Effect of parameters variation on the performance of particle swarm optimization algorithm for tag coverage problem of radio frequency identification network

Optimal tag coverage is the most crucial aspect for deploying RFID (Radio Frequency Identification) system in a large scale. From the literature, optimal tag coverage can be considered as a high dimensional optimization problem and often solved using nature-inspired algorithms. In this paper, PSO (P...

Full description

Bibliographic Details
Main Authors: Nawawi, Azli, Hasnan, Khalid, Ngali, Mohd Zamani, Sidek, Noor Azizah
Format: Conference or Workshop Item
Published: 2015
Subjects:
Online Access:http://eprints.uthm.edu.my/7344/
Description
Summary:Optimal tag coverage is the most crucial aspect for deploying RFID (Radio Frequency Identification) system in a large scale. From the literature, optimal tag coverage can be considered as a high dimensional optimization problem and often solved using nature-inspired algorithms. In this paper, PSO (Particle Swarm Optimization) algorithm is used to optimize the tag coverage problem. This paper also investigates the effect of varying two parameters of PSO (swarm size and iteration number) to the performance of the algorithm. Both parameters are set at 50, 100, 150 and 200. From the experiment, the best set of results is generated when the swarm size is set at 200 and the iteration number is at 50. This is a good sign because for the iteration number at 50, the runtime is much less (4.9s) compared to the higher iteration numbers (100, 150 and 200). The percentages for additional runtimes for iteration number set at 100, 150 and 200 are 103%, 204% and 341% respectively