预测性维护任务计算卸载与资源分配联合优化  

Task Offloading and Resource Allocation Joint Optimization for Predictive Maintenance

作　　者：张博[1] 王承昊 李俊锋[1] ZHANG Bo;WANG Chenghao;LI Junfeng(School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China)

机构地区：[1]郑州大学网络空间安全学院,河南郑州450002

出　　处：《郑州大学学报（理学版）》2024年第6期39-45,共7页Journal of Zhengzhou University:Natural Science Edition

基　　金：国家自然科学基金面上项目(61972092);郑州市协同创新重大专项(20XTZX06013)。

摘　　要：针对预测性维护(predictive maintenance,PdM)人工参与资源调配的问题,提出了一种基于改进人工蜂群算法(artificial bee colony,ABC)的计算卸载和资源分配方案。该方法利用遗传算法的进化思想,改进了侦察蜂的搜寻步骤,解决了传统人工蜂群算法容易陷入局部最优解、多样性不足等缺点,能够根据设备故障率生成维护成本最低的资源分配方案。仿真实验结果表明,该算法较其他算法收敛速度更快、收敛质量更高、减少维护成本更明显,能够有效解决PdM场景的计算卸载和资源分配问题。To address the problem of manual involvement in resource allocation for predictive maintenance(PdM),a computational offloading and resource allocation scheme based on an improved artificial bee colony(ABC)algorithm was proposed.The method utilized the evolutionary idea of genetic algorithm to improve the searching step of scout bees.The shortcomings of traditional artificial bee colony algorithms such as easy to fall into local optimal solutions and insufficient diversity were solved.The ability to generate the lowest maintenance cost resource allocation plan based on equipment failure rates.The simulation experimental results showed that the algorithm had faster convergence speed,higher convergence quality and more obvious reduction of maintenance cost than other algorithms,and could effectively solve the computational offloading and resource allocation problems of PdM scenarios.

关 键 词：移动边缘计算(MEC) 预测性维护(PdM) 任务卸载 资源分配 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]