Electric and Heat Load Forecasting of Integrated Energy System

Accurate load forecasting is essential for optimizing the operation and energy management of integrated energy system (IES). The accuracy of load forecasting depends on both historical data and prediction methods. To address the limitations of traditional load forecasting methods such as inaccurate forecasting and single load, this study proposes a novel approach that combined digital twin (DT) with Transformer for accurate multiple loads forecasting of IES. Next, a virtual representation of the IES is constructed using DT to provide accurate data for load forecasting. The data is then processed and fed into the Transformer model for training, resulted in models with high forecasting performance. Lastly, simulations are used to assess the performance of the proposed model on a park level IES. The results indicate that the proposed model demonstrates high accuracy and can closely track the changes in actual load values.