Pub Date : 2018-04-23DOI: 10.1109/NOMS.2018.8406183
Oussama Soualah, Marouen Mechtri, Chaima Ghribi, D. Zeghlache
This paper proposes an Integer Linear Program (ILP) to address Virtualized Network Function Forwarding Graph (VNF-FG) placement and chaining with Virtualized Network Functions (VNFs) shared across tenants to optimize resource usage and increase provider revenue. The proposed algorithm selects a limited number of candidate hosts from the infrastructure to reduce the complexity of the ILP and scale with problem size. Results from extensive simulations report performance improvements in terms of rejection rate, energy consumption and scalability. Limiting the number of candidates is an efficient heuristic to ensure scalability.
{"title":"A green VNFs placement and chaining algorithm","authors":"Oussama Soualah, Marouen Mechtri, Chaima Ghribi, D. Zeghlache","doi":"10.1109/NOMS.2018.8406183","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406183","url":null,"abstract":"This paper proposes an Integer Linear Program (ILP) to address Virtualized Network Function Forwarding Graph (VNF-FG) placement and chaining with Virtualized Network Functions (VNFs) shared across tenants to optimize resource usage and increase provider revenue. The proposed algorithm selects a limited number of candidate hosts from the infrastructure to reduce the complexity of the ILP and scale with problem size. Results from extensive simulations report performance improvements in terms of rejection rate, energy consumption and scalability. Limiting the number of candidates is an efficient heuristic to ensure scalability.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81311453","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406213
Sheng Luo, Shangru Zhong, Kai Lei
Different from TCP/IP architecture, Named Data Networking (NDN) adopts a data-centric and in-network caching approach to achieve improved network efficiency and reduced traffic redundancy. As NDN begins to incrementally deploy on the real-world, there will be a hybrid network of TCP/IP and NDN during the transitional period. However, redeveloping TCP/IP- based applications for NDN is a daunting and time-consuming task. Thus, a more sensible and economical approach is to design an effective strategies for leveraging NDN to deliver IP datagrams and porting TCP/IP-based applications on NDN without changing its original code. Towards this end, this paper introduces three different migration methods at Internet layer, TCP layer and application layer, respectively to translate TCP/IP-based packets into NDN packets and run TCP/IP-based applications on NDN. By implementing these methods on a real NDN test-bed, we demonstrate the multi-level IP/NDN translation and migration mechanism is feasible. The analysis of testing results shows that each of the proposed methods is valid with varying benefits and costs: translating at TCP layer with more time overhead can have a less packets overhead than Internet layer. And when translated at application layer, the network load is reduced by half because of the in-network cache.
与TCP/IP架构不同，NDN (Named Data Networking)采用以数据为中心的网内缓存方式，提高网络效率，减少流量冗余。随着NDN在现实世界中的逐步部署，过渡时期将出现TCP/IP和NDN的混合网络。然而，为NDN重新开发基于TCP/IP的应用程序是一项艰巨而耗时的任务。因此，一个更明智和经济的方法是设计一个有效的策略，利用NDN来传递IP数据报，并在NDN上移植基于TCP/IP的应用程序，而不改变其原始代码。为此，本文分别在互联网层、TCP层和应用层介绍了三种不同的迁移方法，将基于TCP/ ip的数据包转换为NDN数据包，并在NDN上运行基于TCP/ ip的应用程序。通过在实际的NDN测试平台上实现这些方法，我们证明了多级IP/NDN转换和迁移机制是可行的。对测试结果的分析表明，每种方法都是有效的，并且具有不同的收益和成本:在时间开销较大的TCP层进行转换可以比Internet层进行转换获得更少的数据包开销。当在应用层进行转换时，由于网络内缓存，网络负载减少了一半。
{"title":"IP/NDN: A multi-level translation and migration mechanism","authors":"Sheng Luo, Shangru Zhong, Kai Lei","doi":"10.1109/NOMS.2018.8406213","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406213","url":null,"abstract":"Different from TCP/IP architecture, Named Data Networking (NDN) adopts a data-centric and in-network caching approach to achieve improved network efficiency and reduced traffic redundancy. As NDN begins to incrementally deploy on the real-world, there will be a hybrid network of TCP/IP and NDN during the transitional period. However, redeveloping TCP/IP- based applications for NDN is a daunting and time-consuming task. Thus, a more sensible and economical approach is to design an effective strategies for leveraging NDN to deliver IP datagrams and porting TCP/IP-based applications on NDN without changing its original code. Towards this end, this paper introduces three different migration methods at Internet layer, TCP layer and application layer, respectively to translate TCP/IP-based packets into NDN packets and run TCP/IP-based applications on NDN. By implementing these methods on a real NDN test-bed, we demonstrate the multi-level IP/NDN translation and migration mechanism is feasible. The analysis of testing results shows that each of the proposed methods is valid with varying benefits and costs: translating at TCP layer with more time overhead can have a less packets overhead than Internet layer. And when translated at application layer, the network load is reduced by half because of the in-network cache.