A Steady-State and Generational Evolutionary Algorithm for Dynamic Multiobjective Optimization

Jiang, Shouyong; Yang, Shengxiang

doi:10.1109/tevc.2016.2574621

Cited by 268 publications

(178 citation statements)

References 55 publications

(98 reference statements)

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…Different from F1 to F4, F5 and F6 not only consider a changing number of objectives, but also have a time varying PS. Here we use equation (12) to define the time varying number of objectives; as for the parameters related to the time varying PS, we set its change frequency as τt = 5 and change severity as nt = 10 (these settings are widely used in the literature, e.g., [10,68] and [69]). From the experimental results shown in Table 3 and Table 4, we find that DTAEA has shown the best performance on almost all comparisons (30 out of 32 for MIGD and 28 out of 32 for MHV).…”

Section: Results On F5 and F6mentioning

confidence: 99%

Dynamic Multiobjectives Optimization With a Changing Number of Objectives

Chen

Yao

2018

IEEE Trans. Evol. Computat.

148

104

View full text Add to dashboard Cite

Existing studies on dynamic multi-objective optimization focus on problems with time-dependent objective functions, while the ones with a changing number of objectives have rarely been considered in the literature. Instead of changing the shape or position of the Paretooptimal front/set when having time-dependent objective functions, increasing or decreasing the number of objectives usually leads to the expansion or contraction of the dimension of the Paretooptimal front/set manifold. Unfortunately, most existing dynamic handling techniques can hardly be adapted to this type of dynamics. In this paper, we report our attempt toward tackling the dynamic multi-objective optimization problems with a changing number of objectives. We implement a dynamic two-archive evolutionary algorithm which maintains two co-evolving populations simultaneously. In particular, these two populations are complementary to each other: one concerns more about the convergence while the other concerns more about the diversity. The compositions of these two populations are adaptively reconstructed once the environment changes. In addition, these two populations interact with each other via a mating selection mechanism. Comprehensive experiments are conducted on various benchmark problems with a time-dependent number of objectives. Empirical results fully demonstrate the effectiveness of our proposed algorithm.

show abstract

Section: Results On F5 and F6mentioning

confidence: 99%

Dynamic Multiobjectives Optimization With a Changing Number of Objectives

Chen

Yao

2018

IEEE Trans. Evol. Computat.

148

104

View full text Add to dashboard Cite

show abstract

“…EAs. They are 1) the Pareto dominace based DNSGA-II [7]; the decomposition-based MOEA/D [49]; the multipopulation based dCOEA [14]; the population prediction based PPS [52]; (5) and the steady-generational SGEA [22]. In this paper, PPS with regularity model [50] (PPS+RM2) and nondominated sorting (PPS+NS) are both analysed.…”

Section: A Dmo Algorithmsmentioning

confidence: 99%

“…2) Mean Hypervolume Difference (MHVD): The MHVD [22] is a modification of the static measure HVD [53] that computes the gap between the hypervolume of the obtained PF and that of the true PF. The reference point for the computation of M -dimensional hypervolume is (z 1 +0.5, z 2 + 0.5, · · · , z M +0.5), where z j is the maximum value of the j-th objective of the true PF.…”

Section: B Dmo Performance Measuresmentioning

confidence: 99%

“…Significant contributions have been made mainly toward benchmarking [10], SJ, MK, and NK acknowledge the EPSRC for funding project "Synthetic Portabolomics: Leading the way at the crossroads of the Digital and the Bio Economies (EP/N031962/1)". Shouyong [20], algorithm design [5], [22], [34], [52], and real-life application [17], [48]. Despite these, there are still a number of open topics that need to be addressed in order to further advance the development of the DMO research.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Scalable Test Suite for Continuous Dynamic Multiobjective Optimization

Jiang

Kaiser

Yang

et al. 2020

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

Dynamic multiobjective optimisation has gained increasing attention in recent years. Test problems are of great importance in order to facilitate the development of advanced algorithms that can handle dynamic environments well. However, many of existing dynamic multiobjective test problems have not been rigorously constructed and analysed, which may induce some unexpected bias when they are used for algorithmic analysis. In this paper, some of these biases are identified after a review of widely used test problems. These include poor scalability of objectives and, more importantly, problematic overemphasis of static properties rather than dynamics making it difficult to draw accurate conclusion about the strengths and weaknesses of the algorithms studied. A diverse set of dynamics and features is then highlighted that a good test suite should have. We further develop a scalable continuous test suite, which includes a number of dynamics or features that have been rarely considered in literature but frequently occur in real life. It is demonstrated with empirical studies that the proposed test suite is more challenging to the dynamic multiobjective optimisation algorithms found in the literature. The test suite can also test algorithms in ways that existing test suites can not.

show abstract

“…It has been applied on majority of problems such as engineering, medicine, finance, etc. GA provides two kinds of approaches towards solving problems [33]. One steady state genetic algorithm (SSGA) and one generational genetic algorithm (GGA).…”

Section: Genetic Algorithmmentioning

confidence: 99%

Evolutionary Computation, Optimization, and Learning Algorithms for Data Science

Mohammadi

Amini

Arabnia

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

purpose. This motivates researchers to think about optimization and apply nature inspired algorithms, such as meta-heuristic and evolutionary algorithms (EAs) to solve large-scale optimization problems. Building on the strategies of these algorithms, researchers solve large-scale engineering and computational problems with innovative solutions. Although these algorithms look un-deterministic, they are robust enough to reach an optimal solution. To that end, researchers try to run their algorithms more than usually suggested, around 20 or 30 times, then they compute the mean of result and report only the average of 20 / 30 runs' result. This high number of runs becomes necessary because EAs, based on their randomness initialization, converge the best result, which would not be correct if only relying on one specific run. Certainly, researchers do not adopt evolutionary algorithms unless they face a problem which is suffering from placement in local optimal solution, rather than global optimal solution. In this chapter, we first develop a clear and formal definition of the CoD problem, next we focus on feature extraction techniques and categories, then we provide a general overview of meta-heuristic algorithms, its terminology, and desirable properties of evolutionary algorithms.A large number of engineering, science and computational problems have yet to be solved in a more computationally efficient way. One of the emerging challenges is the evolving technologies and how they enhance towards autonomy. This leads to collection of large amount of data from various sensing and measurement technologies, such as cameras, smart phones, health sensors, and environment sensors. Hence, generation, manipulation and illustration of data grow significantly. Meanwhile, data is structured purposefully through different representations, such as large-scale networks and graphs. Therefore, data plays a pivotal role in technologies by introducing several challenges: how to present, what to present, why to present. Researchers explored various approaches to implement a comprehensive solution to express their results in every particular domain, such that the solution enhances the performance and

show abstract

A Steady-State and Generational Evolutionary Algorithm for Dynamic Multiobjective Optimization

Cited by 268 publications

References 55 publications

Dynamic Multiobjectives Optimization With a Changing Number of Objectives

Dynamic Multiobjectives Optimization With a Changing Number of Objectives

A Scalable Test Suite for Continuous Dynamic Multiobjective Optimization

Evolutionary Computation, Optimization, and Learning Algorithms for Data Science

Contact Info

Product

Resources

About