End-to-end QoS resource management for an IP-based DWDM access network

The ever-increasing use of broad-band Internet and complex multimedia applications is pushing fiber closer and closer to the homes. Within the European project IST HARMONICS (Hybrid Access Reconfigurable Multi-wavelength Optical Networks for IP-based Communication Services), an optical access feeder network and resource management framework were developed that tackle this demand for bandwidth and the desire to stimulate the convergence of last-mile access technologies. To cope with the lack of bandwidth in the access and last-mile networks and the different needs of applications and users, the developed management system provides end-to-end quality of service (QoS) while integrating multiple technologies. In this paper, a detailed overview of the end-to-end QoS management framework and novel time slot/wavelength MAC protocol for the optical feeder network is given. End-to-end QoS is based on Differentiated services (DiffServ) at layer 3, various QoS supporting technologies at layer 2, and QoS mappings between both layers. The paper will also focus on the field trial results of the HARMONICS project and give some guidelines for possible problems and solutions in this area.     

QoS based fair resource allocation in multi-cell TD/CDMA communication systems

Abstract-In a wireless multimedia code division multiple access (CDMA) system, the resources in terms of transmission rate and power should be efficiently distributed to each user to guarantee its quality-of-service (QoS) requirements. In, this paper, a resource allocation algorithm which combines packet scheduling and power assignment is proposed to achieve efficient resource utilization under QoS constraints. The packet scheduling is based on the fair packet loss sharing (FPLS) principle, and the power assignment is determined by the received power limited (RPL) scheme. The basic idea of FPLS is to schedule the transmission of multimedia packets in such a way that, all the users have a fair share of packet loss according to their QoS requirements, which maximizes the number of the served users with QoS satisfaction. The RPL scheme minimizes the received power for each packet. Given the propagation path loss, it in turn minimizes the transmitted power as well. The intercell interference from the scheduled packets is also limited in order to increase the system capacity.     

Dynamic resource management in QoS controlled networks

This paper addresses the problem of resource fragmentation (RF) in QoS controllednetworks. Resources are said to be fragmented when they are available in non-contiguousblocks and hence cannot be utilized by incoming calls with high resource demands. This paper shows the effect of resource fragmentation on QoS controlled networks and presents the Dynamic Resource Redistribution (DRR) algorithm to counteract RF. The DRR algorithm reduces the effects of RF by attempting to redistribute resources in different paths to make resources to incoming calls. A variety of simulation experiments were conducted to study the performance of the DRR algorithm on different network topologies with varying traffic characteristics. The DRR algorithm, when used, increased the number of calls accommodated in the network as well as the overall resource allocation in the network.     

AQUILA: adaptive resource control for QoS using an IP-based layered architecture

Support for quality of service is an essential component of the next-generation Internet. The European research project AQUILA is committed to defining a DiffServ-based architecture for delivering on-demand QoS to requesting applications. Focal characteristics of the proposed solution are backward compatibility to the existing Internet and scalability to very large networks. To achieve such goals, AQUILA implements an overlaid distributed control layer, the resource control layer, implementing a novel mechanism for dynamic control of intradomain resources, the dynamic resource pool. On the interdomain aspects, the AQUILA architecture extends the BGRP framework for the aggregation of interdomain reservations to overcome scalability issues. This article describes the general AQUILA architecture, with a special focus on the DRP and BGRP mechanisms.     

通过有效的端系统动态资源管理实现QoS控制

本文试图采用全局观点，基于连续媒体活动模型，利用数学工具详细分析在保持端到端媒体服务质量前提下，建立高层的细粒度QoS控制技术－端系统动态资源管理来实现QoS控制，及其策略与算法，最后通过实验验证了管理策略的可行性。     

