一种基于SVM的负载识别算法
|
摘要
负载识别技术能够自动识别出电网中正在使用的负载类型。文中提出一种基于支持向量机SVM的负载类型识别算法,由于SVM只支持二分类,算法采用了One-Against-One组合多个SVM的方法来构建多分类器进行负载识别。通过提取特征量并进行归一化预处理构建训练集来训练SVM多分类器,运用遗传算法对SVM参数进行寻优,寻找识别准确率最高的参数组合。测试结果表明,该SVM多分类器的识别效果较好。
Load identification technique can identify the different types of loads in a power system. This paper presents a load identification algorithm based on support vector machine(SVM),which adopted the one-against-one method which combined multiple SVMs to build a multi-classifier to deal with load identification because SVM is only a binary-classifier. In this paper,the SVM-based multi-classifier was trained by extracted characteristic quantities normalized,during which the genetic algorithm(GA) was used to optimize the SVM parameters for the highest recognition accuracy. The experimental results show the validity of the SVM-based multi-classifier.
Load identification technique can identify the different types of loads in a power system. This paper presents a load identification algorithm based on support vector machine(SVM),which adopted the one-against-one method which combined multiple SVMs to build a multi-classifier to deal with load identification because SVM is only a binary-classifier. In this paper,the SVM-based multi-classifier was trained by extracted characteristic quantities normalized,during which the genetic algorithm(GA) was used to optimize the SVM parameters for the highest recognition accuracy. The experimental results show the validity of the SVM-based multi-classifier.
引文
[1]Anonymous.BP statistical review of world energy[R].Houston:BP Global,2016.
[2]Umeh K C,A Mohamed.A rule-based expert system for harmonic load recognition[C].Kuala Lumpur:Power and Energy Conference,2004.
[3]Drenker S,Kader A.Nonintrusive monitoring of electric loads[J].IEEE Computer Applications in Power,1999,12(4):47-51.
[4]Mahmood Akbar,Zubair Ahmad Khan.Modified nonintrusive appliance load monitoring for nonlinear devices[C].Pakistan:Multitopic Conference,INMIC 2007,IEEE International,2007.
[5]Laughman C.Advanced nonintrusive monitoring of electric loads[J].IEEE Power and Energy Magazine,2003(6):56-63.
[6]Cole A,Albicki A.Nonintrusive identification of electrica loads in a three-phase environment based on harmonic content[J].IEEE Power and Energy Magazine,2000(1):24-29.
[7]Jie Mei,Dawei He,Ronald G,et al.Random forest based adaptive non-intrusive load identification[C].Beijing:Internationa Joint Conference on Neural Networks(IJCNN),2014.
[8]Lin Y H,Tsai M S.A novel feature extraction method for the development of nonintrusive load monitoring system based on BP-ANN[C].Tainan:International Symposium on Computer,Communication,Control and Automation(3CA),2010.
[9]Lin Y H,Tsai M S,Chen C S.Applications of fuzzy classification with fuzzy c-means clustering and optimization strategies for load identification in NILM systems[C].Nanjing:IEEE International Conference on Fuzzy Systems,2011.
[10]Jiang L,Luo S,Li J.Automatic power load event detection and appliance classification based on power harmonic features in nonintrusive appliance load monitoring[C].Shanghai:Industrial Electronics and Applications,IEEE,2013.
[11]Makonin S,Popowich F,Baji I V,et al.Exploiting HMMsparsity to perform online real-time nonintrusive load monitoring[J].IEEE Transactions on Smart Grid,2016,7(6):1-11.
[12]Vapnik V N.Statistical learning theory[M].New York:Wiley,1998.
[13]Jiang L,Li J,Luo S,et al.Literature review of power disaggregation[C].Shanghai:IEEE International Conference on Modelling Identification and Control,2011.
[14]张子瑜,陈进,史习智,等.径向高斯核函数时频分布及在故障诊断中的应用[J].振动工程学报,2001,14(1):53-59.
[15]韩盈盈,章毅鹏,沈鸿平,等.基于遗传算法和0-1规划的规则图形碎片拼接[J].电子科技,2015,28(5):136-139.
[16]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent Systems&Technology,2011(2):1-27.
[2]Umeh K C,A Mohamed.A rule-based expert system for harmonic load recognition[C].Kuala Lumpur:Power and Energy Conference,2004.
[3]Drenker S,Kader A.Nonintrusive monitoring of electric loads[J].IEEE Computer Applications in Power,1999,12(4):47-51.
[4]Mahmood Akbar,Zubair Ahmad Khan.Modified nonintrusive appliance load monitoring for nonlinear devices[C].Pakistan:Multitopic Conference,INMIC 2007,IEEE International,2007.
[5]Laughman C.Advanced nonintrusive monitoring of electric loads[J].IEEE Power and Energy Magazine,2003(6):56-63.
[6]Cole A,Albicki A.Nonintrusive identification of electrica loads in a three-phase environment based on harmonic content[J].IEEE Power and Energy Magazine,2000(1):24-29.
[7]Jie Mei,Dawei He,Ronald G,et al.Random forest based adaptive non-intrusive load identification[C].Beijing:Internationa Joint Conference on Neural Networks(IJCNN),2014.
[8]Lin Y H,Tsai M S.A novel feature extraction method for the development of nonintrusive load monitoring system based on BP-ANN[C].Tainan:International Symposium on Computer,Communication,Control and Automation(3CA),2010.
[9]Lin Y H,Tsai M S,Chen C S.Applications of fuzzy classification with fuzzy c-means clustering and optimization strategies for load identification in NILM systems[C].Nanjing:IEEE International Conference on Fuzzy Systems,2011.
[10]Jiang L,Luo S,Li J.Automatic power load event detection and appliance classification based on power harmonic features in nonintrusive appliance load monitoring[C].Shanghai:Industrial Electronics and Applications,IEEE,2013.
[11]Makonin S,Popowich F,Baji I V,et al.Exploiting HMMsparsity to perform online real-time nonintrusive load monitoring[J].IEEE Transactions on Smart Grid,2016,7(6):1-11.
[12]Vapnik V N.Statistical learning theory[M].New York:Wiley,1998.
[13]Jiang L,Li J,Luo S,et al.Literature review of power disaggregation[C].Shanghai:IEEE International Conference on Modelling Identification and Control,2011.
[14]张子瑜,陈进,史习智,等.径向高斯核函数时频分布及在故障诊断中的应用[J].振动工程学报,2001,14(1):53-59.
[15]韩盈盈,章毅鹏,沈鸿平,等.基于遗传算法和0-1规划的规则图形碎片拼接[J].电子科技,2015,28(5):136-139.
[16]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent Systems&Technology,2011(2):1-27.