Short Term Load Forecasting (STLF) Using Generalized Neural Network (GNN) Trained with Adaptive GA
The paper is mainly focus to develop an integration of GNN and wavelet based models for STLF. The model is trained by using error back-propagation algorithm, but there are certain inherent drawbacks of back-propagation algorithm. To overcome the drawbacks of back propagation algorithm such as slow learning, stuck in local minima, needs error gradient etc. genetic algorithm (GA) is proposed. The performance of GA is further improved by making an adaptive GA with the help of fuzzy system. The adaptive GA changes the GA parameters such as cross over probability and mutation rate during execution by using fuzzy system. The GNN-W-AGA is used to forecast electrical load and compared with GNN-W trained with backprop and actual data.
KeywordsLoad Forecasting GNN Wavelet Adaptive GA Fuzzy System
Unable to display preview. Download preview PDF.
- 5.Yang, J., Cheng, H.: Application of SVM to power system short-term load forecast. Power System Automation Equipment China 24(4), 30–32 (2004)Google Scholar
- 6.Hwan, K.J., Kim, G.W.: A short-term load forecasting expert system. In: Proceedings of the Fifth Russian-Korean International Symposium on Science and Technology, pp. 112–116 (2001)Google Scholar
- 10.Chaturvedi, D.K., Satsangi, P.S., Kalra, P.K.: Fuzzified Neural Network Approach for Load Forecasting Problems. Int. J. on Engineering Intelligent Systems 9(1), 3–9 (2001)Google Scholar
- 11.Chaturvedi, D.K., Kumar, R., Mohan, M., Kalra, P.K.: Artificial Neural Network learning using improved Genetic algorithm. J. IE(I), EL 82 (2001)Google Scholar
- 14.Chaturvedi, D.K., Mohan, M., Singh, R.K., Kalra, P.K.: Improved Generalized Neuron Model for Short Term Load Forecasting. Int. J. on Soft Computing - A Fusion of Foundations, Methodologies and Applications 8(1), 10–18 (2004)Google Scholar
- 17.Oonsivilai, A., El-Hawary, M.E.: Wavelet neural network based short-term load forecasting of electric power system commercial load. In: Proc. IEEE Can. Conf. Electrical and Computer Engineering, pp. 1223–1228 (1999)Google Scholar
- 18.Chang, C.S., Fu, W., Yi, M.: Short term load forecasting using wavelet networks. Eng. Intell. Syst. Elect. Eng. Commun. 6, 217–223 (1998)Google Scholar
- 20.Banakar, A., Azeem, A.: Artificial Wavelet Neural Network and its application in Neurofuzzy models. Elsevier Applied Soft Computing (2008)Google Scholar
- 22.Chaturvedi, D.K., Das, V.S.: Optimization of Genetic Algorithm Parameters. In: National Conference on Applied Systems Engineering and Soft Computing (SASESC 2000), pp. 194–198. Organized by Dayalbagh Educational Institute, Dayalbagh (2000)Google Scholar
- 23.Fogarty, T.C.: Varying the Probability of Mutation in the Genetic Algorithm. In: Proceedings of 3rd International Conference in Genetic Algorithms and Applications, Arlington, VA, pp. 104–109 (1981)Google Scholar