Atomic commitment protocols are needed to preserve ACID properties of distributed transactional systems. The performance of such protocols is essential to avoid adding too much overhead to transaction processing. Also, many applications require levels of availability, which cannot be met by using only one backup source (disk or process). Combining these two requirements, this paper presents protocols for use with main memory primary-backup systems, where there are multiple backup processes for each primary. These protocols are evaluated by simulation and verified by statistical analysis. The results show that the best choice of protocol is not static, but varies with the transactional load of the system.
{"title":"Main Memory Commit Protocols for Multiple Backups","authors":"Heine Kolltveit, Svein-Olaf Hvasshovd","doi":"10.1109/ICN.2008.39","DOIUrl":"https://doi.org/10.1109/ICN.2008.39","url":null,"abstract":"Atomic commitment protocols are needed to preserve ACID properties of distributed transactional systems. The performance of such protocols is essential to avoid adding too much overhead to transaction processing. Also, many applications require levels of availability, which cannot be met by using only one backup source (disk or process). Combining these two requirements, this paper presents protocols for use with main memory primary-backup systems, where there are multiple backup processes for each primary. These protocols are evaluated by simulation and verified by statistical analysis. The results show that the best choice of protocol is not static, but varies with the transactional load of the system.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126365942","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}
This paper describes a new way of implementing converged wireless network and service management system using XML as the management message language and SOAP/HTTP as the protocols for configuration, performance, fault and alarm communication between network operation and maitenance (O&M) system and network elements (NE) and service provider's service production systems. Principles described in this article are fully tested and applicable and can be exploited in any current network and service management system.
{"title":"XML Based 3G/LTE Network and Service Management Concept","authors":"E. Wallenius, T. Hämäläinen, Kari Halttunen","doi":"10.1109/ICN.2008.23","DOIUrl":"https://doi.org/10.1109/ICN.2008.23","url":null,"abstract":"This paper describes a new way of implementing converged wireless network and service management system using XML as the management message language and SOAP/HTTP as the protocols for configuration, performance, fault and alarm communication between network operation and maitenance (O&M) system and network elements (NE) and service provider's service production systems. Principles described in this article are fully tested and applicable and can be exploited in any current network and service management system.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121396630","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}
The border gateway protocol (BGP) routing system is one of the key components of today's Internet infrastructure. However, the fundamentals of the BGP routing system have remained unchanged since its standardization. The only fault tolerant mechanism currently available is multihoming, which is about increasing the number of peering autonomous systems (ASes). The reliability of the BGP infrastructure is highly dependent on the statically configured links provided by multihoming, and recovery from larger failures requires cooperation among operators in both parties. Such manual process is problematic, especially during disasters, as it severely delays recovery. As a solution to the problem, this paper proposes a novel on-demand BGP peering method to offer ASes the ability to autonomously and dynamically recover from failures. We introduce a new peering model where peering is established only upon failures. These peers are discovered dynamically and peering is established without any prior configuration. Through evaluation using a prototype implementation, the proposed on-demand BGP peering method provided recovery within 3 seconds of the time of the BGP hold timer expiration. The method is designed to ensure applicability to current ASes with flexibility and adaptability to various failures, contributing toward improving the sustainability of ASes.
{"title":"Improving the Sustainability of Autonomous Systems","authors":"M. Watari, Y. Hei, S. Ano, K. Yamazaki","doi":"10.1109/ICN.2008.24","DOIUrl":"https://doi.org/10.1109/ICN.2008.24","url":null,"abstract":"The border gateway protocol (BGP) routing system is one of the key components of today's Internet infrastructure. However, the fundamentals of the BGP routing system have remained unchanged since its standardization. The only fault tolerant mechanism currently available is multihoming, which is about increasing the number of peering autonomous systems (ASes). The reliability of the BGP infrastructure is highly dependent on the statically configured links provided by multihoming, and recovery from larger failures requires cooperation among operators in both parties. Such manual process is problematic, especially during disasters, as it severely delays recovery. As a solution to the problem, this paper proposes a novel on-demand BGP peering method to offer ASes the ability to autonomously and dynamically recover from failures. We introduce a new peering model where peering is established only upon failures. These peers are discovered dynamically and peering is established without any prior configuration. Through evaluation using a prototype implementation, the proposed on-demand BGP peering method provided recovery within 3 seconds of the time of the BGP hold timer expiration. The method is designed to ensure applicability to current ASes with flexibility and adaptability to various failures, contributing toward improving the sustainability of ASes.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127383277","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}
A novel blind constant modulus algorithm (CMA) for phase modulation signals is proposed. Compared with the CMAs before, this method, which exploits the relative phase information concealed in the M-PSK signals, has the ability to detect the types of modulation without the training information. Furthermore, this idea can apply to the continuous-varying modulation scheme systems. With the detected modulation scheme, the received signals can be recovered correctly. Simulation results prove the superiority of this new method.
