Load Forecasting via Diversified State Prediction in Multi-Area Power Networks

Abstract

Load forecasting has a pivotal role in operating electric utilities. This paper proposes a learning-based tool for short-term load forecasting via first predicting the state parameters of the grid and then delineating load forecasts as functions of the predicted state parameters. Such indirect load forecasting via predicting state parameters leads to improved forecast quality due to the inherent diversity in predictions for state parameters. Specifically, due to the strong inter-connectivity among network components, some state parameters are shared by multiple substations. Hence, allowing each substation to provide local predictions for its associated state parameters based on its local dynamics enables providing multiple predictions for each shared state parameter, leading to a diversified set of predictions for it. Our analysis shows that the proposed aggregation framework provides a prediction for each state parameter such that the quality of this prediction equals to that of the best local prediction provided for that state parameter. This implies that this framework can identify and track the best local prediction for each state parameter without requiring any knowledge about network dynamics.