基于改进遗传算法的可信边缘计算任务卸载方法

打开文本图片集

中图分类号：TP302 文献标志码：A 文章编号：1671-6841（2025）03-0072-09

DOI： 10.13705/j .issn.1671-6841.2023246

Task Offloading Method of Trusted Edge Computing Based on Improved Genetic Algorithm

WANG Yali1，²，LOU Shihao' （1. College of Computer and Information Engineering， Henan Normal University， Xinxiang 4530o7， China; 2. Engineering Laboratory of Intellectual Business and Internet of Things Technologies， Henan Normal University，Xinxiang ，China）

Abstract： Aiming at the problem that the trustworthiness of edge servers could not be guaranteed， a trusted edge computing task ofloading method based on the improved genetic algorithm was proposed. Firstly，in order to encourage edge servers to participate in task ofloading competition，a reputation mechanism was used to motivate edge servers，and the existing reputation was used as the basis for evaluating the credibility of edge servers. Secondly，the Byzantine consensus mechanism based on reputation and distributed consensus protocol was used to elect the edge server leader. Finally，the edge server leader used an improved genetic algorithm to decide the task ofloading behavior of the edge server，so as to select the trusted edge server that met the delay and energy consumption constraints of users to execute the offloading task of the terminal device. Simulation experiment results showed that the cost of the proposed method was reduced by 5.46% to 59.26% compared with the benchmark schemes.

Key Words： edge computing; consensus mechanism； credibility； genetic algorithm； task offloading

0 引言

其产生的数据量急剧增长，由于其受限于计算和存储资源，通常无法满足终端用户日益增长的高计算应用需求[1]。（剩余14022字）