Enhancing Peak Shaving Efficiency in Small Hydro Power Plants Through Machine Learning-Based Predictive Control

Small hydro power plants (HPPs) play an important role in managing fluctuating energy requirements. This article presents a real-world case study where model predictive control (MPC) utilizing lightGBM-based machine learning (ML) forecasts of energy demand and water availability is employed to optimize the scheduling of a small HPP for peak shaving. A comparative analysis is conducted between the current non-predictive control strategy, which relies on operator decisions for peak shaving, and a fully automatic controller that optimally schedules the utilization of available water resources based on ML predictions. Preliminary results show that the MPC can outperform the operator’s decisions and that this has the potential of improving peak shaving capabilities of small HPPs, emphasizing the role of predictive control methodologies for exploiting energy storage resource in the management of the distribution grid. This approach offers a pragmatic solution that small utilities can adopt with minimal effort using their own data.