SSRC:source rate control algorithm for delay-sensitive flow in data center network

Previous work had studied how to ensure the transmission time of delay-sensitive flows,but falled short in its effectiveness for a given period.Motivated by that and based on SDN/OpenFlow framework,a SDN-based source rate control (SSRC) algorithm was proposed.With a global view of network,SSRC can quickly locate the potential congestion node,adjust the transmission rate of source and reduce the response time of SSRC.The experiment results show that compared with DCTCP and other algorithms,SSRC can shorten the completion time of flows by 75% in average,which can ensure the transmission time of delay-sensitive and solve the problem of Incast well.     

Study on distributed and dynamic resource management for delay-sensitive sensor network

The delay-aware dynamic resource management problem was investigated in sensor network,with a focus on resource allocation among the sensors and power control along the time.By taking account of average delay requirements and power constraints,the considered problem was formulated into a stochastic optimization problem.Inspired by Lyapunov optimization theory,the intractable stochastic optimization problem was transformed into a tractable deterministic optimization problem,which was a mixed-integer resource management problem.By exploiting the specific problem structure,the mixed-integer resource management problem was equivalently transformed into a single variable problem,and the cooperative distributed method was present to effectively solve it with guaranteed global optimality.Finally,a dynamic resource management algorithm was proposed to solve the original stochastic optimization problem.Simulation results show the performance of the proposed dynamic algorithm and reveal that there exists a fundamental tradeoff between delay requirements and power consumption.     

延迟敏感的移动多媒体会议端到端服务质量保障

随着异构无线网与智能移动终端的快速发展,移动多媒体会议逐渐成为重要的网络应用.然而,在不可靠、多变的无线网络环境下,因传输单向延迟过长所造成的多媒体视频丢帧、跳帧、断续等现象严重影响会议的服务质量和用户体验.文中提出一种应用层端到端服务质量保障方法.该方法将数据包分段重组与异构无线网路径分集传输相结合,在考虑带宽、延迟、权重以及长度等多种参数情况下对视频数据包分段并发送,各分段经路径分集传输到达客户端、通过有效性检验后进行重组.文中为实现该方法,设计了一种服务器-客户端形式多路径数据包调度算法,构建端到端虚通路保障视频流的快速传输.实验数据表明,此方法能够有效地整合异构无线网带宽,减少传输单向延迟.     

机器类设备基于不同时延需求分组的随机接入方法

针对大规模机器类通信中拥塞导致的时延敏感设备时延高和接入成功率低的问题，提出将小区中设备按时延要求分组，对不同组设备引入不同的退避模型，分析时延敏感设备的时延和吞吐量，按照不同组中设备的时延需求动态分配前导数目，同时通过调整接入类限制因子实现吞吐量的优化。仿真结果表明，在给定时延敏感设备的时延限制条件时，与统一退避的机制对比，所提分组机制的时延敏感设备能够满足时延要求，并且提高了接入效率。     

数据中心负载均衡方法研究综述

随着云计算的发展,数据中心网络成为近年来学术界和工业界关注的研究热点.现代数据中心网络通常采用胖树等多根树拓扑结构,存在多条可用路径以提供高对分带宽.由于等价多路径路由等传统的负载均衡方法无法适应数据中心网络中高动态和强突发的流量特性,多种针对数据中心的负载均衡方法不断涌现.本文围绕数据中心中负载均衡的基本问题,介绍了当前国际国内的研究现状,包括基于中央控制器、基于交换机和基于主机的负载均衡方法,并展望了数据中心网络负载均衡的发展趋势.     

基于优化决策树的时延敏感流智能感知调度

目前流量调度策略无法做到智能按需化,尤其对于网络突发故障造成的拥塞以及高价值业务的护航场景,无法按需保障时延敏感的业务体验。通过分析研究不同网络业务流量时延敏感性属性需求,探索挖掘不同网络业务流量的行为特征与其时延敏感性需求之间的内在关联关系。然后利用AI技术对这种内在的关联关系进行学习,构建其映射关系,实现了时延敏感流智能感知调度。同时,考虑AI模型的可解释性及可部署性实际问题,采用强化学习剪枝优化可解释性决策树模型,提高模型的鲁棒性同时使模型更轻量化,易于设备部署实现。通过真实网络流量实验,强化学习优化后的决策树模型在单次推理情形下感知正确率提高1.75%,推理速度提升约30%;同时,实验也证明了使用局部微观统计特征多次推理有助于提高模型感知正确率。在所有实验中,强化学习优化的决策树模型规模缩小了60.0%～87.2%,并且Saras比Q-learning具有更好的优化表现。     

Resource provisioning in collaborative fog computing for multiple delay-sensitive users

Fog computing is an emerging paradigm that supplies storage, computation, and networking resources between traditional cloud data centers and end devices. This article focuses on the resource provisioning problem in collaborative fog computing for multiple delay-sensitive users. Our goal is to implement a resource provisioning strategy for network operators to minimize the total monetary cost by considering the deadline and capacity constraints. Two scenarios are considered: unlimited-processor fog nodes (UPFN) and limited-processor fog nodes (LPFN). In either scenario, we prove that the resource provisioning problem is NP-hard. First, we consider the UPFN scenario that the processors of fog nodes are unlimited and users' requests can be ideally processed in parallel. Two algorithms are proposed which greedily delete fog nodes based on the local or global collaborative influences until there is no feasible provisioning to guarantee the deadline of users. Then we extend the resource provisioning problem to a more realistic and complicated scenario LPFN in which the scheduling delay cannot be ignored. Two types of tasks are considered. One is the arbitrarily divided tasks, and a near-optimal solution bounded by has been found. m is the number of fog nodes, and is the upper bound on the Lipschitz constant of the delay function. Another one is the application-driven tasks, and we propose a heuristic algorithm. Extensive experiments validate the efficiency of the proposed algorithms.