The optimal dispatch of hydropower plants consists of the challenge of taking advantage of both available head and river flows. Despite the objective of delivering the maximum power to the grid, some variables are uncertain, dynamic, non-linear, and non-parametric. Nevertheless, some models may help hydropower generating players with computer science evolution, thus maximizing the hydropower plants’ power production. Over the years, several studies have explored Machine Learning (ML) techniques to optimize hydropower plants’ dispatch, being applied in the pre-operation, real-time and post-operation phases. Hence, this work consists of a systematic review to analyze how ML models are being used to optimize energy production from hydropower plants. The analysis focused on criteria that interfere with energy generation forecasts, operating policies, and performance evaluation. Our discussions aimed at ML techniques, schedule forecasts, river systems, and ML applications for hydropower optimization. The results showed that ML techniques have been more applied for river flow forecast and reservoir operation optimization. The long-term scheduling horizon is the most common application in the analyzed studies. Therefore, supervised learning was more applied as ML technique segment. Despite being a widely explored theme, new areas present opportunities for disruptive research, such as real-time schedule forecast, run-of-river system optimization and low-head hydropower plant operation.

Hydropower plants (HPP) in the Amazon basin suffer from issues caused by trees and sediments carried by the river. The Jirau HPP, located in the occidental Amazon basin, is directly affected by high sediment transportation. These materials accumulate in the water intakes and obstruct the trash racks installed in the intake system to prevent the entry of materials. As a result, head losses negatively impact the efficiency of the generating units and the power production capacity. The HPP operation team must monitor these losses and take action timely to clear the intakes. One of the possible actions is to stop the GU to let the sediment settle down. Therefore, intelligent methods are required to predict the downtime for sediment settling and restoring operational functionality. Thus, this work proposes a technique that utilizes hidden Markov models and Bayesian networks to predict the fifty Jirau generation units’ downtime, thereby reducing their inactive time and providing methodologies for establishing operating rules. The model is based on accurate operational data extracted from the hydropower plant, which ensures greater fidelity to the daily operational reality of the plant. The results demonstrate the model’s effectiveness and indicate the extent of the impact on downtime under varying sediment levels and when neighboring units are generating or inactive.

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.

The operation of hydroelectric power plants is directly dependent on data from various systems. These systems are classified as Operational Technologies (OT) when focused on fieldlevel control and Information Technologies (IT) when aimed at enterprise-level applications. The efficient integration of these systems is a challenge for industries since each system type has different perspectives and objectives. However, this integration is crucial to achieving the best possible operational performance. In the hydroelectric power generation market, there is often a lack of applications that can successfully integrate and analyze data from IT and OT systems, transforming it into useful information for operation. This often results in manual activities to collect and analyze data, reducing their effectiveness. This article presents an architecture for the integration of IT/OT systems, focusing on the hydroelectric power generation market, and discusses its implementation and results at the Jirau Hydroelectric Plant.