A GRU-Based Short-Term Multi-energy Loads Forecast Approach for Integrated Energy System

Abstract

The dispatching and operation of integrated energy system (IES) is inseparable from accurate load forecasting. The interaction of various energy subsystems in IES makes each load have a strong coupling relationship. Mining this potential coupling is of great significance to short-term load forecasting. Using the feature that gate recurrent unit (GRU) can help in mining the potential relationship between data. A multi-energy coupling short-term load forecasting model based on GRU is constructed in this paper. Taking the historical data of multiple loads, temperature, air pressure, and solar irradiance of an area's IES as input, the trained model can accurately predict electricity, heat energy, and cooling.