{"title":"Design and reconfiguration of virtual private networks (VPNs) over all-optical WDM networks","authors":"Jun Zheng, Bin Zhou, H. Mouftah","doi":"10.1109/ICCCN.2002.1043133","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043133","url":null,"abstract":"This paper studies the virtual topology design and reconfiguration problem of virtual private networks (VPN) over all-optical WDM networks. We formulate the problem as an integer programming problem with objectives to maximize the network throughput, and to minimize the average end-to-end propagation delay, and to minimize the reconfiguration cost. Load balancing and alternate routing are considered in order to increase the network throughput. A balanced alternate routing algorithm (BARA) is also proposed to obtain approximate optimal solutions to the formulated problem. To make the problem computationally tractable, we assume wavelength converters at network nodes and approximately divide the optimization process into two relatively independent stages: route computing and lightpath routing. To improve the computational efficiency, a genetic algorithm is used in BARA. The effectiveness of BARA is shown through simulation results.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121784599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A design and implementation of active network socket programming","authors":"K. Law, R. Leung","doi":"10.1109/ICCCN.2002.1043049","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043049","url":null,"abstract":"The concept of programmable nodes and active networks introduces programmability into communication networks. Code and data can be sent and modified on their routes to the destinations. Various research groups have designed and implemented their own design platforms. Each design has its own benefits and drawbacks. Moreover, there exists an interoperability problem among platforms. As a result, we introduce a concept that is similar to network socket programming. We intentionally establish a set of simple interfaces for programming active applications. This set of interfaces, known as active network socket programming (ANSP), will be working on top of all other execution environments in the future. Therefore, the ANSP offers a concept that is similar to \"write once, run everywhere\". It is an open programming model that active applications can work on all execution environments. It solves the heterogeneity within active networks. This is especially useful when active applications need to access all regions within a heterogeneous network to deploy a special service at critical points or to monitor the performance of the entire networks. Instead of introducing a new platform, our approach provides a thin, transparent layer on top of existing environments that can be easily installed for all active applications.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116734988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Resource allocation for quality of service provision in buffered crossbar switches","authors":"Qiang Duan, John N. Daigle","doi":"10.1109/ICCCN.2002.1043115","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043115","url":null,"abstract":"We consider the problem of allocation of resources within a buffered crossbar switch with credit-based flow control to support quality of service for traffic flows in the Internet. Specifically, we assume there is a collection of classes of service, each characterized by a strict delay upper bound that applies across all packets of the class. Flows entering the switch are characterized by arrival curves, and the switch must achieve delay objectives subject to the arrival curves. We develop a technique for determining the amount of bandwidth and the number of credits that must be allocated to a flow in order to guarantee its delay requirements. This technique also provides the basis for analyzing the maximum traffic handling capacity of a switch. We provide numerical examples that illustrate the application of our techniques. Finally, we discuss the performance of buffered crossbar switches having finite buffers with respect to that of output buffered switches under the same class of scheduling regimes.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121897905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Routing metrics for best-effort traffic","authors":"S. Gokhale, S. Tripathi","doi":"10.1109/ICCCN.2002.1043132","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043132","url":null,"abstract":"Most of the QoS routing research in the literature attempts to increase the performance of QoS traffic without explicitly considering the performance of the best-effort traffic in the network. However, although the trend in the development and use of real-time multimedia applications is on the rise, traditional data applications are still expected to be a dominant percentage of the Internet traffic. Developing routing schemes for best-effort traffic when it coexists with QoS traffic to provide an acceptable performance to the best-effort traffic is thus critical. In this paper we study the effectiveness of the link utilization metric for routing best-effort traffic in a network that supports both QoS as well as best-effort traffic. The main contribution of this paper lies in demonstrating the feasibility of using the link utilization metric and quantifying the improvement in performance so obtained under various distributions of network load. Our results indicate that utilization based routing of best-effort traffic dynamically adapts to the distribution of the QoS traffic in the network, and demonstrates a significant improvement in the performance of best-effort traffic, when compared to the performance obtained by routing best-effort traffic using the static hop count metric.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"1943 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129144103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Traffic grooming for minimizing wavelength usage in WDM networks","authors":"Deying Li, Zhenqiang Sun, X. Jia, S. Makki","doi":"10.1109/ICCCN.2002.1043106","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043106","url":null,"abstract":"We consider the traffic grooming problem on general topology WDM networks. The problem is: given a set of t connections and their routes, and the grooming factor g, to find an optimal wavelength assignment and grooming such that the number of wavelengths required in the network is minimized. We first formulate this problem as an integer linear programming problem, and then propose a heuristics method to solve it. Our simulation results show that an increase of the grooming factor can considerably decrease the number of wavelengths required in the system.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125705175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dongkyun Kim, J. Garcia-Luna-Aceves, K. Obraczka, Juan-Carlos Cano, P. Manzoni
