Online QoS Optimization Using Service Classes in Surveillance Radar Systems

Many application level qualities are functions of available computation resources. Recent studies have handled the computation resource allocation problem to maximize the overall application quality. However, such QoS problems are fundamentally multi-dimensional optimization problems that require extensive computation. Therefore, online usage of optimization procedures may significantly reduce the computation resource available for applications. This raises the question of how to best use the optimization procedures for dynamic real-time task sets. In dynamic real-time systems, it is important to improve the performance by re-allocating the resources adapting to dynamic situations. However, the overhead of changing task parameters (i.e., algorithms and frequencies) for resource re-allocation is non-negligible in many applications. Thus, too frequent change of resource allocation may not be desirable. This paper proposes a method called service classes configuration to address the QoS problem with dynamic arrival and departure of tasks. The method avoids online usage of optimization procedures by offline designing templates (called service classes) of resource allocation, which will be adaptively used depending on online situations. The service classes are designed by best trading-off the accuracy of dynamic adaptation against the overhead of resource re-allocation. A simplified radar application is used as an illustrative example.     

QoS约束的云经济资源管理模型研究

提供用户满意的、具有QoS约束的云计算应用是云计算面临的一大难题。提出了以商品市场为原型的云计算经济资源管理模型,其通过云用户与供应商的SLA协商,实现应用服务层QoS到资源设备层QoS的映射,最后利用效用函数的管理策略实现资源的优化调度。     

可变负载动态反馈弹性调度模型及其算法研究

由于工作负载的动态变化,以多媒体应用为代表的软实时系统的运行具有很大的不确定性.在这种情况下,依靠任务的静态属性进行调度分析和决策不足以为系统提供高效、实用的资源分配支持.提出一种弹性资源调度算法,该算法周期地采集系统的作业总数和作业丢失数,并以此为根据改变部分软实时任务的作业周期,以调整系统在下一个采样周期内的作业总数,达到满足任务的QoS(quality of service)、接纳尽可能多的服务请求、提高系统的并发服务能力的目的.详细分析了模型结构和核心算法的实现机制,并利用模拟平台对该算法进行了验证.实验结果表明,该算法在提高资源利用效率的同时,还具有良好的稳定性和收敛性.     

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.     

Finite-horizon scheduling of radar dwells with online template construction

Timing constraints for radar tasks are usually specified in terms of the minimum and maximum temporal distance between successive radar dwells. We utilize the idea of feasible intervals for dealing with the temporal distance constraints. In order to increase the freedom that the scheduler can offer a high-level resource manager, we introduce a technique for nesting and interleaving dwells online while accounting for the energy constraint that radar systems need to satisfy. Further, in radar systems, the task set changes frequently and we advocate the use of finite horizon scheduling in order to avoid the pessimism inherent in schedulers that assume a task will execute forever. The combination of feasible intervals and online dwell packing allows modular schedule updates whereby portions of a schedule can be altered without affecting the entire schedule, hence reducing the complexity of the scheduler. Through extensive simulations we validate our claims of providing greater scheduling flexibility without compromising on performance when compared with earlier work based on templates constructed offline. We also evaluate the impact of two parameters in our scheduling approach: the template length (or the extent of dwell nesting and interleaving) and the length of the finite horizon. Sathish Gopalakrishnan is a visting scholar in the Department of Computer Science, University of Illinois at Urbana-Champaign, where he defended his Ph.D. thesis in December 2005. He received an M.S. in Applied Mathematics from the University of Illinois in 2004 and a B.E. in Computer Science and Engineering from the University of Madras in 1999. Sathish’s research interests concern real-time and embedded systems, and the design of large-scale reliable systems. He received the best student paper award for his work on radar dwell scheduling at the Real-Time Systems Symposium 2004. Marco Caccamo graduated in computer engineering from the University of Pisa in 1997 and received the Ph.D. degree in computer engineering from the Scuola Superiore S. Anna in 2002. He is an Assistant Professor of the Department of Computer Science at the University of Illinois. His research interests include real-time operating systems, real-time scheduling and resource management, wireless sensor networks, and quality of service control in next generation digital infrastructures. He is recipient of the NSF CAREER Award (2003). He is a member of ACM and IEEE. Chi-Sheng Shih is currently an assistant professor at the Graduate Institute of Networking and Multimedia and Department of Computer Science and Information Engineering at National Taiwan University since February 2004. He received the B.S. in Engineering Science and M.S. in Computer Science from National Cheng Kung University in 1993 and 1995, respectively. In 2003, he received his Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign. His main research interests are embedded systems, hardware/software codesign, real-time systems, and database systems. Specifically, his main research interests focus on real-time operating systems, real-time scheduling theory, embedded software, and software/hardware co-design for system-on-a-chip. Chang-Gun Lee received the B.S., M.S. and Ph.D. degrees in computer engineering from Seoul National University, Korea, in 1991, 1993 and 1998, respectively. He is currently an Assistant Professor in the Department of Electrical Engineering, Ohio State University, Columbus. Previously, he was a Research Scientist in the Department of Computer Science, University of Illinois at Urbana-Champaign from March 2000 to July 2002 and a Research Engineer in the Advanced Telecomm. Research Lab., LG Information & Communications, Ltd. from March 1998 to February 2000. His current research interests include real-time systems, complex embedded systems, QoS management, and wireless ad-hoc networks. Chang-Gun Lee is a member of the IEEE Computer Society. Lui Sha graduated with the Ph.D. degree from Carnegie-Mellon University in 1985. He was a Member and then a Senior Member of Technical Staff at Software Engineering Institute (SEI) from 1986 to 1998. Since Fall 1998, he has been a Professor of Computer Science at the University of Illinois at Urbana Champaign, and a Visiting Scientist of the SEI. He was the Chair of IEEE Real Time Systems Technical Committee from 1999 to 2000, and has served on its Executive Committee since 2001. He was a member of National Academy of Science’s study group on Software Dependability and Certification from 2004 to 2005, and is an IEEE Distinguished Visitor (2005 to 2007). Lui Sha is a Fellow of the IEEE and the ACM.     

