一种求解服务链映射问题的离散粒子群优化算法
发布时间：2018-09-05 12:53
【摘要】：网络功能虚拟化技术的提出,为减少服务提供商的投资成本与管理开销,实现网络功能的灵活组合、新服务的快速部署提供了解决方案,使多样化、可扩展的服务供应成为可能.网络功能虚拟化中的研究难点是服务链映射问题.现有以最小化端到端时延为目标的映射算法受制于资源瓶颈的限制,导致有效服务路径不能被映射,影响服务链的映射成功率.针对这一问题,提出一种求解服务链映射问题的粒子群优化算法(SIFC-SCMPSO),并以路径跳数为约束设计了初始化可行解与位置更新策略.实验结果表明,该算法有效地减少了资源用量,提高了有效路径被发现的概率,在服务链映射成功率、长期平均收益、平均开销等评价指标上均取得了较好的结果.
[Abstract]:The technology of network function virtualization provides a solution for reducing the investment cost and management cost of service providers, realizing the flexible combination of network functions and the rapid deployment of new services. An extensible service supply is possible. The research difficulty of network function virtualization is the service chain mapping problem. The existing mapping algorithms which aim to minimize end-to-end delay are constrained by resource bottleneck, which results in the effective service path cannot be mapped, which affects the mapping success rate of service chain. In order to solve this problem, a particle swarm optimization algorithm (SIFC-SCMPSO) is proposed to solve the service chain mapping problem, and the initialization feasible solution and position update strategy are designed with path hops as constraints. The experimental results show that the proposed algorithm can effectively reduce the amount of resources and increase the probability of finding effective paths. It has achieved good results in the evaluation indexes such as the success rate of service chain mapping, the long-term average income, the average cost and so on.
【作者单位】： 郑州大学信息工程学院;河南工业大学信息科学与工程学院;国家数字交换系统工程技术研究中心;
【基金】：国家“九七三”重点基础研究发展计划基金项目(2012CB315901)资助 国家自然科学基金项目(61379079)资助 河南省国际合作项目(152102410021)资助
【分类号】：TP393.01
，
本文编号：2224334
[Abstract]:The technology of network function virtualization provides a solution for reducing the investment cost and management cost of service providers, realizing the flexible combination of network functions and the rapid deployment of new services. An extensible service supply is possible. The research difficulty of network function virtualization is the service chain mapping problem. The existing mapping algorithms which aim to minimize end-to-end delay are constrained by resource bottleneck, which results in the effective service path cannot be mapped, which affects the mapping success rate of service chain. In order to solve this problem, a particle swarm optimization algorithm (SIFC-SCMPSO) is proposed to solve the service chain mapping problem, and the initialization feasible solution and position update strategy are designed with path hops as constraints. The experimental results show that the proposed algorithm can effectively reduce the amount of resources and increase the probability of finding effective paths. It has achieved good results in the evaluation indexes such as the success rate of service chain mapping, the long-term average income, the average cost and so on.
【作者单位】： 郑州大学信息工程学院;河南工业大学信息科学与工程学院;国家数字交换系统工程技术研究中心;
【基金】：国家“九七三”重点基础研究发展计划基金项目(2012CB315901)资助 国家自然科学基金项目(61379079)资助 河南省国际合作项目(152102410021)资助
【分类号】：TP393.01
，
本文编号：2224334
本文链接：https://www.wllwen.com/guanlilunwen/ydhl/2224334.html
