Pub Date : 2017-11-01DOI: 10.23919/CNSM.2017.8255976
Patrik Kristel, Jan Lucansky, I. Kotuliak
Anonymous communication networks, such as Tor, are facing big challenge how to deliver content to users in low latency and with no interruption. The latency issues were caused by increased amount of transferred data and low-bandwidth nodes in Tor network. Those are limiting overall circuit capacity providing to users. Conflux, the Tor plugin, is improving effort and decreasing latency time by creating multipath within Tor circuits. Conflux is doing dynamic traffic-splitting and load-balancing through multipath to improve throughput and avoid bottlenecks in Tor circuits. Our solution is focusing to analyze and modification network flows and sessions in Tor network. As an output of problem's analysis we're proposing possibilities to improve Conflux's performance by its modification and deploy to the Tor network. The paper describes solution implementation, setup and configuration Tor client and Tor exit node. We're explaining necessary modifications that need to be provided on Tor components. Our solution achieved average improvement versus Conflux more than 20% decrease of download time in various file size.
{"title":"Traffic optimization in anonymous networks","authors":"Patrik Kristel, Jan Lucansky, I. Kotuliak","doi":"10.23919/CNSM.2017.8255976","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8255976","url":null,"abstract":"Anonymous communication networks, such as Tor, are facing big challenge how to deliver content to users in low latency and with no interruption. The latency issues were caused by increased amount of transferred data and low-bandwidth nodes in Tor network. Those are limiting overall circuit capacity providing to users. Conflux, the Tor plugin, is improving effort and decreasing latency time by creating multipath within Tor circuits. Conflux is doing dynamic traffic-splitting and load-balancing through multipath to improve throughput and avoid bottlenecks in Tor circuits. Our solution is focusing to analyze and modification network flows and sessions in Tor network. As an output of problem's analysis we're proposing possibilities to improve Conflux's performance by its modification and deploy to the Tor network. The paper describes solution implementation, setup and configuration Tor client and Tor exit node. We're explaining necessary modifications that need to be provided on Tor components. Our solution achieved average improvement versus Conflux more than 20% decrease of download time in various file size.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127385200","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256007
Hongfu Guo, F. Zhou, Lei Feng, Peng Yu, Wenjing Li
Hybrid cognitive radio (CR) relays serve cellular users in a two-hop fashion, which jointly utilize both licensed and unlicensed radio spectrums to significantly increase the system capacity. User equipments (UEs) need to be actively associated with the macro-cell BS or CR relays having a more lightly loaded spectrum if the quality of services (QoS) can be guaranteed. To this end, this paper investigates optimal user association for load balancing problem in cellular network with hybrid cognitive radio relays. Firstly, we propose a multi-objective user association optimization model to balance the loads among different tiers while reducing the total resource occupancy. Then, this multiobjective problem is converted into a single one by the linear weighing-sum method and a genetic algorithm is introduced to solve it. The numerical simulation results show that our proposed scheme can obtain more balanced resources occupation, better throughput performance, and lower blocking rate compared with the heuristic and max-power strategies.
