A simple and efficient multi-component algorithm for solving dynamic function optimisation problems

Moser, Irene; Hendtlass, Tim

doi:10.1109/cec.2007.4424479

Cited by 35 publications

(48 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has been used by several researchers [13], [24], [27], [30]. The benchmark contains a moving peaks function and performance measures to evaluate the efficiency of an algorithm.…”

Section: Moving Peaks Benchmarkmentioning

confidence: 99%

Differential evolution for dynamic environments with unknown numbers of optima

Plessis

Engelbrecht

2012

J Glob Optim

View full text Add to dashboard Cite

This paper investigates optimization in dynamic environments where the numbers of optima are unknown or fluctuating. The authors present a novel algorithm, Dynamic Population Differential Evolution (DynPopDE), which is specifically designed for these problems. DynPopDE is a Differential Evolution based multi-population algorithm that dynamically spawns and removes populations as required. The new algorithm is evaluated on an extension of the Moving Peaks Benchmark. Comparisons with other state-of-the-art algorithms indicate that DynPopDE is an effective approach to use when the number of optima in a dynamic problem space is unknown or changing over time.

show abstract

“…This has been used by several researchers [13], [24], [27], [30]. The benchmark contains a moving peaks function and performance measures to evaluate the efficiency of an algorithm.…”

Section: Moving Peaks Benchmarkmentioning

confidence: 99%

Differential evolution for dynamic environments with unknown numbers of optima

Plessis

Engelbrecht

2012

J Glob Optim

View full text Add to dashboard Cite

show abstract

“…However, Moser and Hendtlass point out that MMEO is not expected to be very scalable with regard to increasing the number of dimensions. Through personal communication with Moser (2007), it was established that MMEO yields an offline error of 2.67 ± 0.17 in 10 dimensions and an offline error of 5.09 ± 0.36 was found in 15 dimensions. In the same experiments, RMCCPE resulted in an offline error of 2.70 ± 0.23 and 4.55 ± 0.29, respectively.…”

Section: Comparison With Other Approachesmentioning

confidence: 99%

“…The most successful non-population based algorithm is Moser and Hendtlass's Multi-Phase Multi-Individual Extremal Optimization (MMEO) algorithm (Moser and Hendtlass, 2007). Extremal Optimization (EO) (Boettcher and Percus, 1999) makes use of a single solution which is mutated, and consequently finds the optimum of the search space through hill climbing.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Using Competitive Population Evaluation in a differential evolution algorithm for dynamic environments

Plessis

Engelbrecht

2012

European Journal of Operational Research

View full text Add to dashboard Cite

This paper reports three adaptations to DynDE, an approach to using Differential Evolution to solve dynamic optimization problems. The first approach, Competitive Population Evaluation (CPE), is a multi-population DE strategy aimed at locating optima faster in the dynamic environment. This approach is based on allowing populations to compete for function evaluations based on their performance. The second approach, Reinitialization Midpoint Check (RMC), is aimed at improving the technique used by DynDE to maintain populations on different peaks in the search space. A third approach, consisting of a combination of CPE and RMC is investigated. The new strategies are empirically compared to DynDE using various problem sets. The empirical results show that the new approaches constitute an improvement over DynDE and other approaches in the literature.

show abstract

“…In the literature, there are two other methods that are also better than EA-KDTree, but they do not support complete change detection and are not population-based: one is singlebased [21] and the other is multi-agent 1 . …”

Section: ) Comparing With State-of-the-art Evolutionary Algorithmsmentioning

confidence: 99%

Solving dynamic optimisation problems by combining evolutionary algorithms with KD-tree

Nguyễn

Jenkinson

Yang

2013

2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR)

View full text Add to dashboard Cite

Abstract-In this paper we propose a novel evolutionary algorithm that is able to adaptively separate the explored and unexplored areas to facilitate detecting changes and tracking the moving optima. The algorithm divides the search space into multiple regions, each covers one basin of attraction in the search space and tracks the corresponding moving optimum. A simple mechanism was used to estimate the basin of attraction for each found optimum, and a special data structure named KDTree was used to memorise the searched areas to speed up the search process. Experimental results show that the algorithm is competitive, especially against those that consider change detection an important task in dynamic optimisation. Compared to existing multi-population algorithms, the new algorithm also offers less computational complexity in term of identifying the appropriate sub-population/region for each individual.

show abstract

A simple and efficient multi-component algorithm for solving dynamic function optimisation problems

Cited by 35 publications

References 12 publications

Differential evolution for dynamic environments with unknown numbers of optima

Differential evolution for dynamic environments with unknown numbers of optima

Using Competitive Population Evaluation in a differential evolution algorithm for dynamic environments

Solving dynamic optimisation problems by combining evolutionary algorithms with KD-tree

Contact Info

Product

Resources

About