Enhancing virtual environments with QoS aware resource management

Nowadays, the consolidation of application servers is the most common use for current virtualization solutions. Each application server takes the form of a virtual machine (VM) that can be hosted into one physical machine. In a default Xen implementation, the scheduler is configured to handle equally all of the VMs that run on a single machine. As a consequence, the scheduler shares equally all of the available physical CPU resources among the running VMs. However, when the applications that run in the VM dynamically change their resource requirements, a different solution is needed. Furthermore, if the resource usage is associated with service-level agreements, a predefined equal share of the processor power is insufficient for the VMs. Within the Xen’s primitives, even though it is possible to tune the scheduler parameters, there is no tool to achieve the dynamic change of the share of the processor power assigned to each VM. A combination of a number of primitives, however, appears to be suited as a base for achieving this. In this paper, we present an approach to efficiently manage the quality of service (QoS) of virtualized resources in multicore machines. We evaluate different alternatives within Xen for building an enhanced management of virtual CPU resources. We compare these alternatives in terms of performance, flexibility, and ease of use. We devise an architecture to build a high-level service that combines interdomain communication mechanisms with monitoring and control primitives for local resource management. We achieve this by our solution, a local resource manager (LRM), which adjusts the resources needed by each VM according to an agreed QoS. The LRM has been implemented as a prototype and deployed on Xen-virtualized machines. By means of experiments, we show that the implemented management component can meet the service-level objectives even under dynamic conditions by adapting the resources assigned to the virtualized machines according to demand. With the LRM, we therefore achieve both fine-grain resource allocation and efficient assignment.     

一种基于QoS策略的光突发交换网络LSP共享算法

针对光突发交换（OBS）网络中已有的包括抢占和波长分离等服务质量（QoS）保证机制的不足,提出了一种改进的基于QoS的标签交换路径共享（QLS）算法。算法通过链路波长资源的统计复用,在保证高优先级业务传送的可靠性和有效性的同时,提升低优先级业务的QoS性能。使用开源离散事件仿真软件OMNeT++搭建了OBS/GMPLS仿真平台,对4×4对称型MESH网络和NSFNET网络分别采用WP算法和QLS算法进行了仿真。结果表明,QLS算法对于高QoS等级业务性能影响极小,MESH和NSFNET网络中class3业务的丢包率分别减少了近0.2和0.3,平均丢包率分别减少了约0.05和0.1。     

Joint interference coordination approach in femtocell networks for QoS performance optimization

Future heterogeneous networks with dense cell deployment may cause high intercell interference. A number of interference coordination (IC) approaches have been proposed to reduce intercell interference. For dense small‐cell deployment with high intercell interference between cells, traditional forward link IC approaches intended to improve edge user throughput for best effort traffic (ie, file transfer protocol download), may not necessarily improve quality of service performance for delay‐sensitive traffic such as voice over long‐term evolution traffic. This study proposes a dynamic, centralized joint IC approach to improve forward link performance for delay‐sensitive traffic on densely deployed enterprise‐wide long‐term evolution femtocell networks. This approach uses a 2‐level scheme: central and femtocell. At the central level, the algorithm aims to maximize network utility (the utility‐based approach) and minimize network outage (the graphic‐based approach) by partitioning the network into clusters and conducting an exhaustive search for optimized resource allocation solutions among femtocells (femto access points) within each cluster. At the femtocell level, in contrast, the algorithm uses existing static approaches, such as conventional frequency reuse (ReUse3) or soft frequency reuse (SFR) to further improve user equipment quality of service performance. This combined approach uses utility‐ and graphic‐based SFR and ReUse3 (USFR/GSFR and UReUse3/GReUse3, respectively). The cell and edge user throughput of best effort traffic and the packet loss rate of voice over long‐term evolution traffic have been characterized and compared using both the proposed and traditional IC approaches.     

Extending EDCA with distributed resource reservation for QoS guarantees

In this paper we describe how the contention-based medium access mechanism of 802.11e, EDCA, can be enhanced in order to allow stations to reserve medium access for their real-time applications with QoS requirements. We present our proposed scheme, which is called EDCA with resource reservation (EDCA/RR), and describe how it can be extended in order to be used in wireless multi-hop networks. EDCA/RR operates in a completely distributed manner and manages to provide deterministic, contention-free medium access, making it an attractive scheme for wireless networks.     

