考虑服务配置的细粒度电力任务云边协同优化调度策略

新型电力系统的建设促使电力业务范围向用户侧深入，业务种类及数量不断增加。边设备资源有限，只能配置有限数量的服务，任务的时延能耗需求与设备资源有限的矛盾日益突出。为实现云边资源协同与任务的优化调度，提出了一种考虑服务配置的细粒度电力任务云边协同优化调度策略。通过建立微服务的时延与能耗模型，并对任务调度中的约束条件进行分析，将时延与能耗的优化决策问题转化为带约束的多目标优化问题，采用NSGA-Ⅱ算法求解。然后通过基于模糊逻辑的多准则决策方法为任务选择调度方案。仿真结果表明，所提策略在时延和能耗方面的性能优于其他策略，能够适应不同的任务场景并做出最优决策，提高了任务的完成率。

Cloud-edge collaborative optimization scheduling strategy for fine-grained power tasksconsidering service configuration

The construction of new power systems drives the scope of power services deeper into the customer side, and the types and quantities of services are increasing. Edge device resources are limited, and only a limited number of services can be configured at the same time. The contradiction between the time delay and energy consumption of tasks and the limited device resources is increasingly prominent. To realize the coordination of cloud-edge resources and the optimal scheduling of tasks, an optimal scheduling strategy for fine-grained power tasks considering service configuration is proposed. By establishing a delay and energy consumption model of microservices, and analyzing the constraints in task scheduling, the optimization decision problem of delay and energy consumption is transformed into a multi-objective optimization problem with constraints. The NSGA-II algorithm is used to solve the problem. Then the scheduling scheme is selected for the task through a fuzzy logic-based multi-criteria decision-making method. The simulation results show that the performance of the strategy proposed in this paper is better than other strategies in terms of delay and energy consumption, and it can adapt to different task scenarios and make optimal decisions, all of which improves the completion rate of tasks.