Pub Date : 2014-11-01DOI: 10.1109/CNSM.2014.7014144
Maxim Claeys, D. Tuncer, J. Famaey, M. Charalambides, Steven Latré, G. Pavlou, F. Turck
The content delivery market has mainly been dominated by large Content Delivery Networks (CDNs) such as Akamai and Limelight. However, CDN traffic exerts a lot of pressure on Internet Service Provider (ISP) networks. Recently, ISPs have begun deploying so-called Telco CDNs, which have many advantages, such as reduced ISP network bandwidth utilization and improved Quality of Service (QoS) by bringing content closer to the end-user. Virtualization of storage and networking resources can enable the ISP to simultaneously lease its Telco CDN infrastructure to multiple third parties, opening up new business models and revenue streams. In this paper, we propose a proactive cache management system for ISP-operated multitenant Telco CDNs. The associated algorithm optimizes content placement and server selection across tenants and users, based on predicted content popularity and the geographical distribution of requests. Based on a Video-on-Demand (VoD) request trace of a leading European telecom operator, the presented algorithm is shown to reduce bandwidth usage by 17% compared to the traditional Least Recently Used (LRU) caching strategy, both inside the network and on the ingress links, while at the same time offering enhanced load balancing capabilities. Increasing the prediction accuracy is shown to have the potential to further improve bandwidth efficiency by up to 79%.
内容交付市场主要由Akamai和Limelight等大型内容交付网络(cdn)主导。然而，CDN流量给ISP (Internet Service Provider)网络带来了很大的压力。最近，互联网服务提供商已经开始部署所谓的电信cdn，它有很多优点，比如降低了互联网服务提供商的网络带宽利用率，并通过拉近最终用户的距离提高了服务质量(QoS)。存储和网络资源的虚拟化可以使ISP同时将其电信CDN基础设施租赁给多个第三方，从而开辟新的业务模式和收入来源。在本文中，我们提出了一种针对isp运营的多租户电信cdn的主动缓存管理系统。相关的算法基于预测的内容流行度和请求的地理分布，优化跨租户和用户的内容放置和服务器选择。基于一家领先的欧洲电信运营商的视频点播(VoD)请求跟踪，所提出的算法与传统的最近最少使用(LRU)缓存策略相比，在网络内部和入口链路上减少了17%的带宽使用，同时提供了增强的负载平衡能力。研究表明，提高预测精度有可能进一步提高带宽效率，最高可达79%。
{"title":"Proactive multi-tenant cache management for virtualized ISP networks","authors":"Maxim Claeys, D. Tuncer, J. Famaey, M. Charalambides, Steven Latré, G. Pavlou, F. Turck","doi":"10.1109/CNSM.2014.7014144","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014144","url":null,"abstract":"The content delivery market has mainly been dominated by large Content Delivery Networks (CDNs) such as Akamai and Limelight. However, CDN traffic exerts a lot of pressure on Internet Service Provider (ISP) networks. Recently, ISPs have begun deploying so-called Telco CDNs, which have many advantages, such as reduced ISP network bandwidth utilization and improved Quality of Service (QoS) by bringing content closer to the end-user. Virtualization of storage and networking resources can enable the ISP to simultaneously lease its Telco CDN infrastructure to multiple third parties, opening up new business models and revenue streams. In this paper, we propose a proactive cache management system for ISP-operated multitenant Telco CDNs. The associated algorithm optimizes content placement and server selection across tenants and users, based on predicted content popularity and the geographical distribution of requests. Based on a Video-on-Demand (VoD) request trace of a leading European telecom operator, the presented algorithm is shown to reduce bandwidth usage by 17% compared to the traditional Least Recently Used (LRU) caching strategy, both inside the network and on the ingress links, while at the same time offering enhanced load balancing capabilities. Increasing the prediction accuracy is shown to have the potential to further improve bandwidth efficiency by up to 79%.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122671792","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014197
M. Mushtaq, B. Augustin, A. Mellouk
Video streaming over Hypertext Transfer Protocol (HTTP) is highly dominant due to the availability of Internet support on many devices. The multimedia applications that generate IP traffic should be conducive with efficient utilization of network resources. Adaptive video streaming over HTTP becomes attractive for content service providers, as it not only uses the existing infrastructure of Web downloading (thus saving an extra cost), but it also provides the ability to change the video quality (bitrate) according to dynamic network conditions for increasing the user's perceived Quality of Experience (QoE). Video streaming over HTTP is easier and cheaper to move data closer to network users, and the video file is just like a normal Web object. In this paper, we have proposed a novel rate adaptive streaming algorithm that enhances the user's perceived quality with high bandwidth utilization for on-demand video. The proposed algorithm considers the following metrics in order to adapt the video quality, which are; player buffer, dropped of excess video frames per second (fps), and availability of network bandwidth. The algorithm is evaluated in dynamic real time Internet environment by using the wired and wireless network at the client side.
