<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css"> Skip to main content

學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作,涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 6 of 6
  • Item type:Item,
    An intelligent buffer management approach for GFR services in IP/ATM internetworks
    (2000-08-30)
    Wang, PC
    ;
    Chan, CT
    ;
    Chen, YC
    ;
    資訊工程學系
    ;
    Department of Computer Science
    In ATM networks, the Guaranteed Frame Rate (GFR) service has been proposed to accommodate non-real-time traffic with packet size not exceeding a maximum length, such as TCP/IP based traffic. The GFR service not only guarantees a minimum throughput at the frame level, but also supports a fair share of available resources. In this article, we propose a buffering strategy called Intelligent Fair Buffer Allocation (IFBA) that provides minimum cell rate (MCR) guarantees and fair sharing to GFR virtual circuits (VCs). From the simulation results, we demonstrate that IFBA fulfills the requirements of GFR service as well as improves the TCP throughput using the FIFO scheduling. (C) 2000 Elsevier Science B.V. All rights reserved.
  • Item type:Item,
    A new locality-based IP multicasting scheme for mobile hosts
    (2001-03-15)
    Tseng, CC
    ;
    Chi, KH
    ;
    Huang, TL
    ;
    資訊工程學系
    ;
    Department of Computer Science
    Internet protocol multicasting is a mechanism widely used in the Internet to disseminate information. Multicast delivery paths may need to be frequently restructured along with host migrations, at the expense of nontrivial overhead or multicast latency. This paper presents a scheme with short multicast latency, while retaining acceptable overhead in adapting the delivery paths to mobile host locations. We exploit the locality in host movements and keep active the networks that mobile hosts have most recently visited. As long as hosts migrate within these active networks, multicast delivery paths can remain unchanged upon host movements. Performance results show that, compared with the best known proposal, our scheme is promising. (C) 2001 Elsevier Science B.V. All rights reserved.
  • Item type:Item,
    Performance enhancement of XCP for high bandwidth-delay product networks
    (2005)
    Yang, YR
    ;
    Chan, CT
    ;
    Wang, PC
    ;
    Chen, YC
    ;
    資訊工程學系
    It has been demonstrated that as the per-flow product of bandwidth delay increases, TCP becomes inefficient and unstable, regardless of the queuing discipline. By decoupling utilization control from fairness control, the eXplicit Control Protocol (XCP) outperforms TCP in both conventional and high bandwidth-delay environments. In this article,. we present an efficient flow control scheme based on XCP for high bandwidth-delay product networks. It can shorten the response time and improve the performance of XCP. Simulation results show the effectiveness of our proposed scheme in several performance aspects. Moreover, its implementation is simple enough to fulfill the required criteria of high bandwidth-delay product networks.
  • Item type:Item,
    Smart window adjustment for XCP's congestion management
    (2006)
    Yang, YR
    ;
    Chan, CT
    ;
    Chen, YC
    ;
    Chan, YC
    ;
    資訊工程學系
    In the large bandwidth-delay product (BDP) networks, it has been demonstrated that the eXplicit Control Protocol, XCP, outperforms TCP and remains efficient, fair, and stable. However, once a packet drop is detected, an XCP's congestion management should follow TCP's Van Jacobson congestion control. In other words, congestion window should be halved and the fast retransmission/fast recovery, congestion avoidance algorithms should be applied. In the mean time, congestion window should be reduced by the value of the negative feedback. In this article, we present a smart window adjustment scheme for XCP's congestion management to shorten the response time and improve network performance.
  • Item type:Item,
    An efficient per-VC accounting-based buffer management scheme for GFR services in TCP/IP networks
    (2005-06-01)
    Lin, PC
    ;
    Chang, CJ
    ;
    電信工程研究所
    ;
    Institute of Communications Engineering
    An efficient per-virtual connection (per-VC) accounting-based scheme with steepest decent weight updating (PASD) algorithm is proposed for buffer management in TCP/IP networks supporting guaranteed frame rate (GFR) services. It can achieve good fairness, high utilization, and low delay. Also it can be implemented by a genuine FIFO architecture and thus easily support up to 10 Gbps STM-64 rate.
  • Item type:Item,
    An IP-decoupling approach to host mobility
    (2007-01-01)
    Wang, Chun-Chieh
    ;
    Chi, Kuang-Hui
    ;
    Tseng, Chien-Chao
    ;
    資訊工程學系
    ;
    Department of Computer Science
    This paper presents the design, implementation, and performance evaluation of an approach to supporting host mobility in the wireless Internet. We observe that a single IP address conventionally serves dual purposes: a network-level routing directive and an endpoint identity of a certain session in transport or upper layers. Therefore, when a host affiliates with a new IP address due to movements, any pre-established active session thereupon suffers outage. Unlike prior schemes exploiting mobility agents, we propose to let a host use two IP addresses for network- and transport-layer identifications, respectively, and introduce a translation table that associates the two identities. Such an association results from querying or dynamic updates to the Domain Name System, or from direct message exchanges between two communication peers so as to optimize delivery paths. Simulation results show that our scheme outperforms counterpart Mobile IP and Mobile IPv6, in terms of communication delay, packet error rate, message space overhead, and potential packet loss during handoffs. Additionally, qualitative discussions conclude that our proposal lends itself to IPv4 and IPv6 interconnected networks, or multi-tier environment such as wireless Local Area Networks and mobile telecommunication overlay systems.