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89401850","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406147
A. Raschellà, F. Bouhafs, M. Mackay, Q. Shi, J. Ortín, J. Gállego, M. Canales
This paper presents a novel Access Point (AP) selection strategy based on a potential game played at a centralized controller. The proposed approach relies on Software Defined Networking (SDN), which has long been considered in the literature as a method to control management functionalities for Wi-Fi networks. The use of SDN provides a global view of the network, which guarantees an efficient distribution of Wi-Fi users among the APs. The centralized potential game proposed in this paper is based on the Fittingness Factor (FF) concept, which is a metric reflecting the suitability of the available spectrum resources to the application requirements. This paper describes the development of a new SDN-based framework that implements the potential game-based algorithm relying on the FF for efficient AP selection. The simulation campaign illustrates the important gains, both in terms of data rates assigned to the Wi-Fi users and their satisfaction compared against the AP selection suggested by the IEEE 802.11 standards and another algorithm proposed in the literature.
{"title":"AP selection algorithm based on a potential game for large IEEE 802.11 WLANs","authors":"A. Raschellà, F. Bouhafs, M. Mackay, Q. Shi, J. Ortín, J. Gállego, M. Canales","doi":"10.1109/NOMS.2018.8406147","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406147","url":null,"abstract":"This paper presents a novel Access Point (AP) selection strategy based on a potential game played at a centralized controller. The proposed approach relies on Software Defined Networking (SDN), which has long been considered in the literature as a method to control management functionalities for Wi-Fi networks. The use of SDN provides a global view of the network, which guarantees an efficient distribution of Wi-Fi users among the APs. The centralized potential game proposed in this paper is based on the Fittingness Factor (FF) concept, which is a metric reflecting the suitability of the available spectrum resources to the application requirements. This paper describes the development of a new SDN-based framework that implements the potential game-based algorithm relying on the FF for efficient AP selection. The simulation campaign illustrates the important gains, both in terms of data rates assigned to the Wi-Fi users and their satisfaction compared against the AP selection suggested by the IEEE 802.11 standards and another algorithm proposed in the literature.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87350839","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406113
Muhammad Tahir Abbas, T. Khan, Asif Mahmood, Javier Jose Diaz Rivera, Wang-Cheol Song
Network slicing has been considered as one of the fundamental technologies in the fifth generation (5G) mobile networks. Slicing mechanism enables virtual networks while providing customized services on demand. There are several papers attempting to narrow down the architectural requirement for 5G networks. Many of them consider the aspect of slice creation as a central point, sometimes strengthening slices with slice isolation. The aim of this paper is to focus more on network slice management, slicing of transport network (TN) and challenges to elaborate technological options and enablers, irrespective of the slicing mechanism. Our proposed framework creates, manages and associates the slice to user equipment (UE) upon the request made by different applications. Proposed framework exploits the key features offered by CORD including OpenStack and ONOS as well as modules based on M-CORD such as vBBU, NSSF and vEPC for establishing a network slice scenario.
