1.山东大学软件学院,山东济南 250101
2.山大地纬软件股份有限公司,山东济南 250100
3.国网重庆市电力公司,重庆 400015
[ "管永明 男,1984年1月出生,山东济南人. 2009年于山东大学计算机软件与理论专业获得硕士学位,其后在山大地纬软件股份有限公司从事智能电网应用、数据挖掘工作.E-mail:guanyongming@dareway.com.cn" ]
[ "王 刚 男,1988年2月出生,重庆人. 2010年于重庆大学电气工程与自动化专业获得学士学位,其后在国网重庆市电力公司从事电力营销工作.E-mail:wangg@cq.sgcc.com.cn" ]
骆凯波 男,1982年6月出生,河北保定人. 2004年于重庆大学计算机科学与技术专业获得学士学位,高级工程师,其后在国网重庆市电力公司从事用电信息采集建设管理工作.E-mail:luokaibo777@126.com
吕 梁 男,1985年7月出生,山东济南人. 2010年于中国海洋大学信号与信息处理专业获得硕士学位,其后在山大地纬软件股份有限公司从事电力系统设计与分析工作.E-mail:ll@dareway.com.cn
吕晓雯 女,1988年11月出生,山东青岛人. 2015年于山东大学控制科学与工程专业获得硕士学位,其后在山大地纬软件股份有限公司从事电力系统自动化工作.E-mail:lxw@dareway.com.cn
史玉良(通信作者) 男,1978年10月出生,山东威海人. 教授、博士生导师、山东省社会保障大数据工程实验室主任、兼任中国计算机学会协同计算专委会委员、服务计算专委会委员. 2003年、2006年分别于山东大学、复旦大学获得硕士学位、博士学位,2006年后在山东大学从事大数据、服务计算、人工智能等方面的研究工作.E-mail:shiyuliang@sdu.edu.cn
收稿:2019-12-13,
修回:2020-10-09,
纸质出版:2021-08-25
移动端阅览
管永明,王刚,骆凯波等.基于极端不平衡学习的泛化低压异常箱表关系识别研究与应用[J].电子学报,2021,49(08):1507-1514.
GUAN Yong-ming,WANG Gang,LUO Kai-bo,et al.Generalized Identification for Low-Pressure Abnormal Box-Table Relationship Based on Extreme Unbalance Classification Learning[J].ACTA ELECTRONICA SINICA,2021,49(08):1507-1514.
管永明,王刚,骆凯波等.基于极端不平衡学习的泛化低压异常箱表关系识别研究与应用[J].电子学报,2021,49(08):1507-1514. DOI: 10.12263/DZXB.20191372.
GUAN Yong-ming,WANG Gang,LUO Kai-bo,et al.Generalized Identification for Low-Pressure Abnormal Box-Table Relationship Based on Extreme Unbalance Classification Learning[J].ACTA ELECTRONICA SINICA,2021,49(08):1507-1514. DOI: 10.12263/DZXB.20191372.
针对低压配电网箱表关系存在人工核查成本高、异常案例少、难以实现异常规律捕获的问题,采用极端不平衡分类学习方法实现低压异常箱表关系识别的泛化应用推广.通过电压原理识别出部分异常箱表关系样本集,随后构建CNN(卷积神经网络)异常箱表关系识别模型,通过样本三分类赋权值实现类别均衡处理;并在模型推广应用过程中,采用强化学习实现离线模型的在线泛化学习,并以分组模型交互学习和竞争优化的方式筛选出最优泛化识别模型.实验证明,通过人工核查和数据反馈,该方法可实现模型对异常样本数据分布规律的自拟合学习,提高模型对不同应用环境的泛化性,进一步降低人工现场核查工作量,保障低压台区用户拓扑网络关系的准确性.
Due to high labor cost and few abnormal cases of power box-table relations inspection
which difficulty to obtain the law. The extreme unbalanced classification learning method was used to capture the generalization. Through the principle of voltage
abnormal box-table relationship sample sets were identified. And by three-class weighting balance
the CNN(convolutional neural network) abnormal box-table relationship recognition model was constructed. In addition
the grouped parallel generalization learning of recognition model was realized by reinforcement learning. The experiment proves that
through self-learning the distribution of newly identified abnormal sample data
which improve the generalization to different environments. This reduces the workload of manual on-site verification and ensures the accuracy of the topology network relationship in the low-voltage station area.
Su Y , Liang X R , Wang H , et al . A maintenance and troubleshooting method based on integrated information and system principles [J]. IEEE Access , 2019 , 7 : 70513 - 70524 .
吴志鹏 , 杨苹 , 姜新宇 , 等 . 在线监测信息系统结构层次设计与实践 [J]. 电子学报 , 2018 , 46 ( 11 ): 2803 - 2808 .
