Distributed Evolutionary Computation: A New Technique for Solving Large Number of Equations
This addresses the problem of high computational costs in evolutionary computation for researchers and practitioners dealing with large-scale optimization, though it appears incremental as it builds on existing distributed and hybrid methods.
The paper tackles the computational burden of solving large-parameter problems with evolutionary algorithms by proposing a distributed technique that decomposes decision vectors and uses new selection methods, achieving optimal solutions with considerable speedup.
Evolutionary computation techniques have mostly been used to solve various optimization and learning problems successfully. Evolutionary algorithm is more effective to gain optimal solution(s) to solve complex problems than traditional methods. In case of problems with large set of parameters, evolutionary computation technique incurs a huge computational burden for a single processing unit. Taking this limitation into account, this paper presents a new distributed evolutionary computation technique, which decomposes decision vectors into smaller components and achieves optimal solution in a short time. In this technique, a Jacobi-based Time Variant Adaptive (JBTVA) Hybrid Evolutionary Algorithm is distributed incorporating cluster computation. Moreover, two new selection methods named Best All Selection (BAS) and Twin Selection (TS) are introduced for selecting best fit solution vector. Experimental results show that optimal solution is achieved for different kinds of problems having huge parameters and a considerable speedup is obtained in proposed distributed system.