{"title":"HTTP rate adaptive algorithm with high bandwidth utilization","authors":"M. Mushtaq, B. Augustin, A. Mellouk","doi":"10.1109/CNSM.2014.7014197","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014197","url":null,"abstract":"Video streaming over Hypertext Transfer Protocol (HTTP) is highly dominant due to the availability of Internet support on many devices. The multimedia applications that generate IP traffic should be conducive with efficient utilization of network resources. Adaptive video streaming over HTTP becomes attractive for content service providers, as it not only uses the existing infrastructure of Web downloading (thus saving an extra cost), but it also provides the ability to change the video quality (bitrate) according to dynamic network conditions for increasing the user's perceived Quality of Experience (QoE). Video streaming over HTTP is easier and cheaper to move data closer to network users, and the video file is just like a normal Web object. In this paper, we have proposed a novel rate adaptive streaming algorithm that enhances the user's perceived quality with high bandwidth utilization for on-demand video. The proposed algorithm considers the following metrics in order to adapt the video quality, which are; player buffer, dropped of excess video frames per second (fps), and availability of network bandwidth. The algorithm is evaluated in dynamic real time Internet environment by using the wired and wireless network at the client side.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"600 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122905136","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014167
Alexander Shpiner, I. Keslassy, Carmi Arad, Tal Mizrahi, Yoram Revah
Multi-tenant data centers provide a cost-effective many-server infrastructure for hosting large-scale applications. These data centers can run multiple virtual machines (VMs) for each tenant, and potentially place any of these VMs on any of the servers. Therefore, for inter-VM communication, they also need to provide a VM resolution method that can quickly determine the server location of any VM. Unfortunately, existing methods suffer from a scalability bottleneck in the network load of the address resolution messages and/or in the size of the resolution tables. In this paper, we propose Smart Address Learning (SAL), a novel approach that expands the scalability of both the network load and the resolution table sizes, making it implementable on faster memory devices. The key property of the approach is to selectively learn the addresses in the resolution tables, by using the fact that the VMs of different tenants do not communicate. We further compare the various resolution methods and analyze the tradeoff between network load and table sizes. We also evaluate our results using real-life trace simulations. Our analysis shows that SAL can reduce both the network load and the resolution table sizes by several orders of magnitude.
