Pub Date : 2017-06-01DOI: 10.1109/HPSR.2017.7968673
C. Liß, Marian Ulbricht, U. Zia, Hartmut Müller
As line-speeds and packet losses are sufficient well for most applications, reduction of latency and jitter are gaining in importance. We introduce and discuss the architecture of a novel networking device that provides low-latency switching and routing. It integrates an up-to-date FPGA with a standard ×86-64 processor and targets Time-Sensitive Networking (TSN) and machine-to-machine communication (M2M). First results show a cut-through latency of 2 – 2.5 µs for its 12 Gigabit Ethernet ports and full line rate packet processing. It features frequency synchronization across networks and is easily extendable, enabling researchers to build experiments in areas like industrial, automotive, and 5G mobile access networks, with highest precision, repeatability, and ease.
{"title":"Architecture of a synchronized low-latency network node targeted to research and education","authors":"C. Liß, Marian Ulbricht, U. Zia, Hartmut Müller","doi":"10.1109/HPSR.2017.7968673","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968673","url":null,"abstract":"As line-speeds and packet losses are sufficient well for most applications, reduction of latency and jitter are gaining in importance. We introduce and discuss the architecture of a novel networking device that provides low-latency switching and routing. It integrates an up-to-date FPGA with a standard ×86-64 processor and targets Time-Sensitive Networking (TSN) and machine-to-machine communication (M2M). First results show a cut-through latency of 2 – 2.5 µs for its 12 Gigabit Ethernet ports and full line rate packet processing. It features frequency synchronization across networks and is easily extendable, enabling researchers to build experiments in areas like industrial, automotive, and 5G mobile access networks, with highest precision, repeatability, and ease.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130258945","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968692
M. Nascimento, Tiago Primini, Eric Baum, P. Martucci, Francisco Cabelo, Leonardo E. Mariote
Network Function Virtualization (NFV) brings agility and flexibility delivering network services with cost efficiency to network operators. As an emerging technology, it also presents several challenges, among them, ensuring high performance for virtualized network functions, based on software implementation and running on standard IT servers, instead of custom hardware appliances. In this article, we propose an acceleration mechanism for NFV platforms that allows the network traffic to bypass the service chain offloading the network functions. This mechanism can significantly improve performance and scalability, as demonstrated by the evaluation of our NFV platform, which is presented along with the details of the architecture and the implementation. The proposed solution using the proposed acceleration mechanism provided a performance boost of a factor of 23 compared to the same NFV platform without the acceleration mechanism enabled.
网络功能虚拟化(Network Function Virtualization, NFV)为网络运营商提供高性价比的网络服务，带来了敏捷性和灵活性。作为一项新兴技术，它也提出了一些挑战，其中包括确保基于软件实现并在标准it服务器上运行的虚拟化网络功能的高性能，而不是在自定义硬件设备上运行。在本文中，我们提出了一种NFV平台的加速机制，允许网络流量绕过业务链卸载网络功能。这种机制可以显著提高性能和可伸缩性，正如我们的NFV平台的评估所证明的那样，该评估与体系结构和实现的细节一起提供。与未启用加速机制的NFV平台相比，使用加速机制的解决方案提供了23倍的性能提升。
{"title":"Acceleration mechanism for high throughput and low latency in NFV environments","authors":"M. Nascimento, Tiago Primini, Eric Baum, P. Martucci, Francisco Cabelo, Leonardo E. Mariote","doi":"10.1109/HPSR.2017.7968692","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968692","url":null,"abstract":"Network Function Virtualization (NFV) brings agility and flexibility delivering network services with cost efficiency to network operators. As an emerging technology, it also presents several challenges, among them, ensuring high performance for virtualized network functions, based on software implementation and running on standard IT servers, instead of custom hardware appliances. In this article, we propose an acceleration mechanism for NFV platforms that allows the network traffic to bypass the service chain offloading the network functions. This mechanism can significantly improve performance and scalability, as demonstrated by the evaluation of our NFV platform, which is presented along with the details of the architecture and the implementation. The proposed solution using the proposed acceleration mechanism provided a performance boost of a factor of 23 compared to the same NFV platform without the acceleration mechanism enabled.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246737","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968685
A. F. Santos, R. C. Almeida, Marcelo M. Alves, K. Assis
Spectrum-sliced elastic optical path networks (SLICE) enable flexible bandwidth provisioning, which allows efficient resource utilization and support to heterogeneous bandwidth demands. This makes SLICE a very promising networking architecture. In SLICE, finding a route and a slice of the spectrum is an important design problem, which is known as the Routing and Spectrum Assignment (RSA) problem. In this paper, we present a new heuristic, based on Yen's k-shortest path algorithm and capable of dealing with the traffic heterogeneity to find appropriate sets of paths for each source-destination node pairs to mitigate the bottleneck in the network. The results show that the proposed algorithm reduces the lightpath blocking probability and achieves significantly improved spectrum efficiency. We also analyse the maximum number of alternate shortest paths for minimising the blocking probability.
