Chaos-Directed Genetic Algorithms for Water Distribution Network Design: An Enhanced Search Method

The design of a water distribution network (WDN) is an ever-challenging problem. Development and application of optimization techniques for WDN design have been an important area of research. Recently, the introduction of chaos theory-based evolutionary algorithms (EAs) in addition to traditional random-based ones has elevated the scope for further improving the performance of EAs. The present study proposes a chaos-directed genetic algorithm (CDGA) by incorporating chaos ergodicity in GA mechanics for WDN optimal design. Two novel frameworks, the non-sequential approach (NSA) and sequential approach (SA) are introduced. The influence of chaotic systems with high dimensionality maps in improving the search efficacy of GA when compared to the low dimensionality maps is explored. Considering four widely studied WDN benchmark problems, the performance of the proposed GA and CDGA models is evaluated. From the results, it is observed that the CDGA models outperform GA with better search efficacy, requiring fewer function evaluations to locate the optimal solution. Also, concerning the different chaotic maps used in the present study to induce chaos ergodicity, the results highlight the usefulness of chaos-directed search in improving the computational efficiency of GA. From the computational results, the study suggests the usage of a chaotic system with other bio-inspired techniques for their improved search and computational efficiency.

Water Distribution Network Design using Hybrid Self-adaptive Multi-population Elitist Pollination Intelligence (HSAMPEPI) Jaya Algorithm

An optimization model to minimize the cost of designing water distribution network is presented in this study. The model was formulated to reduce the cost coefficient in a plumbing system. A new hybrid method of optimization was constructed by combining the search abilities of Jaya-based algorithm and pollination intelligence algorithm, and was used to solve the designed model. The model was implemented by obtaining geometrical information of a water distribution network layout stationed at Gaa Odota, Ilorin, Kwara State, Nigeria. Result obtained from the model showed a significant reduction in the cost coefficient compared to that of the study area.

Methodological approach for the compilation of a water distribution network model using QGIS and EPANET

This paper presents the development of a methodological approach based on the integration of free-of-charge open-source software, e.g. QGIS and EPANET, and engineering practices applicable to water distribution network design. The use of QGIS and EPANET, as well as the integration thereof with sound engineering practices and judgement, proved to be both viable and practical to enable practitioners to create a water distribution network model of an existing network in smaller developments or towns. Typically, in the latter smaller developments or towns, the professional cost associated with the additional time required when commercial licensed software is used, could be lower than the actual cost associated with the procurement of the licensed software itself. Hence, the developed process flow diagrams will not only potentially save time and money in comparison to a traditional, manual approach in EPANET, but will also provide guidance to practitioners and assist smaller municipalities in southern Africa facing challenges in terms of outdated records and budget constraints. It is envisaged that the implementation of the overall methodology will contribute to improved water infrastructure planning, design and management, especially in the southern African context where water resources are scarce and service delivery remains a pressing issue.

Towards Interactive Evolution: A Distributed Optimiser for Multi-Objective Water Distribution Network Design

It is well known that water distribution networks can be optimised by evolutionary algorithms. However, while such optimisation can result in mathematically optimal solutions, the ability of the algorithm to generate novelty can often lead to solutions that are not practical for implementation. This work describes a distributed optimisation platform that will enable the inclusion of a human decision maker in the optimisation process. The architecture of the platform is described, and examples of its execution on benchmark problems is described, using an automated client that interacts with the platform in lieu of a human decision maker.

Interactive Visualisation of Water Distribution Network Optimisation

Evolutionary algorithms have been used to optimize water systems in the literature for over three decades. However, their use for solving real-world water system problems in industry is still very limited. The work presented in this paper details the development of an interactive visualisation client for water distribution network design, which is part of a larger project to bring EAs closer to practicing engineers. The system aims at engaging engineers by actively involving them in the optimization process through the use of advanced visual analytics and novel interactive evolution techniques.