An Artificial Neural Networks Model to Household Energy Consumption Forecast
The forecast of electric power is a fundamental tool in determining operational and strategic decisions in energy companies, whose lack of precision can generate high economic costs. In this regard, short and long-term electricity demand forecasting allows network operators to make power dispatch decisions, maintenance schedules, reliability and safety analysis of the operation. This work intends to focus on the use of multimodal Artificial Neural Networks (ANNs) for the projection of the demand, taking into account that this is the basis for an adequate planning of electricity distribution networks. The proposed model used for the forecasting was based on available data such as population growth, gross domestic product, Colombian residential electric consumption and the temperature. The artificial neural networks were developed in MATLAB®, trained according to the data recorded, and the final results were compared with the official data provided by the UPME. Thus, in addition to estimate the degree of precision of the forecast used, it is sought to achieve a high degree of accuracy in the decisions, taking into consideration that the increase of residential users and load are important topics for the Colombian energy supply companies in the next decade.