Cross-layer packet scheduling for downlink multiuser OFDM systems

This paper proposes a channel and queue aware fair (CQAF) packet scheduling scheme for the downlink packet transmission in multiuser orthogonal frequency division multiplexing (OFDM) systems. By making use of the information on the channel conditions and the queue lengths, the proposed CQAF packet scheduling scheme efficiently allocates the subcarriers, transmission power and modulation level to users under the constraints of total transmission power, the number of subcarriers, bit-error-rate (BER) requirement and generalized processor sharing (GPS)-based fairness requirement. The numerical results show that the proposed CQAF packet scheduling scheme can reduce the transmission delay and queue length significantly while maximizing system throughput and maintaining fairness among users.     

基于效用公平的多用户下行OFDM系统机会调度

基于对单信道系统中效用公平机会调度的研究,提出了一种多用户下行OFDM多载波系统中的调度方案.该方案充分利用信道的时变和频率选择特性,由参数更新和调度决策两个模块组成:参数更新模块根据调度结果更新控制参数;调度决策模块根据所有用户的信道信息和参数更新模块输出的公平性控制参数决定该时隙每个用户使用哪些子载波.仿真结果表明,参数选取合适时,所提的简单调度方案能够在保证效用公平性的前提下,达到比复杂的Max-Min子裁波分配算法更好的系统性能.     

一种基于效用最优的计算网格资源调度算法

针对具有时间和费用约束的网格资源调度问题，通过分析任务的执行时间和执行费用与用户效用函数的关系，建立了效用函数模型，在此基础上提出了一种针对task farming应用程序模式的基于效用函数最优的启发式调度算法——效用最优调度算法。实验表明，与费用 时间均衡调度算法相比，本算法能给用户带来更高的效用。     

一种多用户正交频分复用系统的PHY-DLL层间联合自适应算法

层间自适应设计已经逐渐成为了当前计算机通信领域研究中的热门问题。文中提出了一种适用于正交频分复用无线通信系统的层间联合自适应传输算法。利用物理层的信道状态信息,该算法将物理层（PHY）的子载波分配同数据链路层（DLL）的数据包业务调度结合起来。仿真结果表明,该方案的性能优于单纯在物理层采用子载波和功率分配自适应算法的方案,能够能支持更多的用户,提高用户数据包传输成功率和降低比特误码率。     

一种基于混沌粒子群优化的OFDM系统资源分配算法

针对无线多用户正交频分复用（OFDM）系统中功率分配问题,提出一种基于效用函数最大化框架的资源分配算法.在实际网络环境中,此类最优化算法为非凸的,利用经典最优化方法很难解决.为此,将智能优化中的粒子群方法应用到非凸优化算法设计中,并针对粒子群优化容易陷入局部极值点的问题,将Logistic混沌搜索嵌入PSO算法中,提出混沌粒子群算法.与同类算法相比,所提出算法不仅有效解决了非凸性问题,而且可以使系统具有更好的性能.     

Novel scheduling strategy for downlink multiuser MIMO system: Particle swarm optimization

In this paper the scheduling problem in downlink multiuser MIMO system is described as an optimization problem and particle swarm optimization (PSO) algorithm is introduced to address such problem. Two PSO scheduling methods with different objective functions applicable to different requirements on capacity and complexity are investigated. One is the capacity based PSO(C-PSO) scheduling method aiming at achieving the near optimal capacity; and the other is the lower bound of eigenvalue based PSO (LBE-PSO) scheduling method with the purpose of reducing computational complexity and at the same time achieving as large as possible capacity gain. Furthermore, convergence analysis of PSO from both the particle and the velocity aspects is also presented to derive the convergent condition, which is validated by several examples of different parameter values. Simulation results reveal that the C-PSO can obtain nearly the same capacity as the exhaustive search method with lower complexity, while the LBE-PSO provides a viable approach by striking a better tradeoff between capacity and computational complexity.     

基于粒子群优化的多用户MIMO下行链路调度算法

将多用户MIMO下行链路调度问题描述为一优化问题,并引入粒子群优化(particle swarm optimization,PSO)算法进行求解.针对容量和复杂度有不同要求的应用场合,给出了两类采用不同目标函数PSO调度算法:基于容量PSO(C-PSO)调度算法和基于特征值下界PSO(LBE-PSO)调度算法.C-PSO算法目标是获得接近最优容量的性能;而LBE-PSO算法旨在有效降低算法复杂度的同时尽可能获得高的容量增益.进一步,从粒子和速度两方面对PSO算法的收敛性进行分析并得出收敛条件,然后通过不同参数值的实例对其进行验证.仿真结果表明,C-PSO算法能够以较低的复杂度获得接近穷搜索算法的容量,而LBE-PSO调度算法则提供了一种能够在容量和复杂度之间很好折中的调度方案.     

