Pub Date : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702535
Matthieu Coudron, Stefano Secci, G. Maier, G. Pujolle, A. Pattavina
External reliability in data-center networking is today commonly reached via forms of provider multihoming, so as to guarantee higher service availability rates. In parallel, Cloud users also resort to multihoming via different device access interfaces (Wi-fi, 3G, Wired). Both practices add path diversity between Cloud users and servers, unusable with legacy communication protocols. To overcome this void, we present a holistic multipath communication architecture for Cloud access and inter-Cloud communications, and defend its possible implementation using three promising recent protocols functionally acting at three different communication layers: MPTCP, LISP and TRILL.
{"title":"Boosting Cloud Communications through a Crosslayer Multipath Protocol Architecture","authors":"Matthieu Coudron, Stefano Secci, G. Maier, G. Pujolle, A. Pattavina","doi":"10.1109/SDN4FNS.2013.6702535","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702535","url":null,"abstract":"External reliability in data-center networking is today commonly reached via forms of provider multihoming, so as to guarantee higher service availability rates. In parallel, Cloud users also resort to multihoming via different device access interfaces (Wi-fi, 3G, Wired). Both practices add path diversity between Cloud users and servers, unusable with legacy communication protocols. To overcome this void, we present a holistic multipath communication architecture for Cloud access and inter-Cloud communications, and defend its possible implementation using three promising recent protocols functionally acting at three different communication layers: MPTCP, LISP and TRILL.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80786658","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702532
A. Basta, W. Kellerer, M. Hoffmann, K. Hoffmann, E. Schmidt
The recent initiative of Network Functions Virtualization (NFV) aims to deliver any data- plane processing or control-plane function in high volume data centers or network elements to decrease operational cost and increase deployment flexibility. In order to dynamically direct traffic flows between respective network elements, Software Defined Networking (SDN) can be seen as one enabler. In this paper, we focus on mobile core network nodes such as the MME, HSS, S- and P- Gateway as standardized for the LTE Evolved Packet Core (EPC). One straightforward solution for a virtualized EPC architecture would be to move all EPC network nodes completely into a data center and handle the data traffic via SDN-enabled switches. However, this solution would keep the conventional monolithic architecture unchanged. A possible split in the EPC functionality between a centralized data center and operator's transport network elements could be needed to provide the desired flexibility, performance and TCO reduction. Therefore, we have analyzed the EPC nodes and classified their functions according to their impact on data-plane and control-plane processing. We propose a mapping for these functions on four alternative deployment frameworks based on SDN and OpenFlow (OF). In addition, we investigate the current OF implementation's capability to realize basic core operations such as QoS, data classification, tunneling and charging. Our analysis shows that functions, which involve high data packet processing such as tunneling, have more potential to be kept on the data-plane network element, i.e. realized by an OpenFlow Switch. We argue for an enhanced OF network element NE+, which contains additional network functions next to the basic OpenFlow protocol.
{"title":"A Virtual SDN-Enabled LTE EPC Architecture: A Case Study for S-/P-Gateways Functions","authors":"A. Basta, W. Kellerer, M. Hoffmann, K. Hoffmann, E. Schmidt","doi":"10.1109/SDN4FNS.2013.6702532","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702532","url":null,"abstract":"The recent initiative of Network Functions Virtualization (NFV) aims to deliver any data- plane processing or control-plane function in high volume data centers or network elements to decrease operational cost and increase deployment flexibility. In order to dynamically direct traffic flows between respective network elements, Software Defined Networking (SDN) can be seen as one enabler. In this paper, we focus on mobile core network nodes such as the MME, HSS, S- and P- Gateway as standardized for the LTE Evolved Packet Core (EPC). One straightforward solution for a virtualized EPC architecture would be to move all EPC network nodes completely into a data center and handle the data traffic via SDN-enabled switches. However, this solution would keep the conventional monolithic architecture unchanged. A possible split in the EPC functionality between a centralized data center and operator's transport network elements could be needed to provide the desired flexibility, performance and TCO reduction. Therefore, we have analyzed the EPC nodes and classified their functions according to their impact on data-plane and control-plane processing. We propose a mapping for these functions on four alternative deployment frameworks based on SDN and OpenFlow (OF). In addition, we investigate the current OF implementation's capability to realize basic core operations such as QoS, data classification, tunneling and charging. Our analysis shows that functions, which involve high data packet processing such as tunneling, have more potential to be kept on the data-plane network element, i.e. realized by an OpenFlow Switch. We argue for an enhanced OF network element NE+, which contains additional network functions next to the basic OpenFlow protocol.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80807337","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702543
M. Ulema, Niranth Amogh, R. Boutaba, C. Buyukkoc, A. Clemm, Jiang Xie, M. Vuran, A. Manzalini, R. Saracco
This paper outlines a proposal for setting up an IEEE initiative on software defined networks (SDNs) to facilitate professional and academic exchange of SDN-related ideas, research, and development. The proposal is a result of an intensive effort of a team consisting of the authors. After a comprehensive gap analysis, gaps and key opportunities were identified. Finally, a specific set of components along with schedule and financial consideration were proposed in the areas of publications, conferences, standards, education, certification, and publicity.
{"title":"IEEE Software Defined Network Initiative","authors":"M. Ulema, Niranth Amogh, R. Boutaba, C. Buyukkoc, A. Clemm, Jiang Xie, M. Vuran, A. Manzalini, R. Saracco","doi":"10.1109/SDN4FNS.2013.6702543","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702543","url":null,"abstract":"This paper outlines a proposal for setting up an IEEE initiative on software defined networks (SDNs) to facilitate professional and academic exchange of SDN-related ideas, research, and development. The proposal is a result of an intensive effort of a team consisting of the authors. After a comprehensive gap analysis, gaps and key opportunities were identified. Finally, a specific set of components along with schedule and financial consideration were proposed in the areas of publications, conferences, standards, education, certification, and publicity.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78814304","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702545
E. Patouni, A. Merentitis, P. Panagiotopoulos, Aristotelis Glentis, N. Alonistioti
The large and increasing variety of proprietary hardware appliances in existing networks poses great difficulties in both their management and the launch of new network services. This is related to a plethora of requirements at the core network part such as energy costs, capital investment challenges and skills necessary to design, integrate and operate increasingly complex hardware- based appliances. At the end user side, the evolution of the Internet of Things envisions to increase the number of connections by yet another order of magnitude (from ~10 billion currently connected "Things"), bringing unprecedented challenges in network scalability, resource efficiency, and privacy considerations. This paper tackles the previous challenges under the prism of network function virtualization focusing on the following use cases: Software Defined Networking controlled wireless integration service, virtual cell management, and sensor networks virtualization. We discuss how the different facets of Virtualization promise to alleviate or resolve some of these challenges, acting as a catalyst for the realization of disruptive networking paradigms, both in the core network and in the end-user side.
{"title":"Network Virtualisation Trends: Virtually Anything Is Possible by Connecting the Unconnected","authors":"E. Patouni, A. Merentitis, P. Panagiotopoulos, Aristotelis Glentis, N. Alonistioti","doi":"10.1109/SDN4FNS.2013.6702545","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702545","url":null,"abstract":"The large and increasing variety of proprietary hardware appliances in existing networks poses great difficulties in both their management and the launch of new network services. This is related to a plethora of requirements at the core network part such as energy costs, capital investment challenges and skills necessary to design, integrate and operate increasingly complex hardware- based appliances. At the end user side, the evolution of the Internet of Things envisions to increase the number of connections by yet another order of magnitude (from ~10 billion currently connected \"Things\"), bringing unprecedented challenges in network scalability, resource efficiency, and privacy considerations. This paper tackles the previous challenges under the prism of network function virtualization focusing on the following use cases: Software Defined Networking controlled wireless integration service, virtual cell management, and sensor networks virtualization. We discuss how the different facets of Virtualization promise to alleviate or resolve some of these challenges, acting as a catalyst for the realization of disruptive networking paradigms, both in the core network and in the end-user side.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76971060","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702560
Francesco Salvestrini, G. Carrozzo, N. Ciulli
Today's Internet is a concatenation of IP networks interconnected by many distributed functions integrated into a plethora of highly specialized middleboxes. These elements implement complex network functions like firewalls, NATs, DPI, traffic scrubbing, etc. The product is a quite complex and rigid internetworking system in which network administrators and users cannot easily determine what is happening to traffic flows as they go toward destinations. SDN research and programmable network functions for flow processing and virtualization are unlocking the current scenario, though most of the COTS products generally support network functions only for virtual L2 switching over IP networks (e.g. VXLAN, GRENV, STT) and LAN based flow pinpointing. This paper presents a different perspective for implementing flow processing via distributed SDN controllers and inter-platform signaling. The distributed end-to-end service provisioning among adjacent flow processing platforms is implemented via a signaling framework in which the different actions/functions to be executed by each platform are described in a generic Flow Processing Route (FPR) object. The FPR is exchanged among the SDN controllers over the end-to-end network service path and contains information on routing rules and local flow processing actions to be instantiated at the different platforms. The proposed signaling architecture has been designed and implemented in the FP7-ICT CHANGE project. This paper reports on the key signaling architectural aspects and the developed signaling prototype.
