Forecasting Combined Electricity-Heat-Cooling-Gas Loads in the Integrated Energy System Based on Multi-Task Learning and Transformers Models

The electricity-heat-cooling-gas (EHCG) loads forecasting is an important prerequisite for the safe and stable operation and economic optimization management of integrated energy system (IES). A new method combining multitask learning (MTL) and Transformers models was proposed for EHCG loads forecasting in the IES in this paper. The MTL model can study the complicated correlated information of combined EHCG loads in the IES, and the Transformers model can effectively identify the GHCG loads correlated-based rule. An industrial park IES in North China was treated as a case, and the forecasting results shows the MTL-Transformers-based hybrid method holds the best forecasting performance compared with that of ARIMA, LSTM, LSSVM, CNN-BiGRU and Transformers without multitask learning model. The proposed EHCG loads forecasting method is effective in this paper.