基于贝叶斯网络的MEC随机任务迁移算法

Bayesian Network-based Stochastic Task Offloading Algorithm in Mobile-Edge Computing

文章提出一种基于贝叶斯网络的MEC随机任务迁移算法,通过将应用转换为包含多个子任务的有向图,利用子任务间的关联关系及贝叶斯网的联合概率来生成一组最小化移动设备能耗的策略。仿真结果表明,该算法相比移动设备本地执行算法在处理计算任务时节省能耗达28.7%。

A Bayesian network-based MEC stochastic task offoading algorithm is proposed in this paper, by transforming the application into a directed graph containing multiple sub-tasks, and then using the correlations between sub-tasks and the joint probabilities of the Bayesian networks, to generate a set of strategies to minimize the energy consumption of mobile devices. The simulation results show that the proposed algorithm saves energy consumption by 28.7% compared with the local execution algorithm when processing the computing tasks.