scholarly journals Offline Learning with a Selection Hyper-Heuristic: An Application to Water Distribution Network Optimisation

2020 ◽  
pp. 1-24
Author(s):  
William B. Yates ◽  
Edward C. Keedwell
Keyword(s):  
Water Distribution ◽  
Learning Algorithm ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Multiobjective Evolutionary Algorithms ◽  
Computationally Efficient ◽  
Offline Learning ◽  
Efficient Alternative ◽  
Computationally Expensive ◽  
Network Optimisation

A sequence-based selection hyper-heuristic with online learning is used to optimise 12 water distribution networks of varying sizes. The hyper-heuristic results are compared with those produced by five multiobjective evolutionary algorithms. The comparison demonstrates that the hyper-heuristic is a computationally efficient alternative to a multiobjective evolutionary algorithm. An offline learning algorithm is used to enhance the optimisation performance of the hyper-heuristic. The optimisation results of the offline trained hyper-heuristic are analysed statistically, and a new offline learning methodology is proposed. The new methodology is evaluated, and shown to produce an improvement in performance on each of the 12 networks. Finally, it is demonstrated that offline learning can be usefully transferred from small, computationally inexpensive problems, to larger computationally expensive ones, and that the improvement in optimisation performance is statistically significant, with 99% confidence.

scholarly journals Water distribution network optimization using maximum entropy under multiple loading patterns

2013 ◽  
Vol 13 (5) ◽  
pp. 1265-1271 ◽  
Author(s):  
Anna M. Czajkowska ◽  
Tiku T. Tanyimboh
Keyword(s):  
Design Optimization ◽  
Maximum Entropy ◽  
Water Distribution ◽  
Optimization Procedure ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Operating Conditions ◽  
Statistical Entropy ◽  
Computationally Efficient ◽  
Nsga Ii

This paper proposes a maximum entropy-based multi-objective genetic algorithm approach for the design optimization of water distribution networks (WDNs). The novelty is that in contrast to previous research involving statistical entropy the algorithm can handle multiple operating conditions. We used NSGA II and EPANET 2 and wrote a subroutine that calculates the entropy value for any given WDN configuration. The proposed algorithm is demonstrated by designing a six-loop network that is well known from previous entropy studies. We used statistical entropy to include reliability in the design optimization procedure in a computationally efficient way.

scholarly journals Prelocalization and leak detection in drinking water distribution networks using modeling-based algorithms: a case study for the city of Casablanca (Morocco)

2020 ◽  
Vol 13 (2) ◽  
pp. 29-41
Author(s):  
Faycal Taghlabi ◽  
Laila Sour ◽  
Ali Agoumi
Keyword(s):  
Drinking Water ◽  
Water Distribution ◽  
Learning Algorithm ◽  
Field Research ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Hydraulic Modeling ◽  
Geographical Information ◽  
First Episode ◽  
Drinking Water Distribution

Abstract. The role of a drinking water distribution network (DWDN) is to supply high-quality water at the necessary pressure at various times of the day for several consumption scenarios. Locating and identifying water leakage areas has become a major concern for managers of the water supply, to optimize and improve constancy of supply. In this paper, we present the results of field research conducted to detect and to locate leaks in the DWDN focusing on the resolution of the Fixed And Variable Area Discharge (FAVAD) equation by use of the prediction algorithms in conjunction with hydraulic modeling and the Geographical Information System (GIS). The leak localization method is applied in the oldest part of Casablanca. We have used, in this research, two methodologies in different leak episodes: (i) the first episode is based on a simulation of artificial leaks on the MATLAB platform using the EPANET code to establish a database of pressures that describes the network's behavior in the presence of leaks. The data thus established have been fed into a machine learning algorithm called random forest, which will forecast the leakage rate and its location in the network; (ii) the second was field-testing a real simulation of artificial leaks by opening and closing of hydrants, on different locations with a leak size of 6 and 17 L s−1. The two methods converged to comparable results. The leak position is spotted within a 100 m radius of the actual leaks.

A study on appropriate investment of pipeline rehabilitation for water distribution network

2005 ◽  
Vol 5 (2) ◽  
pp. 31-38
Author(s):  
A. Asakura ◽  
A. Koizumi ◽  
O. Odanagi ◽  
H. Watanabe ◽  
T. Inakazu
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Water Supply ◽  
Water Distribution ◽  
Ad Hoc ◽  
Distribution Network ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Optimal Basis ◽  
Model Case

In Japan most of the water distribution networks were constructed during the 1960s to 1970s. Since these pipelines were used for a long period, pipeline rehabilitation is necessary to maintain water supply. Although investment for pipeline rehabilitation has to be planned in terms of cost-effectiveness, no standard method has been established because pipelines were replaced on emergency and ad hoc basis in the past. In this paper, a method to determine the maintenance of the water supply on an optimal basis with a fixed budget for a water distribution network is proposed. Firstly, a method to quantify the benefits of pipeline rehabilitation is examined. Secondly, two models using Integer Programming and Monte Carlo simulation to maximize the benefits of pipeline rehabilitation with limited budget were considered, and they are applied to a model case and a case study. Based on these studies, it is concluded that the Monte Carlo simulation model to calculate the appropriate investment for the pipeline rehabilitation planning is both convenient and practical.

