检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]西南交通大学信息编码与传输四川省重点实验室,四川成都610031
出 处:《西南交通大学学报》2011年第5期779-786,共8页Journal of Southwest Jiaotong University
基 金:国家自然科学基金资助项目(60772085)
摘 要:为有效缓解拥塞,并在QoS保证与业务公平性之间找到合适的平衡点,基于定价机制提出了一种链路层逐跳拥塞控制算法.该算法考虑了MAC的时间限制和二进制干扰模型限制,将传输失败率作为网络拥塞的控制准则之一引入拥塞价格函数中;流路径上的每个节点根据接收到的拥塞价格动态调整每个流的传输速率;优化目标是系统中总的流效用之和达到权重比例公平.此外,还考虑了节点内部流的调度策略,根据等待时间函数动态调整节点内各个流的优先级,以保证每个流的QoS需求和公平性.仿真结果表明:提出的拥塞控制策略能够有效缓解链路拥塞,系统总吞吐率比未采用拥塞控制机制提高约41%,公平性提高约29%,且极大地改善了平均时延、平均丢包率、平均吞吐率等其他性能指标.In order to alleviate network congestion effectively and find a proper balance point between QoS guarantee and fairness among different types of traffic,a price-based hop-by-hop congestion control scheme was proposed.In this scheme,the constraints in MAC(medium access control) time and binary interference model are considered,and the transmission failure ratio,as one of the criteria of network congestion control,is introduced into a congestion price function.To each node along a flow path,the transmission rate of each flow is adjusted dynamically in light of the received congestion price.The optimization goal is to obtain proportional fairness for the utility sum of each flow.Additionally,in order to guarantee the QoS requirement and fairness of each flow,the intra-node flow scheduling scheme is taken into account,and the priority of each flow within a node is adjusted dynamically based on the waiting time function.The simulation results show that the proposed scheme can alleviate congestion effectively.Compared with the scheme without congestion control,the proposed scheme can increase the system total throughput by 41% and the fairness by 29%.Furthermore,the performances such as average delay,average packet loss ratio and average throughput are improved significantly.
分 类 号:TN929.5[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.3