{"title":"Towards a Distributed SDN Control: Inter-Platform Signaling among Flow Processing Platforms","authors":"Francesco Salvestrini, G. Carrozzo, N. Ciulli","doi":"10.1109/SDN4FNS.2013.6702560","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702560","url":null,"abstract":"Today's Internet is a concatenation of IP networks interconnected by many distributed functions integrated into a plethora of highly specialized middleboxes. These elements implement complex network functions like firewalls, NATs, DPI, traffic scrubbing, etc. The product is a quite complex and rigid internetworking system in which network administrators and users cannot easily determine what is happening to traffic flows as they go toward destinations. SDN research and programmable network functions for flow processing and virtualization are unlocking the current scenario, though most of the COTS products generally support network functions only for virtual L2 switching over IP networks (e.g. VXLAN, GRENV, STT) and LAN based flow pinpointing. This paper presents a different perspective for implementing flow processing via distributed SDN controllers and inter-platform signaling. The distributed end-to-end service provisioning among adjacent flow processing platforms is implemented via a signaling framework in which the different actions/functions to be executed by each platform are described in a generic Flow Processing Route (FPR) object. The FPR is exchanged among the SDN controllers over the end-to-end network service path and contains information on routing rules and local flow processing actions to be instantiated at the different platforms. The proposed signaling architecture has been designed and implemented in the FP7-ICT CHANGE project. This paper reports on the key signaling architectural aspects and the developed signaling prototype.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87034272","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702544
F. Callegati, W. Cerroni
Following the current evolution of virtualization techniques and software defined networking, edge networks might evolve towards a fully virtualized implementation by means of a number of virtual machines working cooperatively to perform the tasks of existing network middleboxes. In such a scenario the possibility to migrate groups of cooperating virtual machines as a whole set may be a very important feature, but what will be the performance issues of this solution? The live migration performance of multiple virtual machines working in some sort of correlated manner is a topic that has not been widely studied in the literature. This manuscript presents a model reasonably simple to implement that may be used to derive some performance indicators such as the whole service downtime and the total migration time. The model is used to compare some scheduling strategies for the migration and provide guidelines to such implementation.
{"title":"Live Migration of Virtualized Edge Networks: Analytical Modeling and Performance Evaluation","authors":"F. Callegati, W. Cerroni","doi":"10.1109/SDN4FNS.2013.6702544","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702544","url":null,"abstract":"Following the current evolution of virtualization techniques and software defined networking, edge networks might evolve towards a fully virtualized implementation by means of a number of virtual machines working cooperatively to perform the tasks of existing network middleboxes. In such a scenario the possibility to migrate groups of cooperating virtual machines as a whole set may be a very important feature, but what will be the performance issues of this solution? The live migration performance of multiple virtual machines working in some sort of correlated manner is a topic that has not been widely studied in the literature. This manuscript presents a model reasonably simple to implement that may be used to derive some performance indicators such as the whole service downtime and the total migration time. The model is used to compare some scheduling strategies for the migration and provide guidelines to such implementation.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84053841","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702540
Suneth Namal, Ijaz Ahmad, A. Gurtov, M. Ylianttila
Software Defined Networking (SDN) and its one possible realization, OpenFlow, define the trends of future networks. However, the present OpenFlow architecture does not allow the switches to be mobile e.g., in a moving train as it would disrupt flow processing from network switches. We present OFHIP, an architecture that enables OpenFlow switches to change their IP addresses securely during mobility. OFHIP employs IPSec encapsulated security payload (ESP) in transport mode for protection against DoS, data origin authenticity, connectionless integrity, anti-replay protection, and limited traffic flow confidentiality. We demonstrate the benefits of OFHIP compared to present use of SSL in enabling mobility, reducing the connection latency and improving the resilience to known TCP-level attacks.