基于李雅普诺夫优化的容器云队列在线任务和资源调度设计

为在保证任务服务质量（QoS）的条件下提高容器云资源利用率，提出一种基于李雅普诺夫的容器云队列任务和资源调度优化策略。首先，在云计算服务排队模型的基础上，通过李雅普诺夫函数分析任务队列长度的变化；然后，在任务QoS的约束下，构建资源功耗的最小化目标函数；最后，利用李雅普诺夫优化方法求解最小资源功耗目标函数，获得在线的任务和容器资源的优化调度策略，实现对任务和资源调度进行整体优化，从而保证任务的QoS并提高资源利用率。CloudSim仿真结果表明，所提的任务和资源调度策略在保证任务QoS的条件下能获得高的资源利用率，实现容器云在线任务和资源优化调度，并且为基于排队模型的云计算任务和资源整体优化提供必要的参考。     

Resource scheduling with conflicting objectives in grid environments: Model and evaluation

The paper is to consider resource scheduling with conflicting objectives in the grid environment. The objectives of the grid users, the grid resources and the grid system clash with each other. Grid users want to access enough system resources to achieve the desired level of quality of service (QoS). Resource providers pay more attention to the performance of their resources. Our resource scheduling employs market strategies to determine which jobs are executed at what time on which resources and at what prices. A grid resource provider uses its utility function to maximize its profit and a grid user uses its utility function to complete tasks while minimizing its spending. The paper proposes grid system objective optimization scheduling that provides a joint optimization of objectives for both the resource provider and grid user, which combines the benefits of both resource provider objective optimization and user objective optimization. Experiments are designed to study the performances of three resource-scheduling optimization algorithms. Performance metrics are classified into efficiency metrics, utility metrics and time metrics.     

基于多QoS属性的分类优化调度算法

实现用户的服务质量（Qos）是网格计算中力求达到的重要目标,网格资源的分布性、异构性、动态性等特征使网格环境下以服务质量为指导的资源调度成为一个复杂的问题,尤其是在用户的任务具有多种QoS属性的情况下。该文利用经济模型研究网格QoS控制的资源分配问题。以效用最大化为目标通过综合效用函数量化服务质量,设计了在时间和费用受限情况下对任务进行分类的优化调度算法,该调度算法满足用户多QoS属性。仿真实验显示了该算法的有效性。     

BULLET: Particle Swarm Optimization Based Scheduling Technique for Provisioned Cloud Resources

Cloud resource scheduling requires mapping of cloud resources to cloud workloads. Scheduling results can be optimized by considering Quality of Service (QoS) parameters as inherent requirements of scheduling. In existing literature, only a few resource scheduling algorithms have considered cost and execution time constraints but efficient scheduling requires better optimization of QoS parameters. The main aim of this research paper is to present an efficient strategy for execution of workloads on cloud resources. A particle swarm optimization based resource scheduling technique has been designed named as BULLET which is used to execute workloads effectively on available resources. Performance of the proposed technique has been evaluated in cloud environment. The experimental results show that the proposed technique efficiently reduces execution cost, time and energy consumption along with other QoS parameters.     