两跳中继系统中调度算法的改进及性能比较*

提出了一种改进的最大载干比和比例公平（Emax C/I & EPF）调度算法。首先根据到基站的距离,划分BS和RS域,然后分别在BS和RS域内采用改进的最大载干比（Emax C/I）算法和改进的比例公平（EPF）算法。将提出的改进算法（Emax C/I & EPF）分别与部分比例公平（PPF）算法、两跳比例公平（THPF）算法以及改进前的算法进行了比较。仿真结果证明,该改进算法（Emax C/I & EPF）在系统频谱效率性能与公平性能之间达到了较好的权衡。     

基于频谱优化和交织的OFDM-PAPR降低算法

为了降低OFDM系统的PAPR,针对传统算法有损系统性能的缺点,提出了一种优化的算法。该算法基于频谱优化和交织思想,通过确定有效子载波个数来提高OFDM符号的平均功率和系统的频谱效率,并通过预判断,选择性地对OFDM符号进行交织处理。仿真结果表明,该算法在降低OFDM的PAPR的同时,也优化了系统的性能。     

MIMO下行链路中的多用户调度与功率分配

分析了MIMO下行链路中的多用户调度和功率分配方法,讨论了各种功率分配方法的多用户调度性能,并通过仿真实验对性能进行了比较。实验结果表明,在低信噪比条件下,二维注水功率分配的性能最佳,而在高信噪比条件下,各种功率分配方法的性能差别很小。     

一种基于QoE效用函数的OFDM系统子载波和功率分配算法

以系统平均用户感受质量QoE(Quality of Experience)为优化目标,提出一种基于QoE效用函数的子载波和功率分配算法.该算法先根据用户需求与实际信道状态对子载波进行分配,将QoE引入效用函数构建中,并以系统平均QoE最大化为目标对子载波进行功率分配,在功率分配过程中使用导数迭代的方法逼近最优的功率分配...     

An optimization approach for decentralized QoS‐based scheduling based on utility and pricing in Grid computing

This paper presents an optimization approach for decentralized Quality of Service (QoS)‐based scheduling based on utility and pricing in Grid computing. The paper assumes that the quality dimensions can be easily formulated as utility functions to express quality preferences for each task agent. The utility values are calculated by the user‐supplied utility function that can be formulated with the task parameters. The QoS constraint Grid resource scheduling problem is formulated into a utility optimization problem. The QoS‐based Grid resource scheduling optimization is decomposed into two subproblems by applying the Lagrangian method. In the Grid, a Grid task agent acts as a consumer paying for the Grid resource and the resource providers receive profits from task agents. A pricing‐based QoS scheduling algorithm is used to perform optimally decentralized QoS‐based resource scheduling. The experiments investigate the effect of the QoS metrics on the global utility and compare the performance of the proposed algorithm with other economical Grid resource scheduling algorithms. Copyright © 2006 John Wiley & Sons, Ltd.     

混合蚁群优化算法求解卫星数传调度问题

为了求解卫星数传调度问题,提出了混合蚁群优化算法。算法设计了基于任务数传操作的解构造图,提出了基于解构造图的任务调度序列和资源分配序列概率决策模型,采用基于随机加权的混合策略综合利用问题的启发式信息。算法通过基于混沌变异的列信息素向量更新策略增强解构造的多样性,通过具有补偿机制的全局信息素更新策略来保证算法的收敛性。利用STK工具设计了五个调度场景,并利用计算机生成各场景的数传任务。仿真实验结果表明,该算法是可行、有效的,收敛性和解多样性较好。     

数据流程序动态调度与优化

为了解决数据流编程模型的可用性问题,使其能在兼顾程序并行性的前提下适用于动态数据交互速率的流应用,设计了一种动态调度与静态优化相结合的数据流编译系统。编译器以COStream语言编写的源程序为输入,通过对源程序进行分析,以动态速率的数据通信边作为边界划分程序到粗粒度的子图,在子图内部应用静态优化。根据子图的每个计算单元的工作量估计计算资源的使用状况,实现子图内计算单元到处理器核的映射,经过阶段划分分配子图内计算单元到相应流水阶段。在运行时,每个子图在各个处理器核上均启动一个线程,通过对线程间通信的优化,避免了运行时多个线程对同一段内存同时读写产生的同步开销,减少了线程的上下文切换次数。使用信号量控制子图内线程间的同步,基于各子图计算单元运行时数据交互速率并结合当前线程的状态,动态调度各个子图的执行,构建动态的软件流水线,生成相应多线程目标代码。实验以通用X86-64多核处理器作为实验平台,测试和分析数据流编译的性能。实验结果表明,编译系统可以实现动态数据交互速率的数据流应用,扩大了编译系统可用性并且具有一定加速效果。     

