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

10.29007/ltkb ◽  
2018 ◽  
Author(s):  
David Walker ◽  
Matthew Johns ◽  
Ed Keedwell ◽  
Dragan Savic
Keyword(s):  
Evolutionary Algorithms ◽  
Network Design ◽  
Decision Maker ◽  
Water Distribution ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Benchmark Problems ◽  
Optimal Solutions ◽  
Human Decision ◽  
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.

scholarly journals A general multi-objective hyper-heuristic for water distribution network design with discolouration risk

2012 ◽  
Vol 15 (3) ◽  
pp. 700-716 ◽  
Author(s):  
Kent McClymont ◽  
Ed Keedwell ◽  
Dragan Savić ◽  
Mark Randall-Smith
Keyword(s):  
Network Design ◽  
Design Problem ◽  
Water Distribution ◽  
Risk Model ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Nsga Ii ◽  
Multi Objective ◽  
Water Companies ◽  
Water Distribution Network Design

The optimisation of water distribution networks (WDNs) by evolutionary algorithms has gained much coverage in the literature since it was first proposed in the early 1990s. Despite being well studied, the problem and objectives continue to evolve as demands on water companies change. Motivated by the increased focus on reducing the risk of discolouration, this study examines a three objective version of the WDN design problem which takes into account cost, head excess and discolouration risk. Using this formulation, this paper presents a method for producing optimised network designs aimed at reducing discolouration risk in the network design phase and thus reducing the associated long-term maintenance and operational burdens of the system. This paper discusses the use of a discolouration risk model and, using this model, the optimisation of network design, specifically pipe diameters, to produce a range of high quality self-cleaning networks. The network designs are optimised using the Markov-chain hyper-heuristic (MCHH), a new multi-objective online selective hyper-heuristic. The MCHH is incorporated in to the known NSGA-II and SPEA2 and supplied with a range of heuristics tailored for use on the WDN design problem. The results demonstrate an improvement in performance obtained over the original algorithms.

scholarly journals Visualising the Operation of Evolutionary Algorithms Optimising Water Distribution Network Design Problems

10.29007/j62b ◽  
2018 ◽  
Author(s):  
David Walker ◽  
Matthew Craven
Keyword(s):  
Evolutionary Algorithms ◽  
Network Design ◽  
Water Distribution ◽  
Distribution Network ◽  
Water Distribution Network ◽  
Network Design Problem ◽  
Complex Nature ◽  
Design Problems ◽  
Distribution Network Design ◽  
Water Distribution Network Design

Multi-objective evolutionary algorithms (MOEAs) are well known for their ability to optimise the water distribution network design problem. However, their complex nature often restricts their use to algorithm experts. A method is proposed for visualising algorithm performance that will enable an engineer to compare different optimisers and select the best optimisation approach. Results show that the convergence and preservation of diversity can be shown in a simple visualisation that does not rely on in-depth MOEA experience.

Sign in / Sign up

Export Citation Format

Share Document