2024年 04期

摘要(Abstract)：

为了改善电网系统可靠性预测性能，构建多个目标函数并采用多核支持向量机算法对配电网进行可靠性预测；从电网样本特征中筛选供电可用率、户均停电时间、户均停电次数3个关键指标，建立可靠性评价目标函数，且采用多核支持向量机训练可靠性指标特征；将高斯核函数、多项式核函数和Sigmoid核函数进行多核组合，采用多核支持向量机求解不同目标函数，获得电网系统可靠性预测结果，进而确定更佳的可靠性预测核函数组合。结果表明，合理选择核函数组合和电网可靠性指标，多核支持向量机对供电可用率、户均停电时间和户均停电次数指标预测准确率较高，且稳定性好，高斯核函数-Sigmoid核函数组合的可靠性预测准确性最佳，高斯核函数-多项式核函数-Sigmoid核函数组合的预测稳定性最好。

关键词(KeyWords)： 电网系统可靠性;多核函数;支持向量机;目标函数

基金项目(Foundation): 国家自然科学基金项目(61871204);; 南方电网公司科技项目(GXKJXM20222188)

作者(Author): 何井龙,张福泉,阳晟,周智成

DOI: 10.13349/j.cnki.jdxbn.20240605.001

参考文献(References)：

[1] 石赫，杨群，刘绍翰，等.基于深度学习的电网故障预案信息抽取研究[J].计算机科学，2020,47(增刊2):52.

[2] 张学清，梁中会，张莹，等.基于广义量测的地区电网T接线路故障测距系统[J].济南大学学报(自然科学版),2018,32(2):83.

[3] STECCA M,ELIZONDOl L R,SOEIRO T B,et al.A comprehensive review of the integration of battery energy storage systems into distribution networks[J].IEEE Open Journal of the Industrial Electronics Society,2020,1:46-65.

[4] ZHANG H,WANG M K,TANG M J,et al.The reliability mea-sures model of multilayer urban distribution network[J].Soft Computing,2018,22(1):107-118.

[5] KONG X Y,LIU C,SHEN Y,et al.Power supply reliability evaluation based on big data analysis for distribution networks considering uncertain factors[J].Sustainable Cities and Society,2020,63:102483.

[6] 翟洪婷，张庆锐，卞若晨，等.基于图聚类的电力设备异常声音检测方法[J].南京理工大学学报，2022,46(3):270.

[7] ABDULKAREEM A,SOMEFUN T E,AWOSOPE C O A,et al.Power system analysis and integration of the proposed Nigerian 750 kV power line to the grid reliability[J].SN Applied Sciences,2021,3:864.

[8] 杨祎，崔其会，丁奕齐.面向电网设备故障报告的半监督命名实体识别方法[J].计算机应用，2021,41(增刊2):45.

[9] WANG L,GAO X Z.Construction of cross-border e-commerce financial risk analysis system based on support vector machine[J].Journal of Industrial Integration and Management,2023,8(1):30.

[10] SUN F F,SHI G H.Study on the application of big data techniques for the third-party logistics using novel support vector machine algorithm[J].Journal of Enterprise Information Management,2022,35(4/5):1171.

[11] RAJ A,MISRA J P,KHANDUJA D.Modeling of wire electro-spark machining of Inconel 690 superalloy using support vector machine and random forest regression approaches[J].Journal of Advanced Manufacturing Systems,2022,21(3):566.

[12] CHAU N H,KUBO M,HAI LV,et al.Support vector machine-based phase prediction of multi-principal element alloys[J].Vietnam Journal of Computer Science,2023,10(1):112.

[13] YAN X,ZHU H M.A kernel-free fuzzy support vector machine with Universum[J].Journal of Industrial and Management Optimization,2023,19(1):290.

[14] LI W M,LIU X Z,YAN A L,et al.Kernel-based adversarial attacks and defenses on support vector classification[J].Digital Communications and Networks,2022,8(4):494.

[15] HAZARIKA B B,GUPTA D,NATARAJAN N.Wavelet kernel least square twin support vector regression for wind speed prediction[J].Environmental Science and Pollution Research,2022,29:86331.

[16] NITHYA N,NALLAVAN G.Inertial measurement unit-based cricket stroke improviser using polynomial kernel support vector machines[J].Proceedings of the Institution of Mechanical Engineers,Part C:Journal of Mechanical Engineering Science,2022,236(9):4616.