scholarly journals Optimal placement of valves in a water distribution network with CLP(FD)

2011 ◽  
Vol 11 (4-5) ◽  
pp. 731-747 ◽  
Author(s):  
MASSIMILIANO CATTAFI ◽  
MARCO GAVANELLI ◽  
MADDALENA NONATO ◽  
STEFANO ALVISI ◽  
MARCO FRANCHINI
Keyword(s):  
Logic Programming ◽  
Distribution Systems ◽  
Water Distribution ◽  
Distribution Network ◽  
Real Life ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Constraint Logic Programming ◽  
Optimal Placement ◽  
Isolation System

AbstractThis paper presents a new application of logic programming to a real-life problem in hydraulic engineering. The work is developed as a collaboration of computer scientists and hydraulic engineers, and applies Constraint Logic Programming to solve a hard combinatorial problem. This application deals with one aspect of the design of a water distribution network, i.e., the valve isolation system design. We take the formulation of the problem by Giustolisi and Savić (2008 Optimal design of isolation valve system for water distribution networks. InProceedings of the 10th Annual Water Distribution Systems Analysis Conference WDSA2008, J. Van Zyl, A. Ilemobade, and H. Jacobs, Eds.) and show how, thanks to constraint propagation, we can get better solutions than the best solution known in the literature for the Apulian distribution network. We believe that the area of the so-calledhydroinformaticscan benefit from the techniques developed in Constraint Logic Programming and possibly from other areas of logic programming, such as Answer Set Programming.

scholarly journals A computationally efficient estimator for mutual information

2008 ◽  
Vol 464 (2093) ◽  
pp. 1203-1215 ◽  
Author(s):  
Dafydd Evans
Keyword(s):  
Data Analysis ◽  
Mutual Information ◽  
Time Complexity ◽  
Exploratory Data Analysis ◽  
Nearest Neighbour ◽  
Computationally Efficient ◽  
One Dimensional ◽  
Exploratory Data ◽  
Efficient Alternative ◽  
Computationally Expensive

Mutual information quantifies the determinism that exists in a relationship between random variables, and thus plays an important role in exploratory data analysis. We investigate a class of non-parametric estimators for mutual information, based on the nearest neighbour structure of observations in both the joint and marginal spaces. Unless both marginal spaces are one-dimensional, we demonstrate that a well-known estimator of this type can be computationally expensive under certain conditions, and propose a computationally efficient alternative that has a time complexity of order ( N  log  N ) as the number of observations N →∞.

scholarly journals Technical note: Problem specific variators in a genetic algorithm for the optimization of drinking water networks

2018 ◽  
Author(s):  
Karel van Laarhoven ◽  
Ina Vertommen ◽  
Peter van Thienen
Keyword(s):  
Drinking Water ◽  
Real World ◽  
Water Distribution ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Technical Note ◽  
Practical Implementation ◽  
Utility Level ◽  
Water Utility ◽  
Drinking Water Distribution

Abstract. Genetic algorithms can be a powerful tool for the automated design of optimal drinking water distribution networks. Fast convergence of such algorithms is a crucial factor for successful practical implementation at the drinking water utility level. In this technical note, we therefore investigate the performance of a suite of genetic variators that was tailored to the optimisation of a least-cost network design. Different combinations of the variators are tested in terms of convergence rate and the robustness of the results during optimisation of the real world drinking water distribution network of Sittard, the Netherlands. The variator configurations that reproducibly reach the furthest convergence after 105 function evaluations are reported. In the future these may aid in dealing with the computational challenges of optimizing real world networks.

scholarly journals Proposal of optimal operation strategy applied to water distribution network with statistical approach

2020 ◽  
Vol 15 (2) ◽  
pp. 1
Author(s):  
Alex Takeo Yasumura Lima Silva ◽  
Fernando Das Graças Braga da Silva ◽  
André Carlos da Silva ◽  
José Antonio Tosta dos Reis ◽  
Claudio Lindemberg de Freitas ◽  
...  
Keyword(s):  
Genetic Algorithms ◽  
Water Distribution ◽  
Distribution Network ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Optimal Operation ◽  
Optimization Techniques ◽  
Experimental Techniques ◽  
Computational Optimization ◽  
Depth Analysis

