A Short-term Load Forecasting Method Based on HI-Informer-LSTM

The issue of load uncertainty in power system is one of the key research directions of the uncertainty of demand response. Accurate power system load forecasting is a crucial prerequisite to ensure the safe and stable of the power grid and the social normal production. Improving the accuracy for load forecasting, the paper proposes the ID-Informer-LSTM model for load forecasting, this model integrates the Historical-Inertia model, the LSTM model and the Informer model using the LSTM model. Experimental results show that the HI-Informer-LSTM model performs excellently in load forecasting, and its forecasting results are highly consistent with the actual observed values, successfully capturing the load trend and seasonal changes. In contrast, other models showed significant errors in some cases and failed to capture the same features effectively.