Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 7

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  bandwidth allocation
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
This paper considers reasonable bandwidth allocation for multiclass services in peer-to-peer (P2P) networks, measures the satisfaction of each peer as a customer by a utility function when acquiring one service, and develops an optimization model for bandwidth allocation with the objective of utility maximization. Elastic services with concave utilities are first considered and the exact expression of optimal bandwidth allocation for each peer is deduced. In order to obtain an optimum in distributed P2P networks, we develop a gradient-based bandwidth allocation scheme and illustrate the performance with numerical examples. Then we investigate bandwidth allocation for inelastic services with sigmoidal utilities, which is a nonconvex optimization problem. In order to solve it, we analyze provider capacity provisioning for bandwidth allocation of inelastic services and modify the update rule for prices that service customers should pay. Numerical examples are finally given to illustrate that the improved scheme can also efficiently converge to the global optimum.
2
EN
The paper concerns bandwidth allocation problem on the telecommunication market where there are many sellers and buyers. Sellers offer the bandwidth of telecommunication links. Buyers are interested in the purchase of the bandwidth of several links that makes up an end-to-end connection between two nodes of telecommunication network. We analyze three auction models supporting such a bandwidth exchange: NSP (network second price), BCBT (model for balancing communication bandwidth trading) and BCBT-CG which is a modification of BCBT that applies column generation technique. All of these models concern divisible network resources, treat bandwidth of telecommunication links as an elementary commodity offered for sale, and allow for purchasing bandwidth along multiple paths joining two telecommunication nodes. All of them also aim at maximizing the social welfare. Considered auction models have been compared in the respect of economic and computational efficiency. Experimental studies have been performed on several test instances based on the SNDlib library data sets.
EN
Since the telecommunication market becomes more complex and dynamic, a strong need for a new, efficient and flexible bandwidth trading mechanisms appears. We believe that good mechanisms, that allow effective and fair allocation of bandwidth between market participants will help to develop the real competitive bandwidth market. In this paper we compare two different double-sided bandwidth auction mechanisms, that seem to be well suited approaches for trading indivisible units of bandwidth: combinatorial auction c-SeBiDA and multicommodity mechanism BACBR-I. The c-SeBiDA mechanism considers two types of commodities: inter-node links and paths consisting of particular links. Market participants may bid a single link, or a bundle of links, constituting a specific path. The BACBR-I mechanism is a multicommodity exchange model, that allows bidders to place buy offers not only for individual or bundled links, but rather for end-to-end connections. Therefore, it is the decision model that allocates the most efficient links to connections. We run a large set of experiments to test the allocation and computational efficiency obtained under both approaches.
EN
In this paper we present the multicommodity auction model BCBT-I that allocates indivisible network resources among bidders. The approach can be considered as a generalization of the basic multicommodity model for balancing communication bandwidth trade (BCBT). The BCBT model assumes that offers concerning inter-node links and point-to-point bandwidth demands can be realized partially. However, in the real-world trade there might be a need to include capacity modularity in the market balancing process. Thus we state the model for balancing communication bandwidth trade that takes into account the indivisibility of traded bandwidth modules. This requires to solve a mixed integer problem and increases computational complexity. Furthermore, the pricing issue appears nontrivial, as the dual prices cannot be longer used to set fair, competitive market prices. For clearing the market, we examine the multicommodity pricing mechanizm based on differentiation of buy and sell market prices.
5
Content available remote Comparative evaluation of distributed Bandwidth Broker
EN
The Differentiated Services (DS) framework is one of the basic architectures that have been proposed for provision in the Internet. One of the most significant advantages of DS is ability to distinguish management plane of the network to provide the customer Quality of Service. A DS architecture proposed by IETF alone is not sufficient to address the end-to-end guaranties in a network layer but it does show great potential for scalability. To fulfill negotiated QoS services Bandwidth Broker - an additional management entity, has to be implemented. The main tasks of the Broker are: limiting the traffic volume carried through the managed domain and services nego-tiation on behalf of domain with customers and adjacent brokers. The authors concentrated on the concept of distributed Broker as a more scalable and efficient solution. The different bandwidth allocation scenarios are presented and compared with regard to signaling overhead, admission control delay and control complexity. The quota-based admission control algorithm has been briefly described and discussed. The new style of reservation has been proposed to decrease the amount of signaling traffic between core and edge routers. The example of its functioning has been given at the end of the presented paper.