基于SaaS的弹性云平台优化调度策略设计

云计算平台利用虚拟化技术使软件应用变得更有效率的同时, 也给资源管理和服务调度带来了挑战。在研究了软件服务（SaaS）与基础设施服务（IaaS）调度的区别基础上, 重点考虑SaaS层的资源调度, 提出基于随机理论的调度模型, 把该层调度描述成一种多目标的优化问题。除了服务质量的要求, 还考虑了弹性这一云服务的重要特性, 并提供了任务调度与弹性服务副本的匹配策略。实验表明本调度机制的设计优化了云平台的整体性能, 达到了较好的负载均衡与资源利用率。     

QoS-based Task Group Deployment on Grid by Learning the Performance Data

Overhead of executing fine-grain tasks on computational grids led to task group or batch deployment in which a batch is resized according to the characteristics of the tasks, designated resource, and the interconnecting network. An economic grid demands an application to be processed within the given budget and deadline, referred to as the quality of service (QoS) requirements. In this paper, we increase the task success rate in an economic grid by optimally mapping the tasks to the resources prior to the batch deployment. The task-resource mapping (Advance QoS Planning) is decided based on QoS requirement and by mining the historical performance data of the application tasks using a genetic algorithm. The mapping is then used to assist in creating the task groups. Practical experiments are conducted to validate the proposed method and suggestions are given to implement our method in a cloud environment as well as to process real-time tasks.     

网格环境下基于QoS需求的关联任务调度算法*

首先描述QoS调度问题,建立QoS需求模型;然后通过分析任务的依赖性,提出时间花费、资源价格和可靠性三种QoS参数的映射机制;最后针对网格环境的新特征,提出一种以优化用户效用为目标,基于QoS的关联任务调度算法(QBDTS_UO).仿真实验结果表明,该算法能以较小的时间花费为代价,有效满足用户的QoS需求,并能大大提高网格资源的使用率.     

基于分批优化的实时多处理器系统的集成动态调度算法

提出了一种基于分批优化的实时多处理器系统的集成动态调度算法，该算法采用在每次扩充当前局部调度时，通过对所选取的一批任务进行优化分配的策略以及软实时任务的服务质量QoS（quality of service）降级策略，以统一方式实现了对实时多处理器糸统中硬、软实时任务的集成动态调度．进行了大量的模拟研究，结果表明．在多种任务参数取值下，新算法的调度成功率均高于近视算法（Myopic Algorithm）．     

Optimization decomposition approach for layered QoS scheduling in grid computing

The paper presents optimization decomposition based layered Quality of Service (QoS) scheduling for computational grid. Cross layer joint QoS scheduling is studied by considering the global problem as decomposed into three sub-problems: resource allocation at the fabric layer, service composing at the collective layer, and user satisfaction degree at the application layer. The paper proposes a complete solution from optimization modeling, Lagrange relaxation based decomposition, to solutions for each sub-problem Lagrange relaxation based decomposition. These aspects match the vertical organization of the considered grid system: each layer trade with adjacent layers to find a global optimum of the whole grid system. Through multi-layer QoS joint optimization approach, grid global QoS optimization can be achieved. The cross layer policy produces an optimal set of grid resources, service compositions, and user’s payments at the fabric layer, collective layer and application layer, respectively, to maximize global grid QoS. The owner of each layer obtains inputs from other layers, tries to maximize its own utility and provides outputs back to other layers. This iterative process lasts until presumably all layers arrive at the same solution.     

一种基于QoS的网格资源选择优化模型

大量任务请求使用网格资源时,必须进行合理调度和资源分配才能提供较高的服务质量。通过对网格QoS几个重要属性进行量化,以最大化系统服务性价比为目标,提出了一种基于退火遗传算法的网格资源选择优化模型,并介绍了算法的详细流程。最后,通过仿真实验验证了该模型的有效性。     

一种无抖动的分布式多媒体任务调度算法

在分布式多媒体系统中,资源的管理和分配算法是保证应用的服务质量（ＱｏＳ）的关键问题,而资源管理中,ＱｏＳ协商和确认都和多媒体任务调芳算法有关,任务调度算法是资源管理的重要内容。现有的调度算法ＥＤＦ,ＲＭ,ＤＳｒ适用在分布式多媒体系统中,有局限性。本文基于风车调度模型,提出了一种无抖动调度的逐步消除候选项的并行算法ＤＭＳｒ,能达到分布系统中多媒体任务周期调度的无抖动特点,并讨论了算法的计算复杂度,证     