 Inefficiency of sanitation companies’ operation procedures threatens the population’s future supplies. Thus, it is essential to increase water and energy efficiency in order to meet future demand. Optimization techniques are important tools for the analysis of complex problems, as in distribution networks for supply. Currently, genetic algorithms are recognized by their application in literature. In this regard, an optimization model of water distribution network is proposed, using genetic algorithms. The difference in this research is a methodology based on in-depth analysis of results, using statistics and the design of experimental tools and software. The proposed technique was applied to a theoretical network developed for the study. Preliminary simulations were accomplished using EPANET, representing the main causes of water and energy inefficiency in Brazilian sanitation companies. Some parameters were changed in applying this model, such as reservoir level, pipe diameter, pumping pressures, and valve-closing percentage. These values were established by the design of experimental techniques. As output, we obtained the equation of response surface, optimized, which resulted in values of established hydraulic parameters. From these data, the obtained parameters in computational optimization algorithms were applied, resulting in losses of 26.61%, improvement of 16.19 p.p. with regard to the network without optimization, establishing an operational strategy involving three pumps and a pressure-reducing valve.  We conclude that the association of optimization and the planning of experimental techniques constitutes an encouraging method to deal with the complexity of water-distribution network optimization.

scholarly journals Appraisal of water quality indices for service reservoirs in water distribution networks

2020 ◽  
Vol 81 (8) ◽  
pp. 1606-1614 ◽  
Author(s):  
M. S. Nyirenda ◽  
T. T. Tanyimboh
Keyword(s):  
Water Quality ◽  
Water Distribution ◽  
Distribution Network ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Sampling Point ◽  
Quality Indices ◽  
Water Quality Indices ◽  
State Of Water ◽  
Pollution Loads

Abstract The use of water quality indices to aggregate pollution loads in rivers has been widely studied, with researchers using various sub-indices and aggregation methods. These have been used to combine various quality variables at a sampling point in a river into an overall water quality index to compare the state of water quality in different river reaches. Service reservoirs in a water distribution network, like rivers, have complex mixing mechanisms, are subjected to various water quality variables and are variably sized and sited. Water quality indices and the relevant sub-indices are formulated here and applied to service reservoirs within a water distribution network. This is in an attempt to compare holistically the performance of service reservoirs in solutions of optimisation algorithms with regards to water quality.

scholarly journals Prediction of pipe failure rate in Tehran water distribution networks by applying regression models

2018 ◽  
Vol 19 (3) ◽  
pp. 695-702 ◽  
Author(s):  
Homayoun Motiee ◽  
Sonya Ghasemnejad
Keyword(s):  
Logistic Regression ◽  
Statistical Models ◽  
Poisson Regression ◽  
Regression Models ◽  
Water Distribution ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Hydraulic Pressure ◽  
Pipe Failure ◽  
Exponential Regression

Abstract Four statistical models (linear regression, exponential regression, Poisson regression and logistic regression) applied to analyze the variables in pipe vulnerabilities with the objective of finding equations to predict probable future pipe accidents. The most effective variables in pipe failures are material, age, length, diameter and hydraulic pressure. To evaluate these models, the data collected in recent years in the water distribution network of district 1 in Tehran were used, with a total length of 582,702 m of pipes, and 48,500 consumers. The results demonstrate that among the four studied models, the logistic regression model is best able to give a good performance and is capable of predicting future accidents with a higher probability.

scholarly journals An Inverse Transient-Based Optimization Approach to Fault Examination in Water Distribution Networks

Water ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 1154
Author(s):  
Chao-Chih Lin ◽  
Hund-Der Yeh
Keyword(s):  
Water Distribution ◽  
Large Scale ◽  
Water Distribution Network ◽  
Distribution Networks ◽  
Small Scale ◽  
Optimization Approach ◽  
Promising Technique ◽  
Preliminary Screening ◽  
Detection Approach ◽  
Symbiotic Organism Search

This research introduces an inverse transient-based optimization approach to automatically detect potential faults, such as leaks, partial blockages, and distributed deteriorations, within pipelines or a water distribution network (WDN). The optimization approach is named the Pipeline Examination Ordinal Symbiotic Organism Search (PEOS). A modified steady hydraulic model considering the effects of pipe aging within a system is used to determine the steady nodal heads and piping flow rates. After applying a transient excitation, the transient behaviors in the system are analyzed using the method of characteristics (MOC). A preliminary screening mechanism is adopted to sift the initial organisms (solutions) to perform better to reduce most of the unnecessary calculations caused by incorrect solutions within the PEOS framework. Further, a symbiotic organism search (SOS) imitates symbiotic relationship strategies to move organisms toward the current optimal organism and eliminate the worst ones. Two experiments on leak and blockage detection in a single pipeline that have been presented in the literature were used to verify the applicability of the proposed approach. Two hypothetical WDNs, including a small-scale and large-scale system, were considered to validate the efficiency, accuracy, and robustness of the proposed approach. The simulation results indicated that the proposed approach obtained more reliable and efficient optimal results than other algorithms did. We believe the proposed fault detection approach is a promising technique in detecting faults in field applications.

Sign in / Sign up

Export Citation Format

Share Document