Application of Strength Pareto Evolutionary Algorithm II in Multi-Objective Water Supply Optimization Model Design for Mountainous Complex Terrain

Yihong Guan, Yangyang Chu, Mou Lv, Shuyan Li, Hang Li, Shen Dong, Yanbo SuSustainability 2023 · DOI

TL;DR

This paper tackles the complex challenge of designing water distribution networks (WDNs) in mountainous terrain, where traditional optimization methods fall short. By developing a multi-objective model incorporating cost, reliability, and water quality, and applying the Strength Pareto Evolutionary Algorithm II (SPEA-II), the researchers demonstrate a superior approach for achieving safer and more efficient WDN designs in challenging environments.

What Problem Does This Paper Address?

Designing efficient and reliable water distribution networks (WDNs) is crucial for urban infrastructure, but it's particularly challenging in mountainous regions. Unlike flat terrain, these areas present significant elevation differences, leading to issues like unbalanced pressure, increased energy consumption, and a higher risk of water hammer. Existing WDN optimization studies often focus on benchmark networks and overlook the unique complexities of mountainous terrain, such as the impact of terrain on pipe pressure and the potential for catastrophic failures if pumping stations stop. This paper aims to bridge this gap by developing and evaluating a multi-objective optimization model specifically for mountainous WDNs, considering cost, reliability, and water quality.

Methods

The core of this research lies in developing a multi-objective optimization model for WDNs and evaluating two prominent multi-objective evolutionary algorithms (MOEAs): Strength Pareto Evolutionary Algorithm II (SPEA-II) and Non-dominated Sorting Genetic Algorithm II (NSGA-II).

The optimization model incorporates three key objectives:

  • Minimizing construction cost: This involves selecting optimal pipe diameters.
  • Maximizing reliability: Measured by the variance of nodal surplus head, aiming to reduce water wastage and prevent network breakdown.
  • Optimizing water quality: Assessed through water age, which indicates how long water has been in the system, impacting its quality. A novel approach for calculating water age in complex networks is introduced.

The study utilizes EPANET 2.0, a standard hydraulic simulation software, to analyze WDN performance. The decision variables are primarily pipe diameters, chosen from a discrete set of commercially available sizes. The paper also details the specific crossover and variation strategies employed within the MOEAs.

Datasets

The study uses a real-world case study of a WDN in a mountainous area, referred to as "Q city, China." This case study includes detailed information on node elevations, base demands, minimum free head, pipe lengths, and available commercial pipe diameters. The paper does not introduce a new benchmark dataset but rather applies the proposed methodology to an existing, complex real-world scenario.

Key Insights and Ideas

  • Mountainous terrain demands specialized WDN design: The paper strongly emphasizes that the unique topographical challenges of mountainous regions necessitate tailored optimization approaches, as standard methods are insufficient.
  • SPEA-II outperforms NSGA-II in this context: The study's primary finding is that SPEA-II demonstrates superior performance over NSGA-II for mountainous WDN optimization, particularly in terms of convergence speed, solution quality, and efficiency.
  • Water hammer risk is a critical concern: The research highlights how variations in pipe section flow velocity, especially drastic changes, significantly increase the probability of water hammer, a critical safety concern in WDNs. SPEA-II's solutions appear to mitigate this risk more effectively.
  • Balancing multiple objectives is key: The paper underscores the importance of considering cost, reliability, and water quality simultaneously, as optimizing one objective can negatively impact others. SPEA-II shows a better ability to find a favorable trade-off among these objectives.

Key Results

  • SPEA-II generates significantly more Pareto solutions: In the case study, SPEA-II produced 534 non-dominated solutions, while NSGA-II generated only 94. This indicates a broader exploration of the solution space.
  • SPEA-II offers better cost and water age optimization: The median cost achieved by SPEA-II was significantly lower than NSGA-II, and its water age optimization was also superior.
  • SPEA-II demonstrates faster convergence: The running time for SPEA-II was considerably less than NSGA-II, suggesting a more efficient search for optimal solutions.
  • Statistical significance: Hypothesis testing confirmed significant differences between the algorithms for the number of Pareto solutions (NOPS) and running time, with SPEA-II excelling in both. While differences in distance index (SM) and diversity metric (DM) were not statistically significant, SPEA-II's overall performance was deemed better.
  • Improved safety and efficiency: SPEA-II's optimized designs resulted in slower changes in pipe section flow velocity, reducing the risk of water hammer and enhancing overall WDN safety.

Limitations and Future Work

  • Focus on a single case study: While the paper uses a real-world case, the findings are based on this specific mountainous WDN. Further validation on a wider range of mountainous terrains would strengthen the conclusions.
  • Simplified cost model: The pumping station construction price and overhaul costs were not included in the cost function for this specific case. Future work could incorporate these elements for a more comprehensive cost analysis.
  • Further exploration of water quality metrics: While water age is a key indicator, incorporating other water quality parameters could provide a more holistic assessment.

The authors suggest that SPEA-II's effectiveness in optimizing mountainous WDNs makes it a valuable tool for decision-makers. Future research could explore hybrid approaches or further refine the SPEA-II algorithm for even greater efficiency and robustness in complex WDN design scenarios.

Summary updated

Abstract

Water distribution networks (WDN) model optimization is an important part of smart water systems to achieve optimal strategies. WDN optimization focuses on the nonlinearity of the discharge head loss equation, the availability of discrete properties of pipe sizes, and the conservation of constraints. Multi-objective evolutionary algorithms (MOEAs) have been proposed and successfully applied in the field of WDN design optimization. Previous studies have focused on comparing the optimization effects of algorithms in water distribution networks, ignoring the problems of unbalanced pressure distribution and water hammer at the nodes of the pipe network caused by the complex terrain in mountainous areas. In this paper, a multi-objective water supply optimization model that integrated cost, reliability, and water quality was established for a mountainous WDN in real engineering. The method of traversing the nodes to solve the water age was introduced to find a more scientific and practical water age solution model, with setting the weight function to evaluate the water age of the water supply model comprehensively. Strength Pareto Evolutionary Algorithm II (SPEA-II) and Non-dominated Sorting Genetic Algorithm II (NSGA-II) were adopted to optimize the WDN design model in the mountainous complex terrain. The significance levels of the number of Pareto solutions (NOPS) and running time are 0.029 and 0.001, respectively, indicating that the two algorithms have significant differences. Compared to NSGA-II, SPEA-II has a better convergence rate and running time in multi-objective water supply optimization design. The solution set distribution of SPEA-II is more concentrated than that of NSGA-II, also the numerical value is better. The number of SPEA-II optimization schemes is larger and the scheme is more effective. Among them, the Pareto solution set of SPEA-II can obtain more desirable optimization results on cost, reliability index (RI) and water age. In summary, the study provides valuable information for decision makers in WDN with complex terrain.
BibTeX
@inproceedings{guan2023application,
  author = {Yihong Guan and Yangyang Chu and Mou Lv and Shuyan Li and Hang Li and Shen Dong and Yanbo Su},
  title = {{Application of Strength Pareto Evolutionary Algorithm II in Multi-Objective Water Supply Optimization Model Design for Mountainous Complex Terrain}},
  booktitle = {Sustainability},
  year = {2023},
  doi = {10.3390/su151512091},
}
Figure