遗传模拟退火算法在组播路由选择中的应用

Application of the Genetic Simulated Annealing Algorithm in Multicast Routing Optimization

本文研究基于带宽、时延及时延抖动约束最小代价的QoS组播路由优化算法。针对遗传算法在求解多目标优化问题时局部搜索能力弱、易早熟的缺陷,提出了一种基于遗传算法和模拟退火算法混合策略的多目标优化方法。该算法采用树结构编码机制和改进的交叉和变异算子,利用模拟退火算法在可行解范围内构造邻域解集,采用种群早熟评价函数进行局部细化寻优。仿真结果表明,改进的遗传模拟退火算法在解决组播路由多目标优化问题时能够较快地收敛于全局最优解。

This paper studies bandwidth delay and the delay variation constrained leastcost QoS multicast routing problem and proposes a genetic simulated annealing algorithm which can speed up the evolutionary rate and avoid antiprecocity. The algorithm adopts tree structure coding and improved cross and variation operations, and combines the merits in the partial search ability of the simulation annealing algorithm. It constructes a neighbor set in the range of feasible solutions and gives a new criterion for judging the premature convergence.The simulation results show that the revised algorithm has a more rapid convergence rate in the global optimal solution than the only genetic algorithm and the simulated annealing algorithm.