{"title":"Enabling Secure Mobility with OpenFlow","authors":"Suneth Namal, Ijaz Ahmad, A. Gurtov, M. Ylianttila","doi":"10.1109/SDN4FNS.2013.6702540","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702540","url":null,"abstract":"Software Defined Networking (SDN) and its one possible realization, OpenFlow, define the trends of future networks. However, the present OpenFlow architecture does not allow the switches to be mobile e.g., in a moving train as it would disrupt flow processing from network switches. We present OFHIP, an architecture that enables OpenFlow switches to change their IP addresses securely during mobility. OFHIP employs IPSec encapsulated security payload (ESP) in transport mode for protection against DoS, data origin authenticity, connectionless integrity, anti-replay protection, and limited traffic flow confidentiality. We demonstrate the benefits of OFHIP compared to present use of SSL in enabling mobility, reducing the connection latency and improving the resilience to known TCP-level attacks.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90079441","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702562
R. Trivisonno, I. Vaishnavi, Riccardo Guerzoni, Z. Despotovic, A. Hecker, S. Beker, D. Soldani
Software defined networking (SDN) has emerged as an efficient network technology for lowering operating costs through simplified hardware, software and management. Specific research focus has been placed to achieve a successful carrier grade network with SDN, in terms of scalability, reliability, QoS and service management. In the literature, very little material is currently available on traffic engineering (TE) using this technology. This paper presents a novel mixed integer linear programming (MILP) formulation for a centralised controller to calculate optimal end-to-end virtual paths over the underlying network infrastructure, considering multiple requests simultaneously. Extensive simulation results, over a wide range of underlying network topologies and input parameters, demonstrate that the proposed algorithm outperforms traditional shortest path first (SPF) approaches. In some cases, up to 30 % more virtual connections were satisfactorily mapped onto the same substrate, independent of the number of physical nodes.
{"title":"Virtual Links Mapping in Future SDN-Enabled Networks","authors":"R. Trivisonno, I. Vaishnavi, Riccardo Guerzoni, Z. Despotovic, A. Hecker, S. Beker, D. Soldani","doi":"10.1109/SDN4FNS.2013.6702562","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702562","url":null,"abstract":"Software defined networking (SDN) has emerged as an efficient network technology for lowering operating costs through simplified hardware, software and management. Specific research focus has been placed to achieve a successful carrier grade network with SDN, in terms of scalability, reliability, QoS and service management. In the literature, very little material is currently available on traffic engineering (TE) using this technology. This paper presents a novel mixed integer linear programming (MILP) formulation for a centralised controller to calculate optimal end-to-end virtual paths over the underlying network infrastructure, considering multiple requests simultaneously. Extensive simulation results, over a wide range of underlying network topologies and input parameters, demonstrate that the proposed algorithm outperforms traditional shortest path first (SPF) approaches. In some cases, up to 30 % more virtual connections were satisfactorily mapped onto the same substrate, independent of the number of physical nodes.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82544975","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702550
Julius Mueller, Andreas Wierz, T. Magedanz
The design of telecommunication networks and its provisioning is a challenging and complex task, which is constantly influenced by various factors. The disciplines of Traffic Engineering (TE) and Network Management (NM) have addressed these domains with static, semi-automatic and pure self-organizational approaches. Most of the existing approaches usually either relax the problem by taking strong assumptions on the problem instances or by only taking a small portion of the solution space into consideration, thus losing the chance of proving any global optimality gaps. The emerging cloud hosted flexible telecommunication system addressed by the industry nowadays puts new requirements on TE and ND. Current, telecommunication networks are often statically deployed and over-provisioned to cover pre-defined peak data rates, but are inflexible to adapt to dynamic network load situations. This paper presents novel dynamic Traffic Engineering (TE) and adaptive Network Management (NM) approaches for software defined telecommunication networks, which reduce Operational - and Capital Expenditures (OPEX/CAPEX), but also enhance the level of flexibility and elasticity at the same time.
