Idel Montalvo

Particle Swarm Optimization applied to the design of water supply systems

In the past decade, evolutionary methods have been used by various researchers to tackle optimal design problems for water supply systems (WSS). Particle Swarm Optimization (PSO) is one of these evolutionary algorithms which, in spite of the fact that it has primarily been developed for the solution of optimization problems with continuous variables, has been successfully adapted in other contexts to problems with discrete variables. In this work we have applied one of the variants of this algorithm to two case studies: the Hanoi water distribution network and the New York City water supply tunnel system. Both cases occur frequently in the related literature and provide two standard networks for benchmarking studies. This allows us to present a detailed comparison of our new results with those previously obtained by other authors.

Design optimization of wastewater collection networks by PSO

Optimal design of wastewater collection networks is addressed in this paper by making use of the so-called PSO (Particle Swarm Optimization) technique. This already popular evolutionary technique is adapted for dealing both with continuous and discrete variables as required by this problem. An example of a wastewater collection network is used to show the algorithm performance and the obtained results are compared with those given by using dynamic programming to solve the same problem under the same conditions. PSO is shown to be a promising method to solve optimal design problems regarding, in particular, wastewater collection networks, according to the results herein obtained.

Improved performance of PSO with self-adaptive parameters for computing the optimal design of Water Supply Systems

This paper deals with a new variant of Particle Swarm Optimization (PSO) in which no a priori parameter tuning is necessary. PSO, as an efficient and powerful problem-solving technique, has been widely used, but, as in other Evolutionary Algorithms (EA), appropriate adjustment of its parameters is cumbersome and usually requires a lot of time, effort and luck. Thus, a self-adaptive framework is proposed to improve the robustness of the PSO. In this paper, within a framework that also includes other variants previously introduced by the authors, the algorithms parameters are co-evolved with the particles. Its performance results show that the use of this self-adaptive feature averages out the performance of standard PSO and other EA applied to the same problems, namely the design of Water Supply Systems (WSS), while avoiding the process of localizing and fine-tuning suitable parameters values, when using two benchmarking problems presented in the literature, namely the Hanoi Water Supply System and the New York Tunnel Water Supply System. The results provided in the case of a real-world problem demonstrate the scalability of the proposed variant to the realistic water distribution design problems, which are much larger.

A diversity-enriched variant of discrete PSO applied to the design of water distribution networks

The design of water distribution networks (WDNs) is addressed by using a variant of the particle swarm optimization (PSO) algorithm. This variant, which makes use of a discrete version of PSO already considered by the authors, overcomes one of the PSOs main drawbacks, namely its difficulty in maintaining acceptable levels of population diversity and in balancing local and global searches. The performance of the variant proposed here is investigated by applying the model to solve two standard benchmark problems: the Hanoi new water distribution network and the New York Tunnel water supply system. The results obtained show considerable improvements in both convergence characteristics and the quality of the final solutions, and near-optimal results are consistently achieved at reduced computational cost.

Water distribution system computer-aided design by agent swarm optimization

Optimal design of water distribution systems (WDSs), including the sizing of components, quality control, reliability, renewal, and rehabilitation strategies, etc., is a complex problem in water engineering that requires robust methods of optimization. Classical methods of optimization are not well suited for analyzing highly dimensional, multimodal, nonlinear problems, especially given inaccurate, noisy, discrete, and complex data. Agent Swarm Optimization (ASO) is a novel paradigm that exploits swarm intelligence and borrows some ideas from multiagent-based systems. It is aimed at supporting decision-making processes by solving multiobjective optimization problems. ASO offers robustness through a framework where various population-based algorithms coexist. The ASO framework is described and used to solve the optimal design of WDS. The approach allows engineers to work in parallel with the computational algorithms to force the recruitment of new searching elements, thus contributing to the solution process with expert-based proposals.