{"title":"SAL: Scaling data centers using Smart Address Learning","authors":"Alexander Shpiner, I. Keslassy, Carmi Arad, Tal Mizrahi, Yoram Revah","doi":"10.1109/CNSM.2014.7014167","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014167","url":null,"abstract":"Multi-tenant data centers provide a cost-effective many-server infrastructure for hosting large-scale applications. These data centers can run multiple virtual machines (VMs) for each tenant, and potentially place any of these VMs on any of the servers. Therefore, for inter-VM communication, they also need to provide a VM resolution method that can quickly determine the server location of any VM. Unfortunately, existing methods suffer from a scalability bottleneck in the network load of the address resolution messages and/or in the size of the resolution tables. In this paper, we propose Smart Address Learning (SAL), a novel approach that expands the scalability of both the network load and the resolution table sizes, making it implementable on faster memory devices. The key property of the approach is to selectively learn the addresses in the resolution tables, by using the fact that the VMs of different tenants do not communicate. We further compare the various resolution methods and analyze the tradeoff between network load and table sizes. We also evaluate our results using real-life trace simulations. Our analysis shows that SAL can reduce both the network load and the resolution table sizes by several orders of magnitude.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126049307","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014202
Gustavo Pantuza, Frederico Sampaio, L. Vieira, D. Guedes, M. Vieira
Software Defined Networks (SDN) is an emergent architecture that is dynamic, flexible, manageable, low cost, consistent with the dynamics of the modern applications. This paper shows a network representation model using a graph as the control plane of an SDN controller. The graph approach provides a globally consistent view of the network in real time. Our experiments show that graphs are a reliable representation of the real network, simplifying management in Software Defined Networking.
{"title":"Network management through graphs in Software Defined Networks","authors":"Gustavo Pantuza, Frederico Sampaio, L. Vieira, D. Guedes, M. Vieira","doi":"10.1109/CNSM.2014.7014202","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014202","url":null,"abstract":"Software Defined Networks (SDN) is an emergent architecture that is dynamic, flexible, manageable, low cost, consistent with the dynamics of the modern applications. This paper shows a network representation model using a graph as the control plane of an SDN controller. The graph approach provides a globally consistent view of the network in real time. Our experiments show that graphs are a reliable representation of the real network, simplifying management in Software Defined Networking.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122257152","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014183
Hui Zhang, J. Rhee, Nipun Arora, Qiang Xu, C. Lumezanu, Guofei Jiang
Network virtualization has been propounded as a diversifying attribute of the future inter-networking paradigm. However, monitoring and troubleshooting operational virtual networks can be a daunting task, due to their size, distributed state, and additional complexity introduced by network virtualization. We propose an analytics approach for the analysis of network traces collected across hypervisors and switches. To re-organize individual trace events into path-wise slices that represent the life-cycle of individual packets, we first present a trace slicing scheme. Then, we develop a path characterization scheme to extract feature matrices from those trace slices. Using those feature metrics, we develop a set of trace analysis algorithms to cluster, rank, query, and verify packet traces. We have developed the analytics approach in a SDN network management tool, and presented evaluation results to show how it can enable visibility and effective problem diagnosis in a SDN network.
{"title":"An analytics approach to traffic analysis in network virtualization","authors":"Hui Zhang, J. Rhee, Nipun Arora, Qiang Xu, C. Lumezanu, Guofei Jiang","doi":"10.1109/CNSM.2014.7014183","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014183","url":null,"abstract":"Network virtualization has been propounded as a diversifying attribute of the future inter-networking paradigm. However, monitoring and troubleshooting operational virtual networks can be a daunting task, due to their size, distributed state, and additional complexity introduced by network virtualization. We propose an analytics approach for the analysis of network traces collected across hypervisors and switches. To re-organize individual trace events into path-wise slices that represent the life-cycle of individual packets, we first present a trace slicing scheme. Then, we develop a path characterization scheme to extract feature matrices from those trace slices. Using those feature metrics, we develop a set of trace analysis algorithms to cluster, rank, query, and verify packet traces. We have developed the analytics approach in a SDN network management tool, and presented evaluation results to show how it can enable visibility and effective problem diagnosis in a SDN network.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125303721","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014175
Alisson Puska, M. N. Lima, A. Santos
The increasing amount of unwanted traffic on the Internet consumes the available bandwidth on any network connected to it. Despite efforts to address this issue, it is still a challenge to differentiate unwanted traffic. Due to lack of knowledge or investment, organizations fail to implement security policies, such as BCP 38, which helps blocking the flow of unwanted data. This paper presents a method based on lowinteraction honeypots and network telescopes for identification and classification of unwanted traffic on IP networks. Our method aims to be simple and support low cost of deployment. An evaluation employed traces of real environments to show the method effectiveness. Results offer useful information about unwanted traffic, reaching a private network in a simple manner and with the reduced cost to block it.
