Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting
This addresses the problem of efficient power system operations for smart grid technology, though it is incremental as it applies a known method to a specific domain.
The paper tackles the challenge of selecting suitable forecasting models under varying conditions in short-term load forecasting by developing a reinforcement learning based dynamic model selection method, which improves forecasting accuracy by approximately 50% compared to state-of-the-art models.
With the growing prevalence of smart grid technology, short-term load forecasting (STLF) becomes particularly important in power system operations. There is a large collection of methods developed for STLF, but selecting a suitable method under varying conditions is still challenging. This paper develops a novel reinforcement learning based dynamic model selection (DMS) method for STLF. A forecasting model pool is first built, including ten state-of-the-art machine learning based forecasting models. Then a Q-learning agent learns the optimal policy of selecting the best forecasting model for the next time step, based on the model performance. The optimal DMS policy is applied to select the best model at each time step with a moving window. Numerical simulations on two-year load and weather data show that the Q-learning algorithm converges fast, resulting in effective and efficient DMS. The developed STLF model with Q-learning based DMS improves the forecasting accuracy by approximately 50%, compared to the state-of-the-art machine learning based STLF models.