A Markov Decision Process and Adapted Particle Swarm Optimization-Based Approach for the Hydropower Dispatch Problem—Jirau Hydropower Plant Case Study

This work focuses on optimizing energy dispatch in a hydroelectric power plant (HPP) with a large number of generating units (GUs) and uncertainties caused by sediment accumulation in the water intakes. The study was realized at Jirau HPP, and integrates Markov Decision Processes (MDPs) and Particle Swarm Optimization (PSO) to minimize losses and enhance the performance of the plant’s GUs. Given the complexity of managing the huge number of units (50) and mitigating load losses from sediment accumulation, this approach enables real-time decision-making and optimizes energy dispatch. The methodology involves modeling the operational characteristics of the GUs, developing an objective function to minimize water consumption and maximize energy efficiency, and utilizing MDPs and PSO to find globally optimal solutions. Our results show that this methodology improves efficiency, reducing the turbinated flow by 0.9% while increasing energy generation by 0.34% and overall yield by 0.33% compared to the HPP traditional method of dispatch over the analyzed period. This strategy could be adapted to varying operational conditions, and could provide a reliable framework for hydropower dispatch optimization.