{"title":"Adapting Constant Modulus Algorithm for Phase Modulation Signals","authors":"Xin Wang, G. Feng","doi":"10.1109/ICN.2008.11","DOIUrl":"https://doi.org/10.1109/ICN.2008.11","url":null,"abstract":"A novel blind constant modulus algorithm (CMA) for phase modulation signals is proposed. Compared with the CMAs before, this method, which exploits the relative phase information concealed in the M-PSK signals, has the ability to detect the types of modulation without the training information. Furthermore, this idea can apply to the continuous-varying modulation scheme systems. With the detected modulation scheme, the received signals can be recovered correctly. Simulation results prove the superiority of this new method.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116578135","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}
We propose and evaluate fast reservation (FR) protocols for optical burst switched (OBS) networks. The proposed reservation schemes aim at reducing the end-to-end delay of a data burst, by sending the burst header packet (BHP) in the core network before the burst assembly is completed at the ingress node. We use linear prediction filters to estimate the expected length of the burst and the time needed for the burstification process to complete. A BHP packet carrying these estimates is sent before burst completion, in order to reserve bandwidth at each intermediate node for the time interval the burst is expected to pass from that node. Reducing the total time needed for a packet to be transported over an OBS network is important, especially for real-time applications. Reserving bandwidth only for the time interval it is actual going to be used by a burst is important for network utilization efficiency. In the simulations conducted we evaluate the proposed extensions and prove their usefulness.
{"title":"Fast Reservation Protocols for Latency Reduction in Optical Burst-Switched Networks Based on Predictions","authors":"Kyriaki Seklou, Emmanouel Varvarigos","doi":"10.1109/ICN.2008.90","DOIUrl":"https://doi.org/10.1109/ICN.2008.90","url":null,"abstract":"We propose and evaluate fast reservation (FR) protocols for optical burst switched (OBS) networks. The proposed reservation schemes aim at reducing the end-to-end delay of a data burst, by sending the burst header packet (BHP) in the core network before the burst assembly is completed at the ingress node. We use linear prediction filters to estimate the expected length of the burst and the time needed for the burstification process to complete. A BHP packet carrying these estimates is sent before burst completion, in order to reserve bandwidth at each intermediate node for the time interval the burst is expected to pass from that node. Reducing the total time needed for a packet to be transported over an OBS network is important, especially for real-time applications. Reserving bandwidth only for the time interval it is actual going to be used by a burst is important for network utilization efficiency. In the simulations conducted we evaluate the proposed extensions and prove their usefulness.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134364642","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}
The models of network control and resource management in stochastic environment are of great importance. The choice of models and methods depends on adequacy of identification and real measurements of traffic characteristics. Without robust theoretical preconditions network environment modeling will fail to simple simulation results. Therefore Internet as environment of control which is characterized by specific features including dynamism, hierarchy and adaptability is a topic of active fundamental researches. In the paper we consider Internet properties which can be presented by dynamic TCP model and stochastic character of observable fluctuations. Proposed approach is based on the analysis of experimental results, modeling, and analytical approximation of distribution function of stochastic intervals between fast recovery TCP phases.
{"title":"TCP Flows in Stochastic Network Environment: Models and Characteristics","authors":"V. Zaborovsky, Sergey Ygorov, Nikolay Fedorov","doi":"10.1109/ICN.2008.101","DOIUrl":"https://doi.org/10.1109/ICN.2008.101","url":null,"abstract":"The models of network control and resource management in stochastic environment are of great importance. The choice of models and methods depends on adequacy of identification and real measurements of traffic characteristics. Without robust theoretical preconditions network environment modeling will fail to simple simulation results. Therefore Internet as environment of control which is characterized by specific features including dynamism, hierarchy and adaptability is a topic of active fundamental researches. In the paper we consider Internet properties which can be presented by dynamic TCP model and stochastic character of observable fluctuations. Proposed approach is based on the analysis of experimental results, modeling, and analytical approximation of distribution function of stochastic intervals between fast recovery TCP phases.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133418290","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}
In this paper, we describe a possible approach for using mobile agents to manage a group of networked devices. Our system goes one step further from the traditional one-to- one device management setting by providing a one-to-many architecture able to perform simple administrative tasks on behalf of the user. We show how the use of mobile agents eases the task of maintaining, monitoring and managing a very large number of devices and consequently, reduces the work load of the people in charge of these devices.
{"title":"Large Scale Deployment a Mobile Agent Approach to Network Management","authors":"G. Autran, Xining Li","doi":"10.1109/ICN.2008.28","DOIUrl":"https://doi.org/10.1109/ICN.2008.28","url":null,"abstract":"In this paper, we describe a possible approach for using mobile agents to manage a group of networked devices. Our system goes one step further from the traditional one-to- one device management setting by providing a one-to-many architecture able to perform simple administrative tasks on behalf of the user. We show how the use of mobile agents eases the task of maintaining, monitoring and managing a very large number of devices and consequently, reduces the work load of the people in charge of these devices.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122682450","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}
The use of 802.11 long-distance links is a cost-effective means of providing wireless connectivity to rural areas. Although deployments in such settings are increasing, there are few empirical results reported on the performance of 802.11 over long distances. An empirical evaluation of 802.11 performance over long distances is a non-trivial task since it involves several variables such as the network topology, tower heights, antenna types used and their orientations, and radio transmit powers. The task is further complicated by the presence of network performance constraints, and the inter-dependence among the variables. In this paper we present an empirical performance study of long-distance 802.11g links using metrics such as signal strength, free space loss, jitter and round-trip time. In addition, we also develop a theoretical model of the wireless link to validate our experimental measurements.