{"title":"Power-aware routing based on the energy drain rate for mobile ad hoc networks","authors":"Dongkyun Kim, J. Garcia-Luna-Aceves, K. Obraczka, Juan-Carlos Cano, P. Manzoni","doi":"10.1109/ICCCN.2002.1043126","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043126","url":null,"abstract":"Mobile ad hoc networks' (MANETs) inherent power limitation makes power-awareness a critical requirement for MANET protocols. We propose a new routing metric, the drain rate, which predicts the lifetime of a node as a function of current traffic conditions. We describe the minimum drain rate (MDR) mechanism which uses a combination of the drain rate with remaining battery capacity to establish routes. MDR can be employed by any existing MANET routing protocol to achieve a dual goal: extend both nodal battery life and connection lifetime. Using the ns-2 simulator and the dynamic source routing (DSR) protocol, we compared MDR to the minimum total transmission power routing (MTPR) scheme and the min-max battery cost routing (MM-BCR) scheme and proved that MDR is the best approach to achieve the dual goal.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125661443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"On the transient behavior of TCP Vegas","authors":"Sarut Vanichpun, Wu-chun Feng","doi":"10.1109/ICCCN.2002.1043114","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043114","url":null,"abstract":"Research has shown that TCP Vegas performs better than TCP Reno with respect to overall network utilization, stability, fairness, throughput, packet loss, and burstiness. We analyze and improve the transient behavior of TCP Vegas, an important issue in today's large \"bandwidth-delay product\" networks. To quantify of our analysis, we introduce a new metric that captures the transient performance of TCP, namely, the (normalized) convergence time. We then consider the slow-start mechanism in TCP Vegas and show that, with a properly configured /spl gamma/ parameter, the transient behavior of TCP Vegas improves with respect to convergence time.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128955312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Forward-only uni-directional routing","authors":"J. Cobb","doi":"10.1109/ICCCN.2002.1043093","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043093","url":null,"abstract":"Wireless computer networks have properties that differ significantly from traditional wireline networks. One prominent difference is the presence of unidirectional channels. That is, it may be possible for a computer p to send a message to a neighboring computer q, but it may not be possible for computer q to send a message to computer p. This introduces significant changes in routing protocols. In particular, routing protocols that tolerate unidirectional links incur an O(N/sup 2/) message overhead between neighboring nodes, where N is the number of nodes in the network. This is significantly higher than the typical O(N) message overhead in some traditional routing protocols. We present a protocol with an O(N) message overhead even in the presence of unidirectional links. This low overhead comes at the price of not always finding the optimum path. However, the protocol is guaranteed to always find a path between each pair of nodes. Furthermore, the cost of this path is guaranteed not to exceed the cost of the optimal bidirectional path between the nodes.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129318445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"R and D priorities and challenges for optical networking","authors":"B. Mukherjee","doi":"10.1109/ICCCN.2002.1043134","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043134","url":null,"abstract":"Summary form only given. Today, the telecommunication industry is experiencing \"a nuclear winter\". It is a challenging proposition right now to debate research and development (R and D) priorities for optical networking. However, even though the telecommunication market is unsettled today, we need to be ready with appropriate technological solutions to meet the growing bandwidth needs of our information society. Optical networking - using wavelength-division multiplexing (WDM) - is the technology for meeting these demands. While there is a glut of dark fiber and WDM transmission capacity today, we believe that there will be a tremendous need for optical switching equipment for managing high-capacity optical signals. This talk first makes the case for the important role software plays in bringing cost-effective and intelligent optical networking to the marketplace. After providing an overview of telecommunication networks, we discuss promising R and D challenges for optical networking in access and metropolitan areas. Then, we examine the near-term R and D challenges for backbone optical networks: namely, dynamic provisioning of high-capacity connections of different bandwidths, fault management, and topology engineering. Finally, we state R and D priorities over a longer-term horizon.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"34 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131501604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"COPAS: dynamic contention-balancing to enhance the performance of TCP over multi-hop wireless networks","authors":"C. Cordeiro, Samir R Das, D. Agrawal","doi":"10.1109/ICCCN.2002.1043095","DOIUrl":"https://doi.org/10.1109/ICCCN.2002.1043095","url":null,"abstract":"Most studies on TCP over multi-hop wireless ad hoc networks have only addressed the issue of performance degradation due to temporarily broken routes, which results in TCP inability to distinguish between losses due to link failures or congestion. This problem tends to become more serious as network mobility increases. We tackle the equally important capture problem to which there has been little or no solution, and is present mostly in static and low mobility multihop wireless networks. This is a result of the interplay between the MAC layer and TCP backoff policies, which causes nodes to unfairly capture the wireless shared medium, hence preventing neighboring nodes to access the channel. This has been shown to have major negative effects on TCP performance comparable to the impact of mobility. We propose a novel algorithm, called COPAS (COntention-based PAth Selection), which incorporates two mechanisms to enhance TCP performance by avoiding capture conditions. First, it uses disjoint forward (sender to receiver for TCP data) and reverse (receiver to sender for TCP ACKs) paths in order to minimize the conflicts of TCP data and ACK packets. Second, COPAS employs a dynamic contention-balancing scheme where it continuously monitors and changes forward and reverse paths according to the level of MAC layer contention, hence minimizing the likelihood of capture. Through extensive simulation, COPAS is shown to improve TCP throughput by up to 90% while keeping routing overhead low.","PeriodicalId":302787,"journal":{"name":"Proceedings. Eleventh International Conference on Computer Communications and Networks","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133708759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}