{"title":"Unwanted traffic characterization on IP networks by low interactive honeypot","authors":"Alisson Puska, M. N. Lima, A. Santos","doi":"10.1109/CNSM.2014.7014175","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014175","url":null,"abstract":"The increasing amount of unwanted traffic on the Internet consumes the available bandwidth on any network connected to it. Despite efforts to address this issue, it is still a challenge to differentiate unwanted traffic. Due to lack of knowledge or investment, organizations fail to implement security policies, such as BCP 38, which helps blocking the flow of unwanted data. This paper presents a method based on lowinteraction honeypots and network telescopes for identification and classification of unwanted traffic on IP networks. Our method aims to be simple and support low cost of deployment. An evaluation employed traces of real environments to show the method effectiveness. Results offer useful information about unwanted traffic, reaching a private network in a simple manner and with the reduced cost to block it.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127496408","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014187
D. Mocanu, G. Santandrea, W. Cerroni, F. Callegati, A. Liotta
Today the performance of network services and devices is mainly assessed using Quality of Services (QoS) factors. These provide statistics about the quality of the network behavior but cannot accurately reflect how the unpredictable impairments which might occur in the network end up affecting the perception of the final beneficiary of these services, i.e. the user. This situation arises because QoS-based performance analysis does not capture the combined end-to-end properties of networks and applications. In this paper, we introduce a new network performance methodology based on Quality of Experience benchmarks, whereby we estimate the quality of the service as it is perceived by the user. We illustrate this approach in the context of video streaming services, showing how to evaluate quality degradation in Software Defined Networks. Our approach is better suited to the evaluation of dynamic networks and helps better pinpointing the critical factors that affect the applications the most.
{"title":"Network performance assessment with Quality of experience benchmarks","authors":"D. Mocanu, G. Santandrea, W. Cerroni, F. Callegati, A. Liotta","doi":"10.1109/CNSM.2014.7014187","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014187","url":null,"abstract":"Today the performance of network services and devices is mainly assessed using Quality of Services (QoS) factors. These provide statistics about the quality of the network behavior but cannot accurately reflect how the unpredictable impairments which might occur in the network end up affecting the perception of the final beneficiary of these services, i.e. the user. This situation arises because QoS-based performance analysis does not capture the combined end-to-end properties of networks and applications. In this paper, we introduce a new network performance methodology based on Quality of Experience benchmarks, whereby we estimate the quality of the service as it is perceived by the user. We illustrate this approach in the context of video streaming services, showing how to evaluate quality degradation in Software Defined Networks. Our approach is better suited to the evaluation of dynamic networks and helps better pinpointing the critical factors that affect the applications the most.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130509238","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014180
Mark Shtern, Marin Litoiu
In order to extract value from Big Data, a data source provider has to share data among many consumers. As such, data sharing becomes an important feature of Big Data platforms. However, privacy concerns are the key obstacles that prevent organizations from implementing data sharing solutions. Moreover, currently, the data owner is responsible for preparing the data before releasing it to a 3rd party. The preparation of data for release is a complex task and can become an obstacle. In this paper, we propose an ecosystem which enables data sharing responsibilities among producers and consumers and mitigates some of the obstacles.
