Reinforcement Learning Based Electricity Price Controller in Smart Grids

Striking a balance between power supply and demand is the most imperative target for any electricity grid system. In order to address variability of renewable energy in the modern grid, a robust and elastic balancing scheme is required. Conventional model-based approaches can suffer from great performance degradation given the uncertainty induced by the renewable energy. As such, this study explores a model-free approach by proposing a reinforcement learning based pricing scheme that balances the power supply and demand. A price signal is considered as the control signal for the balance management. Case studies involving different market parameters and different time resolutions were conducted to show the effectiveness of the proposed methodology.