2026-05-11T21:05:15.264Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:2:3949 2016-02-26T18:17:23Z 2

Single Home Electricity Power Consumption Forecast Using Neural Networks Model 2016 ISSN 2348 – 7968 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/2/3949 www.ijiset.com N. Farag M. Milosavljević This work analyzes an electricity power consumption forecast for a single home using a multi-layer perceptron (MLP) artificial neural network (ANN). The predictor composes of parallel banks of MLP (PBMLP) for each hour within a day. Training PBMLP is performed separately for each day of the week using appropriate training sets of past electricity power consumption. The performance of the predictor was evaluated using real data which represents power consumption per minute measured over almost 4 years for a single home near Paris, France (approximately 2 million data points). Experiments show that proposed system for predicting power consumption one day ahead gave mean absolute value of relative percentage error (MARPE) lower more than 25% comparing to persistent prediction, which is to our knowledge the best reported result up to now. article 3 1 100 106 2348-7968 IJISET - International Journal of Innovative Science, Engineering & Technology