作者: Zhanyu Ma , Jiyang Xie , Hailong Li , Qie Sun , Fredrik Wallin
DOI: 10.1109/TBDATA.2019.2907127
关键词:
摘要: Prediction of heat demand using artificial neural networks has attracted enormous research attention. Weather conditions, such as direct solar irradiance and wind speed, have been identified key parameters affecting demand. This paper employs an Elman network to investigate the impacts speed on from perspective entire district heating network. Results overall mean absolute percentage error (MAPE) show that quite similar impacts. However, involvement can clearly reduce maximum deviation when only involving respectively. In addition, simultaneous both does not obvious improvement MAPE. Moreover, prediction accuracy also be affected by other factors like data discontinuity outliers.