Information sharing impact of stochastic diffusion search on differential evolution algorithm
- PDF / 815,201 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 61 Downloads / 171 Views
REGULAR RESEARCH PAPER
Information sharing impact of stochastic diffusion search on differential evolution algorithm Mohammad Majid al-Rifaie · John Mark Bishop · Tim Blackwell
Received: 27 December 2011 / Accepted: 19 October 2012 / Published online: 9 November 2012 © Springer-Verlag Berlin Heidelberg 2012
Abstract This work details the research aimed at applying the powerful resource allocation mechanism deployed in stochastic diffusion search (SDS) to the differential evolution (DE), effectively merging a nature inspired swarm intelligence algorithm with a biologically inspired evolutionary algorithm. The results reported herein suggest that the hybrid algorithm, exploiting information sharing between the population elements, has the potential to improve the optimisation capability of classical DE algorithms. This claim is verified by running several experiments using state-of-the-art benchmarks. Additionally, the significance of the frequency within which SDS introduces communication and information exchange is also investigated. Keywords Stochastic diffusion search · Differential evolution · Metaheuristic · Global optimisation · Information sharing
1 Introduction Nature inspired swarm intelligence algorithms and biologically inspired evolutionary algorithms in the literature are typically evaluated using benchmarks that are often small in
M. M. al-Rifaie (B) · J. M. Bishop · T. Blackwell Goldsmiths, University of London, New Cross, London SE14 6NW, UK e-mail: [email protected]; [email protected] J. M. Bishop e-mail: [email protected] T. Blackwell e-mail: [email protected]
terms of their objective function computational costs [14,40]; this is often not the case in real-world applications. This paper is an attempt to pave the way for more effectively optimising computationally expensive objective functions by deploying the stochastic diffusion search (SDS) diffusion mechanism to more efficiently allocate differential evolution (DE) resources via information-sharing between the members of the population. The use of SDS as an efficient resource allocation algorithm was first explored in [22,27,30] and these results provided motivation to investigate the application of the information diffusion mechanism originally deployed in SDS1 with DE. Communication—social interaction or information exchange—observed in social insects is important in all swarm intelligence and evolutionary algorithms, including SDS and DE algorithms. This work investigates the communication between the members of the population as the mean to maintain population diversity, which is facilitated by using the resource allocation and resource dispensation of SDS algorithm. In a former work [6], SDS is merged with Particle Swarm Optimisation (PSO) algorithm and the promising results of this hybridisation alongside some statistical analysis of its performance are reported. Although in real social interactions, not just the syntactical information is exchanged between the individuals but also semantic rules and beliefs about how to p
Data Loading...
