Parked vehicle edge computing uses parked vehicle (PV) as a complement resource provider to assist MEC server in computing tasks. In this paper, we consider the PVs in parking lot to share the workload of MEC server and propose a balance-oriented task unloading optimizing algorithm. In a typical parked vehicle edge computing environment, we define the serviceability to assess whether the PV can be selected to assist in computing. Based on the serviceability, a joint optimization problem of the task vehicle’s cost and the PV’s resource balance is designed, and it is modeled with integer linear programming. Then, the Computational Unloading Greedy Particle Swarm Optimization (CUGPSO) algorithm is proposed to solve this optimization. The simulation results show that the proposed algorithm can effectively reduce the average unloading cost of users and balance the workload of PVs, tend to occupy an equal proportion of computing resources and storage resources of different PVs, and better balance resource allocation.
Balance-Oriented Task Unloading Optimizing Algorithm for Parked Vehicle Edge Computing
Lect. Notes Electrical Eng.
International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021
2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021) ; Kapitel : 45 ; 512-525
2022-06-01
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Balance-Oriented Task Unloading Optimizing Algorithm for Parked Vehicle Edge Computing
British Library Conference Proceedings | 2022
|Parked vehicle subtask unloading decision-making method based on reinforcement learning
Europäisches Patentamt | 2023
|