| 基于脉冲神经网络伪量测建模的配电网三相状态估计 |
| |
| 引用本文： | 黄蔓云,孙国强,卫志农,臧海祥,陈通,陈胜.基于脉冲神经网络伪量测建模的配电网三相状态估计[J].电力系统自动化,2016,40(16):38-43. |
| |
| 作者姓名： | 黄蔓云 孙国强 卫志农 臧海祥 陈通 陈胜 |
| |
| 作者单位： | 河海大学能源与电气学院, 江苏省南京市 210098,河海大学能源与电气学院, 江苏省南京市 210098,河海大学能源与电气学院, 江苏省南京市 210098,河海大学能源与电气学院, 江苏省南京市 210098,河海大学能源与电气学院, 江苏省南京市 210098,河海大学能源与电气学院, 江苏省南京市 210098 |
| |
| 基金项目： | 国家自然科学基金资助项目(51277052) |
| |
| 摘 要： | 为了给配电网管理系统提供全面准确的实时数据,配电网三相状态估计显得尤为重要。针对当前配电网量测信息不足,提出了基于脉冲神经网络(SNN)伪量测建模的配电网三相状态估计。该方法首先将实时和部分历史支路功率量测输入SNN进行伪量测建模,然后由高斯混合模型生成相应的量测误差,最后进行基于加权最小二乘法的配电网三相状态估计。理论分析和算例验证表明,所提模型不仅能够在正常通信时有效提高配电网状态估计精度,而且能在通信故障时保证估计精度在合理范围内,进而为配电网的运行控制提供参考依据。
|
| 关 键 词： | 配电网 状态估计 脉冲神经网络 高斯混合模型 伪量测 |
| 收稿时间： | 2015/12/7 0:00:00 |
| 修稿时间： | 6/2/2016 12:00:00 AM |
Three-phase State Estimation in Distribution Systems Based on Pseudo Measurement Modeling Using Spiking Neural Network |
| |
| HUANG Manyun,SUN Guoqiang,WEI Zhinong,ZANG Haixiang,CHEN Tong and CHEN Sheng.Three-phase State Estimation in Distribution Systems Based on Pseudo Measurement Modeling Using Spiking Neural Network[J].Automation of Electric Power Systems,2016,40(16):38-43. |
| |
| Authors: | HUANG Manyun SUN Guoqiang WEI Zhinong ZANG Haixiang CHEN Tong and CHEN Sheng |
| |
| Affiliation: | College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China,College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China,College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China,College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China,College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China and College of Energy and Electrical Engineering, Hohai University, Nanjing 210098, China |
| |
| Abstract: | To provide comprehensive and accurate real-time data for distribution management system(DMS), three-phase state estimation in distribution system is critically required. Lacking in real-time measurements in distribution system state estimation(DSSE), this paper presents a spiking neural network(SNN)based method for pseudo measurement modeling. In the proposed method, the pseudo measurements are firstly derived from a few real measurements using SNN. Then, the error associated with the generated pseudo measurements is created by Gaussian mixture model(GMM). At last, the three-phase state estimation in distribution system is made based on weighted least square method. The simulation results demonstrate the accurate performance of the proposed pseudo modeling in DSSE with both regards to normal situation and communication failure. This work is supported by National Natural Science Foundation of China(No.51277052). |
| |
| Keywords: | distribution network state estimation spiking neural network Gaussian mixture model pseudo measurement |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《电力系统自动化》浏览原始摘要信息 |
|
点击此处可从《电力系统自动化》下载全文 |
|
