Comprehensive identification of multiple harmonic sources using fuzzy logic and adjusted probabilistic neural network

This paper presents a comprehensive approach based on fuzzy logic and probabilistic neural network (PNN) to identify location, relative level, and type of multiple harmonic sources in power distribution systems. The location and relative level of harmonic sources were determined in the fuzzy stage by interpreting harmonic powers together with network impedances. Then, the type of the harmonic sources was classified in the neural stage using adjusted PNN. In the proposed method, the harmonic powers were considered as classification features. Then, ReliefF feature selection method was used to reduce the redundant data and dimension of features vector. A new modified adaptive imperialist competitive algorithm (MAICA) was proposed to determine the only adjusted parameter of the PNN classifier. Furthermore, a deep belief network (DBN) was applied in the neural stage, and its results were compared with the PNN classifier. The proposed approach was evaluated on IEEE 18-bus and IEEE 69-bus test systems. Unlike the single point methods, the presented method provides information on multiple harmonic sources in the whole of the distribution system. The results show that the comprehensive approach identifies the multiple harmonic sources with high accuracy.

[1]  H. Wayne Beaty,et al.  Electrical Power Systems Quality , 1995 .

[2]  Seyedmohsen Hosseini,et al.  A survey on the Imperialist Competitive Algorithm metaheuristic: Implementation in engineering domain and directions for future research , 2014, Appl. Soft Comput..

[3]  Newton Spolaôr,et al.  Filter Approach Feature Selection Methods to Support Multi-label Learning Based on ReliefF and Information Gain , 2012, SBIA.

[4]  Azah Mohamed,et al.  Identification of multiple harmonic sources in power systems using independent component analysis and mutual information , 2010 .

[5]  Ekrem Gursoy,et al.  Harmonic Load Identification Using Complex Independent Component Analysis , 2009 .

[6]  Yilu Liu,et al.  A method for determining customer and utility harmonic contributions at the point of common coupling , 2000 .

[7]  S. M. Hosseini,et al.  Solving Euclidean minimal spanning tree problem using a new meta-heuristic approach: Imperialist Competitive algorithm (ICA) , 2012, 2012 IEEE International Conference on Industrial Engineering and Engineering Management.

[8]  S. N. Singh,et al.  Identification of Multiple Harmonic Sources in Power System Using Optimally Placed Voltage Measurement Devices , 2014, IEEE Transactions on Industrial Electronics.

[9]  Zahra Mohammadi,et al.  A hybrid intelligent model combining ANN and imperialist competitive algorithm for prediction of corrosion rate in 3C steel under seawater environment , 2017, Neural Computing and Applications.

[10]  Maryam Mirzaei,et al.  Comparative Analysis of Probabilistic Neural Network, Radial Basis Function, and Feed-forward Neural Network for Fault Classification in Power Distribution Systems , 2011 .

[11]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[12]  Asghar Akbari Foroud,et al.  Cost-effective optimal allocation and sizing of active power filters using a new fuzzy-MABICA method , 2016 .

[13]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[14]  Whei-Min Lin,et al.  Multiple harmonic source detection and equipment identification with cascade correlation network , 2005 .

[15]  Surya Santoso,et al.  Understanding Power System Hannonics , 2001, IEEE Power Engineering Review.

[16]  José Carlos de Oliveira,et al.  The sharing of responsibility between the supplier and the consumer for harmonic voltage distortion : A case study , 2008 .

[17]  Chia-Hung Lin,et al.  Multiple harmonic-source classification using a Self-Organization Feature Map network with voltage–current wavelet transformation patterns☆ , 2015 .

[18]  Gustavo Adolfo,et al.  Uncertainty and State Estimation of Power Systems , 2012 .

[19]  Asghar Akbari Foroud,et al.  Recognition and assessment of different factors which affect flicker in wind turbines , 2016 .

[20]  Mehmet Tümay,et al.  Hierarchical neuro-fuzzy current control for a shunt active power filter , 2005, Neural Computing & Applications.

[21]  Azah Mohamed,et al.  An enhanced method for contribution assessment of utility and customer harmonic distortions in radial and weakly meshed distribution systems , 2012 .

[22]  J. Arrillaga,et al.  An adaptive Kalman filter for dynamic harmonic state estimation and harmonic injection tracking , 2005, IEEE Transactions on Power Delivery.

[23]  M. Kazerani,et al.  Identification and Measurement of Harmonic Pollution for Radial and Nonradial Systems , 2009, IEEE Transactions on Power Delivery.

[24]  Amir Moradifar,et al.  A Fuzzy Based Solution for Allocation and Sizing of Multiple Active Power Filters , 2012 .

[25]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[26]  Zhengtao Ding,et al.  A dynamic approach to identification of multiple harmonic sources in power distribution systems , 2016 .

[27]  Satish Vadlamani,et al.  Hybrid imperialist competitive algorithm, variable neighborhood search, and simulated annealing for dynamic facility layout problem , 2014, Neural Computing and Applications.

[28]  Maciej Kusy,et al.  Application of Reinforcement Learning Algorithms for the Adaptive Computation of the Smoothing Parameter for Probabilistic Neural Network , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[29]  V. Suresh Kumar,et al.  Determining true harmonic contributions of sources using neural network , 2016, Neurocomputing.

[30]  Azah Mohamed,et al.  A Rule Based Expert System for Identification of Harmonics Originating from Single Phase Nonlinear Loads , 2006 .

[31]  Abdullah Al Khaled,et al.  Fuzzy adaptive imperialist competitive algorithm for global optimization , 2014, Neural Computing and Applications.

[32]  Jiancheng Lv,et al.  Classification model of restricted Boltzmann machine based on reconstruction error , 2016, Neural Computing and Applications.

[33]  Dejan Stevanovic,et al.  A single-point method based on distortion power for the detection of harmonic sources in a power system , 2014 .

[34]  A.C. Liew,et al.  Neural-network-based signature recognition for harmonic source identification , 2006, IEEE Transactions on Power Delivery.

[35]  Yu Xue,et al.  Text classification based on deep belief network and softmax regression , 2016, Neural Computing and Applications.

[36]  Andrew Hunter,et al.  Feature Selection Using Probabilistic Neural Networks , 2000, Neural Computing & Applications.

[37]  A. E. Emanuel,et al.  On the assessment of harmonic pollution [of power systems] , 1995 .

[38]  Gabriele D'Antona,et al.  State Estimation for the Localization of Harmonic Sources in Electric Distribution Systems , 2009, IEEE Transactions on Instrumentation and Measurement.

[39]  A. Cataliotti,et al.  A Novel Approach Based on Nonactive Power for the Identification of Disturbing Loads in Power Systems , 2007, IEEE Transactions on Power Delivery.