A cyber-physical-social system with parallel learning for distributed energy management of a microgrid
A cyber-physical-social system with parallel learning for distributed energy management of a microgrid
复制标题
用于微电网分布式能源管理的具有并行学习功能的网络物理社会系统
DOI：
10.1016/j.energy.2018.09.069
复制
发表时间：
2018
期刊：
影响因子：
9
通讯作者：
Zhun Fan
中科院分区：
文献类型：
--
作者：
Xiaoshun Zhang;Tao Yu;Zhao Xu;Zhun Fan
提出了一种具有并行学习功能的新型网络物理社会系统（CPSS），用于微电网的分布式能源管理（DEM）。 CPSS是将传统的信息物理系统扩展到人类参与和交互的社会空间而发展起来的。每个能源供给者或每个能源需求者都被视为社会空间中的一个人，能够学习知识、与他人合作、做出各种偏好行为的决策。基于相关均衡（CE）的一般和博弈用于实现复杂优化子任务上的人类交互，而新颖的自适应共识算法用于实现具有多能量平衡约束的简单优化子任务上的人类交互。基于小世界网络引入一个真实世界系统和多个虚拟人工系统进行并行交互执行，从而能够以高概率快速出现更高质量的DEM最优值。对具有 11 个能源供应商和 7 个能源需求商的微电网的案例研究表明，与其他集中式启发式算法相比，该技术可以有效实现人机协作并快速获得更高质量的 DEM 最优值。
A novel cyber-physical-social system (CPSS) with parallel learning is presented for distributed energy management (DEM) of a microgrid. CPSS is developed by extending the conventional cyber-physical system to the social space with human participation and interaction. Each energy supplier or each energy demander is regarded as a human in the social space, who is able to learn the knowledge, co-operate with others, and make a decision with various preference behaviors. The correlated equilibrium (CE) based general-sum game is employed for realizing the human interaction on the complex optimization subtask, while the novel adaptive consensus algorithm is used for achieving that on the simple optimization subtask with multi-energy balance constraints. A real-world system and multiple virtual artificial systems are introduced for parallel and interactive execution based on the small world network, thus a higher quality optimum of DEM can be rapidly emerged with a high probability. Case studies of a microgrid with 11 energy suppliers and 7 energy demanders demonstrate that the proposed technique can effectively achieve the human-computer collaboration and rapidly obtain a higher quality optimum of DEM compared with other centralized heuristic algorithms.