Effective management of modern electrical transport systems is a very important and difficult task. Much of the transport of passengers in cities is based on electric vehicles. Tram and trolley transport in Sofia is quite largely developed. It is one of the largest consumers of electricity in the city, which makes the question of electricity prediction very important for its operation. The paper presents two models predicting electricity consumption. One model is based on Artificial Neural Networks (ANN), and the other on Time Series Analysis (TSA). The purpose of this paper is to compare the two models in certain indicators to determine and to identify their advantages and disadvantages. The main conclusion will be that the ANN model is much more precise but requires more inputs and computational efforts, while the TSA model, against some errors, shows a low demanding input entries and an easy computational approach. In addition, the ANN model has a lower range of prediction, since it needs many recent inputs in order to produce the output. On the contrary, the TSA model prediction, once the model has been calibrated on a certain time range, can be extended to any time, of course losing precision in the forecast.
Public Transportation Energy Consumption Prediction by means of Neural Network and Time Series Analysis Approaches
GUARNACCIA, CLAUDIO;QUARTIERI, Joseph;TEPEDINO, CARMINE;
2015-01-01
Abstract
Effective management of modern electrical transport systems is a very important and difficult task. Much of the transport of passengers in cities is based on electric vehicles. Tram and trolley transport in Sofia is quite largely developed. It is one of the largest consumers of electricity in the city, which makes the question of electricity prediction very important for its operation. The paper presents two models predicting electricity consumption. One model is based on Artificial Neural Networks (ANN), and the other on Time Series Analysis (TSA). The purpose of this paper is to compare the two models in certain indicators to determine and to identify their advantages and disadvantages. The main conclusion will be that the ANN model is much more precise but requires more inputs and computational efforts, while the TSA model, against some errors, shows a low demanding input entries and an easy computational approach. In addition, the ANN model has a lower range of prediction, since it needs many recent inputs in order to produce the output. On the contrary, the TSA model prediction, once the model has been calibrated on a certain time range, can be extended to any time, of course losing precision in the forecast.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
