4 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 4 / 4
Yayın A priority based packet scheduler with deadline considerations(IEEE Computer Soc, 2006) Dağ, Tamer; Gökgöl, OralQoS issues have become a focal point of research on Next Generation Networks (NGNs). In order to supply the various QoS requirement for different kinds of applications, new scheduling policies need to be developed and evaluated. This paper introduces a new kind of packet scheduler which tries to integrate an important QoS parameter (the delay) with the classical schedulers. The two sets of algorithms introduced; Static Priority with Deadline Considerations (SPD) and Dynamic Priority with Deadline Considerations (DPD); not only simplify the complexity and overhead of a classical Earliest Deadline First (EDF) or Static Priority (SP) algorithm, but also provide a better QoS based on the results of the simulations conducted.Yayın SPD (Static Priority with Deadline considerations) packet scheduling algorithm for achieving better QoS(IEEE, 2007) Dağ, TamerProviding quality of service (QoS) to applications with different traffic characteristics based on their needs is an important research area for today's and tomorrow's high speed networks. Various techniques have been proposed to achieve good QoS for diverse application types. Among these techniques, packet scheduling algorithms decide on how to process packets at network nodes; however they have limited support for better QoS. In order to supply the various QoS requirements for different kinds of applications, new scheduling policies need to be developed and evaluated. This paper proposes a new kind of packet scheduling algorithm, Static Priority with Deadline Considerations (SPD), which integrates an important QoS parameter (the delay) into the classical static priority packet scheduling algorithm and analyses the packet losses by considering the two different components of losses; buffer overflows and deadline violations. The proposed algorithm not only reduces the complexity of the static priority algorithm by introducing degree sorting but also solves the starving problem and provides fairness to applications with different priorities.Yayın The modified proactive feedback based flow control scheme for best-effort applications(International Institute of Informatics and Systemics (IIIS), 2007) Dağ, TamerHigh speed networks that are characterized by large bandwidth propagation delay products are expected to support applications with diverse traffic characteristics and Quality of Service (QoS) requirements. Thus, flow control schemes are needed for an efficient usage of the network bandwidth. A proactive feedback (PF) based flow control scheme developed by the author attempts to eliminate the bandwidth mismatch problem seen in such networks by generating and transmitting early feedbacks based on the application characteristics. In this paper, an extension of this scheme to large scale networks is presented. Due to the bottlenecked network nodes, some best effort applications may not be able to use their assigned bandwidth. For such cases, a modified version of the proactive feedback based (MPF) flow control scheme is introduced. It is observed that without affecting the other applications the best effort traffic can be significantly increased.Yayın QoS-constrained core selection for group communication(IEEE, 2005) Karaman, Ayşe; Hassanein, HossamThe core-based approach in multipoint communication enhances the solution space in terms of QoS-efficiency of solutions in inter and intra-domain routing. In an earlier work [KH04], we showed that the constrained cost minimization solutions in core-based approach proposed to date are restrictive in their search to a subrange of solutions, and we proposed SPAN, a generic framework to process in our identified extended solution space. In this paper, we study the core selection component of SPAN and propose two novel algorithms, SPAN/COST and SPAN/ADJUST, which define the core-selection component of SPAN. SPAN/COST mainly optimizes the cost distances to be traveled between the source-core and core-receiver pairs on the multicast trees, while SPAN/ADJUST selects the cores based on the numbers of nodes they dominate and adjusting the set based on cost. Our algorithms consistently outperform their counterparts proposed to date and can be considered pioneering in their optimization range of multiple metrics and processing in the extended solution space.
