Pub Date : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488159
Stefano Secci, J. Rougier, A. Pattavina
This article proposes an architecture and algorithms to select optimal diverse AS paths for end-to-end LSPs computation. The multi-domain architecture relies upon a service plane consisting of a service broker and an AS Selection Agent. Through the broker, every domain advertises transit metrics representing its transit policies (cost, routing policies) and potentially some Traffic Engineering (TE) information. The metrics are assumed to be directional, i.e. depending on the incoming and outgoing ASs. The Agent uses them to compute AS paths based on both costs and TE constraints, considering also, if needed, local policies and statistics on past transactions stored by the broker. A set of diverse AS paths can be computed, in order to proactively increase the success rate of tunnel set-up, in the case of imprecision or absence of advertised TE information (each AS path being subsequently tested), or to meet end-to-end protection requirements. If an AS path can be activated, the source router trigger the router-level inter-AS path computation along the AS path, which is accomplished by the PCE-based architecture. Within this framework, we formalize the inter-AS diverse route selection problem with directional metrics, and compare a breadth-first search heuristic with limited depth to the optimal approach. Simulations on realistic topologies prove that the heuristic scales with the number of diverse routes, and that it has an optimality gap under the 5% at least once every two times.
{"title":"On the selection of optimal diverse AS-paths for inter-domain IP/(G)MPLS tunnel provisioning","authors":"Stefano Secci, J. Rougier, A. Pattavina","doi":"10.1109/ITNEWS.2008.4488159","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488159","url":null,"abstract":"This article proposes an architecture and algorithms to select optimal diverse AS paths for end-to-end LSPs computation. The multi-domain architecture relies upon a service plane consisting of a service broker and an AS Selection Agent. Through the broker, every domain advertises transit metrics representing its transit policies (cost, routing policies) and potentially some Traffic Engineering (TE) information. The metrics are assumed to be directional, i.e. depending on the incoming and outgoing ASs. The Agent uses them to compute AS paths based on both costs and TE constraints, considering also, if needed, local policies and statistics on past transactions stored by the broker. A set of diverse AS paths can be computed, in order to proactively increase the success rate of tunnel set-up, in the case of imprecision or absence of advertised TE information (each AS path being subsequently tested), or to meet end-to-end protection requirements. If an AS path can be activated, the source router trigger the router-level inter-AS path computation along the AS path, which is accomplished by the PCE-based architecture. Within this framework, we formalize the inter-AS diverse route selection problem with directional metrics, and compare a breadth-first search heuristic with limited depth to the optimal approach. Simulations on realistic topologies prove that the heuristic scales with the number of diverse routes, and that it has an optimality gap under the 5% at least once every two times.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122125876","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488152
Y. Gotoh, T. Yoshihisa, M. Kanazawa
Due to the recent popularization of digital broadcasting systems, selective contents, i.e., watching contents selected by the users themselves, have attracted great attention. For example, in news programs, after watching a summary of each story, a user selects one and watches it. By providing selective contents, clients can watch programs that reflect their preferences. However, the server has to deliver several contents to give clients choices. This increases the waiting time for clients. In this paper, we propose a scheduling method that reduces waiting time by considering playing time for contents. The waiting time is effectively reduced compared to previous works.
{"title":"A scheduling method considering playing time in selective contents broadcasting","authors":"Y. Gotoh, T. Yoshihisa, M. Kanazawa","doi":"10.1109/ITNEWS.2008.4488152","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488152","url":null,"abstract":"Due to the recent popularization of digital broadcasting systems, selective contents, i.e., watching contents selected by the users themselves, have attracted great attention. For example, in news programs, after watching a summary of each story, a user selects one and watches it. By providing selective contents, clients can watch programs that reflect their preferences. However, the server has to deliver several contents to give clients choices. This increases the waiting time for clients. In this paper, we propose a scheduling method that reduces waiting time by considering playing time for contents. The waiting time is effectively reduced compared to previous works.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125662513","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488158
B. Fu, F. Kuipers, P. Mieghem
A Link-State Update Policy (LSUP) has the task to distribute information regarding the network resources, and is therefore considered to be an integral part of future Quality of Service (QoS) routing protocols. The argument is that in order to guarantee QoS to applications, one must know the available resources. Unfortunately, the high dynamics in available resources complicates the development of an LSUP, which on its turn will result in high deployment costs for Internet Service Providers. In this paper we will re-examine whether the gain in network performance, which is expected under the deployment of LSUPs, will outweigh its investment and complexity costs. To capture the complete range of possible LSUPs, we take a pragmatic approach and confine ourselves to examining two extreme strategies: routing with exact resource information and routing with no resource information. Our study comprises of an analytical exercise and extensive simulations on various network topologies under a large range of network loads. Our objective is to determine where static information provides acceptable network performance and where dynamic LSUPs are indispensable.
