Adaptive Balance Factor in Particle Swarm Optimization
Particle Swarm Optimization (PSO) is a refined optimization method, that has drawn interest of researchers in different areas because of its simplicity and efficiency. In standard PSO, particles roam over the search area with the help of two accelerating
- PDF / 271,577 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 58 Downloads / 224 Views
Abstract. Particle Swarm Optimization (PSO) is a refined optimization method, that has drawn interest of researchers in different areas because of its simplicity and efficiency. In standard PSO, particles roam over the search area with the help of two accelerating parameters. The proposed algorithm is tested over 12 benchmark test functions and compared with basic PSO and two other algorithms known as Gravitational search algorithm (GSA) and Biogeography based Optimization (BBO). The result reveals that ABF-PSO will be a competitive variant of PSO. Keywords: Meta-heuristic optimization techniques · Particle swarm optimization algorithm · Swarm intelligence · Acceleration coefficients · Nature inspired algorithm
1
Introduction
Generally, real-world optimization problems are very difficult to solve. Optimization tools are used to solve these kind of problems, though there is no surety to get optimal solution always. So, by using different optimization methods several problems are solved by trial and errors [8]. Development of Swarm intelligence and bio-inspired algorithms make a new subject, inspired by nature. Based on the origins of motivation, these kind of meta-heuristic algorithms can be known as swarmintelligence-based, bio-inspired-based algorithm [6]. Particle Swarm Optimization (PSO) is a refined optimization method, that has drawn interest of researchers in different areas because of its simplicity and efficiency. Different versions of PSO have been suggested already. PSO is a swarm - based, modifying search development facility firstly suggested by James Kennedy and Russell Eberhart (1995). This algorithm is inspired by mimicking the collective behavior of natural swarm’s like fishes and birds and even human common routine etc. [9]. In standard PSO (SPSO), particles roam over the search area with the help of two accelerating parameters. One parameter, known as the cognitive parameter, controls the local exploration of the particles, while the second parameter, known as the social parameter, guides the global search capability of the particles. Generally, diversification and intensification properties are managed by these two parameter. Various researchers have c Springer Nature Singapore Pte Ltd. 2017 K. Deep et al. (eds.), Proceedings of Sixth International Conference on Soft Computing for Problem Solving, Advances in Intelligent Systems and Computing 546, DOI 10.1007/978-981-10-3322-3 2
Adaptive Balance Factor in Particle Swarm Optimization
13
found that, in the SPSO, particles immediately get a fine local solution, though get stuck to that solution for rest of the iterations without a further improvement [7,12,13]. In order to increase the convergence speed as well as the exploration capabilities of PSO algorithms, an acceleration parameter PSO strategy has been presented in this paper. In this paper a time differing acceleration parameter scheme is introduced to efficiently manage the universal search and convergence to the universal best solution. The primary attention of this modification is to neglect overearly c
Data Loading...