{"title":"YBS heuristic for routing and spectrum allocation in flexible optical networks","authors":"A. F. Santos, R. C. Almeida, Marcelo M. Alves, K. Assis","doi":"10.1109/HPSR.2017.7968685","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968685","url":null,"abstract":"Spectrum-sliced elastic optical path networks (SLICE) enable flexible bandwidth provisioning, which allows efficient resource utilization and support to heterogeneous bandwidth demands. This makes SLICE a very promising networking architecture. In SLICE, finding a route and a slice of the spectrum is an important design problem, which is known as the Routing and Spectrum Assignment (RSA) problem. In this paper, we present a new heuristic, based on Yen's k-shortest path algorithm and capable of dealing with the traffic heterogeneity to find appropriate sets of paths for each source-destination node pairs to mitigate the bottleneck in the network. The results show that the proposed algorithm reduces the lightpath blocking probability and achieves significantly improved spectrum efficiency. We also analyse the maximum number of alternate shortest paths for minimising the blocking probability.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115294765","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968675
Jeferson Rodrigues Cotrim, J. H. Kleinschmidt
IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) is the only standardized routing protocol for Low Power and Lossy Networks. Therefore, RPL is the routing protocol chosen for most Internet of Things (IoT) applications. However, the RPL protocol has some open issues when the scenario includes mobile nodes. Since many IoT applications include mobility, this is an important problem to address. Node mobility does not permit the network to stabilize and because of this keep exchanging control messages. Mobility increases the packet loss because mobile nodes may leave the coverage area before transmitting the data. This problems also increase the power consumption. Another important factor affects the RPL performance. To save nodes energy, the data link layer implements a radio duty cycle. These duty cycles turn the radio off when it is not used. One common and used radio duty cycle protocol is the ContikiMAC. Changes in the frequency of the duty cycle modifies the RPL performance. This work shows how the change of radio duty cycle of ContikiMAC on a hybrid scenario, composed by fixed and mobile nodes, interferes on RPL performance. Results show that the nodes mobility degrade the metrics tested. The choice of radio duty cycle is very important to the network performance. The results show that the RPL performance is strictly dependent of the duty cycle.
RPL (IPv6 Routing Protocol for Low-Power and Lossy Networks)是目前唯一针对低功耗和有损网络的标准化路由协议。因此，RPL是大多数物联网(IoT)应用所选择的路由协议。然而，当场景包含移动节点时，RPL协议有一些开放的问题。由于许多物联网应用包括移动性，这是一个需要解决的重要问题。节点移动不允许网络稳定，因此不断交换控制消息。移动性增加了丢包，因为移动节点可能在传输数据之前离开覆盖区域。这些问题也增加了功耗。影响RPL性能的另一个重要因素。为了节省节点能量，数据链路层实现了无线电占空比。当不使用时，这些占空比会关闭收音机。一个常用的无线电占空比协议是ContikiMAC。改变占空比的频率会改变RPL的性能。这项工作显示了在由固定和移动节点组成的混合场景下，ContikiMAC的无线电占空比的变化如何干扰RPL性能。结果表明，节点迁移降低了测试指标。无线电占空比的选择对网络性能的影响非常重要。结果表明，RPL性能严格依赖于占空比。
{"title":"Performance evaluation of RPL on a mobile scenario with different ContikiMAC radio duty cycles","authors":"Jeferson Rodrigues Cotrim, J. H. Kleinschmidt","doi":"10.1109/HPSR.2017.7968675","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968675","url":null,"abstract":"IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) is the only standardized routing protocol for Low Power and Lossy Networks. Therefore, RPL is the routing protocol chosen for most Internet of Things (IoT) applications. However, the RPL protocol has some open issues when the scenario includes mobile nodes. Since many IoT applications include mobility, this is an important problem to address. Node mobility does not permit the network to stabilize and because of this keep exchanging control messages. Mobility increases the packet loss because mobile nodes may leave the coverage area before transmitting the data. This problems also increase the power consumption. Another important factor affects the RPL performance. To save nodes energy, the data link layer implements a radio duty cycle. These duty cycles turn the radio off when it is not used. One common and used radio duty cycle protocol is the ContikiMAC. Changes in the frequency of the duty cycle modifies the RPL performance. This work shows how the change of radio duty cycle of ContikiMAC on a hybrid scenario, composed by fixed and mobile nodes, interferes on RPL performance. Results show that the nodes mobility degrade the metrics tested. The choice of radio duty cycle is very important to the network performance. The results show that the RPL performance is strictly dependent of the duty cycle.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124266571","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968690
L. Chiaraviglio, N. Blefari-Melazzi, C. Chiasserini, Bogdan Iatco, F. Malandrino, S. Salsano
We target the evaluation of a Superfluid 5G network from an economic point of view. The considered 5G architecture has notably features, such as flexibility, agility, portability and high performance, as shown by the H2020 SUPERFLUIDITY project. The proposed economic model, tailored to the Superfluid network architecture, allows to compute the CAPEX, the OPEX, the Net Present Value (NPV) and the Internal Rate of Return (IRR). Specifically, we apply our model to estimate the impact for the operator of migrating from a legacy 4G to a 5G network. Our preliminary results, obtained over two realistic case studies located in Bologna (Italy) and San Francisco (CA), show that the monthly subscription fee for the subscribers can be kept sufficiently low, i.e., typically around 5 [USD] per user, while allowing a profit for the operator.
