基于自适应遗传蚁群算法的SDN路由规划研究

Research on SDN routing planning based on adaptive genetic ant colony algorithm

技术的快速发展使网络规模不断扩大,结构日益复杂,传统路由算法已无法满足不同业务服务质量(quality of service,QoS)需求的数据传输。设计了基于软件定义网络(software defined network,SDN)的实时路由规划框架,以有效地管理网络资源。结合遗传算法和蚁群算法的优点,提出基于自适应遗传蚁群(adaptive genetic ant colony,AGAC)的QoS路由算法,通过仿真试验将该算法与遗传算法、蚁群算法在不同网络规模中进行对比,并进行了路由仿真。结果表明:该算法能在大规模网络中通过快速搜索得到多个优选路径,可充分利用正反馈来缩小最大搜索时间,快速找到满足不同业务的最优路径,且面对大规模网络时,效率和稳定性更高。基于自适应遗传蚁群的QoS路由算法在不同业务需求下的寻优能力均得到保障,对比其他两种传统算法寻优效率得到明显提升。

With the rapid development of the network scale expanding and structure increasingly complex,the traditional routing algorithms can no longer meet the data transmission of different service QoS requirements.To address this problem,a real-time routing planning framework based on SDN is designed to effectively manage network resources;A QoS routing algorithm based on adaptive genetic ant colony is proposed,which combines the advantages of the genetic algorithm and the ant colony algorithm to obtain multiple preferred paths by fast search in large-scale networks and full use of positive feedback to reduce the maximum search time,and then quickly find the optimal path to satisfy different reguirements.In the simulation experiments,the proposed algorithm is first compared with the genetic algorithm and the ant colony algorithm in different network sizes,and the algorithm is more efficient and stable in the face of large-scale networks.The simulation results show that the QoS routing algorithm based on an adaptive genetic ant colony is guaranteed to be able to find the optimal path for different service requirements,and the efficiency of finding the optimal path is significantly improved compared to the other two traditional algorithms.