{"title":"To update network state or not?","authors":"B. Fu, F. Kuipers, P. Mieghem","doi":"10.1109/ITNEWS.2008.4488158","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488158","url":null,"abstract":"A Link-State Update Policy (LSUP) has the task to distribute information regarding the network resources, and is therefore considered to be an integral part of future Quality of Service (QoS) routing protocols. The argument is that in order to guarantee QoS to applications, one must know the available resources. Unfortunately, the high dynamics in available resources complicates the development of an LSUP, which on its turn will result in high deployment costs for Internet Service Providers. In this paper we will re-examine whether the gain in network performance, which is expected under the deployment of LSUPs, will outweigh its investment and complexity costs. To capture the complete range of possible LSUPs, we take a pragmatic approach and confine ourselves to examining two extreme strategies: routing with exact resource information and routing with no resource information. Our study comprises of an analytical exercise and extensive simulations on various network topologies under a large range of network loads. Our objective is to determine where static information provides acceptable network performance and where dynamic LSUPs are indispensable.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133314698","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488145
Masataka Ohta
Session initiation protocol (SIP), which is widely used for Internet telephony, is an application-layer protocol to handle sessions between two points. SIP is implemented on the top of user datagram protocol (UDP) or transmission control protocol (TCP). SIP messages are transmitted by UDP or TCP. This study is on the performance of SIP signaling network using UDP and TCP. A network simulator (ns-2) is used to evaluate throughput and call setup delay as performance measures. We have implemented new agents that act as SIP elements in the ns-2 and a significant performance difference was found to exist. In the case of SIP over UDP, retransmissions of SIP messages decrease throughput. On the other hand, in the case of SIP over TCP, the window control of TCP enlarges a call setup delay.
会话发起协议(SIP)是一种处理两点间会话的应用层协议，广泛应用于互联网电话。SIP协议是在用户数据报协议(UDP)或传输控制协议(TCP)之上实现的。SIP消息通过UDP或TCP传输。本文研究了基于UDP和TCP协议的SIP信令网络的性能。网络模拟器(ns-2)用于评估吞吐量和呼叫设置延迟作为性能度量。我们已经在ns-2中实现了作为SIP元素的新代理，并且发现存在显著的性能差异。在SIP over UDP的情况下，SIP消息的重传会降低吞吐量。另一方面，在SIP over TCP的情况下，TCP的窗口控制增大了呼叫建立延迟。
{"title":"Performance comparisons of transport protocols for session initiation protocol signaling","authors":"Masataka Ohta","doi":"10.1109/ITNEWS.2008.4488145","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488145","url":null,"abstract":"Session initiation protocol (SIP), which is widely used for Internet telephony, is an application-layer protocol to handle sessions between two points. SIP is implemented on the top of user datagram protocol (UDP) or transmission control protocol (TCP). SIP messages are transmitted by UDP or TCP. This study is on the performance of SIP signaling network using UDP and TCP. A network simulator (ns-2) is used to evaluate throughput and call setup delay as performance measures. We have implemented new agents that act as SIP elements in the ns-2 and a significant performance difference was found to exist. In the case of SIP over UDP, retransmissions of SIP messages decrease throughput. On the other hand, in the case of SIP over TCP, the window control of TCP enlarges a call setup delay.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132123226","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488163
D. Ciullo, M. Mellia, M. Meo
In this paper we present measurement results collected from real traces on the network of FastWeb, an Italian ISP which is the main broadband telecommunication company in Italy. The network relies on a fully IP architecture and delivers to the user data, VoIP and IPTV services over a single broadband connection. The aims of this work are the evaluation of traditional measurement indexes in a novel network environment with a mixture of traffic generated by various services and the identification of possible changes of the traffic properties due to this traffic mixture. Our measurement campaign, based on passive techniques, provides traffic characterization at both the packet and the connection/flow levels and focuses on time evolution, distributions, long range dependence and periodicity properties. We discover that the main characteristics of data traffic are kept unmodified, showing LRD properties both at the packet and flow levels. VoIP and IPTV traffic instead presents periodicities of the packet arrival process, due to periodicity of the sources. Considering the VoIP flow arrival process, the traditional Markovian assumption still holds true.
