Multi-variable Echo State Network Optimized by Bayesian Regulation for Daily Peak Load Forecasting

In this paper, a multi-variable echo state network trained with Bayesian regulation has been developed for the short-time load forecasting. In this study, we focus on the generalization of a new recurrent network. Therefore, Bayesian regulation and Levenberg-Marquardt algorithm is adopted to modify the output weight. The model is verified by data from a local power company in south China and its performance is rather satisfactory. Besides, traditional methods are also used for the same task as comparison. The simulation results lead to the conclusion that the proposed scheme is feasible and has great robustness and satisfactory capacity of generalization.

[1]  Furong Li,et al.  Risk comprehensive evaluation of urban network planning based on fuzzy Bayesian LS_SVM , 2010, Kybernetes.

[2]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[3]  Yang Shao,et al.  Comparison of Early Stopping Criteria for Neural-Network-Based Subpixel Classification , 2011, IEEE Geoscience and Remote Sensing Letters.

[4]  Yudong Zhang,et al.  WEIGHTS OPTIMIZATION OF NEURAL NETWORK VIA IMPROVED BCO APPROACH , 2008 .

[5]  Shady Aly,et al.  Fuzzy aggregation and averaging for group decision making: A generalization and survey , 2009, Knowl. Based Syst..

[6]  A. Lansner,et al.  Bayesian neural networks with confidence estimations applied to data mining , 2000 .

[7]  Zuren Feng,et al.  Hourly electric load forecasting algorithm based on echo state neural network , 2011, 2011 Chinese Control and Decision Conference (CCDC).

[8]  J. J. De Groote,et al.  Generalization of finite size Boolean perceptrons with genetic algorithms , 2008, Neurocomputing.

[9]  Zehong Yang,et al.  Short-term stock price prediction based on echo state networks , 2009, Expert Syst. Appl..

[10]  J Zhao,et al.  A Two-Stage Online Prediction Method for a Blast Furnace Gas System and Its Application , 2011, IEEE Transactions on Control Systems Technology.

[11]  Paulin Coulibaly,et al.  Reservoir Computing approach to Great Lakes water level forecasting , 2010 .

[12]  Kwong-Sak Leung,et al.  Data mining of Bayesian networks using cooperative coevolution , 2004, Decis. Support Syst..

[13]  Hussein A. Abbass,et al.  Stopping criteria for ensemble of evolutionary artificial neural networks , 2005, Appl. Soft Comput..

[14]  Herbert Jaeger,et al.  Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

[15]  BehzadMohsen,et al.  Generalization performance of support vector machines and neural networks in runoff modeling , 2009 .

[16]  Ming-Kuen Chen,et al.  A hybrid Delphi-Bayesian method to establish business data integrity policy: A benchmark data center case study , 2010, Kybernetes.

[17]  Maziar Palhang,et al.  Generalization performance of support vector machines and neural networks in runoff modeling , 2009, Expert Syst. Appl..

[18]  Pavel V. Pakshin,et al.  Parametrization of static output feedback controllers for Markovian switching systems and related robust control problems , 2009, Kybernetes.

[19]  Hong Peng,et al.  Shared reservoir modular echo state networks for chaotic time series prediction , 2010, 2010 International Conference on Machine Learning and Cybernetics.