{"title":"An economic analysis of 5G Superfluid networks","authors":"L. Chiaraviglio, N. Blefari-Melazzi, C. Chiasserini, Bogdan Iatco, F. Malandrino, S. Salsano","doi":"10.1109/HPSR.2017.7968690","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968690","url":null,"abstract":"We target the evaluation of a Superfluid 5G network from an economic point of view. The considered 5G architecture has notably features, such as flexibility, agility, portability and high performance, as shown by the H2020 SUPERFLUIDITY project. The proposed economic model, tailored to the Superfluid network architecture, allows to compute the CAPEX, the OPEX, the Net Present Value (NPV) and the Internal Rate of Return (IRR). Specifically, we apply our model to estimate the impact for the operator of migrating from a legacy 4G to a 5G network. Our preliminary results, obtained over two realistic case studies located in Bologna (Italy) and San Francisco (CA), show that the monthly subscription fee for the subscribers can be kept sufficiently low, i.e., typically around 5 [USD] per user, while allowing a profit for the operator.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131640073","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968678
Andreas Fiessler, Sven Hager, B. Scheuermann
Packet classification is a core feature needed in firewalls, SDN switches, and QoS routers. Current research to accelerate the classification with hardware employing Field-programmable Gate Arrays (FPGAs) created a variety of approaches, with significant differences in terms of hardware resource requirements, memory usage, configuration update time, and power dissipation. However, there is no optimal, universal method for classification at link rate, due to inherent conflicts between large generic circuits with high resource consumption, and optimized circuits with limited versatility. Thus, current implementations have different trade-offs in terms of memory usage, resource requirements, power consumption, and flexibility. As a new approach to tackle this challenge, we present a hybrid concept that combines an highly optimized configuration-specialized and thus energy- and resource-efficient classification circuit with a generic matching circuit whose configuration can be updated quickly. The combined circuit can thus support reasonably fast configuration updates, has a low power dissipation, and can process network packets at link rate.
{"title":"Flexible line speed network packet classification using hybrid on-chip matching circuits","authors":"Andreas Fiessler, Sven Hager, B. Scheuermann","doi":"10.1109/HPSR.2017.7968678","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968678","url":null,"abstract":"Packet classification is a core feature needed in firewalls, SDN switches, and QoS routers. Current research to accelerate the classification with hardware employing Field-programmable Gate Arrays (FPGAs) created a variety of approaches, with significant differences in terms of hardware resource requirements, memory usage, configuration update time, and power dissipation. However, there is no optimal, universal method for classification at link rate, due to inherent conflicts between large generic circuits with high resource consumption, and optimized circuits with limited versatility. Thus, current implementations have different trade-offs in terms of memory usage, resource requirements, power consumption, and flexibility. As a new approach to tackle this challenge, we present a hybrid concept that combines an highly optimized configuration-specialized and thus energy- and resource-efficient classification circuit with a generic matching circuit whose configuration can be updated quickly. The combined circuit can thus support reasonably fast configuration updates, has a low power dissipation, and can process network packets at link rate.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134355945","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968679
E. O. Figueiroa, Emerson A. O. Lima, C. J. A. B. Filho, J. C. Silva, A. V. S. Xavier, Danilo R. B. Araújo
This paper proposes a decision model based on fuzzy logics to assign the route between source-destination nodes in elastic optical networks. The route is chosen dynamically based on the lowest cost criterion, which is calculated based on a weighted summation of three metrics, called availability of contiguous slots on the route, average availability of slots on the route and physical length of the lightpath. To accomplish this task, we use the Takagi-Sugeno defuzzification process to calculate the cost of the route under analysis. By using our proposal in three different scenarios, we obtained a better network performance regarding blocking probability and an increase in the throughput when compared to other well-known routing algorithms, such as Shortest Path, Minimum Hop, Congested Aware Shortest Path and Spectrum Continuity based Shortest Path.
{"title":"A routing algorithm based on fuzzy logics for elastic optical networks","authors":"E. O. Figueiroa, Emerson A. O. Lima, C. J. A. B. Filho, J. C. Silva, A. V. S. