A novel ACO algorithm with adaptive parameter

  • Authors:

  • Han Huang;Xiaowei Yang;Zhifeng Hao;Ruichu Cai

  • Affiliations:

  • College of Computer Science and Engineering, South China University of Technology, Guangzhou, P.R. China;College of Mathematical Science, South China University of Technology, Guangzhou, P.R. China;,College of Computer Science and Engineering, South China University of Technology, Guangzhou, P.R. China;College of Mathematical Science, South China University of Technology, Guangzhou, P.R. China

  • Venue:
  • ICIC'06 Proceedings of the 2006 international conference on Computational Intelligence and Bioinformatics - Volume Part III
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

ACO has been proved to be one of the best performing algorithms for NP-hard problems as TSP. Many strategies for ACO have been studied, but little theoretical work has been done on ACO's parameters α and β, which control the relative weight of pheromone trail and heuristic value. This paper describes the importance and functioning of α and β, and draws a conclusion that a fixed β may not enable ACO to use both heuristic and pheromone information for solution when α=1. Later, following the analysis, an adaptive β strategy is designed for improvement. Finally, a new ACO called adaptive weight ant colony system (AWACS) with the adaptive β and α=1 is introduced, and proved to be more effective and steady than traditional ACS through the experiment based on TSPLIB test.