A Throughput-Driven Scheduling Algorithm of Differentiated Service for Web Cluster

Requests distribution is an key technology for Web cluster server. This paper presents a throughput-driven scheduling algorithm （TDSA）. The algorithm adopts the throughput of cluster back-ends to evaluate their load and employs the neural network model to predict the future load so that the scheduling system features a self-learning capability and good adaptability to the change of load. Moreover, it separates static requests from dynamic requests to make full use of the CPU resources and takes the locality of requests into account to improve the cache hit ratio. Experimental re suits from the testing tool of WebBench^TM show better per formance for Web cluster server with TDSA than that with traditional scheduling algorithms.

A New Self-Adapting Admission Control Algorithm for Differential Service in Web Clusters

A new admission control algorithm considering the network self-similar access characteristics is proposed. Taking advantage of the mathematical model of the network traffic admission control which can effectively overcome the self-similar characteristics of the network requests, through the scheduling of the differential service qucue based on priority while at the same time taking into account various factors including access characteristics of requests, load information, etc, smoothness of the admission control is ensured by the algorithm proposed in this paper. We design a non-linear self-adapting control algorithm by introducing an exponential admission function, thus overcomes the negative aspects introduced by static threshold parameters. Simulation results show that the scheme proposed in this paper can effectively improve the resource utilization of the clusters, while at the same time protecting the service with high priority. Our simulation results also show that this algorithm can improve system stability and reliability too. Key words Web cluster - admission control - differential service - self-similar - self-adapting CLC number TP 393 Foundation item: Supported by the National Natural Science Foundation of China (10375024) and the Hunan Natural Science Foundation of China(03JJY4054)Biography: LIU An-feng(1971-), male, Ph. D candidate, majoring in network computing, Web QoS.

ECC:Edge Collaborative Caching Strategy for Differentiated Services Load-Balancing

Due to the explosion of network data traffic and IoT devices,edge servers are overloaded and slow to respond to the massive volume of online requests.A large number of studies have shown that edge caching can solve this problem effectively.This paper proposes a distributed edge collaborative caching mechanism for Internet online request services scenario.It solves the problem of large average access delay caused by unbalanced load of edge servers,meets users’differentiated service demands and improves user experience.In particular,the edge cache node selection algorithm is optimized,and a novel edge cache replacement strategy considering the differentiated user requests is proposed.This mechanism can shorten the response time to a large number of user requests.Experimental results show that,compared with the current advanced online edge caching algorithm,the proposed edge collaborative caching strategy in this paper can reduce the average response delay by 9%.It also increases the user utility by 4.5 times in differentiated service scenarios,and significantly reduces the time complexity of the edge caching algorithm.

Research of MPLS traffic engineering over differentiated services

An approach to traffic engineering that uses differentiated services (DS) andmulti-protocol label switching (MPLS) to provide quantitative network quality of service (QoS)guarantees over an IP network was proposed. The traffic associated with assured forwarding (AF)Per-Hop behavior (PHB) in differentiated services enabled IP network was modeled. Furthermore, theeffect of such traffic on network resources with die objective of developing efficient trafficengineering methodologies was analyzed and the optimization problem relating to traffic engineeringin DS networks with an MPLS core was formulated. The service received by TCP and UDP flows when theyshare either a link or a MPLS traffic trunk was also compared and found that in order to benefitfrom traffic engineering, MPLS trunks should be implemented end-end (first router to last router).If some part of the network is MPLS trunk-unaware, the benefits are reduced or eliminated.

Improvements on Analytical Models for IEEE 802.11e EDCF Differential Services

Zhu introduced typical analytical models to simulate the 802. 11e EDCF channel access protocol. But our analysis indicates that there are some inaccurate derivations in his presentation. This paper intends to improve analytical model with some corrections. Furthermore, for the probability of the channel being busy pb in Zhu＇s model, different points and analysis method are proposed. When the network is under saturation condition, the new results about the probabilities of collision and channel busy, transmission probabilities, successful transmission probabilities, throughput and MAC layer latency are presented.

