Hydraulic Behavior in Sanitary Sewer Networks Using Optimization Algorithms in the High-Altitude Andean Regions of Peru

Abstract

This study evaluates the hydraulic behavior of sanitary sewer networks in high-altitude Andean regions (Peru) using advanced optimization algorithms. A quantitative, explanatory experimental approach was employed, analyzing 51 inspection chambers through in-situ measurements of velocity, hydraulic depth, and flow rate. Data were systematically recorded on structured observation sheets for statistical analysis. To assess hydraulic performance, Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) techniques were applied. Key hydraulic parameters, including flow velocity, flow rate, flow type, and pipe diameter, were collected to calculate the Manning coefficient. This data was processed in a Python environment, where both algorithms simulated network behavior under varying conditions. Performance metrics such as flow stability, drainage efficiency, and solution convergence were analyzed. Results indicate that PSO outperforms GA in accuracy and stability, offering superior estimations of flow parameters such as velocity, hydraulic depth, and Reynolds number. PSO demonstrated lower deviation from real-world measurements, making it a more reliable tool for hydraulic modeling and sewer network optimization. While GA exhibited moderate variability, it still contributed to enhancing system performance. Despite these advancements, challenges remain, including limited access to high-quality hydraulic data and the need for real-time sensor integration. This study underscores the importance of investing in smart sanitation technologies and hybrid optimization approaches that integrate machine learning with hydraulic simulations. Such methodologies can enhance sustainability, mitigate overflow risks, and optimize wastewater management in vulnerable regions. Future research should explore scalable applications of PSO and GA across diverse hydraulic environments, ensuring broader applicability in global sanitation infrastructure projects.