Confidence Estimation Transformer for Long-Term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching

Abstract

Expansion of renewable energy could help realize the goals of peaking carbon dioxide emissions and carbon neutralization. Some existing grid dispatching methods integrating short-term renewable energy prediction and reinforcement learning (RL) have been proven to alleviate the adverse impact of energy fluctuations risk. However, these methods omit long-term output prediction, which leads to stability and security problems on optimal power flow. This paper proposes a confidence estimation Transformer for long-term renewable energy forecasting in reinforcement learning-based power grid dispatching (Conformer-RLpatching). Conformer-RLpatching predicts long-term active output of each renewable energy generator with an enhanced Transformer to ensure stable operation of the hybrid energy grid and improve the utilization rate of renewable energy, thus boosting dispatching performance. Furthermore, a confidence estimation method is proposed to reduce the prediction error of renewable energy. Meanwhile, a dispatching necessity evaluation mechanism is put forward to decide whether the active output of a generator needs to be adjusted. Experiments carried out on the SG-126 power grid simulator show that Conformer-RLpatching achieves great improvement over the second best algorithm DDPG in security score by 25.8% and achieves a better total reward compared with the golden medal team in the power grid dispatching competition sponsored by State Grid Corporation of China under the same simulation environment. Codes are outsourced in https://github.com/BUPT-ANTlab/Conformer-RLpatching.

Keywords

• Conformer-RLpatching
• optimal power flow
• reinforcement learning
• renewable energy prediction