Interest in the subject of prediction has increased in recent years and modern and advanced methods have emerged, including neural network models, chaotic algorithms, hybrid algorithms, and others. All of these methods are able to learn and self-adapt to any model, and do not need assumptions for the nature of the time series. Taking more than one method may lead to an increase in the accuracy of future estimates, so a neural network and chaotic genetic algorithms are used, so a model combines the strengths of two techniques to develop a hybrid CGANN model to obtain more accurate prediction results and reduce prediction errors.
The aim of this study is to shed light on some of the statistical methods used in predicting the future demand for electric power in the southern region, as well as pointing to the most accurate methods in predicting the future of energy. The annual electrical energy consumption data for the southern region was used to make a comparison through practical application and it was found that the three methods are very high accuracy and suitable for use in the prediction process, but the most accurate models are the hybrid algorithm consisting of neural networks and the chaotic genetic algorithm CGANN that gives better and more results efficient, and thus was used to predict the electrical load of the southern region up to 2032.