{"title":"Traditional IP measurements: What changes in a today multimedia IP network","authors":"D. Ciullo, M. Mellia, M. Meo","doi":"10.1109/ITNEWS.2008.4488163","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488163","url":null,"abstract":"In this paper we present measurement results collected from real traces on the network of FastWeb, an Italian ISP which is the main broadband telecommunication company in Italy. The network relies on a fully IP architecture and delivers to the user data, VoIP and IPTV services over a single broadband connection. The aims of this work are the evaluation of traditional measurement indexes in a novel network environment with a mixture of traffic generated by various services and the identification of possible changes of the traffic properties due to this traffic mixture. Our measurement campaign, based on passive techniques, provides traffic characterization at both the packet and the connection/flow levels and focuses on time evolution, distributions, long range dependence and periodicity properties. We discover that the main characteristics of data traffic are kept unmodified, showing LRD properties both at the packet and flow levels. VoIP and IPTV traffic instead presents periodicities of the packet arrival process, due to periodicity of the sources. Considering the VoIP flow arrival process, the traditional Markovian assumption still holds true.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133459878","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488143
D. Giustiniano, I. Tinnirello, L. Scalia, A. Levanti
Service differentiation in WLAN has been traditionally faced at the MAC layer. However, some PHY layer parameters, such as the transmission power, the antenna, and the modulation/coding scheme, have a deep impact on network performance. Since the criterion for selecting these parameters is left to the vendor specific implementations, the performance spread of most experimental results about 802.11 WLAN could be affected by vendor proprietary schemes. The focus of this paper is an experimental analysis of the undisclosed antenna diversity mechanisms employed by some widely used cards (namely, the Atheros and Intel based cards), and a thorough understanding of the optimization goals which guided their design. Although these mechanisms have been introduced for improving the transmission robustness to fading, we proved that they may have dramatic side- effects on link performance, whenever the available antennas are not homogeneous.
{"title":"Revealing transmit diversity mechanisms and their side-effects in commercial IEEE 802.11 cards","authors":"D. Giustiniano, I. Tinnirello, L. Scalia, A. Levanti","doi":"10.1109/ITNEWS.2008.4488143","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488143","url":null,"abstract":"Service differentiation in WLAN has been traditionally faced at the MAC layer. However, some PHY layer parameters, such as the transmission power, the antenna, and the modulation/coding scheme, have a deep impact on network performance. Since the criterion for selecting these parameters is left to the vendor specific implementations, the performance spread of most experimental results about 802.11 WLAN could be affected by vendor proprietary schemes. The focus of this paper is an experimental analysis of the undisclosed antenna diversity mechanisms employed by some widely used cards (namely, the Atheros and Intel based cards), and a thorough understanding of the optimization goals which guided their design. Although these mechanisms have been introduced for improving the transmission robustness to fading, we proved that they may have dramatic side- effects on link performance, whenever the available antennas are not homogeneous.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130232198","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488161
D. Rossi, M. Mellia, M. Meo
Skype is beyond any doubt the VoIP application in the current Internet. Its amazing success drawn the attention of telecom operators and the research community, both interested in knowing its internal mechanisms, characterizing its traffic, understanding its users' behavior. One of the most peculiar characteristics of Skype is that it relies on a P2P infrastructure for the exchange of signaling information that is distributed between active peers. Leveraging on the use of an accurate Skype classification engine that we recently proposed, we carry on an experimental study of Skype signaling based on extensive passive measurements collected from our campus LAN. In particular, we focus on the signaling traffic in the attempt of inferring some interesting properties of the overlay maintenance and, possibly, some hints about its structure. Our results show that, despite the signaling bandwidth used by normal peers is exiguous, it may however constitute a very significant portion of the total traffic generated by a Skype client - since, in order to guarantee reachability, Skype application is running most of the time even if no active call is in progress. Skype performs peer discovery and refresh by using a large number of single packets probes - which may be as effective for the purpose of the overlay maintenance as costly from the viewpoint of statefull layer-4 network devices. At the same time, single packet probes constitute only a minor portion of the signaling traffic: therefore, we dig into further details the traffic exchanged among more stable peers in the attempt of learning how the peer selection mechanism works.
