有序用电智能多代理系统架构与机制研究  被引量:5

Intelligent multi-agent system for orderly power utilization: architecture and coordination mechanism design

在线阅读下载全文

作  者:陈霄[1] 童星[2] 张宁[2] 易永仙 栾开宁 周玉[1] 

机构地区:[1]江苏省电力公司电力科学研究院国家电网公司电能计量重点实验室,江苏南京210019 [2]电力系统及发电设备控制和仿真国家重点实验室(清华大学电机系),北京100084 [3]国网江苏省电力公司,江苏南京210024

出  处:《电力系统保护与控制》2016年第9期75-82,共8页Power System Protection and Control

基  金:国家电网公司科技项目(智能有序用电辅助决策支持技术研究)

摘  要:有序用电是需求侧管理的重要组成部分。当系统存在电力供应缺口时,通过削减用户负荷保障电力供需平衡。其方案编制以人工为主,缺乏互动,智能化程度较低,导致有序用电缺口指标分配工作精细化程度不高,执行较粗放。设计了一种覆盖空间上多层电网的有序用电智能多代理系统架构。该架构将电网物理结构分为"系统—节点—用户"三层,并分别为系统、节点和用户建立智能代理模型。在智能代理内部,嵌入了学习机制使得智能代理能对环境变化作出自适应的响应。在智能代理之间,提出了一种鼓励用户互济的协商机制,该机制使得一个用户无法完成指标缺口时,其他用户可对其进行支援并获得补偿。通过智能代理模型的协作,实现了有序用电缺口指标的多层次、自适应、交互式分配。Orderly power utilization is an important measurement of demand side management. When there is power supply shortage or emergency events, orderly power utilization can be applied to decrease electricity demand and ensure the balance of electricity supply and demand. Nowadays orderly power utilization is mainly carried out in a manually manner without optimization and communicating with consumers, which cannot obtain a precise and strategic allocation of load shedding. This paper designs an intelligent multi-agent system architecture and coordination mechanism for the multi-layer distribution of load shedding in orderly power utilization. The electrical grid is decomposed into three layers: system layer, node layer and customer layer. The three layers are modelled using intelligent agent. For each agent, a learning mechanism is embedded to make the agent be able to adaptively response to the environment. Among different agents, an agent coordination mechanism is designed to encourage customers' mutual support. Through the cooperation of agents, the proposed method can adaptively and interactively distribute the load shedding, obtaining a strategic orderly power utilization in a multi-layer electrical grid.

关 键 词:有序用电 需求侧管理 多代理系统 协商机制 缺口分配 

分 类 号:TM73[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象