A number of recent empirical studies of traffic measurements from a variety of working packet networks have convincingly demonstrated that actual network traffic is self-similar or long-range dependent in nature (i.e., bursty over a wide range of time scales) -- in sharp contrast to commonly made traffic modeling assumptions. In this paper, we provide a plausible physical explanation for the occurrence of self-similarity in LAN traffic. Our explanation is based on new convergence results for processes that exhibit high variability (i.e., infinite variance) and is supported by detailed statistical analyses of real-time traffic measurements from Ethernet LAN's at the level of individual sources. This paper is an extended version of [53] and differs from it in significant ways. In particular, we develop here the mathematical results concerning the superposition of strictly alternating ON/OFF sources. Our key mathematical result states that the superposition of many ON/OFF sources (also k...

Interact hosting centers serve multiple service sites from a common hardware base. This paper presents the design and implementation of an architecture for resource management in a hosting center op-erating system, with an emphasis on energy as a driving resource management issue for large server clusters. The goals are to provi-sion server resources for co-hosted services in a way that automati-cally adapts to offered load, improve the energy efficiency of server dusters by dynamically resizing the active server set, and respond to power supply disruptions or thermal events by degrading service in accordance with negotiated Service Level Agreements (SLAs). Our system is based on an economic approach to managing shared server resources, in which services "bid " for resources as a func-tion of delivered performance. The system continuously moni-tors load and plans resource allotments by estimating the value of their effects on service performance. A greedy resource allocation algorithm adjusts resource prices to balance supply and demand, allocating resources to their most efficient use. A reconfigurable server switching infrastructure directs request traffic to the servers assigned to each service. Experimental results from a prototype confirm that the system adapts to offered load and resource avail-ability, and can reduce server energy usage by 29 % or more for a typical Web workload. 1.

Existing approaches for providing guaranteed services require routers to manage per ow states and perform per ow operations [9, 21]. Such a stateful network architecture is less scalable and robust than stateless network architectures like the original IP and the recently proposed Di serv [3]. However, services provided with current stateless solutions, Di serv included, have lower exibility, utilization, and/or assurance level as compared to the services that can be provided with per ow mechanisms. In this paper, we propose techniques that do not require per ow management (either control or data planes) at core routers, but can implement guaranteed services with levels of exibility, utilization, and assurance similar to those that can be provided with per ow mechanisms. In this way we can simultaneously achieve high quality of service, high scalability and robustness. The key technique we use is called Dynamic Packet State (DPS), which provides a lightweight and robust mechanism for routers to coordinate actions and implement distributed algorithms. We present an implementation of the proposed algorithms that has minimum incompatibility with IPv4.

Transmission of multimedia streams imposesa minimum-bandwidth requirementon the path being used to ensureend-to-end Quality-ofService (QoS) guarantees. While any shortest-path algorithm can be used to select a feasible path, additional constraints that limit resource consumption and balance the network load are needed to achieve efficient resource utilization. We present a systematic evaluation of four routing algorithms that offer different tradeoffs between limiting the path hop count and balancing the network load. Our evaluation considers not only the call blocking rate but also the fairness to requests for different bandwidths, robustness to inaccurate routing information, and sensitivity to the routing information update frequency. It evaluates not only the performance of these algorithms for the sessions with bandwidth guarantees, but also their impact on the lower priority best-effort sessions. Our results show that a routing algorithm that gives preference to limiting the hop ...

Variable bit-rate (VBR) compressed video traffic is expected to be a significant component of the traffic mix in integrated services networks. This traffic is hard to manage because it has strict delay and loss requirements while simultaneously exhibiting burstiness at multiple time scales. We show that burstiness over long time scales, in conjunction with resource reservation using one-shot traffic descriptors, can substantially degrade the loss rate, end-to-end delay, and statistical multiplexing gain of a connection. We use large-deviation theory to model the performance of multiple time-scale traffic and to motivate the design of renegotiated constant bit rate (RCBR) service. Sources using

In just a few years the "Internet Multicast Backbone", or MBone, has risen from a small, research curiosity to a large scale and widely used communications infrastructure. A driving force behind this growth was our development of multipoint audio, video, and shared whiteboard conferencing applications that are now used daily by the large and growing MBone community. Because these real-time media are transmitted at a uniform rate to all the receivers in the network, the source must either run below the bottleneck rate or overload portions of the multicast distribution tree. In this dissertation, we propose a solution to this problem by moving the burden of rate-adaptation from the source to the receivers with a scheme we call Receiver-driven Layered Multicast, or RLM. In RLM, a source distr...

In networks that support Quality of Service (QoS), an admission control algorithm determines whether or not a new traffic flow can be admitted to the network such that all users will receive their required performance. Such an algorithm is a key component of future multi-service networks as it determines the extent to which network resources are utilized and whether the promised QoS parameters are actually delivered. Our goals in this paper are threefold. First, we describe and classify a broad set of proposed admission control algorithms. Second, we evaluate the accuracy of these algorithms via experiments using both on-off sources and long traces of compressed video; we compare the admissible regions and QoS parameters predicted by our implementations of the algorithms with those obtained from trace-driven simulations. Finally, we identify the key aspects of an admission control algorithm necessary for achieving a high degree of accuracy and hence a high statistical multiplexing gain...

This paper describes the design, implementation, and experimental evaluation of OverQoS, an overlay-based architecture for enhancing the best-effort service of today's Internet. Using a Controlled loss virtual link (CLVL) abstraction to bound the loss rate observed by a traffic aggregate, OverQoS can provide a variety of services including: (a) smoothing packet losses; (b) prioritizing packets within an aggregate; (c) statistical loss and bandwidth guarantees.

RSVP has been designed to support resource reservation in the Internet. However, it has two major problems: complexity and scalability. The former results in large message processing overhead at end systems and routers, and inefficient firewall processing at the edge of the network. The latter implies that in a backbone environment, the amount of bandwidth consumed by refresh messages and the storage space that is needed to support a large number of flows at a router are too large. We have developed a new reservation mechanism that simplifies the process of establishing reserved flows while preserving many unique features introduced by RSVP. Simplicity is measured in terms of control message processing, data packet processing, and user-level flexibility. Features such as robustness, advertising network service availability and resource sharing among multiple senders are also supported in the proposal. The proposed mechanism, YESSIR (YEt another Sender Session Internet Reservations) generates reservation requests by senders to reduce the processing overhead, builds on top of RTCP, uses soft state to maintain reservation states, supports shared reservation and associated flow merging and is compatible with the IETF Integrated Services models. YESSIR extends the all-or-nothing reservation model to support partial reservations that improve over the duration of the session. To address the scalability issue, we investigate the possibility of using YESSIR for per-stream reservation and RSVP for aggregate reservation.

This paper describes a framework for admission control for a packet-based network where the decisions are taken by edge devices or end-systems, rather than resources within the network. The decisions are based on the results of probe packets that the end-systems send through the network, and require only that resources apply a mark to packets in a way that is load dependent. One application example is the Internet, where marking information is fed back via an ECN bit, and we show howthis approach allows a rich QoS framework for ows or streams. Our approach allows networks to be explicitly analysed, and consequently engineered.