Short Term Load Forecasting by Using Neural Networks with Variable Activation Functions and Embedded Chaos Algorithm
In this paper a novel variant activation (transform) sigmoid function with three parameters is proposed, and then the improved BP algorithm based on it is educed and discussed, then Embedded Chaos-BP algorithm is proposed by means of combining the new fast BP algorithm and chaos optimization algorithm, Embedded chaos-BP algorithm converges fast and globally, and has no local minimum. The efficiency and advantage of our method is proved by simulation results of nonlinear function and prediction results of short-term load based on the improved and traditional BP ANNs.
KeywordsBack Propagation Load Forecast Back Propagation Algorithm Short Term Load Chaos System
Unable to display preview. Download preview PDF.
- 1.Niu, D., Cao, S.: Electric Load Forecasting Technology and Its Application. Chinese Electric Press (1998)Google Scholar
- 2.Ma, W., Bai, X.: Short Term Load Forecasting Using Artificial Neuron Network and Fuzzy Inference. Power System Technology 27(5), 29–32 (2003)Google Scholar
- 3.Wu, Y., Zhao, M.: A New Neural Networks with Variable Activation Functions and Its Application. Science in China (Series E) 27(1), 55–60 (1997)Google Scholar
- 4.Hu, Y., Yan, X., Zhang, X.: An Improved BP Algorithm Based on a Variant Sigmoid Function with Three Parameters. DCABES Proceedings, 144–148 (2004)Google Scholar
- 5.Long, X., Xiao, T.: Neural Networks with Variable Activation Functions. Computer Engineering 27(12), 71–73 (2001)Google Scholar
- 6.Treadgold Nicholas, K., Gedeon Tamas, D.: Simulated Annealing and Weight Decay in Adaptive Learning: The Sarprop Algorithm. IEEE Trans on Neural Networks, 662–668 (1998)Google Scholar
- 8.Jing, J., Sun, Y.: Short-Term Load Forecasting Using Chaotic Learning Algorithm for Neural Network. Automation Electric Power System 7, 32–35 (2004)Google Scholar