Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.938148
K. Segaric, P. Knezevic, B. Blašković
This paper considers stability problems regarding topology produced by a spanning tree algorithm in transparent bridged networks, and presents an approach to build a stable spanning tree structure that is not dependent on a root bridge. This approach relies on tuning spanning-tree port cost in a way that the produced topology resists possible attacks or newly connected misconfigured bridges. Special care was taken to ensure stability in transition periods, where bridges negotiate about a new root. This approach is completely standards-based and requires only that is possible to tune link costs of switch/bridge ports.
{"title":"An approach to build stable spanning tree topology","authors":"K. Segaric, P. Knezevic, B. Blašković","doi":"10.1109/EURCON.2001.938148","DOIUrl":"https://doi.org/10.1109/EURCON.2001.938148","url":null,"abstract":"This paper considers stability problems regarding topology produced by a spanning tree algorithm in transparent bridged networks, and presents an approach to build a stable spanning tree structure that is not dependent on a root bridge. This approach relies on tuning spanning-tree port cost in a way that the produced topology resists possible attacks or newly connected misconfigured bridges. Special care was taken to ensure stability in transition periods, where bridges negotiate about a new root. This approach is completely standards-based and requires only that is possible to tune link costs of switch/bridge ports.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121827470","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937796
Chung Chi, Chengpeng Fu, Liew Soung Chang
TCP Veno (see Fu ChengPeng et al., "TCP Veno: Equilibrium-oriented End-to-end Congestion Control over Heterogeneous Networks", http://www.broadband.ie.cuhk.edu.hk) is a new TCP version that employs the refined AIMD (additive increase and multiplicative decrease) congestion control algorithm with its implementation only on the sending side. In addition to achieving significant throughput improvement over TCP Reno (particularly in wireless networks), Veno shows good compatibility and flexibility in heterogeneous networks. In this paper, we demonstrate the benefits of combining the retransmission strategy of SACK (selective acknowledgement) option with TCP Veno's congestion control mechanism. Our implementation is referred as SACK TCP/sub Veno/, similar to the definition of SACK TCP given by K. Fall and S. Floyd (see "Simulation-based Comparisons of Tahoe, Reno, and SACK TCP", Computer Communication Review, July 1996), which refines the recovery strategy of Reno by using the SACK option (see Mathis, M. et al., "TCP Selective Acknowledgement Options", RFC 2018, IETF, October 1996). By means of simulation and real network experiments, we demonstrate that SACK TCP/sub Veno/ can obtain a satisfactory throughput improvement over SACK TCP. Also, we show SACK TCP/sub Veno/'s compatibility with SACK TCP.
{"title":"Improvements achieved by SACK employing TCP Veno equilibrium-oriented mechanism over lossy networks","authors":"Chung Chi, Chengpeng Fu, Liew Soung Chang","doi":"10.1109/EURCON.2001.937796","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937796","url":null,"abstract":"TCP Veno (see Fu ChengPeng et al., \"TCP Veno: Equilibrium-oriented End-to-end Congestion Control over Heterogeneous Networks\", http://www.broadband.ie.cuhk.edu.hk) is a new TCP version that employs the refined AIMD (additive increase and multiplicative decrease) congestion control algorithm with its implementation only on the sending side. In addition to achieving significant throughput improvement over TCP Reno (particularly in wireless networks), Veno shows good compatibility and flexibility in heterogeneous networks. In this paper, we demonstrate the benefits of combining the retransmission strategy of SACK (selective acknowledgement) option with TCP Veno's congestion control mechanism. Our implementation is referred as SACK TCP/sub Veno/, similar to the definition of SACK TCP given by K. Fall and S. Floyd (see \"Simulation-based Comparisons of Tahoe, Reno, and SACK TCP\", Computer Communication Review, July 1996), which refines the recovery strategy of Reno by using the SACK option (see Mathis, M. et al., \"TCP Selective Acknowledgement Options\", RFC 2018, IETF, October 1996). By means of simulation and real network experiments, we demonstrate that SACK TCP/sub Veno/ can obtain a satisfactory throughput improvement over SACK TCP. Also, we show SACK TCP/sub Veno/'s compatibility with SACK TCP.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116939325","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.938118