{"title":"A runtime sharing mechanism for Big Data platforms","authors":"Mark Shtern, Marin Litoiu","doi":"10.1109/CNSM.2014.7014180","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014180","url":null,"abstract":"In order to extract value from Big Data, a data source provider has to share data among many consumers. As such, data sharing becomes an important feature of Big Data platforms. However, privacy concerns are the key obstacles that prevent organizations from implementing data sharing solutions. Moreover, currently, the data owner is responsible for preparing the data before releasing it to a 3rd party. The preparation of data for release is a complex task and can become an obstacle. In this paper, we propose an ecosystem which enables data sharing responsibilities among producers and consumers and mitigates some of the obstacles.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122996903","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014161
M. Mehari, E. D. Poorter, I. Couckuyt, D. Deschrijver, Jono Vanhie-Van Gerwen, T. Dhaene, I. Moerman
A large amount of research focuses on experimentally optimizing performance of wireless solutions. Finding the optimal performance settings typically requires investigating all possible combinations of design parameters, while the number of required experiments increases exponentially for each considered design parameter. The aim of this paper is to analyze the applicability of global optimization techniques to reduce the optimization time of wireless experimentation. In particular, the paper applies the Efficient Global Optimization (EGO) algorithm implemented in the SUrrogate MOdeling (SUMO) toolbox inside a wireless testbed. The proposed techniques are implemented and evaluated in a wireless testbed using a realistic wireless conference network problem. The performance accuracy and experimentation time of an exhaustively searched experiment is compared against a SUMO optimized experiment. In our proof of concept, the proposed SUMO optimizer reaches 99.51% of the global optimum performance while requiring 10 times less experiments compared to the exhaustive search experiment.
{"title":"Efficient multi-objective optimization of wireless network problems on wireless testbeds","authors":"M. Mehari, E. D. Poorter, I. Couckuyt, D. Deschrijver, Jono Vanhie-Van Gerwen, T. Dhaene, I. Moerman","doi":"10.1109/CNSM.2014.7014161","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014161","url":null,"abstract":"A large amount of research focuses on experimentally optimizing performance of wireless solutions. Finding the optimal performance settings typically requires investigating all possible combinations of design parameters, while the number of required experiments increases exponentially for each considered design parameter. The aim of this paper is to analyze the applicability of global optimization techniques to reduce the optimization time of wireless experimentation. In particular, the paper applies the Efficient Global Optimization (EGO) algorithm implemented in the SUrrogate MOdeling (SUMO) toolbox inside a wireless testbed. The proposed techniques are implemented and evaluated in a wireless testbed using a realistic wireless conference network problem. The performance accuracy and experimentation time of an exhaustively searched experiment is compared against a SUMO optimized experiment. In our proof of concept, the proposed SUMO optimizer reaches 99.51% of the global optimum performance while requiring 10 times less experiments compared to the exhaustive search experiment.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127748688","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 : 2014-11-01DOI: 10.1109/CNSM.2014.7014196
S. S. L. Pereira, J. L. C. Silva, J. Maia
This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as a pipeline consisting of three modules: packet capture and preprocessing, flow reassembly, and classification with Machine Learning (ML). The modules are built as concurrent processes with well defined data interfaces between them so that any module can be improved and updated independently. In this pipeline, the flow reassembly function becomes the bottleneck of the performance. In this implementation, was used a efficient method of reassembly which results in a average delivery delay of 0.49 seconds, aproximately. For the classification module, the performances of the K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexible Naive Bayes (FNB) and AdaBoost Ensemble Learning Algorithm are compared in order to validate our approach.
{"title":"NTCS: A real time flow-based network traffic classification system","authors":"S. S. L. Pereira, J. L. C. Silva, J. Maia","doi":"10.1109/CNSM.2014.7014196","DOIUrl":"https://doi.org/10.1109/CNSM.2014.7014196","url":null,"abstract":"This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as a pipeline consisting of three modules: packet capture and preprocessing, flow reassembly, and classification with Machine Learning (ML). The modules are built as concurrent processes with well defined data interfaces between them so that any module can be improved and updated independently. In this pipeline, the flow reassembly function becomes the bottleneck of the performance. In this implementation, was used a efficient method of reassembly which results in a average delivery delay of 0.49 seconds, aproximately. For the classification module, the performances of the K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexible Naive Bayes (FNB) and AdaBoost Ensemble Learning Algorithm are compared in order to validate our approach.","PeriodicalId":268334,"journal":{"name":"10th International Conference on Network and Service Management (CNSM) and Workshop","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115716481","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：