Verifying distributed real-time properties of embedded systems via graph transformations and model checking

Component middleware provides dependable and efficient platforms that support key functional, and quality of service (QoS) needs of distributed real-time embedded (DRE) systems. Component middleware, however, also introduces challenges for DRE system developers, such as evaluating the predictability of DRE system behavior, and choosing the right design alternatives before committing to a specific platform or platform configuration. Model-based technologies help address these issues by enabling design-time analysis, and providing the means to automate the development, deployment, configuration, and integration of component-based DRE systems. To this end, this paper applies model checking techniques to DRE design models using model transformations to verify key QoS properties of component-based DRE systems developed using Real-time CORBA. We introduce a formal semantic domain for a general class of DRE systems that enables the verification of distributed non-preemptive real-time scheduling. Our results show that model-based techniques enable design-time analysis of timed properties and can be applied to effectively predict, simulate, and verify the event-driven behavior of component-based DRE systems. This research was supported by the NSF Grants CCR-0225610 and ACI-0204028 Gabor Madl is a Ph.D. student and a graduate student researcher at the Center for Embedded Computer Systems at the University of California, Irvine. His advisor is Nikil Dutt. His research interests include the formal verification, optimization, component-based composition, and QoS management of distributed real-time embedded systems. He received his M.S. in computer science from Vanderbilt University and in computer engineering from the Budapest University of Technology and Economics. Dr. Sherif Abdelwahed received his Ph.D. degree in Electrical and Computer Engineering from the University of Toronto, Canada, in 2001. During 2000–2001, he was a research scientist with the system diagnosis group at the Rockwell Scientific Company. Since 2001 he has been with the Department of Electrical Engineering and Computer Science at Vanderbilt University as a Research Assistant Professor. His research interests include verification and control of distributed real-time systems, and model-based diagnosis of discrete-event and hybrid systems. Dr. Douglas C. Schmidt is a Professor of Computer Science, Associate Chair of the Computer Science and Engineering program, and a Senior Researcher in the Institute for Software Integrated Systems (ISIS) all at Vanderbilt University. He has published over 300 technical papers and 6 books that cover a range of research topics, including patterns, optimization techniques, and empirical analyses of software frameworks and domain-specific modeling environments that facilitate the development of distributed real-time and embedded (DRE) middleware and applications. Dr. Schmidt has served as a Deputy Office Director and a Program Manager at DARPA, where he lead the national R&D effort on middleware for DRE systems. In addition to his academic research and government service, Dr. Schmidt has over fifteen years of experience leading the development of ACE, TAO, CIAO, and CoSMIC, which are widely used, open-source DRE middleware frameworks and model-driven tools that contain a rich set of components and domain-specific languages that implement patterns and product-line architectures for high-performance DRE systems.     

A distributed multiple dimensional QoS constrained resource scheduling optimization policy in computational grid

This paper is to solve efficient QoS based resource scheduling in computational grid. It defines a set of QoS dimensions with utility function for each dimensions, uses a market model for distributed optimization to maximize the global utility. The user specifies its requirement by a utility function. A utility function can be specified for each QoS dimension. In the grid, grid task agent acted as consumer pay for the grid resource and resource providers get profits from task agents. The task agent' utility can then be defined as a weighted sum of single-dimensional QoS utility function. QoS based grid resource scheduling optimization is decomposed to two subproblems: joint optimization of resource user and resource provider in grid market. An iterative multiple QoS scheduling algorithm that is used to perform optimal multiple QoS based resource scheduling. The grid users propose payment for the resource providers, while the resource providers set a price for each resource. The experiments show that optimal QoS based resource scheduling involves less overhead and leads to more efficient resource allocation than no optimal resource allocation.     

