Energy Efficiency Optimisation of Joint Computational Task Offloading and Resource Allocation Using Particle Swarm...

Area of Science:

• Intelligent Transportation Systems
• Edge Computing
• Wireless Communications

Background:

• Connected autonomous vehicles (CAVs) require significant computational power for complex tasks like path planning and object detection.
• Intensive computations in CAVs lead to high energy consumption, posing sustainability challenges.
• The Internet of Vehicles (IoV) framework offers potential for distributed computing but requires efficient resource management.

Purpose of the Study:

• To propose a low-cost, sustainable solution for managing computational demands in CAVs.
• To optimize the trade-off between energy consumption and computational time for offloading decisions.
• To enhance Quality of Service (QoS) in IoV environments through efficient resource allocation.

Main Methods:

• Utilized computational offloading and efficient resource allocation at edge devices within the IoV framework.
• Implemented a joint optimization of computational resources and task offloading decisions.
• Employed the meta-heuristic Particle Swarm Optimization (PSO) algorithm and Decision Analysis (DA) for near-optimal solutions.
• Assigned the offloading process at a minimum wireless resource block level for Beyond 5G (B5G) networks.

Main Results:

• The proposed approach demonstrated superior performance compared to existing algorithms (CTORA, CODO, Heuristics).
• Achieved an 8% increase in energy efficiency.
• Achieved a 5% increase in computational efficiency.
• Validated the effectiveness of PSO and DA in joint optimization for task offloading and resource allocation.

Conclusions:

• The novel approach effectively addresses the energy consumption and computational time trade-off in CAVs.
• The proposed method offers a sustainable and efficient solution for IoV environments.
• The joint optimization strategy significantly enhances performance metrics, outperforming existing algorithms.