Glenford
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 09.05.2024
• Subjects: Algorithms; Cloud computing; Communication; Data transmission; Decision-making; Driverless cars; Edge computing; Energy consumption; Energy efficiency; Energy management systems; Energy use; Mathematical optimization; meta-heuristic algorithm; nature-inspired algorithm; particle swarm optimisation; Privacy; Quality of service; task offloading; Vehicles; vehicular edge computing; Workloads; nature-inspired algorithm; computation resource allocation; particle swarm optimisation; task offloading; meta-heuristic algorithm; vehicular edge computing; energy efficiency
• DOI: 10.3390/s24103001
• ISSN: 1424-8220

With the progression of smart vehicles, i.e., connected autonomous vehicles (CAVs), and wireless technologies, there has been an increased need for substantial computational operations for tasks such as path planning, scene recognition, and vision-based object detection. Managing these intensive computational applications is concerned with significant energy consumption. Hence, for this article, a low-cost and sustainable solution using computational offloading and efficient resource allocation at edge devices within the Internet of Vehicles (IoV) framework has been utilised. To address the quality of service (QoS) among vehicles, a trade-off between energy consumption and computational time has been taken into consideration while deciding on the offloading process and resource allocation. The offloading process has been assigned at a minimum wireless resource block level to adapt to the beyond 5G (B5G) network. The novel approach of joint optimisation of computational resources and task offloading decisions uses the meta-heuristic particle swarm optimisation (PSO) algorithm and decision analysis (DA) to find the near-optimal solution. Subsequently, a comparison is made with other proposed algorithms, namely CTORA, CODO, and Heuristics, in terms of computational efficiency and latency. The performance analysis reveals that the numerical results outperform existing algorithms, demonstrating an 8% and a 5% increase in energy efficiency.