期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2015
卷号：12
期号：1
出版社：IJCSI Press
摘要：Electricity demand forecasting model based on single algorithm at least have two problems related to local optima and computational cost. We consider to utilised the hybrid real value genetic algorithm and extended Nelder-Mead to solved local optima and reduced the number of iteration. The model is known as the hybrid Real-Value GA and Extended Nelder-Mead (RVGA-ENM). The GA has been enhanced to accept real value while the Nelder-Mead local search is extended to assist in overcoming the local optima problem. The actual electricity demand data of Turkey were used in the experiments to evaluate the performance of the proposed model. Results of the proposed model were compared to the hybrid GA and Nelder-Mead original, Real Code Genetic Algorithm and Particle Swarm Optimisation. Through our evaluation, the proposed hybrid model produced higher accuracy for electricity demand estimation. This model can be used to assist decision-makers in forecasting electricity demand.
关键词：Genetic Algorithm; Electricity Demand Forecasting; Local Optimal.
