| 引用本文: | 孙国强,钱嫱,陈亮,卫志农,臧海祥,王晗雯,黄强.基于深度信念网络伪量测建模的配电网状态估计[J].电力自动化设备,2018,(12): |
| SUN Guoqiang,QIAN Qiang,CHEN Liang,WEI Zhinong,ZANG Haixiang,WANG Hanwen,HUANG Qiang.State estimation of distribution system based on pesudo measurement modeling using deep belief network[J].Electric Power Automation Equipment,2018,(12): |
|
| 摘要: |
| 针对配电网实时量测不足需要增加伪量测以提高量测冗余度的情况，提出基于深度信念网络(DBN)伪量测建模的配电网状态估计方法。利用多种类型负荷的历史数据及对应温度、日期类型对DBN进行训练，训练完成后输入测试数据得到精度较高的伪量测；基于改进的等效电流量测变换法进行配电网状态估计，以线性约束的形式处理虚拟量测。仿真结果验证了所提方法的有效性。 |
| 关键词: 配电网 状态估计 深度信念网络 伪量测 虚拟量测 |
| DOI：10.16081/j.issn.1006-6047.2018.12.014 |
| 分类号:TM761 |
| 基金项目:国家自然科学基金资助项目(51277052)；国家电网公司科学技术项目(521001160038) |
|
| State estimation of distribution system based on pesudo measurement modeling using deep belief network |
|
SUN Guoqiang1, QIAN Qiang1, CHEN Liang2, WEI Zhinong1, ZANG Haixiang1, WANG Hanwen1, HUANG Qiang2
|
|
1.College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China;2.State Grid Jiangsu Electric Power Company Research Institute, Nanjing 211103, China
|
| Abstract: |
| Aiming at the situation that the pseudo measurements need to be added to improve the redundancy of measurements due to the insufficient real-time measurements in distribution system, a state estimation method based on pseudo measurement modeling method using DBN(Deep Belief Network) is proposed for distribution system. After training DBN by various historical load data, corresponding temperature and date type, the test data is input to obtain pseudo measurements with high accuracy. The state estimation of distribution system is carried out based on the improved equivalent current measurement transformation method, and the virtual measurements are processed in the form of linear constraint. Simulative results verify the effectiveness of the proposed method. |
| Key words: distribution network state estimation deep belief network pseudo measurement virtual measurement |