MCHOKeM algorithm with assured bandwidth allocation in DiffServ networks

An active queue management（AQM） algorithm called MCHOKeM is presented,which is borrowed from CHOKeW that draws multi-packets at random from the buffer,the multi-packets are compared with an arriving packet and abandoned if they are from the same flow.But MCHOKeM uses multiple virtual queues for different priority packets and enhances the drawing function by adjusting the maximum number of draws based on the current status of virtual queue length.The number of parameters that MCHOKeM needs to maintain is determined by the number of priority levels being supported by the router,which usually has a small limited value.In order to explain the features of MCHOKeM,an analytical model is used.A series of simulation tests to evaluate the performance are given.

A novel differentiated services supporting scheme for optical burst switched networks

In this letter, we analyze the drawback of tail-dropping contention resolution in optical burst switched networks. Once contention occurs, we adopt modified head-dropping policy to resolve contention. This policy drops the head of the contending burst only if the overlapping region of the two bursts is less than the whole contending burst size, otherwise drops the whole contending burst. In order to have a better support of differentiated service, a new burst assembly policy, namely, Priority-based proportional mixed burst assembly, is proposed. Simulation results show that the proposed scheme performs very well in terms of performance metrics such as the times of contention and packet loss probability.

Supporting service differentiation with enhancements of the IEEE 802.11 MAC protocol:Models and analysis

As one of the fastest growing wireless access technologies, wireless LANs must evolve to support adequate degrees of service differentiation. Unfortunately, current WLAN standards like IEEE 802.11 Distributed Coordination Function （DCF） lack this ability. Work is in progress to define an enhanced version capable of supporting QoS for multimedia traffic at the MAC layer. In this paper, we aim at gaining insight into three mechanisms to differentiate among traffic categories, i.e., differentiating the minimum contention window size, the Inter-Frame Spacing （IFS）, and the length of the packet payload according to the priority of different traffic categories. We propose an analysis model to compute the throughput and packet transmission delays. In addition, we derive approximations to obtain simpler but more meaningful relationships among different parameters. Comparisons with discrete-event simulation results show that good accuracy of performance evaluation can be achieved by using the proposed analysis model.

Priority-Based Mixed Assembly Supporting Differentiated Service for Optical Burst Switched Networks

In order to have a better support of differentiated service, we propose Priority-based mixed burst assembly, in which packets of different priorities are assembled in a burst with an assigned proportion, and the priorities are lined in an ascending order in a burst from head to tail. Simulation results show that the proposed scheme performs very well in terms of latency and packet loss probability.

Secure Application-Aware Service Differentiation in Public Area Wireless Networks

We are witnessing the increasing demand for pervasive Internet access from public area wireless networks （PAWNs）. As their popularity grows, the inherent untrusted nature of public places and the diverse service requirements of end users are two key issues that need to be addressed. We have proposed two approaches to address these issues. First, the Home-based Authentication Protocol （HAP） that provides a framework by which to establish trust between a nomadic client and a service provider using a trusted third party （home）. Second, we argue that the best-effort-based service model provided by many access points is not enough to satisfy the end user fairness and to maximize the wireless link utilization for a diverse user population. We have proposed an application-aware service differentiation （AASD） mechanism that takes both application semantics and user requirements into consideration. Our analysis of this framework shows several fruitful results. The total authentication latency increases with the number of clients but at a rate that is much less than linear increasing latency. Also, in comparison with two other bandwidth allocation approaches, the best effort and static access control, our proposed application-aware service differentiation method, outperforms them in terms of the client fairness and wireless bandwidth utilization.

A Teletraffic Model for Service Differentiation in OPS Networks

This paper present a formal teletraffic model for service diferentiation in optical packet switched networks by utilizing the wavelength domain.Expressions for the time congestion are derived.Simulation results are also reported.

