Multi-Objective Optimization Task Offloading Strategy Based on Load Prediction
With the upgrading of intelligent connected vehicles in the Internet of Vehicles(IoV),new on-board applications introduce higher requirements for computing power.The computing power of on-board units is far from sufficient.The emergence of Mobile Edge Computing(MEC)can provide more reliable services for vehicles.Aiming at the task offloading problem in edge computing for the IoV,a multi-objective optimization offloading strategy algorithm based on load prediction is proposed to reduce the task delay and realize load balance among edge servers.By using a load prediction algorithm based on adaptive optimization neural networks to predict the load of MEC servers,the load changes of MEC servers are sensed in advance,solving the problem of task offloading lag.A multi-objective optimization model is constructed with the goal of minimizing latency and balancing MEC server load,considering factors such as communication environment,computing resources,and task volume.The optimal task offloading strategy is obtained through the Non-dominated Sorting Genetic Algorithm(NSGA)-Ⅲ(NSGA-Ⅲ).The simulation results show that this algorithm can accurately predict the load of MEC servers.Compared with the MTUOA,NSGA2,QTD,and AOS algorithms,NSGA-Ⅲ reduced task latency by 1.7％,7.3％,12.4％,and 17.5％,respectively,and achieved significant advantages in MEC server load balancing,solving the problem of MEC server load imbalance.In addition,the proposed algorithm can develop differentiated task offloading plans based on factors such as the communication environment and number of vehicles in different communication cells.
Internet of Vehicles(IoV)Mobile Edge Computing(MEC)task offloadingload predictionload balancingtime delay
国家科技期刊平台
NSTL
万方数据
维普
