Artificial intelligency methods used for electrical energy consumption forecasting

摘要

The aspects, presented in the paper, refer to an Artificial Neural Network (ANN) architecture for mid term, monthly load forecasting. The paper offers some recommendations for the training set used to teach the ANN, and also approaches an ANN learning method insuring quick load dynamics learning. The software created, based on these aspects, can analyze several load evolution scenarios and can establish a correct trend for the electric load evolution. Selection between different types of load forecasting are discussed in this paper.