考虑样本不平衡的并行化用户负荷类型辨识方法Parallel Load Type Identification Algorithm Considering Sample Class Imbalance
刘洋;高丽霞;刘璐;
摘要(Abstract):
电力物联网背景下的态势感知技术,是以电力系统运行数据为驱动,通过对数据信息的获取、理解、分析预测,实现正确的决策与行动。该文针对此背景下对于海量用户负荷类型辨识和用电行为态势感知,提出一种基于MapReduce的并行化长短期记忆网络(parallel long short-term memory,Par-LSTM)的负荷分类方法,该方法通过将负荷数据分割交给多个LSTM并行处理以提高分类速度。并且采用一种考虑样本合成倍率的改进Borderline-SMOTE方法(BorderlineSMOTE considering synthetic multiple,SMB-SMOTE)处理负荷训练样本类别不平衡现象。算例表明,对SMB-SMOTE方法处理样本不平衡后的负荷数据进行Par-LSTM分类,能够有效提高小类负荷样本的分类精度。
关键词(KeyWords): 电力物联网;负荷类型辨识;并行化;Par-LSTM;SMB-SMOTE
基金项目(Foundation):
作者(Author): 刘洋;高丽霞;刘璐;
Email:
DOI: 10.13335/j.1000-3673.pst.2020.0116
参考文献(References):
- [1]Eun S Lee,Yeong H Sohn,Byeong G Choi,et al.A modularized IPTwith magnetic shielding for a wide-range ubiquitous wi-power zone[J].IEEE Transactions on Power Electronics,2018,33(11):9669-9690.
- [2]Wang Yanxin,Yan Jing,Sun Qifeng,et al.A mobile nets convolutional neural network for GIS partial discharge pattern recognition in the ubiquitous power internet of things context:optimization,comparison,and application[J].IEEE Access,2019(7):226-236.
- [3]傅质馨,李潇逸,袁越.泛在电力物联网关键技术探讨[J].电力建设,2019,40(5):1-12.Fu Zhixin,Li Xiaoyi,Yuan Yue.Research on key technologies of ubiquitous power internet of things[J].Electric Power Construction,2019,40(5):1-12(in Chinese).
- [4]Yang H,Zhang J,Qiu J,et al.A practical pricing approach to smart grid demand response based on load classification[J].IEEETransactions on Smart Grid,2017,9(1):179-190.
- [5]张亚健,杨挺,孟广雨.泛在电力物联网在智能配电系统应用综述及展望[J].电力建设,2019,40(6):1-12.Zhang Yajian,Yang Ting,Meng Guangyu.Review and prospect of ubiquitous power internet of things in smart distribution system[J].Electric Power Construction,2019,40(6):1-12(in Chinese).
- [6]林顺富,田二伟,符杨,等.基于信息熵分段聚合近似和谱聚类的负荷分类方法[J].中国电机工程学报,2017,37(8):76-87.Lin Shunfu,Tian Erwei,Fu Yang,et al.Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J].Proceedings of the CSEE,2017,37(8):76-87(in Chinese).
- [7]赵俊华,董朝阳,文福拴,等.面向能源系统的数据科学:理论、技术与展望[J].电力系统自动化,2017,41(4):1-11.Zhao Junhua,Dong Zhaoyang,Wen Fushuan,et al.Distributed optimization of electric-gas integrated energy flow using serial and parallel iterative modes for alternating direction method of multipliers[J].Automation of Electric Power Systems,2017,41(4):1-11(in Chinese).
- [8]刘洋,刘洋,许立雄.适用于海量负荷数据分类的高性能反向传播神经网络算法[J].电力系统自动化,2018,42(21):131-140.Liu Yang,Liu Yang,Xu Lixiong.High-performance backpropagation neural network algorithm for mass load data classification[J].Automation of Electric Power Systems,2018,42(21):131-140(in Chinese).
- [9]Wang Y,Chen Q,Sun M,et al.An ensemble forecasting method for the aggregated load with sub profiles[J].IEEE Transactions on Smart Grid,2018,9(4):3906-3908.
- [10]Cui Mingjian,Wang Jianhui,Yue Meng.Machine learning-based anomaly detection for load forecasting under cyberattacks[J].IEEETransactions on Smart Grid,2019,10(5):5724-5734.