M. Štefanec, I. Benc, S. Srbljic
Proxy caches in classical server-client architecture may decrease the amount of data transfer and reduce network congestion, hut they also impose a cache-coherence problem. Objects replicated in proxy caches must be kept coherent. Although various protocols for maintaining cache coherence in the World Wide Web (WWW) have been introduced, there does not exist a highly efficient solution to the coherence problem. We have designed a new hybrid self-adaptive protocol (hSATTL) for maintaining cache coherence. The protocol dynamically switches between three basic cache coherence mechanisms: server-oriented write-invalidate, server-oriented write-update, and proxy-oriented time-to-live (TTL). We describe the implementation of the hSATTL protocol and compare it to other currently used protocols. In order to perform measurements, we also develop a special software package. As performance measures, we use the level of coherence maintained by the protocols and the amount of network traffic generated by the protocols in order to maintain cache coherence.
{"title":"Hybrid self-adaptive WWW cache coherence protocol (hSATTL): improving the coherence of WWW objects","authors":"M. Štefanec, I. Benc, S. Srbljic","doi":"10.1109/EURCON.2001.938118","DOIUrl":"https://doi.org/10.1109/EURCON.2001.938118","url":null,"abstract":"Proxy caches in classical server-client architecture may decrease the amount of data transfer and reduce network congestion, hut they also impose a cache-coherence problem. Objects replicated in proxy caches must be kept coherent. Although various protocols for maintaining cache coherence in the World Wide Web (WWW) have been introduced, there does not exist a highly efficient solution to the coherence problem. We have designed a new hybrid self-adaptive protocol (hSATTL) for maintaining cache coherence. The protocol dynamically switches between three basic cache coherence mechanisms: server-oriented write-invalidate, server-oriented write-update, and proxy-oriented time-to-live (TTL). We describe the implementation of the hSATTL protocol and compare it to other currently used protocols. In order to perform measurements, we also develop a special software package. As performance measures, we use the level of coherence maintained by the protocols and the amount of network traffic generated by the protocols in order to maintain cache coherence.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120854724","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937761
K. Soyjaudah, B. Rajkumarsingh
An adaptive forward error control and modulation scheme is proposed for slow Rayleigh fading channels. The adaptive scheme employs a family of RS codes of different rates and multiple phase shift keying (MPSK) modulation schemes according to the states of the channel. This uses a channel estimator to select the most appropriate codulation (coded-modulation) scheme. Simulation results show that the adaptive scheme gives significant improvement in the BER and throughput performance.
{"title":"Adaptive coding and modulation using Reed Solomon codes for Rayleigh fading channels","authors":"K. Soyjaudah, B. Rajkumarsingh","doi":"10.1109/EURCON.2001.937761","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937761","url":null,"abstract":"An adaptive forward error control and modulation scheme is proposed for slow Rayleigh fading channels. The adaptive scheme employs a family of RS codes of different rates and multiple phase shift keying (MPSK) modulation schemes according to the states of the channel. This uses a channel estimator to select the most appropriate codulation (coded-modulation) scheme. Simulation results show that the adaptive scheme gives significant improvement in the BER and throughput performance.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127180245","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.938182
M. Otta, S. Racek
The paper presents a method which can be used to verify properties of asynchronous distributed algorithms and programs during their execution. The method can detect an occurrence of either stable global predicates or unstable strong or weak global predicates which are a conjunction of locally detectable predicates. Unstable predicates can be detected even if the observed run of the distributed program does not contain global states which fulfil the predicate. An example of a CORBA-based distributed debugger implementation serves as a feasibility study of the presented method.