{"title":"Following skype signaling footsteps","authors":"D. Rossi, M. Mellia, M. Meo","doi":"10.1109/ITNEWS.2008.4488161","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488161","url":null,"abstract":"Skype is beyond any doubt the VoIP application in the current Internet. Its amazing success drawn the attention of telecom operators and the research community, both interested in knowing its internal mechanisms, characterizing its traffic, understanding its users' behavior. One of the most peculiar characteristics of Skype is that it relies on a P2P infrastructure for the exchange of signaling information that is distributed between active peers. Leveraging on the use of an accurate Skype classification engine that we recently proposed, we carry on an experimental study of Skype signaling based on extensive passive measurements collected from our campus LAN. In particular, we focus on the signaling traffic in the attempt of inferring some interesting properties of the overlay maintenance and, possibly, some hints about its structure. Our results show that, despite the signaling bandwidth used by normal peers is exiguous, it may however constitute a very significant portion of the total traffic generated by a Skype client - since, in order to guarantee reachability, Skype application is running most of the time even if no active call is in progress. Skype performs peer discovery and refresh by using a large number of single packets probes - which may be as effective for the purpose of the overlay maintenance as costly from the viewpoint of statefull layer-4 network devices. At the same time, single packet probes constitute only a minor portion of the signaling traffic: therefore, we dig into further details the traffic exchanged among more stable peers in the attempt of learning how the peer selection mechanism works.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127316493","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488148
M. Hashimoto, A. Fukuda, K. Yukimatsu
This paper proposes a traffic control scheme that uses application flows as identified by application information in the packets being transferred. The proposal increases flexibility in terms of IP packet routing. First, it is confirmed that individual application flows can be routed through their own minimum-cost paths. Cost is determined, for each flow, from one or more QoS parameters, for example, delay and availability. Next, it facilitates traffic engineering, namely the efficient utilization of network resources. In this situation, one source-destination traffic demand is satisfied by setting one or more flows as needed for traffic grooming. Numerical results show that the proposal allows the network to accommodate more traffic even if the cost-routed traffic create a bottleneck link.
{"title":"Novel traffic engineering scheme based upon application flows for QoS enhancement","authors":"M. Hashimoto, A. Fukuda, K. Yukimatsu","doi":"10.1109/ITNEWS.2008.4488148","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488148","url":null,"abstract":"This paper proposes a traffic control scheme that uses application flows as identified by application information in the packets being transferred. The proposal increases flexibility in terms of IP packet routing. First, it is confirmed that individual application flows can be routed through their own minimum-cost paths. Cost is determined, for each flow, from one or more QoS parameters, for example, delay and availability. Next, it facilitates traffic engineering, namely the efficient utilization of network resources. In this situation, one source-destination traffic demand is satisfied by setting one or more flows as needed for traffic grooming. Numerical results show that the proposal allows the network to accommodate more traffic even if the cost-routed traffic create a bottleneck link.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115578905","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488128
Antonio Capone, J. Elias, F. Martignon
Service Overlay Networks (SONs) are currently one of the most promising architectures envisioned to provide end-to- end Quality of Service guarantees in the Internet, without requiring significant changes to the underlying network infrastructure. A SON is an application-layer network operated by a third- party Internet Service Provider (ISP) that owns a set of overlay nodes, residing in the underlying ISP domains, interconnected by overlay links. The deployment of a SON can be a capital-intensive investment, and hence its planning requires careful decisions, including the overlay nodes' placement, the capacity provisioning of overlay links as well as of access links that connect the end-users to the SON infrastructure. In this paper we propose two novel optimization models for the planning of Service Overlay Networks which aim to select the number and positions of overlay nodes, as well as the capacity reserved for each overlay link, while taking into account in an accurate way traffic routing. The first model minimizes the SON installation cost while providing full coverage to all network's users. The second model maximizes the SON revenue by further choosing which users to serve, based on the expected gain, and taking into consideration budget constraints that the SON operator could specify. We provide the optimal solutions of the proposed problem formulations on a set of realistic-size instances and discuss the effect of different parameters on the characteristics of the planned networks.