{"title":"User association for load balancing in cellular network with hybrid cognitive radio relays","authors":"Hongfu Guo, F. Zhou, Lei Feng, Peng Yu, Wenjing Li","doi":"10.23919/CNSM.2017.8256007","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256007","url":null,"abstract":"Hybrid cognitive radio (CR) relays serve cellular users in a two-hop fashion, which jointly utilize both licensed and unlicensed radio spectrums to significantly increase the system capacity. User equipments (UEs) need to be actively associated with the macro-cell BS or CR relays having a more lightly loaded spectrum if the quality of services (QoS) can be guaranteed. To this end, this paper investigates optimal user association for load balancing problem in cellular network with hybrid cognitive radio relays. Firstly, we propose a multi-objective user association optimization model to balance the loads among different tiers while reducing the total resource occupancy. Then, this multiobjective problem is converted into a single one by the linear weighing-sum method and a genetic algorithm is introduced to solve it. The numerical simulation results show that our proposed scheme can obtain more balanced resources occupation, better throughput performance, and lower blocking rate compared with the heuristic and max-power strategies.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130438026","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8255998
P. Casas, J. Vanerio, K. Fukuda
The application of machine learning models to the analysis of network measurement problems has largely increased in the last decade; however, there is still no clear best-practice or silver bullet approach to address these problems in a general context, and only adhoc and tailored approaches have been evaluated so far. While deep-learning models have provided a major breakthrough in highly-dimensional problems such as image processing, it is difficult to say today which is the best model to address the analysis of large volumes of highly-dimensional data collected in operational networks. In this paper we present a potential solution to fill this gap, exploring the application of ensemble learning models to multiple network measurement problems. We introduce GML Learning, a generic Machine Learning model for the analysis of network measurements. The GML model is a generalization of the well-known stacking approach to ensemble learning, and follows the concepts of the Super Learner model. The Super Learner performs asymptotically as well as the best input base or weak learners, providing a very powerful approach to tackle multiple problems with the same technique. In addition, it defines an approach to minimize over-fitting likelihood during training, using a variant of cross-validation. We deploy the GML model on top of Big-DAMA, a big data analytics framework for network measurement applications. We test the proposed solution in five different and assorted network measurement problems, including detection of network attacks and anomalies, QoE modeling and prediction, and Internet-paths dynamics tracking. Results confirm that the GML model provides better results than any of the single baseline models of the stack, and outperforms traditional bagging and boosting ensemble learning approaches. The GML Learning model opens the door for a generalization of a best-practice technique for the analysis of network measurements.
{"title":"GML learning, a generic machine learning model for network measurements analysis","authors":"P. Casas, J. Vanerio, K. Fukuda","doi":"10.23919/CNSM.2017.8255998","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8255998","url":null,"abstract":"The application of machine learning models to the analysis of network measurement problems has largely increased in the last decade; however, there is still no clear best-practice or silver bullet approach to address these problems in a general context, and only adhoc and tailored approaches have been evaluated so far. While deep-learning models have provided a major breakthrough in highly-dimensional problems such as image processing, it is difficult to say today which is the best model to address the analysis of large volumes of highly-dimensional data collected in operational networks. In this paper we present a potential solution to fill this gap, exploring the application of ensemble learning models to multiple network measurement problems. We introduce GML Learning, a generic Machine Learning model for the analysis of network measurements. The GML model is a generalization of the well-known stacking approach to ensemble learning, and follows the concepts of the Super Learner model. The Super Learner performs asymptotically as well as the best input base or weak learners, providing a very powerful approach to tackle multiple problems with the same technique. In addition, it defines an approach to minimize over-fitting likelihood during training, using a variant of cross-validation. We deploy the GML model on top of Big-DAMA, a big data analytics framework for network measurement applications. We test the proposed solution in five different and assorted network measurement problems, including detection of network attacks and anomalies, QoE modeling and prediction, and Internet-paths dynamics tracking. Results confirm that the GML model provides better results than any of the single baseline models of the stack, and outperforms traditional bagging and boosting ensemble learning approaches. The GML Learning model opens the door for a generalization of a best-practice technique for the analysis of network measurements.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134371055","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256004
Meng Li, Wenjing Li, Peng Yu, F. Zhou
The power SCADA system is designed to ensure the safe operation of the power system. The SCADA communication network as an information exchange carrier between remote terminal units and master stations, is the key part of the SCADA system, and it has a high requirement for security. However, due to the wide distribution of the network and the interconnected network structure, it is susceptible to risks. So there is an urgent need for accurate and real-time risk prediction. In this paper, we propose a risk prediction model based on entropy-gray model, where the gray model is used to predict the values of the network risk indexes, and the entropy method is to determine the weight of those risk indexes. Finally, the overall risk value of the network is decided with analytic hierarchy process. Simulation results show that the proposed entropy-gray method can achieve accurate and timely risk prediction.