{"title":"Introducing network slice management inside M-CORD-based-5G framework","authors":"Muhammad Tahir Abbas, T. Khan, Asif Mahmood, Javier Jose Diaz Rivera, Wang-Cheol Song","doi":"10.1109/NOMS.2018.8406113","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406113","url":null,"abstract":"Network slicing has been considered as one of the fundamental technologies in the fifth generation (5G) mobile networks. Slicing mechanism enables virtual networks while providing customized services on demand. There are several papers attempting to narrow down the architectural requirement for 5G networks. Many of them consider the aspect of slice creation as a central point, sometimes strengthening slices with slice isolation. The aim of this paper is to focus more on network slice management, slicing of transport network (TN) and challenges to elaborate technological options and enablers, irrespective of the slicing mechanism. Our proposed framework creates, manages and associates the slice to user equipment (UE) upon the request made by different applications. Proposed framework exploits the key features offered by CORD including OpenStack and ONOS as well as modules based on M-CORD such as vBBU, NSSF and vEPC for establishing a network slice scenario.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87967089","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406236
Kostas Katsalis, N. Nikaein, A. Huang
Network slicing is expected to be the main pillar around which virtualization technologies together with SDN control and NFV, will provide on-demand network and cloud infrastructures and facilitate rapid service deployment. In this paper we present JOX, an event-driven orchestrator for the virtu- alized network, operating on top of the Juju management system, that inherently supports network slicing. JOX is a python-based generic network slicing orchestrator, with a plugins architecture that is able to support different segments of a modern mobile edge network. We present a concrete prototype implementation of JOX for LTE, with experimental results considering footprint analysis, performance metrics, and implementation experience for slicing and orchestrating of an operational LTE network.
{"title":"JOX: An event-driven orchestrator for 5G network slicing","authors":"Kostas Katsalis, N. Nikaein, A. Huang","doi":"10.1109/NOMS.2018.8406236","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406236","url":null,"abstract":"Network slicing is expected to be the main pillar around which virtualization technologies together with SDN control and NFV, will provide on-demand network and cloud infrastructures and facilitate rapid service deployment. In this paper we present JOX, an event-driven orchestrator for the virtu- alized network, operating on top of the Juju management system, that inherently supports network slicing. JOX is a python-based generic network slicing orchestrator, with a plugins architecture that is able to support different segments of a modern mobile edge network. We present a concrete prototype implementation of JOX for LTE, with experimental results considering footprint analysis, performance metrics, and implementation experience for slicing and orchestrating of an operational LTE network.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91415652","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406228
Stanislav Lange, Lorenz Reinhart, T. Zinner, D. Hock, N. Gray, P. Tran-Gia
With software defined networking (SDN), operators benefit from a higher flexibility, cost efficiency, as well as programmability of their networks. Since modern networks are comprised of a multitude of heterogeneous devices and also include non-SDN legacy devices, network management systems (NMSs) are often used in order to monitor and configure the network. Although both, the SDN controller and the NMS, have a centralized view of the network, they operate at different time scales and deal with information at different levels of granularity. In this work, we investigate the impact on the network performance when an NMS regularly provides information to an SDN controller. To this end, we design, implement, and compare three interaction mechanisms based on the ONOS controller. These represent different trade-offs regarding the complexity of the resulting system and its performance. In addition to the default ONOS controller, we develop two extended versions. One performs hash-based load balancing on equal cost paths while the other utilizes external NMS information via ONOS's intent and annotation framework to optimize control plane decisions. In addition to evaluations that show a significant performance improvement when using the optimized controllers, we present a parameter study that highlights the performance impact of network characteristics like the flow interarrival time, the flow duration, and the number of active flows.