{"title":"A method for testing and debugging distributed applications","authors":"M. Otta, S. Racek","doi":"10.1109/EURCON.2001.938182","DOIUrl":"https://doi.org/10.1109/EURCON.2001.938182","url":null,"abstract":"The paper presents a method which can be used to verify properties of asynchronous distributed algorithms and programs during their execution. The method can detect an occurrence of either stable global predicates or unstable strong or weak global predicates which are a conjunction of locally detectable predicates. Unstable predicates can be detected even if the observed run of the distributed program does not contain global states which fulfil the predicate. An example of a CORBA-based distributed debugger implementation serves as a feasibility study of the presented method.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124992794","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937805
C.S. Hutchison
The E-FOLIO and NetPro projects confront problems in knowledge acquisition and management by individuals and in e-learning teams. This paper seeks to clarify the epistemological issues and to propose a model for managing personal and shared knowledge.
{"title":"Personal knowledge, team knowledge, real knowledge","authors":"C.S. Hutchison","doi":"10.1109/EURCON.2001.937805","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937805","url":null,"abstract":"The E-FOLIO and NetPro projects confront problems in knowledge acquisition and management by individuals and in e-learning teams. This paper seeks to clarify the epistemological issues and to propose a model for managing personal and shared knowledge.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126749656","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.938109
C. Ripoll, D. Miller, S. Vachet
The aim is to create a complete environment for the design and testing of an instructional set of boards for the HF transmission of digital data in QPSK or OQPSK modulation format. During the 30 hours of the study, the electrical engineering student must simulate with MACHXL/sup TM/, Matlab/sup TM/ and HPADS/sup TM/ the digital and HF parts of the six boards constituting the link. The tests and measurements are done under a graphical environment developed with Delphi/sup TM/ that allows the validation of the critical points encountered during the circuit and system design steps.
{"title":"Evaluation board for education of engineers in wireless communications","authors":"C. Ripoll, D. Miller, S. Vachet","doi":"10.1109/EURCON.2001.938109","DOIUrl":"https://doi.org/10.1109/EURCON.2001.938109","url":null,"abstract":"The aim is to create a complete environment for the design and testing of an instructional set of boards for the HF transmission of digital data in QPSK or OQPSK modulation format. During the 30 hours of the study, the electrical engineering student must simulate with MACHXL/sup TM/, Matlab/sup TM/ and HPADS/sup TM/ the digital and HF parts of the six boards constituting the link. The tests and measurements are done under a graphical environment developed with Delphi/sup TM/ that allows the validation of the critical points encountered during the circuit and system design steps.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"233 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115015926","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937766
M. Ashibani, D. Mashao, B. Nleya
The use of high-speed networks to carry bursty traffic, such as IP packets, image, compressed video etc., over ATM networks, requires a new thinking. Instead of controlling connections, we are faced with the problem of controlling the bursts. Thus the new problem is how to control the bursts and how the resources are allocated optimally for the bursty applications. This paper provides performance analysis of a burst level bandwidth allocation algorithm based on multipath/multilinks routing to allocate resources efficiently for real time traffic, where fast reservation of resources in the network is crucial, as the resource availability changes rapidly. In this scheme, different predetermined paths are searched for the extra required resources to accommodate bursts from real time applications in multiple path routes. In the paper, the performance of multipath routing is compared to a single path reservation approach without reattempt (i.e., retry after a failure) and with reattempt allowed. The main performance metrics considered in this paper are network throughput, blocking probability and reservation time delay. The analysis shows that while the multipath reservation algorithm has better performance compared to single path reservation algorithms (either persistent or non persistent), the burst-by-burst connection setup time using multipath reservation is significantly lower than for the single path reservation approaches.
