An Improved Informer Network for Short-Term Electric Load Forecasting

Background: Electric load forecasting plays an essential role in the dispatching operation of power systems. It can be divided into long-term, medium-term, and short-term according to the forecast time. Accurate short-term electric forecasting helps the system operate safely and reliably, reduces resource waste, and improves economic efficiency. Objective: To fully use the time-series characteristics in load data and improve the accuracy of short-term electric load forecasting, we propose an improved Informer model called Nysformer. Methods: Firstly, the input of data is improved, and the information is input into the model in the form of difference. Then, the Nystrom self-attention mechanism was proposed, approximating the standard self-attention mechanism using an approximation with O(n) time complexity and memory utilization. Results: We conducted experiments on a publicly available dataset, and the results show that the proposed Nysformer model has lower time complexity and higher accuracy than the standard Informer model. Conclusion: An improved informer network is proposed for short-term electric load forecasting, and the experimental results demonstrate the proposed model Nysformer can improve the accuracy of short-term electric load forecasting.