{"title":"Risk prediction of the SCADA communication network based on entropy-gray model","authors":"Meng Li, Wenjing Li, Peng Yu, F. Zhou","doi":"10.23919/CNSM.2017.8256004","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256004","url":null,"abstract":"The power SCADA system is designed to ensure the safe operation of the power system. The SCADA communication network as an information exchange carrier between remote terminal units and master stations, is the key part of the SCADA system, and it has a high requirement for security. However, due to the wide distribution of the network and the interconnected network structure, it is susceptible to risks. So there is an urgent need for accurate and real-time risk prediction. In this paper, we propose a risk prediction model based on entropy-gray model, where the gray model is used to predict the values of the network risk indexes, and the entropy method is to determine the weight of those risk indexes. Finally, the overall risk value of the network is decided with analytic hierarchy process. Simulation results show that the proposed entropy-gray method can achieve accurate and timely risk prediction.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123728595","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256025
J. Hyun, Y. Won, Kenjiro Cho, Romain Fontugne, J. Chung, J. W. Hong
This paper provides a temporal cellular and WiFi networks analysis from a nationwide crowdsourcing measurement study. Our dataset consists of 2.98M user-initiated quality tests on 3G/LTE/WiFi involving 157K mobile devices from Nov. 2012 to July 2016 (187 weeks) in South Korea. Our analysis explains changes in QoS from the user perspective, not Mobile Network Operators (MNO). We revealed that WiFi shows twice higher compounded quarterly growth rate for download throughput against LTE. Yet, LTE and WiFi show almost no difference in absolute download throughput value as of mid 2016. Second, LTE delivers relatively low latency, less-varying loss rate, and higher throughput in overall. Finally, the result shows that the evolution for the high-end LTE services has been faster than user adoption, where the majority of the LTE users stays below 75 Mbps of throughput.
{"title":"High-end LTE service evolution in Korea: 4 years of nationwide mobile network measurements","authors":"J. Hyun, Y. Won, Kenjiro Cho, Romain Fontugne, J. Chung, J. W. Hong","doi":"10.23919/CNSM.2017.8256025","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256025","url":null,"abstract":"This paper provides a temporal cellular and WiFi networks analysis from a nationwide crowdsourcing measurement study. Our dataset consists of 2.98M user-initiated quality tests on 3G/LTE/WiFi involving 157K mobile devices from Nov. 2012 to July 2016 (187 weeks) in South Korea. Our analysis explains changes in QoS from the user perspective, not Mobile Network Operators (MNO). We revealed that WiFi shows twice higher compounded quarterly growth rate for download throughput against LTE. Yet, LTE and WiFi show almost no difference in absolute download throughput value as of mid 2016. Second, LTE delivers relatively low latency, less-varying loss rate, and higher throughput in overall. Finally, the result shows that the evolution for the high-end LTE services has been faster than user adoption, where the majority of the LTE users stays below 75 Mbps of throughput.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124654944","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256017
H. Alameddine, Long Qu, C. Assi
The fifth generation (5G) of cellular networks is emerging as the key enabler of killer real-time applications, such as tactile Internet, augmented and virtual reality, tele-driving, autonomous driving, etc., providing them with the much needed ultra-reliable and ultra-low latency services. Such applications are expected to take full advantages of recent developments in the areas of cloud and edge computing, and exploit emerging industrial initiatives such as Software Defined Networks (SDN) and Network Function Virtualization (NFV). Often, these 5G applications require network functions (e.g., IDSs, load balancers, etc.) to cater for their end-to-end services. This paper focuses on chaining network functions and services for these applications, and in particular considers those delay sensitive ones. Here, we account for services with deadlines and formulate the joint problem of network function mapping, routing and scheduling mathematically and highlight its complexity. Then, we present an efficient method for solving these sub-problems sequentially and validate its performance numerically. We also propose and characterize the performance of a Tabu search-based approach that we design to solve the problem. Our numerical evaluation reveals the efficiency of our sequential method and the scalability of our Tabu-based algorithm.
