The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The increasing availability of 10G Ethernet network capabilities challenges existing transport layer protocols. As 10G connections gain momentum outside of backbone networks, the choice of appropriate TCP congestion control algorithms becomes even more relevant for networked applications running in environments such as data centers. Therefore, we provide an extensive overview of relevant TCP congestion...
The improvement of the scalability of routing decisions is quite relevant in modern telecommunication networks. In this regard, effective approach is associated with the implementation of hierarchical routing. This involves carrying out a structural and functional decomposition of the network, based on the introduction and supporting of multi-level routing decisions. However, the existing protocol...
As the rising applications of Named Data Networking (NDN) continue to increase the demand on network bandwidth, developing effective congestion mechanisms has become one of the high-priority research tasks for NDN architecture. This paper explores rate control protocol (RCP), a unique hop-by-hop feature in NDN routing, and one-to-one relationship between interest requests and data packets to develop...
We have designed and investigated a new congestion control scheme, called the OFEX (Optimal and Fully EXplicit) controller. Different from the existing relatively explicit controllers, this new scheme is able to provide not only optimal bandwidth allocation but also fully explicit congestion signal to sources. It overcomes the drawback of the relatively explicit controllers that “bias” the multi-bottlenecked...
The present situation of current data center network is described, and the existing problems in the data center network is analyzed, according to practical engineering experience, analyzing the switch virtualization and the load equipment bypass deployment model, providing some actual experience for solving existing technological problems in traditional data center.
In this paper, we further evaluate our previously-proposed NewRAPID by comparing with TCP CUBIC and TCP RAPID in the following aspects: intra-protocol fairness, inter-protocol fairness, and convergence time. The result shows that TCP CUBIC provides more intra-protocol fairness than others because of its stability characteristic while TCP RAPID and TCP NewRAPID provide almost the same. Our designed...
Explicit feedback based congestion control schemes can capture network congestion status more accurately than pure end-to-end schemes. However, some of such schemes require modifying IP header in order to achieve near optimal performance, which incurs complicated computation in routers as well as makes them difficult to deploy in real networks. In contrast, the VCP protocol achieves good performance...
The Datagram Congestion Control Protocol (DCCP) protocol was proposed to provide a great variety of functionality to real-time applications. Its congestion control mechanisms were defined to be friendly to the TCP-Reno, which makes its operation inappropriate to high speed networks. In this paper, a variant of the DCCP, called FAST DCCP, is proposed to overcome such deficiency. As evidenced by experimental...
The eXplicit Control Protocol (XCP) is a promising congestion control protocol that outperforms TCP in terms of efficiency, fairness, persistent queue length, and packet loss rate. However, XCP will behave in a noticeably unstable manner if the maximum round trip time of a flow is much larger than average round trip time of all flows, which is a typical nonlinear instability. In this paper, eXCP is...
The problem of fairly distributing the capacity of a network among a set of sessions has been widely studied. In this problem, each session connects via a single path a source and a destination, and its goal is to maximize its assigned transmission rate (i.e., its throughput). Since the links of the network have limited bandwidths, some criterion has to be defined to fairly distribute their capacity...
Since the TCP transmission rate is low during the startup phase, the QoS of various applications is seriously degraded. To improve the TCP transmission rate in the startup phase, many fast startup algorithms have been proposed. In this paper, we evaluate the fundamental performance of fast startup algorithms. Specifically, we focus on the initial window size and Rate-Based Pacing (RBP) start method,...
In Shared Path Protection, backup resources can be shared by multiple backup lightpaths as long as their respective working lightpaths are not affected by the same (single) failure event. This property is known as backup sharing among existing backup paths. The goal of this work is to experimentally evaluate the impact of the traffic dynamics when the control information on resource sharing is either...
The Internet transport layer protocols, TCP and UDP, do not provide an efficient transport for multimedia streams. In despite of that, UDP is often employded for such type of application, due to its low overhead. Since UDP does not implement any kind of congestion control mechanism, it has the potential of hindering Internet operability. To address such issue, a novel transport layer protocol, namely...
Live streaming of video content using overlay networks has gained widespread adoption on the Internet. This paper presents Sepidar, a distributed market-based model, that builds and maintains overlay network trees, which are approximately minimal height, for delivering live media as a number of sub streams. A streaming tree is constructed for each sub stream such that nodes that contribute higher...
Our proposed information-diffusion-based routing (IDBR) is implemented on Tsinghua University's large-scale ASON test-bed. The procedure of IDBR is validated together with RSVP-TE signaling in the experiment. Results show that the IDBR is fast converged and has low bandwidth consumption.
Traditional gossip communications does not consider the difference between nodes in the overlay, and fix the number of node descriptors exchanged during an interaction. It severely reduces the effectiveness of the overlay construction. It takes nodes more time to reach stable state, and when a node achieves stable state, useless node descriptors exchanging incurs extra network bandwidth wasting. This...
While Transmission Control Protocol (TCP) is the most popular transport protocol used in terrestrial networks, its performance is not adequate in wireless networks with long delay, e.g., satellite networks. Though some improvements of TCP and new transport protocols have been proposed, we focus on Variable-structure congestion Control Protocol (VCP) designed for high Bandwidth Delay Product (BDP)...
High-performance sockets implementations such as the Sockets Direct Protocol (SDP) have traditionally showed major performance advantages compared to the TCP/IP stack over InfiniBand (IPoIB). These stacks bypass the kernel-based TCP/IP and take advantage of network hardware features, providing enhanced performance. SDP has excellent performance but limited utility as only applications relying on the...
We propose a novel information-diffusion-based routing (IDBR) scheme in wavelength routed WDM mesh networks. The IDBR scheme has the fast convergence and the low bandwidth consumption of OSPF-TE while requires lower computational complexity as RIP.
Traditional congestion control algorithms exhibit low convergence speed to equilibrium in high BDP (Bandwidth Delay Product) networks. The Fast Max-Min Kelly Control (FMKC) is a new and promising protocol that performs well especially in fairness convergence speed. FMKC utilizes packet loss to switch temporarily into a fairing mode and thereby improve the fairness convergence speed. In this paper,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.