A Novel Group Search Optimizer Inspired by Animal Behavioural Ecology

In this paper, we propose a novel optimization algorithm, group search optimizer (GSO), which is inspired by animal searching behaviour and group living theory. The algorithm is based on the Producer-Scrounger model, which assumes group members search either for 'finding' (producer) or for 'joining' (scrounger) opportunities. Animal scanning mechanisms (e.g., vision) are incorporated to develop the algorithm. We also employ 'rangers' which perform random walks to avoid entrapment in local minima. When tested against benchmark functions, GSO outperformed competitively with other evolutionary algorithms in terms of accuracy and convergence speed on most of the benchmark functions.

I. Introduction

Nature-inspired optimization algorithms [2], notably Evolutionary Algorithms (EAs), have been widely used to solve various scientific and engineering problems. Currently, there are three well-known EAs, namely, Genetic Algorithms (GAs), Evolutionary Programming (EP) and Evolution Strategies (ES). The inspiration of all the EAs is Darwin's evolution theory: survival of the fitness. Recently, a new global optimization algorithm paradigm, Swarm Intelligence (SI), has been proposed. There are two different SI algorithms: Ant Colony Optimizer (ACO) and Particle Swarm Optimizer (PSO). They are inspired by real ant foraging behaviour and Artificial Life, respectively.