{"title":"STLF Based on Optimized Neural Network Using PSO","authors":"H. Shayeghi, H. A. Shayanfar, G. Azimi","volume":28,"journal":"International Journal of Computer and Information Engineering","pagesStart":1190,"pagesEnd":1201,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/14888","abstract":"
The quality of short term load forecasting can improve the efficiency of planning and operation of electric utilities. Artificial Neural Networks (ANNs) are employed for nonlinear short term load forecasting owing to their powerful nonlinear mapping capabilities. At present, there is no systematic methodology for optimal design and training of an artificial neural network. One has often to resort to the trial and error approach. This paper describes the process of developing three layer feed-forward large neural networks for short-term load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. Particle Swarm Optimization (PSO) is used to develop the optimum large neural network structure and connecting weights for one-day ahead electric load forecasting problem. PSO is a novel random optimization method based on swarm intelligence, which has more powerful ability of global optimization. Employing PSO algorithms on the design and training of ANNs allows the ANN architecture and parameters to be easily optimized. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. The experimental results show that the proposed method optimized by PSO can quicken the learning speed of the network and improve the forecasting precision compared with the conventional Back Propagation (BP) method. Moreover, it is not only simple to calculate, but also practical and effective. Also, it provides a greater degree of accuracy in many cases and gives lower percent errors all the time for STLF problem compared to BP method. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.<\/p>\r\n","references":"[1] A.-U. Asar, S.R.-U. Hassnain, A. Khan, \"Short-term load forecasting\r\nusing particle swarm optimization based ANN approach\", Proc. of\r\nIEEE Int. Joint Conf. on Neural Networks, Orlando, Florida, USA,\r\n2007, pp. 6.\r\n[2] K.-H. Kim, H.-S. Youn, Y.-C. Kang, \"Short-term load forecasting for\r\nspecial days in anomalous load conditions using neural networks and\r\nfuzzy inference method\", IEEE Trans. on Power Systems, vol. 15, No. 2,\r\n2000, pp. 559-565.\r\n[3] H. Shayeghi, H. A. Shayanfar, G. Azimi, Intelligent neural network\r\nbased STLF\", Int. J. of Intelligent Systems and Technologies, vol. 4.,\r\nNo. 1, 2009, pp. 17-27.\r\n[4] G. Box, G.M. Jenkins, \"Time series analysis, forecasting and control\",\r\nSan Francisco: Holden-Day; 1970.\r\n[5] J.H. Park, Y.M. Park, K.Y. Lee, \"Composite modeling for adaptive\r\nshort-term load forecasting\", IEEE Trans. on Power Systems, vol. 6,\r\n1991, pp. 450-457.\r\n[6] A. D. Papalexopoulos, T. C. Hesterberg, \"A regression-based approach\r\nto short-term system load forecasting\", IEEE Trans on Power Systems,\r\nvol. 4, No. 4, 1990, pp. 1535-1547.\r\n[7] Z. Baharudin and N. Kamel, \"Autoregressive method in short term load\r\nforecast\", in Proc. of 2nd IEEE Int. Conf. on Power and Energy\r\n(PECON 08), Johor Baharu, Malaysia, 2008, pp. 1603-1608.\r\n[8] Z. A. Bashir and M. E. El-Hawary, \"Short-term load forecasting using\r\nartificial neural network based on particle swarm optimization\r\nalgorithm\", in Proc. of IEEE Electrical and Computer Engineering\r\nCanadian Conf., 2007, pp. 272-275.\r\n[9] T. W. S. Chow, C. T. Leung, \"Neural networks based short term load\r\nforecasting using weather compensation\", in Proc. of IEEE Conf., 1996,\r\npp. 1736-1742.\r\n[10] R. Afkhami, F. Mosalman Yazdi, \"Application of neural networks for\r\nshort-term load forecasting\", in Proc. of IEEE Power India Conf., 2006,\r\npp. 5.\r\n[11] W. Charytoniuk, M.S. Chen, \"Neural network design short-term load\r\nforecasting\", in Proc. of IEEE Int. Conf. on Electric Utility\r\nDeregulation and Restructuring and Power Technologies, City\r\nUniversity, London, 2000, pp. 554-561.\r\n[12] E. Banda and K. A. Folly, \"Short-term load forecasting using artificial\r\nneural network\", in Proc. of IEEE Power Technology Conf., Lausanne,\r\n2007, pp. 108-112.\r\n[13] G.-C. Liao, T.-P. Tsao, \"Application of a fuzzy neural network combined\r\nwith a chaos genetic algorithm and simulated annealing to short-term\r\nload forecasting\", IEEE Trans. on Evolutionary. Computation, vol. 10,\r\nNo. 3, 2006, pp. 330-340.\r\n[14] S. H. Ling, F. H. F. Leung, H. K. Lam, Y.-S. Lee, P. K. S. Tam, \"A novel\r\ngenetic-algorithm-based neural network for short-term load\r\nforecasting\", IEEE Trans. on Industrial Electronics, vol. 50, No. 4,\r\n2003, pp. 793-799.\r\n[15] J.-R. Zhang, J. Zhang, T.-M. Lok, M. R. Lyu, \"A hybrid particle swarm\r\noptimization-back propagation algorithm for feed-forward neural\r\nnetwork training\", Applied Mathematics and Computation, vol. 185,\r\n2007, pp. 1026-1037.\r\n[16] C.-F. Juang, \"A hybrid of genetic algorithm and particle swarm\r\noptimization for recurrent network design\", IEEE Trans. on systems,\r\nMan and Cybernetics-Part B: Cybernetics, vol. 34, No.2, 2004, pp. 997-\r\n1006.\r\n[17] H. Shayeghi, A. Jalili and H. A. Shayanfar, \"Multi-stage fuzzy load\r\nfrequency control using PSO\", Energy Conversion and Management,\r\nvol. 49, 2008, pp. 2570-2580.\r\n[18] M. Clerc and J. Kennedy, \"The particle swarm-Explosion, stability, and\r\nconvergence in a multidimensional complex space\", IEEE Trans. on\r\nEvolutionary. Computation, vol. 6, No. 1, 2002, pp. 58-73.\r\n[19] C. Zhang, H. Shao, Y. Li, \"Particle swarm optimization for evolving\r\nartifical network\", in Proc. of IEEE Int. Conf. on Systems., Man and\r\nCybernetics, vol. 4, 2000, pp. 2487-2490.\r\n[20] R. Mendes, P. Cortez, M. Rocha, and J. Neves, \"Particle swarms for\r\nfeedforward neural network training\", in Proc. Int. Joint Conf. on\r\nNeural Networks, vol. 2, 2002, pp. 1895-1899.\r\n[21] J. Kennedy and R. Eberhart, \"Particle swarm optimization, in Proc. of\r\nIEEE Int. Conf. on Neural Networks, vol. 4, 1995, pp. 1942-1948.\r\n[22] C. Sun, D. Gong, \"Support vector machines with PSO algorithm for\r\nshort-term load forecasting\", in Proc. of IEEE Int. Conf. on Networking,\r\nSensing and Control, 2006, pp. 676-680","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 28, 2009"}