{"title":"Scheduling service function chains for ultra-low latency network services","authors":"H. Alameddine, Long Qu, C. Assi","doi":"10.23919/CNSM.2017.8256017","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256017","url":null,"abstract":"The fifth generation (5G) of cellular networks is emerging as the key enabler of killer real-time applications, such as tactile Internet, augmented and virtual reality, tele-driving, autonomous driving, etc., providing them with the much needed ultra-reliable and ultra-low latency services. Such applications are expected to take full advantages of recent developments in the areas of cloud and edge computing, and exploit emerging industrial initiatives such as Software Defined Networks (SDN) and Network Function Virtualization (NFV). Often, these 5G applications require network functions (e.g., IDSs, load balancers, etc.) to cater for their end-to-end services. This paper focuses on chaining network functions and services for these applications, and in particular considers those delay sensitive ones. Here, we account for services with deadlines and formulate the joint problem of network function mapping, routing and scheduling mathematically and highlight its complexity. Then, we present an efficient method for solving these sub-problems sequentially and validate its performance numerically. We also propose and characterize the performance of a Tabu search-based approach that we design to solve the problem. Our numerical evaluation reveals the efficiency of our sequential method and the scalability of our Tabu-based algorithm.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115679503","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256002
P. Vizarreta, Kishor S. Trivedi, B. Helvik, P. Heegaard, W. Kellerer, C. M. Machuca
Software Defined Networking (SDN) exposes critical networking decisions, such as traffic routing or enforcement of the critical security policies, to a software entity known as the SDN controller. Controller software, as written by humans, is intrinsically prone to bugs, which may impair the network performance as a whole, if activated. Software reliability growth models (SRGM) are often used to estimate and predict the reliability of the software in the operational phase based on the fault report data during the testing phase. These models can be used to predict the number of residual bugs in the software, as well as failure intensity, software reliability and optimal software release time. In this paper we analyze ten releases of ONOS open source controller, whose uncensored fault reports are available online.
{"title":"An empirical study of software reliability in SDN controllers","authors":"P. Vizarreta, Kishor S. Trivedi, B. Helvik, P. Heegaard, W. Kellerer, C. M. Machuca","doi":"10.23919/CNSM.2017.8256002","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256002","url":null,"abstract":"Software Defined Networking (SDN) exposes critical networking decisions, such as traffic routing or enforcement of the critical security policies, to a software entity known as the SDN controller. Controller software, as written by humans, is intrinsically prone to bugs, which may impair the network performance as a whole, if activated. Software reliability growth models (SRGM) are often used to estimate and predict the reliability of the software in the operational phase based on the fault report data during the testing phase. These models can be used to predict the number of residual bugs in the software, as well as failure intensity, software reliability and optimal software release time. In this paper we analyze ten releases of ONOS open source controller, whose uncensored fault reports are available online.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"314 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531545","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256050
P. Thorat, Seil Jeon, S. M. Raza, Hyunseung Choo
An essential requirement in operating a carriergrade network (CGN) is ensuring the high availability and reliability. Software-defined networking (SDN) is expected to address such requirement while improving the network management. One challenging issue faced in the process of enhancing the reliability of SDN-enabled CGN is how to achieve rapid recovery with minimal effort. There are two well-known approaches to determine the failover scope: end-to-end (global) detouring and local detouring. Particularly, the local detouring approach provides an efficient means to achieve faster recovery, as it locally detours the disrupted flows around the failed network components using a preconfigured alternative path. However, it requires thousands of flow entries per switch to be configured. To address the technical challenges, we propose a fault-tolerant forwarding table design (FFTD), which groups the flows using group entries and aggregates the flows using a tagging mechanism for scalable and rapid recovery from the dual-failures of switches or links without overburdening the controller and the flow table's memory. Our extensive emulation results reveal that the proposed FFTD satisfies the CGN's 50 ms recovery requirement. Additionally, it reduces the alternate path flow storage requirement by up to 99%.
