A hybrid short-term load forecasting model and its application in ground source heat pump with cooling storage system

Abstract

This paper proposed a hybrid hour-ahead forecast model, which combines multiple superimposed long and short term memory (LSTM) network and back-propagation neural network (BPNN), for the purpose of the load forecast on a building-level. The model (hybrid LSTM-BPNN) takes full consideration of the influence of the meteorological information, time information, the information of persons and devices and indoor thermal parameters. A method (LSTM-BPNN + BPNN) is further developed based on the forecasting advantages of sensible heat by hybrid LSTM-BPNN and latent heat by BPNN, in which the cooling load was split into sensible heat and latent heat to forecast separately. The results show that the method achieves the best performance for hour-ahead load forecasting compared with several classic forecasting models. An operation strategy based on the proposed LSTM-BPNN + BPNN method and LSTM model is applied to an improved ground source heat pump system integrated with cooling storage (GSHPs-CS) which was equipped with two storage tanks to achieve the variable volume control of stored chilled water. The system model is established by TRNSYS. Compared to conventional GSHPs-CS, the energy consumption and operating cost of the improved GSHPs-CS system were reduced by 11.5% and 7.5%, respectively. • A hybrid short-term load forecasting model and method is proposed. • Proposed model improved forecasting accuracy than classical models. • The forecasting models and method were applied to an improved GSHP-CS system. • The forecasting model can achieve a predictive control and realize energy saving.