Neural Network Based on Dynamic Multi-swarm Particle Swarm Optimizer for Ultra-Short-Term Load Forecasting

Ultra-Short-Term Load Forecasting plays an important role in Power Load Forecasting. Back Propagation Neural Network(BPNN) has become one of the most commonly used methods in Power System Ultra-Short-Term Load Forecasting for its ability of computing complex samples and training large-scale samples. However, traditional BPNN algorithm needs to set up a large amount of network training parameters, and it is easy to be trapped into local optima. A new algorithm which is Neural Network based on Dynamic Multi-Swarm Particle Swarm Optimizer (DMSPSO-NN) is proposed for Ultra-Short-Term Load Forecasting in this paper. DMSPSO-NN overcomes the shortage of traditional BPNN and has a good global search and higher accuracy which shows that it is suitable to be used for Ultra-Short-Term Load Forecasting.

[1]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .

[2]  Jing J. Liang,et al.  Dynamic multi-swarm particle swarm optimizer , 2005, Proceedings 2005 IEEE Swarm Intelligence Symposium, 2005. SIS 2005..

[3]  R. E. Abdel-Aal.  Improving electric load forecasts using network committees , 2005 .

[4]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[5]  Jie Hu,et al.  A hybrid PSO-BP algorithm and its application , 2010, 2010 Sixth International Conference on Natural Computation.

[6]  Zuo Li,et al.  Forecasting of short-term load based on fuzzy clustering and improved BP algorithm , 2011, 2011 International Conference on Electrical and Control Engineering.

[7]  HairuLi,et al.  Based on PSO-BP network algorithm for fault diagnosis of power transformer , 2010 .

[8]  Zhou Hui.  Forecasting the Daily Load Based on ANN , 2007 .

[9]  James Kennedy,et al.  Particle swarm optimization , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10]  Zhang-ping You,et al.  Modeling and Simulation of Screw Axis Based on PSO-BP Neural Network and Orthogonal Experiment , 2009, 2009 Second International Symposium on Computational Intelligence and Design.

[11]  Y. H. Song,et al.  Wavelet transform and neural networks for short-term electrical load forecasting , 2000 .

[12]  G. Gross,et al.  Short-term load forecasting , 1987, Proceedings of the IEEE.

[13]  Jianfeng Ma,et al.  PSO-BP Neural Network in Reservoir Parameter Dynamic Prediction , 2011, 2011 Seventh International Conference on Computational Intelligence and Security.

[14]  In-Keun Yu,et al.  Kohonen neural network and wavelet transform based approach to short-term load forecasting , 2002 .

[15]  Shuai Yang,et al.  An Improved PSO-BP Network Model , 2010, 2010 Third International Symposium on Information Science and Engineering.

[16]  Jing J. Liang,et al.  Dynamic multi-swarm particle swarm optimizer with local search , 2005, 2005 IEEE Congress on Evolutionary Computation.

[17]  Stefan Rüping,et al.  Incremental Learning with Support Vector Machines , 2001, ICDM.

[18]  Y.-Y. Hsu,et al.  Fuzzy expert systems: an application to short-term load forecasting , 1992 .