{"title":"Pre-provisioning of local protection for handling dual-failures in OpenFlow-based networks","authors":"P. Thorat, Seil Jeon, S. M. Raza, Hyunseung Choo","doi":"10.23919/CNSM.2017.8256050","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256050","url":null,"abstract":"An essential requirement in operating a carriergrade network (CGN) is ensuring the high availability and reliability. Software-defined networking (SDN) is expected to address such requirement while improving the network management. One challenging issue faced in the process of enhancing the reliability of SDN-enabled CGN is how to achieve rapid recovery with minimal effort. There are two well-known approaches to determine the failover scope: end-to-end (global) detouring and local detouring. Particularly, the local detouring approach provides an efficient means to achieve faster recovery, as it locally detours the disrupted flows around the failed network components using a preconfigured alternative path. However, it requires thousands of flow entries per switch to be configured. To address the technical challenges, we propose a fault-tolerant forwarding table design (FFTD), which groups the flows using group entries and aggregates the flows using a tagging mechanism for scalable and rapid recovery from the dual-failures of switches or links without overburdening the controller and the flow table's memory. Our extensive emulation results reveal that the proposed FFTD satisfies the CGN's 50 ms recovery requirement. Additionally, it reduces the alternate path flow storage requirement by up to 99%.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114744672","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 : 2017-11-01DOI: 10.23919/CNSM.2017.8256033
A. Jakaria, M. Rahman, Carol J. Fung
Cyber defense today heavily depends on expensive and proprietary hardware deployed at fixed locations. Network functions virtualization (NFV) reduces the limitations of these vendor specific hardware by allowing a flexible and dynamic implementation of virtual network functions in virtual machines running on commercial off-the-shelf servers. These network functions can work as a filter to distinguish between a legitimate packet and an attack packet, and can be deployed dynamically to balance the variable attack load. However, allocating resources to these virtual machines is an NP-hard problem. In this work, we propose a solution to this problem and determine the number and placement of the VMs. We design and implement NFVSynth, an automated framework that models the resource specifications, incoming packet processing requirements, and network bandwidth constraints. It uses satisfiability modulo theories (SMT) for modeling this synthesis problem and provides a satisfiable solution. We also present simulated experiments to demonstrate the scalability and usability of the solution.
{"title":"Automated synthesis of NFV topology: A security requirement-oriented design","authors":"A. Jakaria, M. Rahman, Carol J. Fung","doi":"10.23919/CNSM.2017.8256033","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8256033","url":null,"abstract":"Cyber defense today heavily depends on expensive and proprietary hardware deployed at fixed locations. Network functions virtualization (NFV) reduces the limitations of these vendor specific hardware by allowing a flexible and dynamic implementation of virtual network functions in virtual machines running on commercial off-the-shelf servers. These network functions can work as a filter to distinguish between a legitimate packet and an attack packet, and can be deployed dynamically to balance the variable attack load. However, allocating resources to these virtual machines is an NP-hard problem. In this work, we propose a solution to this problem and determine the number and placement of the VMs. We design and implement NFVSynth, an automated framework that models the resource specifications, incoming packet processing requirements, and network bandwidth constraints. It uses satisfiability modulo theories (SMT) for modeling this synthesis problem and provides a satisfiable solution. We also present simulated experiments to demonstrate the scalability and usability of the solution.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129643437","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 network virtualization environment, multiple virtual networks share the same resource of a physical network. Since the physical resources of a substrate network is limited, it is necessary to improve the utilization of physical resources. Considering the resource requirement of a virtual network may change over its lifetime, we propose a prediction-based resource management mechanism. To increase the utilization of the substrate network, we can adjust the resource allocated to the virtual network based on the result of prediction. Additionally, in order to avoid the result of prediction deviates from the real requirement, we compare our prediction result with the collection of the resource utilization at real time to ensure the correctness of our result. The simulation results show that our approach can increase the utilization of the physical resource and improve the virtual network acceptance ratio while ensuring the requirement of the virtual networks.
{"title":"A prediction-based dynamic resource management approach for network virtualization","authors":"Jiacong Li, Ying Wang, Zhanwei Wu, Sixiang Feng, Xue-song Qiu","doi":"10.23919/CNSM.2017.8255980","DOIUrl":"https://doi.org/10.23919/CNSM.2017.8255980","url":null,"abstract":"In network virtualization environment, multiple virtual networks share the same resource of a physical network. Since the physical resources of a substrate network is limited, it is necessary to improve the utilization of physical resources. Considering the resource requirement of a virtual network may change over its lifetime, we propose a prediction-based resource management mechanism. To increase the utilization of the substrate network, we can adjust the resource allocated to the virtual network based on the result of prediction. Additionally, in order to avoid the result of prediction deviates from the real requirement, we compare our prediction result with the collection of the resource utilization at real time to ensure the correctness of our result. The simulation results show that our approach can increase the utilization of the physical resource and improve the virtual network acceptance ratio while ensuring the requirement of the virtual networks.","PeriodicalId":211611,"journal":{"name":"2017 13th International Conference on Network and Service Management (CNSM)","volume":"1973 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134194892","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：