{"title":"Performance analysis of burst level bandwidth allocation using multipath routing reservation","authors":"M. Ashibani, D. Mashao, B. Nleya","doi":"10.1109/EURCON.2001.937766","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937766","url":null,"abstract":"The use of high-speed networks to carry bursty traffic, such as IP packets, image, compressed video etc., over ATM networks, requires a new thinking. Instead of controlling connections, we are faced with the problem of controlling the bursts. Thus the new problem is how to control the bursts and how the resources are allocated optimally for the bursty applications. This paper provides performance analysis of a burst level bandwidth allocation algorithm based on multipath/multilinks routing to allocate resources efficiently for real time traffic, where fast reservation of resources in the network is crucial, as the resource availability changes rapidly. In this scheme, different predetermined paths are searched for the extra required resources to accommodate bursts from real time applications in multiple path routes. In the paper, the performance of multipath routing is compared to a single path reservation approach without reattempt (i.e., retry after a failure) and with reattempt allowed. The main performance metrics considered in this paper are network throughput, blocking probability and reservation time delay. The analysis shows that while the multipath reservation algorithm has better performance compared to single path reservation algorithms (either persistent or non persistent), the burst-by-burst connection setup time using multipath reservation is significantly lower than for the single path reservation approaches.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114512051","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937756
K. Jagath-Kumara
In digital communication links, data is transmitted in blocks referred to as frames and the frame error status is the most important link parameter which determines the throughput. In this paper, a real-time method for estimating the reliability of data frames is presented. Attention is given to those methods that use only the decoder metrics of the coded-modulation scheme which is employed by the link. It is shown that improved accuracy in estimation can be obtained by processing properly modified decoder metrics. The methods are applicable for both block-coded and convolutionally-coded modulation schemes.
{"title":"A new frame error estimation criterion for digital communication links","authors":"K. Jagath-Kumara","doi":"10.1109/EURCON.2001.937756","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937756","url":null,"abstract":"In digital communication links, data is transmitted in blocks referred to as frames and the frame error status is the most important link parameter which determines the throughput. In this paper, a real-time method for estimating the reliability of data frames is presented. Attention is given to those methods that use only the decoder metrics of the coded-modulation scheme which is employed by the link. It is shown that improved accuracy in estimation can be obtained by processing properly modified decoder metrics. The methods are applicable for both block-coded and convolutionally-coded modulation schemes.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121919024","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}
Pub Date : 2001-07-04DOI: 10.1109/EURCON.2001.937774
M. Nibouche, A. Bouridane, O. Nibouche
FPGA technology offers an attractive combination of low cost and high performance combined with an apparent flexibility. Although the programming model, which FPGA typically present to signal/image processing application developers, is prohibitively low-level, they remain very good target devices for rapid prototyping. The purpose of this paper is to present a methodology for rapid prototyping of biorthogonal wavelet transforms on FPGA. The methodology is based on an adequate partitioning of a bit-serial, time-interleaved "wait cycles" free architecture. The efficiency of the approach has been verified on the Xilinx 4000 FPGA series.
{"title":"Design and FPGA implementation of biorthogonal discrete wavelet transforms","authors":"M. Nibouche, A. Bouridane, O. Nibouche","doi":"10.1109/EURCON.2001.937774","DOIUrl":"https://doi.org/10.1109/EURCON.2001.937774","url":null,"abstract":"FPGA technology offers an attractive combination of low cost and high performance combined with an apparent flexibility. Although the programming model, which FPGA typically present to signal/image processing application developers, is prohibitively low-level, they remain very good target devices for rapid prototyping. The purpose of this paper is to present a methodology for rapid prototyping of biorthogonal wavelet transforms on FPGA. The methodology is based on an adequate partitioning of a bit-serial, time-interleaved \"wait cycles\" free architecture. The efficiency of the approach has been verified on the Xilinx 4000 FPGA series.","PeriodicalId":205662,"journal":{"name":"EUROCON'2001. International Conference on Trends in Communications. Technical Program, Proceedings (Cat. No.01EX439)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116605027","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：