Power-aware opportunistic downlink scheduling in IEEE 802.16 wireless networks

The IEEE 802.16 is a standard for fixed and mobile Broadband Wireless Access (BWA). In this paper, we deal with two key challenges of 802.16-based networks. First, terminals close to cell edge experience poor channel quality, due to severe path-loss and high interference from concurrent transmissions in nearby cells. To address this issue, we propose a framework based on a static partitioning of bandwidth into chunks with different transmission power levels. Terminals with impaired channel conditions can then benefit from being allocated a higher amount of transmission power than the others. Secondly, transmissions should be scheduled according to Quality of Service (QoS) requirements to keep users with real-time video or voice calls satisfied, while best-effort connections should fairly share the remaining capacity. To this aim, we propose a scheduling algorithm, called Power-aware Opportunistic Downlink Scheduling (PODS), that aims at meeting both the QoS and fairness requirements, while taking into account the different power levels of the bandwidth chunks. The performance of the proposed scheduler is assessed through detailed packet-level simulation in realistic scenarios and compared with well-known scheduling algorithms. Results confirm that PODS is able to exploit power boosting to provide real-time connections with the desired level of QoS, irrespectively of their MSs’ channel quality.     

多用户正交频分复用加权比例公平调度

传统的正交频分复用(OFDM)调度进行资源分配时没有考虑用户间速率比例公平性。针对这一问题,提出了一种新的适合于混合业务的多用户OFDM系统比例公平调度方案,其用户队列承载混合类型业务。该方案在用户间速率成比例约束条件下最大化系统权重容量和;授予用户队列中不同类型的分组不同的权重因子,并通过权重因子计算用户的权重;在子载波分配时不仅定义了信道优先级因子,而且在用户间速率成比例公平约束条件下通过该因子为用户分配子载波;最后推导出一种线性的功率分配方式。仿真结果与分析显示,该方案可以较好地满足用户速率和业务时延的需求,且可以在有效提高系统容量的基础上,严格地保证用户容量公平性。     

LTE系统下行基于调度度量值的资源分配方案

在多业务的正交频分多址(OFDMA)蜂窝系统中,为改善小区整体的吞吐量并提高多用户之间传输数据的公平性,提出一种基于最优调度优先级进行资源块分配的长期演进项目(LTE)下行分配方案。打破传统资源分配过程中顺序分配资源的束缚,将用户与资源块(RB)配对,优先把服务质量最好的RB资源分配给相应的用户,尽量保证用户在各自有利的信道上传输数据。仿真结果表明,该方案在不增大丢包率的前提下,有效提高了系统的吞吐量和公平性指数,对LTE下行链路是一个很好的选择。     

卫星数传调度的蚁群优化模型及算法

针对卫星数传调度问题,提出了基于任务－资源关联结点的新型解构造图模型,人工蚁群通过任务边和资源弧分阶段进行任务调度序列和资源分配序列构造,设计了任务调度和资源分配启发式信息,以增强蚁群在伪随机状态转移过程中的搜索能力。通过局部信息素更新防止算法陷入局部最优,利用全局信息素更新的信息素正反馈机制使算法逐渐收敛到全局最优。仿真结果表明,新型解构造图反映了任务与资源之间的密切联系,分阶段状态转移策略和启发式信息的利用有助于增强算法的寻优能力,算法正确可行,并具有良好的收敛性、鲁棒性。     

Multi-level scheduling for global optimization in grid computing

The paper presents a multi-level scheduling algorithm for global optimization in grid computing. This algorithm provides a global optimization through a cross-layer optimization realized by decomposing the optimization problem in different sub-problems each of them corresponding to one among the grid layers such as application layer, collective layer and fabric layer. The QoS of an abstraction level is a utility function that assigns at every level a different value and that depends on the kind of task that is executed on the grid. The global QoS is given by processing of the utility function values of the three different levels, using the Lagrangian method. Multi-level QoS scheduling algorithm is evaluated in terms of system efficiency and their economic efficiency, respectively. Economic efficiency includes user utility, service provider’s revenue and grid global utility. System efficiency includes execution success ratio and resource allocation ratio.     

混部数据中心负载特征及其任务调度优化分析

随着现代互联网数据中心的规模越来越大,数据中心面临着能耗、可靠性、可管理性与可扩展性等方面的挑战。同时,数据中心承载的服务多样,既有在线Web服务,也有离线批处理任务。在线任务要求较低的延迟,而离线任务要求较高的吞吐量。为了提高服务器利用率,降低数据中心能耗,当前数据中心往往将在线任务和离线任务混合部署到同一个计算集群中。在混部场景下,如何同时满足在线和离线任务的不同要求,是目前面临的关键挑战。分析了阿里巴巴于2018年发布的含有4034台服务器的混部计算集群在8天内的日志数据(cluster-trace-v2018),从静态配置信息、动态混部运行状态、离线批处理作业DAG依赖结构等出发,揭示其负载特征,包括任务倾斜与容器部署的相关关系等,根据任务依赖关系与关键路径,提出了相应的任务调度优化策略。