首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|证明资料|样刊邮寄查询|常见问题解答|联系我们
况华,何鑫,何觅,等. 基于双向长短期记忆神经网络的配网电压异常数据检测[J]. 科学技术与工程, 2021, 21(24): 10291-10297.
Kuang Hua,He Xin,He Mi,et al.Abnormal Voltage Data Detection of Distribution Network Based on Bidirectional Long Short-term Memory Neural Network[J].Science Technology and Engineering,2021,21(24):10291-10297.
基于双向长短期记忆神经网络的配网电压异常数据检测
Abnormal Voltage Data Detection of Distribution Network Based on Bidirectional Long Short-term Memory Neural Network
投稿时间:2021-02-04  修订日期:2021-06-05
DOI:
中文关键词:  异常数据检测  配网电压  双向长短期记忆神经网络  时序
英文关键词:abnormal data detection  distribution network voltage  bidirectional long short-term memory neural network  time series
基金项目:云南电网科技项目
              
作者单位
况华 云南电网有限责任公司
何鑫 云南电网有限责任公司电力科学研究院
何觅 云南电网有限责任公司昆明供电局
覃日升 云南电网有限责任公司电力科学研究院
姜訸 云南电网有限责任公司电力科学研究院
摘要点击次数: 162
全文下载次数: 39
中文摘要:
      受自然环境、计量仪器等影响,量测数据会出现异常,导致调度人员错误决策,威胁电力系统安全稳定运行。为保障电力系统安全稳定运行,提出了一种基于双向长短期记忆(Bi-LSTM)神经网络的配网电压无监督异常数据检测方法。利用Bi-LSTM神经网络处理时序数据的双向特性,建立时序预测模型,通过对比预测值和实际值的误差检测异常数据。最后,基于某实际配网电压数据进行仿真验证,仿真结果表明:所提方法在准确率、F1分数等指标方面均优于决策树、K近邻、支持向量机、长短期记忆(LSTM)神经网络等方法。
英文摘要:
      Due to the influence of natural environment, metering instruments, etc., abnormal measurement data lead to dispatchers’ wrong decisions, which threatens the safe and stable operation of the power systems. To ensure the safe and stable operation of power systems, an unsupervised abnormal voltage data detection method is proposed for distribution networks based on a Bidirectional Long Short-term Memory (Bi-LSTM) neural network in this paper. Considering the bidirectional characteristics of Bi-LSTM neural network in dealing with time series data, a time series prediction model is constructed to detect abnormal data by comparing the error values between the predicted and the actual values. Finally, simulations on the voltage data of actual distribution network is used to show that the advantages of the proposed method in accuracy, F1 Score, etc., over the decision tree, K-nearest neighbor, support vector machine, and Long Short-term Memory (LSTM) neural network.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第44553308位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号