A Novel Framework for IP DiffServ over Optical Burst Switching Networks

This paper presents a novel framework for IP Differentiated Services (DiffServ) over optical burst switching (OBS), namely, DS-OBS. The network architecture, functional model of edge nodes and core nodes, the control packet format, a novel burst assembly scheme at ingress nodes and scheduling algorithm of core nodes are presented. The basic idea is to apply DiffServ capable burst assembly at ingress nodes and perform different per hop behavior (PHB) electronic treatments for control packets of different QoS class services at core nodes. Simulation results show that the proposed schemes can provide the best differentiated service for expedited forwarding (EF), assured forwarding (AF) and best effort (BE) services in terms of end-to-end delay, throughput and IP packet loss probability. Keywords IP quality of service - differentiated service - per hop behavior - optical burst switching NoteThis work is supported by the National Natural Science Foundation of China (Grant No.90304004), the National Hi-Tech Development 863 Program of China (Grant No.2003AA121540), and the research grants by the Ministry of Education of China (Grant No.204125), the Chongqing Education Commission (Grant No.050309) and the Chongqing Science Commission.

Web Caching： A Way to Improve Web QoS

As the Internet and World Wide Web grow at a fast pace, it is essential that the Web's performance should keep up with increased demand and expectations. Web Caching technology has been widely accepted as one of the effective approaches to alleviating Web traffic and increase the Web Quality of Service (QoS). This paper provides an up-to-date survey of the rapidly expanding Web Caching literature. It discusses the state-of-the-art web caching schemes and techniques, with emphasis on the recent developments in Web Caching technology such as the differentiated Web services, heterogeneous caching network structures, and dynamic content caching.

Influence of the GEO satellite orbit error fluctuation correction on the BDS WADS zone correction

Decimeter-level service is provided by the BeiDou satellite navigation system wide area differential service(BDS WADS)for users who collect carrier phase measurements.However,the fluctuations in Geostationary Earth Orbit(GEO)satellite orbit errors reduce the spatial correlation of orbit errors.These fluctuations not only decrease the accuracy and stability of zone correction service provided by BDS WADS,but also shorten its effective range.In this paper,we proposed an algorithm to weaken the influence of GEO satellite orbit error fluctuations and verified the method using data from eight sparsely distributed zones.The results show that orbit errors can be stabilized using orbit fluctuation corrections,and the positioning precision and stability of the BDS WADS can be improved simultaneously.Under normal circumstances,the horizontal and vertical positioning accuracy of users within 1000 km from the center of the zone can reach 0.19 m and 0.34 m.Furthermore,the effective range is increased.The positioning performance within 1800 km could reach 0.24 m and 0.38 m for the horizontal and vertical components,respectively.

DEMONSTRATING THE SYNERGY BETWEEN CAC AND SCHEDULING IN WIRELESS NETWORKS

Wireless technology is now an integral part of communication network infrastructure.From their first beginnings,such as connection-oriented General System Mobile networks for voice traffic only and connectionless wireless local area networks for data traffic,new generation wireless networks are connection-oriented and provide differentiated services to the user.With the arrival of more sophisticated services and mobility,have arisen the need for Connection Admission Control and traffic scheduling in the network to enhance the quality of experience(QoE)of the user and optimizing the revenue in dynamic workload environments.A great deal of research effort has gone into the study of the performance of one such network standard,namely the IEEE 802.16 networks.Most optimization studies focus on scheduling(a very mature subject in computing)and ignore connection admission(a very mature subject in telephone engineering)or vice versa.In this paper we claim that one should not study the two in isolation and provide empirical evidence to prove our claim.

Joint admission control algorithm in access network

To deal with long probing delay and inaccurate probing results in the endpoint admission control method,a joint local and end-to-end admission control algorithm is proposed,which introduces local probing of access net-work besides end-to-end probing.Through local probing,the algorithm accurately estimated the resource status of the access network.Simulation shows that this algorithm can improve admission control performance and reduce users’average waiting time when the access network is heavily loaded.