- [11]张宇帆,艾芊,林琳,等.基于深度长短时记忆网络的区域级超短期负荷预测方法[J].电网技术,2019,43(6):1884-1892.Zhang Yufan,Ai Qian,Lin Lin,et al.A very short-term load forecasting method based on deep LSTM RNN at zone level[J].Power System Technology,2019,43(6):1884-1892(in Chinese).
- [12]Shi Heng,Xu Minghao,Li Ran.Deep learning for household load forecasting-a novel pooling deep RNN[J].IEEE Transactions on Smart Grid,2017,9(5):5271-5280.
- [13]Wang S,Minku L L,Yao X.Resampling-based ensemble methods for online class imbalance learning[J].IEEE Transactions on Knowledge and Data Engineering,2015,27(5):1356-1368.
- [14]Janakiraman V M,Nguyen X L,Sterniak J,et al.Identification of the dynamic operating envelope of HCCI engines using class imbalance learning[J].IEEE Transactions on Neural Networks and Learning Systems,2015,26(1):98-112.
- [15]刘洋,刘洋,许立雄,等.计及数据类别不平衡的海量用户负荷典型特征高性能提取方法[J].中国电机工程学报,2019,39(14):4093-4104.Liu Yang,Liu Yang,Xu Lixiong,et al.A high performance extraction method for massive user load typical characteristics considering data class imbalance[J].Proceedings of the CSEE,2019,39(14):4093-4104(in Chinese).
- [16]王凯亮,陆俊,徐志强,等.基于先验知识与DBM采样的类不平衡用电数据分类方法[J].电力系统自动化,2019,43(20):57-64.Wang Kailiang,Lu Jun,Xu Zhiqiang,et al.Classification method of unbalanced power consumption data based on prior knowledge and deep boltzmann machine sampling[J].Automation of Electric Power Systems,2019,43(20):57-64(in Chinese).
- [17]古平,杨炀.面向不均衡数据集中少数类细分的过采样算法t[J].计算机工程,2017,43(2):241-247.Gu Ping,Yang Yang.Oversampling algorithm oriented to subdivision of minority class in imbalanced data set[J].Computer Engineering,2017,43(2):241-247(in Chinese).
- [18]陈振宇,刘金波,李晨,等.基于LSTM与XGBoost组合模型的超短期电力负荷预测[J].电网技术,2019,43(2):614-620.Chen Zhenyu,Liu Jinbo,Li Chen,et al.Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J].Power System Technology,2019,43(2):614-620(in Chinese).
- [19]王潇笛,刘俊勇,刘友波,等.采用自适应分段聚合近似的典型负荷曲线形态聚类算法[J].电力系统自动化,2019,43(1):150-161.Wang Xiaodi,Liu Junyong,Liu Youbo,et al.Shape clustering algorithm of typical load curves based on adaptive piecewise aggregate approximation[J].Automation of Electric Power Systems,2019,43(1):150-161(in Chinese).
- [20]黄世泽,陈威,张帆,等.基于弗雷歇距离的道岔故障诊断方法[J].同济大学学报(自然科学版),2018,46(12):80-85.Huang Shize,Chen Wei,Zhang Fan,et al.Method of turnout fault diagnosis based on fréchet distance[J].Journal of Tongji University(Natural Science),2018,46(12):80-85(in Chinese).
- [21]罗康洋,王国强.L-SMOTE与SVM结合的不平衡数据集分类研究[J].计算机工程与应用,2019,10(17):55-62.Luo Kangyang,Wang Guoqiang.Research on Imbalanced Data Classification Based on L-SMOTE and SVM[J].Computer Engineering and Applications,2019,10(17):55-62(in Chinese).
- [22]王莉,陈红梅,王生武.新的基于代价敏感集成学习的非平衡数据集分类方法NIBoost[J].计算机应用,2019,39(3):629-633.Wang Li,Chen Hongmei,Wang Shengwu.NIBoost:new imbalanced dataset classification method based on cost sensitive ensemble learning[J].Journal of Computer Applications,2019,39(3):629-633(in Chinese).