G. Jeyakumar

A comparative performance analysis of Differential Evolution and Dynamic Differential Evolution variants

In this paper we present an empirical, comparative performance, analysis of fourteen variants of Differential Evolution (DE) and Dynamic Differential Evolution (DDE) algorithms to solve unconstrained global optimization problems. The aim is to compare DDE, which employs a dynamic evolution mechanism, against DE and to identify the competitive variants which perform reasonably well on problems with different features. The fourteen variants of DE and DDE are benchmarked on 6 test functions grouped by features - unimodal separable, unimodal nonseparable, multimodal separable and multimodal non-separable. The analysis identifies the competitive variants and shows that DDE variants consistently outperform their classical counter parts.

Empirical study on migration topologies and migration policies for island based distributed differential evolution variants

In this paper we present an empirical performance analysis of fourteen variants of Differential Evolution (DE) on a set of unconstrained global optimization problems. The island based distributed differential evolution counterparts of the above said 14 variants have been implemented with mesh and ring migration topologies and their superior performance over the serial implementation has been demonstrated. The competitive performance of ring topology based distributed differential evolution variants on the chosen problem has also been demonstrated. Six different migration policies are experimented for ring topology, and their performances are reported.

An empirical comparison of Differential Evolution variants on different classes of unconstrained global optimization problems

This paper presents an empirical analysis of the performance of Differential Evolution (DE) variants on different classes of unconstrained global optimization benchmark problems. This analysis has been undertaken to identify competitive DE variants which perform reasonably well on a range of problems with different features. Towards this, fourteen DE variants were implemented and tested on 14 high dimensional benchmark functions grouped by their modality and decomposability viz., unimodal separable, unimodal nonseparable, multimodal separable and multimodal nonseparable. This extensive performance analysis provides some insight about the competitiveness of DE variants in solving test problems with representative landscape features such as modality and decomposability.

Distributed mixed variant differential evolution algorithms for unconstrained global optimization

This paper proposes a novel distributed differential evolution algorithm called Distributed Mixed Variant Differential Evolution (dmvDE). To alleviate the time consuming trial-and-error selection of appropriate Differential Evolution (DE) variant to solve a given optimization problem, dmvDE proposes to mix effective DE variants with diverse characteristics in a distributed framework. The novelty of dmvDEs lies in mixing different DE variants in an island based distributed framework. The 19 dmvDE algorithms, discussed in this paper, constitute various proportions and combinations of four DE variants (DE/rand/1/bin, DE/rand/2/bin, DE/best/2/bin and DE/rand-to-best/1/bin) as subpopulations with each variant evolving independently but also exchanging information amongst others to co-operatively enhance the efficacy of the distributed DE as a whole. The dmvDE algorithms have been run on a set of test problems and compared to the distributed versions of the constituent DE variants. Simulation results show that dmvDEs display a consistent overall improvement in performance than that of distributed DEs. The best of dmvDE algorithms has also been benchmarked against five distributed differential evolution algorithms. Simulation results reiterate the superior performance of the mixing of the DE variants in a distributed frame work. The best of dmvDE algorithms outperforms, on average, all five algorithms considered.

Theoretical Analysis of Expected Population Variance Evolution for a Differential Evolution Variant

In this paper we derive an analytical expression to describe the evolution of expected population variance for Differential Evolution (DE) variant—DE/current-to-best/1/bin (as a measure of its explorative power). The derived theoretical evolution of population variance has been validated by comparing it against the empirical evolution of population variance by DE/current-to-best/1/bin on four benchmark functions.

Distributed heterogeneous mixing of differential and dynamic differential evolution variants for unconstrained global optimization

This paper proposes a novel distributed differential evolution framework called distributed mixed variants (dynamic) differential evolution (

Empirical Measurements on the Convergence Nature of Differential Evolution Variants

dmvD^{2}E)

A comparative study on theoretical and empirical evolution of population variance of differential evolution variants

dmvD2E). This novel framework is a heterogeneous mix of effective differential evolution (DE) and dynamic differential evolution (DDE) variants with diverse characteristics in a distributed framework to result in