EN
This paper focuses on performance of channel access methods in the HIPERLAN/2 standard. It discusses commonly used approaches to bandwidth allocation and presents a modified algorithm for effective bandwidth management based on pre-scheduled resource grants. Simulation results show that the new algorithm ensures much higher throughput compared to the standard method.
EN
The main goal of this work is to develop a computational framework in the context of the bandwidth needs for traffic generated in a distributed multimedia environment. Conceived as a groupware system able to run real-time applications, which model complex phenomena like multimedia applications which integrate audio, video and data and ensure parallel processing, this framework appear as a higher-level Computer Supported Collaborative Work (CSCW) system. For this purpose a specific platform architecture was proposed, that uses for communications between members real-time dependable (RTD) channels, a communication-oriented abstraction that can be configured to meet the QoS requirements of a variety of distributed applications. This customization ability is based in the construction of middle-ware services out of software modules called micro-protocols. Each micro-protocol implements a different semantic property or property variant and interacts with other micro-protocols using an event-driven model. On the platform prototype was tested a resource allocation protocol that uses a combination of bandwidth reservation and bandwidth borrowing to provide network uses with QoS in terms of guaranteed bandwidth, call blocking, and call dropping probabilities. Quite the first experiments were executed on a cluster of Pentium PCs, the final goal is to use wireless channels in order to value the additional flexibility afforded by the ability of multimedia applications to tolerate and adapt to transient changes in QoS and to ensure agent's mobility. Some preliminary simulation results are also presented.
PL
Zasadniczym celem artykułu jest przedstawienie platformy obliczeniowej uwzględniającej wymagania dotyczące pasma do przenoszenia ruchu w rozproszonym środowisku multimedialnym. Platforma ta została przemyślana jako system pracy grupowej zdolny do realizacji aplikacji w czasie rzeczywistym, które modelują złożone zjawiska. Aplikacje te mogą mieć charakter zintegrowany, łącząc elementy audio, video i klasycznych danych, mogą być wykonywane w sposób równoległy. Platforma należy do kategorii wyższego poziomu systemów Computer Supported Collaborative (CSCW). Do realizacji platformy posłużono się specjalną architekturą, która dla zapewnienia komunikacji pomiędzy uczestnikami używa zależnościowych kanałów czasu rzeczywistego (RTD) i abstrakcji zorientowanych na komunikację, skonfigurowanych tak, że możliwe jest spełnienie wymagań jakościowych dotyczących usług (QoS) dla szerokiej palety aplikacji. Lokalizacje platformy można łatwo wykonać dzięki wykorzystaniu serwisów warstwy pośredniej nazywanych mikro-protokołami. Każdy mikro-protokół realizuje inną własność semantyczną lub jej wariant oraz może współdziałać z innymi mikro-protokołami korzystając z modelu definiowanego zdarzeniami (eventdriven). Platforma posłużyła do testowania protokołu alokacji zasobów, który korzysta z rezerwacji i "pożyczania" pasma w celu zapewnienia żądanej jakości usług (QoS), zwłaszcza w obszarze zagwarantowaniu pasma, blokowania wywołań oraz prawdopodobieństw odrzucenia odwołań. Eksperymenty zostały przeprowadzone na komputerze klastrowym Pentium PC. Planuje się użycie kanałów łączności bezprzewodowej w celu oceny zdolności aplikacji multimedialnych do tolerowania i adaptowania się do przejściowych zmian w zakresie jakości wymaganych usług (QoS) oraz zapewnienia mobilności wykorzystywanego w rozwiązaniu agenta. Pierwsze symulacje w tym zakresie przyniosły zachęcające wyniki.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.