Artificial neural network application to load forecasting in a large hospital facility

A Smart Grid approach to electric distribution system management needs to front uncertainties in generation and demand thus making forecasting an up-to-date area of research in electric energy systems. This works aims to propose a day-ahead load forecasting procedure for a medium voltage customer. The load forecasting is performed through the implementation of an artificial neural network (ANN). The proposed multi-layer perceptron ANN, based on backpropagation training algorithm, is able to take as inputs: loads, data concerning the type of day (e.g. weekday/holiday), time of the day and weather data (e.g. temperature, humidity). This procedure has been tested to predict the loads of a large university hospital facility located in Rome.