基于软件定义网络的数据中心自适应多路径负载均衡算法

针对传统多路径负载均衡算法无法有效地感知网络的运行状态、不能综合考虑链路的实时传输状态以及大多数算法缺少自适应性的问题,基于软件定义网络(SDN)的集中控制和全网管控思想,提出一种基于蜘蛛猴优化的SDN自适应多路径负载均衡算法(SMO-LBA)。首先,利用数据中心网络的感知能力来获取多路径的实时链路状态信息;然后,利用蜘蛛猴算法的全局探索和局部开采能力将链路空闲率作为每条路径的适应度值,并引入自适应权重对路径进行动态评估及更新;最后,寻找数据中心网络中链路占用率最小的路径,确定其为最优转发路径。选用胖树拓扑在Mininet平台上进行仿真实验,实验结果表明SMO-LBA可提高数据中心网络的吞吐量和平均链路利用率,实现网络自适应负载均衡。

Enhanced Metaheuristics-Based Clustering Scheme for Wireless Multimedia Sensor Networks

Traditional Wireless Sensor Networks(WSNs)comprise of costeffective sensors that can send physical parameters of the target environment to an intended user.With the evolution of technology,multimedia sensor nodes have become the hot research topic since it can continue gathering multimedia content and scalar from the target domain.The existence of multimedia sensors,integrated with effective signal processing and multimedia source coding approaches,has led to the increased application of Wireless Multimedia Sensor Network(WMSN).This sort of network has the potential to capture,transmit,and receive multimedia content.Since energy is a major source in WMSN,novel clustering approaches are essential to deal with adaptive topologies of WMSN and prolonged network lifetime.With this motivation,the current study develops an Enhanced Spider Monkey Optimization-based Energy-Aware Clustering Scheme(ESMO-EACS)for WMSN.The proposed ESMO-EACS model derives ESMO algorithm by incorporating the concepts of SMO algorithm and quantum computing.The proposed ESMO-EACS model involves the design of fitness functions using distinct input parameters for effective construction of clusters.A comprehensive experimental analysis was conducted to validate the effectiveness of the proposed ESMO-EACS technique in terms of different performance measures.The simulation outcome established the superiority of the proposed ESMO-EACS technique to other methods under various measures.

混合蛛猴算法及其在乙炔加氢参数优化中的应用

蛛猴算法(SMO)是模拟蛛猴觅食行为的群智能优化算法,因其具有其良好的自组织能力而被广泛应用于数值优化领域。本文提出了一种混合蛛猴算法(QSMO)。该算法在SMO的基础上引入Metropolis准则、二次逼近法、局部随机搜索策略,并结合人工蜂群算法提高种群多样性,有效地提升了算法性能。选取了多个标准测试函数进行仿真对比,结果表明SMO的搜索精度与搜索速度均得到了显著提升。基于混合优化算法进行工业乙炔加氢反应器模型参数优化,结果表明该算法能够更好地求解工程优化问题。