Throughput analysis for interference limited TDMA and TDMA/CDMA wireless ad hoc networks

The node throughput, which is defined as the total rate received at each node, is evaluated for the interference limited TDMA and TDMA/CDMA wireless ad hoc networks. In the TDMA wireless ad hoc network, there is only one transmission link connected to each node in the same time slot, whereas in the TDMA/CDMA wireless ad hoc network there are multiple transmission links connected to each node in the same time slot. We first derive the node throughput for these two wireless ad hoc networks and then make a comparison of the node throughput between them. The theoretical results and simulation results both reveal that the TDMA wireless ad hoc network outperforms the TDMA/CDMA wireless ad hoc network in the node throughput. Copyright © 2008 John Wiley & Sons, Ltd.     

Coherent and limiter-discriminator detection of GMSK in interference limited conditions

The bit error rate performance of GMSK (BT product of 0.5) in a single interferer environment is considered. It is shown that the superiority of coherent over LD detection is not as marked as for the noise only case, and depends strongly on receiver filtering. Comparative estimates of spectral efficiency suggest that, for small cell cordless and mobile networks with irregular layouts, the adoption of coherent receiver techniques may provide small system gains only.<>     

Analysis of QoS aware energy-efficient resource provisioning techniques in cloud computing

By incorporating on-demand resources, software and data for collaborative services through the Internet, the conventional Information Technology enterprise has been transformed by cloud computing. Based on the pay-per-use approach, Infrastructure, platform or Software resources and servers located across data centres are among the several types of resources offered to consumers in cloud computing. Data centres handle these resources. These resources are constantly provisioned to users based on their availability, demand, and quality requirements. Cloud computing systems are known as one of the largest utilisers of energy resources all over the world. Also, power consumption has become a crucial aspect as most cloud computing systems work on traditional nonrenewable resources of energy. In order to make data centres environment-friendly, there is a need for optimal approaches to reduce energy consumption and their hazardous effects on the environment. To analyse different available strategies for building and maintaining an energy-efficient cloud is the main objective of this paper. The paper will comprehensively review several energy-efficient resource provisioning methods and provide a graphical comparative study of Quality of Service (QoS) Metrics in cloud computing. Moreover, the present study identifies the areas of study that need to be further improved to increase the energy efficiency of cloud computing systems.     

基于 QoS 保障的密集 WLAN 多维资源分配算法

针对密集无线局域网覆盖环境,以提升网络性能为目标,提出了一种多维无线资源分配方法。通过网络覆盖衡量参数、干扰衡量参数和QoS衡量参数联合评估网络性能,建立了网络性能与资源分配向量之间的优化目标函数,进而采用禁忌搜索的方法求解目标函数后得到最优多维资源分配向量,包括所用AP、信道和功率分配向量。仿真结果表明,所提算法提升了网络性能,更好地保证了用户QoS需求。     

Joint resource allocation with QoS provisioning in K-tier heterogeneous cellular networks

In this paper, the joint resource allocation （RA） problem with quality of service （QoS） provisioning in downlink heterogeneous cellular networks （HCN） is studied. To fully exploit the network capacity, the HCN is modeled as a K-tier cellular network where each tier＇s base stations （BSs） have different properties. However, deploying numbers of low power nodes （LPNs） which share the same frequency band with macrocell generates severe inter-cell interference. Enhancement of system capacity is restricted for inter-cell interference. Therefore, a feasible RA scheme has to be developed to fully exploit the resource efficiency. Under the constraint of inter-cell interference, we formulate the RA problem as a mixed integer programming problem. To solve the optimization problem we develop a two-stage solution. An integer subchannel assignment algorithm and Lagrangian-based power allocation algorithm are designed. In addition, the biasing factor is also considered and the caused influence on system capacity is evaluated. Simulation results show that the proposed algorithms achieve a good tradeoff between network capacity and interference. Moreover, the average network efficiency is highly improved and the outage probability is also decreased.     

Energy efficient resource allocation in two-tier OFDMA networks with QoS guarantees

Wireless Networks - In this paper, we introduce the joint power and subchannel allocations techniques for OFDMA based femtocell networks with focus on uplink direction. These techniques minimize...     