{"title":"Scalable On-Demand Network Management Module for Software Defined Telecommunication Networks","authors":"Julius Mueller, Andreas Wierz, T. Magedanz","doi":"10.1109/SDN4FNS.2013.6702550","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702550","url":null,"abstract":"The design of telecommunication networks and its provisioning is a challenging and complex task, which is constantly influenced by various factors. The disciplines of Traffic Engineering (TE) and Network Management (NM) have addressed these domains with static, semi-automatic and pure self-organizational approaches. Most of the existing approaches usually either relax the problem by taking strong assumptions on the problem instances or by only taking a small portion of the solution space into consideration, thus losing the chance of proving any global optimality gaps. The emerging cloud hosted flexible telecommunication system addressed by the industry nowadays puts new requirements on TE and ND. Current, telecommunication networks are often statically deployed and over-provisioned to cover pre-defined peak data rates, but are inflexible to adapt to dynamic network load situations. This paper presents novel dynamic Traffic Engineering (TE) and adaptive Network Management (NM) approaches for software defined telecommunication networks, which reduce Operational - and Capital Expenditures (OPEX/CAPEX), but also enhance the level of flexibility and elasticity at the same time.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72790847","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 : 2013-11-01DOI: 10.1109/SDN4FNS.2013.6702538
R. Riggio, T. Rasheed, F. Granelli
Software Defined Networking (SDN) and Network Function Virtualization (NFV) are making their way into the research agenda of all the major players in the networking domain. Parallely, testbeds and experimental facilities are widely regarded as the fundamental step-stone to future "clean slate" networking. However, designing and building experimental facilities can hardly be considered a trivial step for either researchers and practitioners. Scale, flexibility, and ease of use are just some of the challenges faced by a testbed designer. These considerations are at the base of efforts such as GENI in USA, AKARI in Japan, FEDERICA, NOVI and OFELIA in Europe which provide federated and open facilities for the Future Internet research agenda. Albeit the importance of such facilities is unquestioned, today there is still a dearth of testbed exploiting SDN and NFV concepts in the wireless networking domain. In this paper we present EmPOWER an experimental testbed which aims at filling this gap by offering an open platform on top of which novel concepts can be tested at scale. The EmPOWER testbed is composed by 30 nodes and is currently used by both undergraduate and graduate students at the University of Trento and by the research staff at CREATE-NET.
{"title":"EmPOWER: A Testbed for Network Function Virtualization Research and Experimentation","authors":"R. Riggio, T. Rasheed, F. Granelli","doi":"10.1109/SDN4FNS.2013.6702538","DOIUrl":"https://doi.org/10.1109/SDN4FNS.2013.6702538","url":null,"abstract":"Software Defined Networking (SDN) and Network Function Virtualization (NFV) are making their way into the research agenda of all the major players in the networking domain. Parallely, testbeds and experimental facilities are widely regarded as the fundamental step-stone to future \"clean slate\" networking. However, designing and building experimental facilities can hardly be considered a trivial step for either researchers and practitioners. Scale, flexibility, and ease of use are just some of the challenges faced by a testbed designer. These considerations are at the base of efforts such as GENI in USA, AKARI in Japan, FEDERICA, NOVI and OFELIA in Europe which provide federated and open facilities for the Future Internet research agenda. Albeit the importance of such facilities is unquestioned, today there is still a dearth of testbed exploiting SDN and NFV concepts in the wireless networking domain. In this paper we present EmPOWER an experimental testbed which aims at filling this gap by offering an open platform on top of which novel concepts can be tested at scale. The EmPOWER testbed is composed by 30 nodes and is currently used by both undergraduate and graduate students at the University of Trento and by the research staff at CREATE-NET.","PeriodicalId":6455,"journal":{"name":"2013 IEEE SDN for Future Networks and Services (SDN4FNS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80698714","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}