考虑任务耦合的配电网边缘计算终端部署与任务分配方法

Deployment and Task Allocation Method of Edge Computing Terminals in Distribution Network Considering Task Coupling

边缘计算是实现配电网海量异构信息深度感知和高效处理、满足多元化业务需求的关键技术,但当前存在资源部署冗余、利用率低等问题。文中提出一种考虑配电网任务耦合的边缘计算终端部署与任务分配方法。首先,提出基于节点簇划分的边缘计算架构与任务处理模型,刻画任务处理特征及任务耦合关系。其次,建立终端部署与任务分配的双层优化模型,上层模型求解任务在边缘计算终端间的分配问题,下层模型求解边缘计算终端在节点簇内的部署问题。再次,分析双层模型的耦合关系,提出改进的K-means法划分节点簇,并利用带边界条件的隐枚举法求解双层模型。最后,算例验证了所提方法的有效性与可行性。

Edge computing is the key technology which realizes the deep perception and efficient processing of massive heterogeneous information and meets the needs of diversified services in the distribution network.However,there are some problems such as redundant resource deployment and low utilization rate.This paper proposes a deployment and task allocation method of edge computing terminal in distribution network considering the task coupling.First,the edge computing architecture based on node cluster classification in distribution network is described,and a task processing model is proposed to describe the processing characteristics of tasks and the coupling relationship among different tasks.Secondly,a bi-layer model considering terminal deployment and task allocation is established.The upper model solves the problem of task allocation in edge computing terminals,and the lower model solves the problem of deployment of edge computing terminals in node clusters.Thirdly,the coupling relationship of the bi-layer model is analyzed,an improved K-means method is proposed to divide the node clusters,and the implicit enumeration method with boundary conditions is used to solve the proposed bi-layer optimization model.Finally,an example is given to verify the effectiveness and feasibility of the proposed method.