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

Small hydropower plants (HPPs) equipped with water storage play an important role in managing fluctuating energy demand. This article presents a real-world case study in which model predictive control (MPC), driven by energy-demand and water-inflow forecasts produced using the Light Gradient Boosting Machine (LGBM), is applied to optimize the operation of a small hydropower plant 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. Results show that the MPC can outperform the operator-based scheduling and that this has the potential to improve the peak shaving capabilities of small HPPs. Unlike previous studies that predominantly focus on large and complex hydropower systems or introduce new control formulations evaluated under idealized assumptions, this work offers a pragmatic solution to the underexplored context of peak shaving for small HPPs operated with limited data and resources, that small utilities can adopt with minimal effort using their own data. We show that even these small-scale hydropower operations have room for improvement through optimal scheduling.