The impact of Quality Indicators on the rating of Multi-objective Evolutionary Algorithms

Ravber, Miha; Mernik, Marjan; repinek, Matej

doi:10.1016/j.asoc.2017.01.038

Cited by 40 publications

(24 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The metric ED can only partially reflect convergence [42] and GS only works for bi-objective problems [42]. The metric epsilon-indicator tends to give very similar results to HV, as shown theoretically [10] and experimentally [59].…”

Section: Performance Metricsmentioning

confidence: 98%

Many-Objective Test Suite Generation for Software Product Lines

Hierons

Liu

et al. 2020

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

show abstract

Section: Performance Metricsmentioning

confidence: 98%

Many-Objective Test Suite Generation for Software Product Lines

Hierons

Liu

et al. 2020

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

show abstract

“…The results show that I + , IGD, and HV are consistent with each other on the convex Pareto front, but IGD is inconsistent with HV on the concave Pareto front. Ravber et al [36] investigated 11 quality indicators using a chess rating system. They used objective vector sets found by EMOAs on some test problems.…”

Section: A Ranking Information Based Approachesmentioning

confidence: 99%

An Analysis of Quality Indicators Using Approximated Optimal Distributions in a 3-D Objective Space

Tanabe

Ishibuchi

2020

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Although quality indicators play a crucial role in benchmarking evolutionary multi-objective optimization algorithms, their properties are still unclear. One promising approach for understanding quality indicators is the use of the optimal distribution of objective vectors that optimizes each quality indicator. However, it is difficult to obtain the optimal distribution for each quality indicator, especially when its theoretical property is unknown. Thus, optimal distributions for most quality indicators have not been well investigated. To address these issues, first, we propose a problem formulation of finding the optimal distribution for each quality indicator on an arbitrary Pareto front. Then, we approximate the optimal distributions for nine quality indicators using the proposed problem formulation. We analyze the nine quality indicators using their approximated optimal distributions on eight types of Pareto fronts of three-objective problems. Our analysis demonstrates that uniformly-distributed objective vectors over the entire Pareto front are not optimal in many cases. Each quality indicator has its own optimal distribution for each Pareto front. We also examine the consistency among the nine quality indicators.

show abstract

“…Additionally, jMetal supports computation of eleven quality indicators such as Spread, Epsilon, Hypervolume, and Generational Distance. These quality indicators assess the performance of such methods in terms of distribution and convergence of solutions in the Pareto front [25]. In Section 2.2.1 we expand on quality indicators in the context of multi-objective optimization.…”

Section: Jmetal: Framework For Multi-objective Evolutionary Optimizationmentioning

confidence: 99%

“…Unfortunately none of the available quality indicators can either meet simultaneously the above properties, or simultaneously measure convergence and distribution [29]. Therefore, the performance of a given multi-objective algorithm is often determined by a combination of indicators from different categories [25,28]. Table 1 summarizes the characteristics of the quality indicators considered for this study, namely Epsilon (I + ε ) [32], Spread (I SP ) [33], and Hypervolume (I HV ) [15,34,35].…”

Section: Quality Indicatorsmentioning

confidence: 99%

jHawanet: An Open-Source Project for the Implementation and Assessment of Multi-Objective Evolutionary Algorithms on Water Distribution Networks

Gutiérrez-Bahamondes

Salgueiro

Silva-Rubio

et al. 2019

Water

View full text Add to dashboard Cite

Efficient design and management of water distribution networks is critical for conservation of water resources and minimization of both energy requirements and maintenance costs. Several computational routines have been proposed for the optimization of operational parameters that govern such networks. In particular, multi-objective evolutionary algorithms have proven to be useful both properly describing a network and optimizing its performance. Despite these computational advances, practical implementation of multi-objective optimization algorithms for water networks is an abstruse subject for researchers and engineers, particularly since efficient coupling between multi-objective algorithms and the hydraulic network model is required. Further, even if the coupling is successfully implemented, selecting the proper set of multi-objective algorithms for a given network, and addressing the quality of the obtained results (i.e., the approximate Pareto frontier) introduces additional complexities that further hinder the practical application of these algorithms. Here, we present an open-source project that couples the EPANET hydraulic network model with the jMetal framework for multi-objective optimization, allowing flexible implementation and comparison of different metaheuristic optimization algorithms through statistical quality assessment. Advantages of this project are discussed by comparing the performance of different multi-objective algorithms (i.e., NSGA-II, SPEA2, SMPSO) on case study water pump networks available in the literature.

show abstract

The impact of Quality Indicators on the rating of Multi-objective Evolutionary Algorithms

Cited by 40 publications

References 17 publications

Many-Objective Test Suite Generation for Software Product Lines

Many-Objective Test Suite Generation for Software Product Lines

An Analysis of Quality Indicators Using Approximated Optimal Distributions in a 3-D Objective Space

jHawanet: An Open-Source Project for the Implementation and Assessment of Multi-Objective Evolutionary Algorithms on Water Distribution Networks

Contact Info

Product

Resources

About