{"title":"Optimal design of service overlay networks","authors":"Antonio Capone, J. Elias, F. Martignon","doi":"10.1109/ITNEWS.2008.4488128","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488128","url":null,"abstract":"Service Overlay Networks (SONs) are currently one of the most promising architectures envisioned to provide end-to- end Quality of Service guarantees in the Internet, without requiring significant changes to the underlying network infrastructure. A SON is an application-layer network operated by a third- party Internet Service Provider (ISP) that owns a set of overlay nodes, residing in the underlying ISP domains, interconnected by overlay links. The deployment of a SON can be a capital-intensive investment, and hence its planning requires careful decisions, including the overlay nodes' placement, the capacity provisioning of overlay links as well as of access links that connect the end-users to the SON infrastructure. In this paper we propose two novel optimization models for the planning of Service Overlay Networks which aim to select the number and positions of overlay nodes, as well as the capacity reserved for each overlay link, while taking into account in an accurate way traffic routing. The first model minimizes the SON installation cost while providing full coverage to all network's users. The second model maximizes the SON revenue by further choosing which users to serve, based on the expected gain, and taking into consideration budget constraints that the SON operator could specify. We provide the optimal solutions of the proposed problem formulations on a set of realistic-size instances and discuss the effect of different parameters on the characteristics of the planned networks.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"305 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121699837","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 : 2008-04-11DOI: 10.1109/ITNEWS.2008.4488141
D. Ficara, S. Giordano, F. Oppedisano, G. Procissi, F. Vitucci
The extensive availability of cost effective commodity PC hardware pushed the development of flexible and versatile traffic monitoring software such as protocol analyzers, protocol dissectors, traffic sniffers, traffic characterizers and IDSs (Intrusion Detection Systems). The largest part of these pieces of software is based on the well known libpcap API, which in the last few years has become a de facto standard for PC based packet capturing. Many improvements have been applied to this library but it still suffers from several performance flaws that are due not to the software itself but rather to the underlying hardware bottlenecks. In this paper we present a new traffic monitoring device, implemented by an Intel IXP2400 Network Processor PCI-X card connected to a gigabit Ethernet LAN hosting a cluster of common personal computers running any libpcap based application. This architecture outperforms the previous solutions in terms of packet capturing power and timestamp accuracy.
{"title":"A cooperative PC/Network-Processor architecture for multi gigabit traffic analysis","authors":"D. Ficara, S. Giordano, F. Oppedisano, G. Procissi, F. Vitucci","doi":"10.1109/ITNEWS.2008.4488141","DOIUrl":"https://doi.org/10.1109/ITNEWS.2008.4488141","url":null,"abstract":"The extensive availability of cost effective commodity PC hardware pushed the development of flexible and versatile traffic monitoring software such as protocol analyzers, protocol dissectors, traffic sniffers, traffic characterizers and IDSs (Intrusion Detection Systems). The largest part of these pieces of software is based on the well known libpcap API, which in the last few years has become a de facto standard for PC based packet capturing. Many improvements have been applied to this library but it still suffers from several performance flaws that are due not to the software itself but rather to the underlying hardware bottlenecks. In this paper we present a new traffic monitoring device, implemented by an Intel IXP2400 Network Processor PCI-X card connected to a gigabit Ethernet LAN hosting a cluster of common personal computers running any libpcap based application. This architecture outperforms the previous solutions in terms of packet capturing power and timestamp accuracy.","PeriodicalId":255580,"journal":{"name":"2008 4th International Telecommunication Networking Workshop on QoS in Multiservice IP Networks","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133202323","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：