Object-Oriented Genetic Algorithm Based Artificial Neural Network for Load Forecasting

This paper illustrates an integrated Computational Intelligence (CI) technique using Artificial Neural Networks (ANN) and Genetic Algorithms (GA) for Electric Load Forecasting. A load forecasting model has been developed based on ANN and GA. The model produces a short-term forecast of the load in the 24 hours of the forecast day concerned. Optimum weights and the biases of ANN are found by the Genetic Algorithm. The technique has been tested on data provided by an Italian power company and the results obtained through the application of integrated computational intelligence approach show that this approach is not practical without high computational facilities as this problem is very complex. However, this points to the direction of evolutionary computing being integrated with parallel processing techniques to solve practical problems.

[1]  Gerald B. Sheblé,et al.  Short-term load forecasting by a neural network and a refined genetic algorithm , 1994 .

[2]  A. C. Liew,et al.  Short term load forecasting using genetic algorithm and neural networks , 1998, Proceedings of EMPD '98. 1998 International Conference on Energy Management and Power Delivery (Cat. No.98EX137).

[3]  M. Sforna,et al.  Practical application of object oriented techniques to designing neural networks for short-term electric load forecasting , 1998, Proceedings of EMPD '98. 1998 International Conference on Energy Management and Power Delivery (Cat. No.98EX137).

[4]  Loi Lei Lai,et al.  Intelligent System Applications in Power Engineering: Evolutionary Programming and Neural Networks , 1998 .

[5]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.

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

[7]  Abdolhosein S. Dehdashti,et al.  Forecasting of Hourly Load by Pattern Recognition??? a Deterministic Approach , 1982, IEEE Power Engineering Review.

[8]  Saifur Rahman,et al.  An expert system based algorithm for short term load forecast , 1988 .