Wu Z P , Yang P , Jiang X Y , et al . Hierarchical structure design and application for online monitoring information system [J]. Acta Electronica Sinica , 2018 , 46 ( 11 ): 2803 - 2808 . (in Chinese)
高泽璞 , 赵云 , 余伊兰 , 等 . 基于知识图谱的低压配电网拓扑结构辨识方法 [J]. 电力系统保护与控制 , 2020 , 48 ( 2 ): 34 - 43 .
Gao Z P , Zhao Y , Yu Y L , et al . Low-voltage distribution network topology identification method based on knowledge graph [J]. Power System Protection and Control , 2020 , 48 ( 2 ): 34 - 43 . (in Chinese)
肖勇 , 赵云 , 涂治东 , 等 . 基于改进的皮尔逊相关系数的低压配电网拓扑结构校验方法 [J]. 电力系统保护与控制 , 2019 , 47 ( 11 ): 37 - 43 .
Xiao Y , Zhao Y , Tu Z D , et al . Topology checking method for low voltage distribution network based on improved pearson correlation coefficient [J]. Power System Protection and Control , 2019 , 47 ( 11 ): 37 - 43 . (in Chinese)
Hang Q , Yang J H , Xing L N . Diagnosis of rolling bearing based on classification for high dimensional unbalanced data [J]. IEEE Access , 2019 , 7 ( 1 ): 79159 - 79172 .
Zhang P B , Yang Z X . A novel AdaBoost framework with robust threshold and structural optimization [J]. IEEE Transactions on Cybernetics , 2018 , 48 ( 1 ): 64 - 76 .
Kim C , Shin D , Kim B , et al . Mosaic-CNN: A combined two-step zero prediction approach to trade off accuracy and computation energy in convolutional neural networks [J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems , 2018 , 8 ( 4 ): 770 - 781 .
Dilokthanakul N , Kaplanis C , Pawlowski N , et al . Feature control as intrinsic motivation for hierarchical reinforcement learning [J]. IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 11 ): 3409 - 3418 .
Barriga N A , Stanescu M , Besoain F , et al . Improving RTS game AI by supervised policy learning, tactical search, and deep reinforcement learning [J]. IEEE Computational Intelligence Magazine , 2019 , 14 ( 3 ): 8 - 18 .
Bruin T D , Kober J , Tuyls K , et al . Integrating state representation learning into deep reinforcement learning [J]. IEEE Robotics and Automation Letters , 2018 , 3 ( 3 ): 1394 - 1401 .
Sevakula R K , Verma N K . Assessing generalization ability of majority vote point classifiers [J]. IEEE Transactions on Neural Networks and Learning Systems , 2017 , 28 ( 12 ): 2985 - 2997 .
于昕妍 , 沈艳霞 , 陈杰 , 等 . 考虑概率区间的微电网短期负荷多目标预测方法 [J]. 电子学报 , 2017 , 45 ( 4 ): 930 - 936 .
Yu X Y , Shen Y X , Chen J , et al . A multi-objective prediction method for short-term microgrid load considering interval probability [J]. Acta Electronica Sinica , 2017 , 45 ( 4 ): 930 - 936 . (in Chinese)
Xiang W M , Tran H D , Johnson T T , et al . Output reachable set estimation and verification for multilayer neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems , 2018 , 29 ( 11 ): 5777 - 5783 .
Lu Y J , Wu H F , Tu B , et al . Ultra-wide output voltage range power supply based on modular switched-converter principle [J]. IEEE Transactions on Power Electronics , 2020 , 35 ( 1 ): 94 - 106 .
Kim C , Shin D , Kim B , et al . Mosaic-CNN: A combined two-step zero prediction approach to trade off accuracy and computation energy in convolutional neural networks [J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems , 2018 , 8 ( 4 ): 770 - 781 .
Passalis N , Tefas A . Training lightweight deep convolutional ceural cetworks using gag-of-features pooling [J]. IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 6 ): 1705 - 1715 .
Chen G , Colin I J D , Zhang M J . Accuracy-based learning classifier systems for multistep reinforcement learning: A fuzzy logic approach to handling continuous inputs and learning continuous actions [J]. IEEE Transactions on Evolutionary Computation , 2016 , 20 ( 6 ): 953 - 971 .
Wang Y J , Sun F M , Li B . Multiscale neighborhood normalization-based multiple dynamic PCA monitoring method for batch processes with frequent operations [J]. IEEE Transactions on Automation Science and Engineering , 2018 , 15 ( 3 ): 1053 - 1064 .
Tang Z Q , Zhou X J , Zhang F M , et al . Migration modeling and learning algorithms for containers in fog computing [J]. IEEE Transactions on Services Computing , 2019 , 12 ( 5 ): 712 - 725 .
胡峰 , 王蕾 , 周耀 . 基于三支决策的不平衡数据过采样方法 [J]. 电子学报 , 2018 , 46 ( 1 ): 135 - 144 .
Hu F , Wang L , Zhou Y . An oversampling method for imbalance data based on three-way decision model [J]. Acta Electronica Sinica , 2018 , 46 ( 1 ): 135 - 144 . (in Chinese)
0
浏览量
15
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621