Hydropower station scheduling with ship arrival prediction and energy storage

• Published in: Scientific reports Vol. 13; no. 1; p. 18969
• Main Authors: Zhou, Enjiang, Liu, Xiao, Meng, Zhihang, Yu, Song, Mei, Jinxiu, Qu, Qiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 03-11-2023; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/4073/4100; 639/705/117; Algorithms; Energy storage; Humanities and Social Sciences; Hydroelectric power; Load distribution; multidisciplinary; Predictions; Scheduling; Science; Science (multidisciplinary); Theoretical analysis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-45995-3

Effectiveness improvement in power generation and navigation for grid-connected hydropower stations have emerged as a significant concern due to the challenges such as discrepancies between declared and actual ship arrival times, as well as unstable power generation. To address these issues, this paper proposes a multi-objective real-time scheduling model. The proposed model incorporates energy storage and ship arrival prediction. An energy storage mechanism is introduced to stabilize power generation by charging the power storage equipment during surplus generation and discharging it during periods of insufficient generation at the hydropower stations. To facilitate the scheduling with the eneragy storage mechanism, the arrival time of ships to the stations are predicted. We use the maximization of generation minus grid load demand and the maximization of navigability assurance rate as two objective functions in the scheduling process. The model uses the Non-Dominated Sorting Beluga Whale Optimization (NSBWO) algorithm to optimize and solve the real-time discharge flow scheduling of the hydropower stations in different time periods. The NSBWO algorithm combines the Elitist Non-Dominated Sorting Genetic Algorithm (NSGA-II) and the Beluga Whale Optimization (BWO). The experimental results show that the proposed method has advantages in predicting the expected arrival time of ships and scheduling the discharge flow. The prediction using XGBoost model reaches accuracy with more than 0.9, and the discharged flow obtained from scheduling meets the demand of hydropower stations grid load while also improves the navigation benefits. This study provides theoretical analysis with its practical applications in a real hyropower station as a case study for solving hydropower scheduling problems.