Multi-agent adaptive boosting on semi-supervised water supply clusters

The division of a water supply network (WSN) into isolated supply clusters aims at improving the management of the whole system. This paper deals with the application of spectral clustering to achieve this aim. A semi-supervised approach can take into account the graph structure of a network and incorporate the corresponding hydraulic constraints and the other available vector information from the WSN. Several of the disadvantages of these methodologies stem from the largeness of the most WSN and the associated computational complexity. To solve these problems, we propose subsampling graph data to run successive weak clusters and build a single robust cluster configuration. The resulting methodology has been tested in a real network and can be used to successfully partition large WSNs.

Division of Water Supply Systems into District Metered Areas Using a Multi-agent Based Approach

Technical management of large water supply systems (WSS) is an increasingly complex problem. Water companies managing these systems have witnessed how the mathematical models of their networks lose accuracy and their engineering tools become obsolete. Consequently, they have no clear vision of the balance between production and distribution, that is to say, between supply and demand. As a result, water companies are interested in improving the control and management of their networks. One of the methods attracting great interest is that of division into DMAs (district metered areas). Division into DMAs splits an interconnected and intricate network into smaller, virtually independent sub-networks that can be better managed. However, the complexity of the problem of creating DMAs demands efficient techniques. In this contribution we use a multi-agent based approach that takes advantage of the distributed nature of WSS.

Identification of surgical practice patterns using evolutionary cluster analysis

Modern data analysis and machine learning are strongly dependent on efficient search techniques. However, in general, further exploration into high-dimensional and multi-modal spaces is needed, and moreover, many real-world problems exhibit inaccurate, noisy, discrete and complex data. Thus, robust methods of optimization are often required to generate results suitable for these data. Some algorithms that imitate certain natural principles, namely the so-called evolutionary algorithms, have been used in different fields with great success. In this paper, we apply a variant of Particle Swarm Optimization (PSO), recently introduced by the authors, to partitional clustering of a real-world data set to distinguish between perioperative practices and associate them with some unknown relevant facts. Our data were obtained from a survey conducted in Spain based on a pool of colorectal surgeons. The PSO derivative we consider here: (i) is adapted to consider mixed discrete-continuous optimization, with statistical clustering criteria arranged to take these types of mixed measures; (ii) is able to find optimum or near-optimum solutions much more efficiently and with considerably less computational effort because of the richer population diversity it introduces; and (iii) is able to select the right parameter values through self-adaptive dynamic parameter control, thus overcoming the cumbersome aspect common to all metaheuristics.

Water supply system component evaluation from GPR radargrams using a multi-agent approach ☆

Abstract This paper uses a multi-agent approach as a quick and easy tool for the interpretation and analysis of the characteristics of Water Supply System (WSS) components when working on a collection of Ground Penetrating Radar (GPR) survey files. The multi-agent algorithm proposed in this paper has been developed in Matlab and is based on Game Theory. The input is the result of the GPR radargram survey and the output consists of the agent scores in the game proposed in this paper. Useful information can be gained by interpreting the columns of the output matrix that describe the agents’ movements, together with the associated racing times. In effect, this analysis enables a simple determination of the electromagnetic properties of the underground system and provides an accurate classification of these properties. The results of this agent racing algorithm are promising, since it groups, and consequently, decreases the number of points that make up the initial radargrams; while at the same time preserving its main properties, and enabling clearer views of pipes and a better identification of the components in WSS.

On the Complexities of the Design of Water Distribution Networks

Water supply is one of the most recognizable and important public services contributing to quality of life. Water distribution networks (WDNs) are extremely complex assets. A number of complex tasks, such as design, planning, operation, maintenance, and management, are inherently associated with such networks. In this paper, we focus on the design of a WDN, which is a wide and open problem in hydraulic engineering. This problem is a large-scale combinatorial, nonlinear, nonconvex, multiobjective optimization problem, involving various types of decision variables and many complex implicit constraints. To handle this problem, we provide a synergetic association between swarm intelligence and multiagent systems where human interaction is also enabled. This results in a powerful collaborative system for finding solutions to such a complex hydraulic engineering problem. All the ingredients have been integrated into a software tool that has also been shown to efficiently solve problems from other engineering fields.