{"title":"Integrating network management information into the SDN control plane","authors":"Stanislav Lange, Lorenz Reinhart, T. Zinner, D. Hock, N. Gray, P. Tran-Gia","doi":"10.1109/NOMS.2018.8406228","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406228","url":null,"abstract":"With software defined networking (SDN), operators benefit from a higher flexibility, cost efficiency, as well as programmability of their networks. Since modern networks are comprised of a multitude of heterogeneous devices and also include non-SDN legacy devices, network management systems (NMSs) are often used in order to monitor and configure the network. Although both, the SDN controller and the NMS, have a centralized view of the network, they operate at different time scales and deal with information at different levels of granularity. In this work, we investigate the impact on the network performance when an NMS regularly provides information to an SDN controller. To this end, we design, implement, and compare three interaction mechanisms based on the ONOS controller. These represent different trade-offs regarding the complexity of the resulting system and its performance. In addition to the default ONOS controller, we develop two extended versions. One performs hash-based load balancing on equal cost paths while the other utilizes external NMS information via ONOS's intent and annotation framework to optimize control plane decisions. In addition to evaluations that show a significant performance improvement when using the optimized controllers, we present a parameter study that highlights the performance impact of network characteristics like the flow interarrival time, the flow duration, and the number of active flows.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91518707","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406203
P. Velan
Network flow monitoring has been used for more than 20 years and has become an important part of network accounting and security. A significant effort was invested into the standardization of flow monitoring by the Internet Engineering Task Force (IETF). The flow monitoring has steadily evolved to satisfy new requirements created by the demand for increased visibility and accuracy. Therefore, it is not surprising that even the most recent flow definition created by the IETF does not consider several specifics of the flow monitoring process as it is used nowadays. This paper presents a revised flow definition that is more generic and is designed to accommodate more specific flow monitoring requirements. Moreover, we formalize our definition to avoid ambiguity and imprecision introduced by the use of natural language. One additional benefit of formalizing the flow definition is that it implicitly describes the flow creation process as well.
{"title":"Improving network flow definition: Formalization and applicability","authors":"P. Velan","doi":"10.1109/NOMS.2018.8406203","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406203","url":null,"abstract":"Network flow monitoring has been used for more than 20 years and has become an important part of network accounting and security. A significant effort was invested into the standardization of flow monitoring by the Internet Engineering Task Force (IETF). The flow monitoring has steadily evolved to satisfy new requirements created by the demand for increased visibility and accuracy. Therefore, it is not surprising that even the most recent flow definition created by the IETF does not consider several specifics of the flow monitoring process as it is used nowadays. This paper presents a revised flow definition that is more generic and is designed to accommodate more specific flow monitoring requirements. Moreover, we formalize our definition to avoid ambiguity and imprecision introduced by the use of natural language. One additional benefit of formalizing the flow definition is that it implicitly describes the flow creation process as well.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74935426","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406140
Thomas Lin, Byungchul Park, H. Bannazadeh, A. Leon-Garcia
The SAVI testbed is a multi-tier SDN-enabled het-erogeneous cloud created as an application enablement platform for academic research. It was developed to investigate the hypothesis that the entire infrastructure can be virtualized and abstracted as a service. Key to this investigation was the creation of a resource management system based on the concept of Software-Defined Infrastructure (SDI), which enables integrated control and management over heterogeneous resources and exposes a programmable interface for users. In this paper, we present our experiences in designing and deploying the Canadian national SAVI testbed, and discuss the various lessons learned along the way. In addition, we describe our ongoing work to enhance the testbed management system to meet the demands and challenges of the IoT era.
{"title":"Deploying a multi-tier heterogeneous cloud: Experiences and lessons from the SAVI testbed","authors":"Thomas Lin, Byungchul Park, H. Bannazadeh, A. Leon-Garcia","doi":"10.1109/NOMS.2018.8406140","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406140","url":null,"abstract":"The SAVI testbed is a multi-tier SDN-enabled het-erogeneous cloud created as an application enablement platform for academic research. It was developed to investigate the hypothesis that the entire infrastructure can be virtualized and abstracted as a service. Key to this investigation was the creation of a resource management system based on the concept of Software-Defined Infrastructure (SDI), which enables integrated control and management over heterogeneous resources and exposes a programmable interface for users. In this paper, we present our experiences in designing and deploying the Canadian national SAVI testbed, and discuss the various lessons learned along the way. In addition, we describe our ongoing work to enhance the testbed management system to meet the demands and challenges of the IoT era.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73232180","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406287
Fenfen Huang, Wenbin Yao
Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with large number of weights consume considerable storage and memory bandwidth. To address this limitation, pruning is an effective way to compress neural networks with high accuracy. To address this limitation, we proposed a method for optimization on parametric model. This method contains three steps. First, we train the network like conventional training. Next, we prune the unimportant connections and retrain the network to get the sparse weight matrix. Finally, we use Singularly Valuable Decomposition (SVD) to do further compression on the sparse weight matrix. Our experiments on MNIST dataset show that our method has the ability on reducing the model size by 4 times and the accuracy could still be kept over 90%.