{"title":"Experimental Evaluation and Characterization of Long-Distance 802.11g Links","authors":"H. El-Sayed, S. Zeadally, M. Boulmalf","doi":"10.1109/ICN.2008.32","DOIUrl":"https://doi.org/10.1109/ICN.2008.32","url":null,"abstract":"The use of 802.11 long-distance links is a cost-effective means of providing wireless connectivity to rural areas. Although deployments in such settings are increasing, there are few empirical results reported on the performance of 802.11 over long distances. An empirical evaluation of 802.11 performance over long distances is a non-trivial task since it involves several variables such as the network topology, tower heights, antenna types used and their orientations, and radio transmit powers. The task is further complicated by the presence of network performance constraints, and the inter-dependence among the variables. In this paper we present an empirical performance study of long-distance 802.11g links using metrics such as signal strength, free space loss, jitter and round-trip time. In addition, we also develop a theoretical model of the wireless link to validate our experimental measurements.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124429548","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}
Anti-virus applications play an important role in today's Internet communication security. Virus scanning is usually performed on email, Web and file transfer traffic flows at intranet security gateways. The performance of popular anti-virus applications relies on the pattern matching algorithms implemented in these security devices. The growth of network bandwidth and the increase of virus signatures call for high speed and scalable pattern matching algorithms. Motivated by several observations of a real-life virus signature database from Clam-AV, a popular antivirus application, a fast pattern matching algorithm named MRSI is proposed in this paper. Compared to the current algorithm implemented in Clam-AV, MRSI achieved an 80%~100% faster virus scanning speed without excessive memory usages.
{"title":"MRSI: A Fast Pattern Matching Algorithm for Anti-virus Applications","authors":"Xin Zhou, Bosheng Xu, Yaxuan Qi, Jun Li","doi":"10.1109/ICN.2008.119","DOIUrl":"https://doi.org/10.1109/ICN.2008.119","url":null,"abstract":"Anti-virus applications play an important role in today's Internet communication security. Virus scanning is usually performed on email, Web and file transfer traffic flows at intranet security gateways. The performance of popular anti-virus applications relies on the pattern matching algorithms implemented in these security devices. The growth of network bandwidth and the increase of virus signatures call for high speed and scalable pattern matching algorithms. Motivated by several observations of a real-life virus signature database from Clam-AV, a popular antivirus application, a fast pattern matching algorithm named MRSI is proposed in this paper. Compared to the current algorithm implemented in Clam-AV, MRSI achieved an 80%~100% faster virus scanning speed without excessive memory usages.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128606871","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}
This paper describes a new approach to converged communication and computer networks. It was designed a new architecture of nodal active network element that is powerful enough and supports priority processing of different types of connection. It is exactly the missing support of priority processing that constitutes the greatest drawback of the majority of present-day active network elements. The proposed new architecture is based on the technology of artificial neural networks. Neural networks are used to optimize switching input requirements to outputs. This paper also describes design and computer simulations of a new architecture network element, based on artificial neural network technology with the support of priority processing for different connection types. As an example of a network element was selected switching area. This network element with optimized switching area is able to transfer large data quantity with minimum delay. Architecture of network element, that contains artificial neural network for optimized priority switching is described in this paper. It describes implementation of neural network in control process for data units switching. The programming language MATLAB 7.0 was used for software simulation. Network elements with new architecture, which uses a neural network, as well as intimated simulation, are suitable for working for example in personal wireless network communication systems.
{"title":"New Approach to Converged Networks","authors":"V. Skorpil","doi":"10.1109/ICN.2008.127","DOIUrl":"https://doi.org/10.1109/ICN.2008.127","url":null,"abstract":"This paper describes a new approach to converged communication and computer networks. It was designed a new architecture of nodal active network element that is powerful enough and supports priority processing of different types of connection. It is exactly the missing support of priority processing that constitutes the greatest drawback of the majority of present-day active network elements. The proposed new architecture is based on the technology of artificial neural networks. Neural networks are used to optimize switching input requirements to outputs. This paper also describes design and computer simulations of a new architecture network element, based on artificial neural network technology with the support of priority processing for different connection types. As an example of a network element was selected switching area. This network element with optimized switching area is able to transfer large data quantity with minimum delay. Architecture of network element, that contains artificial neural network for optimized priority switching is described in this paper. It describes implementation of neural network in control process for data units switching. The programming language MATLAB 7.0 was used for software simulation. Network elements with new architecture, which uses a neural network, as well as intimated simulation, are suitable for working for example in personal wireless network communication systems.","PeriodicalId":250085,"journal":{"name":"Seventh International Conference on Networking (icn 2008)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116692480","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：