An Enhanced Horned Lizard Optimization Algorithm for Flood Control Operation of Cascade Reservoirs

The multi-reservoir flood control operation (MRFCO) problem is characterized by high dimensions and multiple constraints. These features pose significant challenges to algorithms aiming to solve the MRFCO problem, requiring them not only to handle high-dimensional variables effectively but also to manage constraints efficiently. The Horned Lizard Optimization Algorithm (HLOA) performs excellently in handling high-dimensional problems and effectively integrates with penalty functions to manage constraints. However, it still exhibits poor convergence when dealing with certain benchmark functions. Therefore, this paper proposes the Enhanced Horned Lizard Optimization Algorithm (EHLOA), which incorporates Circle initialization and two strategies for avoiding local optima, thereby enhancing HLOA's convergence performance. Firstly, EHLOA was tested on benchmark functions, where it demonstrated strong robustness and scalability. Then, EHLOA was applied to the MRFCO problem at the upper section of Lanzhou of the Yellow River in China, showing excellent convergence capabilities and the ability to escape local optima. The reduction rates of flood peaks achieved by EHLOA for the two millennial floods and two decamillennial floods were 55.6%, 52.8%, 58.1%, and 56.4%, respectively. Additionally, the generated operation schemes showed that the reservoir volumes changes were reasonable, and the discharge processes were stable under EHLOA's operation. Overall, EHLOA can be considered a reliable algorithm for addressing the MRFCO problem.