A simulated annealing based genetic local search algorithm for multi-objective multicast routing problems

Xu, Ying and Qu, Rong and Li, Renfa (2013) A simulated annealing based genetic local search algorithm for multi-objective multicast routing problems. Annals of Operations Research, 260 (1). pp. 527-555. ISSN 1572-9338

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (638kB) | Preview

Abstract

This paper presents a new hybrid evolutionary algorithm to solve multi-objective multicast routing problems in telecommunication networks. The algorithm combines simulated annealing based strategies and a genetic local search, aiming at a more flexible and effective exploration and exploitation in the search space of the complex problem to find more non-dominated solutions in the Pareto Front. Due to the complex structure of the multicast tree, crossover and mutation operators have been specifically devised concerning the features and constraints in the problem. A new adaptive mutation probability based on simulated annealing is proposed in the hybrid algorithm to adaptively adjust the mutation rate according to the fitness of the new solution against the average quality of the current population during the evolution procedure. Two simulated annealing based search direction tuning strategies are applied to improve the efficiency and effectiveness of the hybrid evolutionary algorithm. Simulations have been carried out on some benchmark multi-objective multicast routing instances and a large amount of random networks with five real world objectives including cost, delay, link utilisations, average delay and delay variation in telecommunication networks. Experimental results demonstrate that both the simulated annealing based strategies and the genetic local search within the proposed multi-objective algorithm, compared with other multi-objective evolutionary algorithms, can efficiently identify high quality non-dominated solution set for multi-objective multicast routing problems and outperform other conventional multi-objective evolutionary algorithms in the literature.

Item Type: Article
Additional Information: The final publication is available at Springer via http://dx.doi.org/10.1007/s10479-013-1322-7
Keywords: Multi-objective Genetic Local Search, Simulated Annealing, Multicast Routing
Schools/Departments: University of Nottingham UK Campus > Faculty of Science > School of Computer Science
Identification Number: https://doi.org/10.1007/s10479-013-1322-7
Depositing User: Qu, Rong
Date Deposited: 26 Feb 2015 15:09
Last Modified: 14 Sep 2016 19:55
URI: http://eprints.nottingham.ac.uk/id/eprint/28284

Actions (Archive Staff Only)

Edit View Edit View