{"title":"Optimization on parametric model","authors":"Fenfen Huang, Wenbin Yao","doi":"10.1109/NOMS.2018.8406287","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406287","url":null,"abstract":"Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with large number of weights consume considerable storage and memory bandwidth. To address this limitation, pruning is an effective way to compress neural networks with high accuracy. To address this limitation, we proposed a method for optimization on parametric model. This method contains three steps. First, we train the network like conventional training. Next, we prune the unimportant connections and retrain the network to get the sparse weight matrix. Finally, we use Singularly Valuable Decomposition (SVD) to do further compression on the sparse weight matrix. Our experiments on MNIST dataset show that our method has the ability on reducing the model size by 4 times and the accuracy could still be kept over 90%.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83789481","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 : 2018-04-23DOI: 10.1109/NOMS.2018.8406257
José Santos, P. Leroux, T. Wauters, B. Volckaert, F. Turck
In recent years, the Internet of Things (IoT) has introduced a whole new set of challenges and opportunities in Telecommunications. Traffic over wireless networks has been increasing exponentially since many sensors and everyday devices are being connected. Current networks must therefore adapt to and cope with the specific requirements introduced by IoT. One fundamental need of the next generation networked systems is to monitor IoT applications, especially those dealing with personal health monitoring or emergency response services, which have stringent latency requirements when dealing with malfunctions or unusual events. Traditional anomaly detection approaches are not suitable for delay-sensitive IoT applications since these approaches are significantly impacted by latency. With the advent of 5G networks and by exploiting the advantages of new paradigms, such as Software-Defined Networking (SDN), Network Function Virtualization (NFV) and edge computing, scalable, low-latency anomaly detection becomes feasible. In this paper, an anomaly detection solution for Smart City applications is presented, focusing on low-power Fog Computing solutions and evaluated within the scope of Antwerp's City of Things testbed. Based on a collected large dataset, the most appropriate Low Power Wide Area Network (LPWAN) technologies for our Smart City use case are investigated.
{"title":"Anomaly detection for Smart City applications over 5G low power wide area networks","authors":"José Santos, P. Leroux, T. Wauters, B. Volckaert, F. Turck","doi":"10.1109/NOMS.2018.8406257","DOIUrl":"https://doi.org/10.1109/NOMS.2018.8406257","url":null,"abstract":"In recent years, the Internet of Things (IoT) has introduced a whole new set of challenges and opportunities in Telecommunications. Traffic over wireless networks has been increasing exponentially since many sensors and everyday devices are being connected. Current networks must therefore adapt to and cope with the specific requirements introduced by IoT. One fundamental need of the next generation networked systems is to monitor IoT applications, especially those dealing with personal health monitoring or emergency response services, which have stringent latency requirements when dealing with malfunctions or unusual events. Traditional anomaly detection approaches are not suitable for delay-sensitive IoT applications since these approaches are significantly impacted by latency. With the advent of 5G networks and by exploiting the advantages of new paradigms, such as Software-Defined Networking (SDN), Network Function Virtualization (NFV) and edge computing, scalable, low-latency anomaly detection becomes feasible. In this paper, an anomaly detection solution for Smart City applications is presented, focusing on low-power Fog Computing solutions and evaluated within the scope of Antwerp's City of Things testbed. Based on a collected large dataset, the most appropriate Low Power Wide Area Network (LPWAN) technologies for our Smart City use case are investigated.","PeriodicalId":19331,"journal":{"name":"NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88859910","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：