大数据背景下云计算共享资源平台的应用探究

随着计算机网络技术的不断发展,人们进入了一个大数据的时代,在这样的背景下诞生了云计算技术,其在各个领域,特别是在资源、信息领域中有着广泛的应用。文章主要探讨了在大数据时代背景下云计算共享资源平台的建设和应用,主要从虚拟技术中探讨平台的建设,并从现实角度分析平台在用户服务和社会针对性发展方面的两个重要应用。     

Flexible resource allocation strategies for class-based QoS provisioning in mobile networks

Flexible resource-allocation (FRA) strategies have been proposed in the literature to mitigate the high blocking rate caused in high-speed mobile communication networks when resource aggregation is used to increase the data rate. In this paper, new FRA strategies that cope with scenarios with multiple service types and multiple priorities are proposed. These are called the FRA strategy with differentiated priorities and quality of service (FRAQoS) and the FRA strategy with prioritized levels (FRASPL). The main distinguishing feature of these strategies is their capacity to prioritize some service types over others. FRAQoS prioritizes the quality of service (QoS) of particular service types over others by introducing the concepts of prioritized call degradation and compensation. However, FRAQoS provides a limited ability to prioritize particular service types over the rest because any incoming call, irrespective of its service type and priority, may trigger resource reallocations to service it. The FRASPL overcomes this limitation by introducing a call-admission mechanism that, when necessary, rejects calls originated by low-priority service types. This enhances the protection to high-priority service types. By prioritizing some services over the others, FRASPL can trade off capacity against QoS. FRAQoS represents particular limiting cases of FRASPL. A mathematical model is developed to investigate the performance of FRAQoS and FRASPL. Then, they are compared with other FRA strategies in a scenario with multiple differentiated service types. Results show that the proposed strategies effectively prioritize service types, providing them with better QoS. This makes FRAQoS and FRASPL specially suitable for class-based QoS provisioning in mobile networks.     

Radio resource sharing games: enabling QoS support in unlicensed bands

Distributed quality of service support in wireless networks that are sharing unlicensed frequency bands is an increasingly significant research problem. The spectral coexistence of dissimilar radio systems has to be addressed in the near future in concerning the widely deployed IEEE 802.11 wireless local area networks and other future radio systems operating in unlicensed or opportunistically used frequency bands. The competition between independent wireless networks for allocating a common shared radio channel is modeled in this article as a stage-based game model: players, representing wireless networks, interact repeatedly in radio resource sharing games, without direct coordination or information exchange. Solution concepts derived from game theory allow the analysis of such models under the microeconomic aspects of welfare. Decisions players repeatedly have to make are about when and how often to attempt medium access. In multistage games the players apply strategies in order to maximize their observed utility as a summarizing value for successfully supported quality of service. Strategies determine whether competing radio networks cooperate or ignore the presence of other radio networks. The traffic requirements of a player thereby decide which strategy is adequate to guarantee quality of service.     

基于共享资源量的动态多资源公平分配策略

针对云计算共享系统中多资源分配问题,提出一种基于共享资源量的动态多资源公平分配策略。该策略根据不同用户资源需求和共享资源量建立一个线性规划模型,同时证明该模型满足公平分配的4个重要属性：动态帕累托最优、激励共享、动态无嫉妒性和防止策略性操作,而且给出一种改进的动态多资源公平分配算法来提高算法运行效率。实验结果表明,所提动态多资源公平分配策略能够在满足任务资源需求的同时,尽可能保证公平分配下最大化占优资源份额,并且改进的分配算法能够有效地提高资源的分配效率。     

一种QoS保证的移动自组网低能耗资源发现协议

如何在大规模的移动自组网络中快速地找到所需的资源是一个迫切需要解决的问题.提出了一种称为EAQOS(Energy Aware QoS)的资源发现协议,本协议将资源查询请求过程同路由协议紧密结合,通过合并资源请求、QoS探测以及路径请求信息能够快速定位网络中的最优QoS的资源供应者并进行访问,同时有效降低了网络中的通信量以及能量消耗.最后通过NS2进行模拟实验,与两种不同的Qos资源发现协议相比,结果表明所提出协议的性能,包括查询延迟、通信代价以及能量消耗都有显著的提高.