QoS Control Strategies for High-Quality Video Processing

Video processing in software is often characterized by highly fluctuating, content-dependent processing times, and a limited tolerance for deadline misses. We present an approach that allows close-to-average-case resource allocation to a single video processing task, based on asynchronous, scalable processing, and QoS adaptation. The QoS adaptation balances different QoS parameters that can be tuned, based on user-perception experiments: picture quality, deadline misses, and quality changes. We model the balancing problem as a discrete stochastic decision problem, and propose two solution strategies, based on a Markov decision process and reinforcement learning, respectively. We enhance both strategies with a compensation for structural (non-stochastic) load fluctuations. Finally, we validate our approach by means of simulation experiments, and conclude that both enhanced strategies perform close to the theoretical optimum.Clemens Wüst received the M.Sc. degree in mathematics with honors from the University of Groningen, The Netherlands. Since then, he has been with the Philips Research Laboratories in Eindhoven, The Netherlands, where he has been working mainly on QoS for resource-constrained real-time systems using stochastic optimization techniques. Currently, he is pursuing a Ph.D. degree at the Technische Universiteit Eindhoven.Liesbeth Steffens received her M.Sc. from Utrecht University (NL) in 1972. She spent most of her professional life in Philips Research in Eindhoven. She contributed to the design of a real-time distributed operating system, a video-on-demand server, a DVD player, a set-top box, and a QoS-based Resource-Management framework for streaming video. Her current focus is on characterization of resource requirements, resource reservation, and system-on-chip infrastructure.Wim F. J. Verhaegh received the mathematical engineering degree with honors in 1990 from the Technische Universiteit Eindhoven, The Netherlands. Since then, he is with the Philips Research Laboratories in Eindhoven, The Netherlands. From 1990 until 1998, he has been a member of the department Digital VLSI, where he has been working on high-level synthesis of DSP systems for video applications, with the emphasis on scheduling problems and techniques. Based on this work, he received a Ph.D. degree in 1995 from the Technische Universiteit Eindhoven. Since 1998, he is working on various optimization aspects of multimedia systems, networks, and applications. On the one hand, this concerns application-level resource management and scheduling, for optimization of quality of service of multimedia systems. On the other hand, this concerns adaptive algorithms and machine learning algorithms for user interaction issues, such as content filtering and automatic playlist generation.Reinder J. Bril received a B.Sc. and a M.Sc. (both with honors) from the Department of Electrical Engineering of the University of Twente, and a Ph.D. from the Technische Universiteit Eindhoven (TU/e), The Netherlands. He started his professional career at the Delft University of technology in the Department of Electrical Engineering. From May 1985 till August 2004, he has been with Philips. He has worked in both Philips Research as well as Philips Business Units, on various topics, including fault-tolerance, formal specifications, and software architecture analysis, and in different application domains. The last five years, he worked at Philips Research Laboratories Eindhoven (PRLE), the Netherlands, in the area of Quality of Service (QoS) for consumer devices, with a focus on dynamic resource management in receivers in broadcast environments (such as digital TV-sets and set-top boxes). In September 2004, he made a transfer to the Technische Universiteit Eindhoven (TU/e), Department of Mathematics and Computer Science, Group System Architecture and Networking (SAN), i.e. back to the academic world, after 19 years in industry.Christian Hentschel received his Dr.-Ing. (Ph.D.) in 1989 and Dr.-Ing. habil. in 1996 at the University of Technology in Braunschweig, Germany. He worked on digital video signal processing with focus on quality improvement. In 1995, he joined Philips Research in Briarcliff Manor, USA, where he headed a research project on moiré analysis and suppression for CRT based displays. In 1997, he moved to Philips Research in Eindhoven, The Netherlands, leading a cluster for Programmable Video Architectures. Later he held a position of a Principal Scientist and coordinated a project on scalable media processing with dynamic resource control between different research laboratories. In 2003, he became a full professor at the Brandenburg University of Technology in Cottbus, Germany. Currently he chairs the department of Media Technology. He is a member of the Technical Committee of the International Conference on Consumer Electronics (IEEE) and a member of the FKTG in Germany.     

云工作流中基于分时虚拟机的任务层调度算法

云计算是新的一种面向市场的商业计算模式,向用户按需提供服务,云计算的商业特性使其关注向用户提供服务的服务质量。任务调度和资源分配是云计算中两个关键的技术,所使用的虚拟化技术使得其资源分配和任务调度有别于以往的并行分布式计算。目前主要的调度算法是借鉴网格环境下的调度策略,研究基于QoS的调度算法,存在执行效率较低的问题。我们对云工作流任务层调度进行深入研究,分析由底层资源虚拟化形成的虚拟机的特性,结合工作流任务的各类QoS约束,提出了基于虚拟机分时特性的任务层ACS调度算法。经过试验,我们提出的算法相比于文献[1]中的算法在对于较多并行任务的执行上存在较大的优势,能够很好的利用虚拟的分时特性,优化任务到虚拟机的调度。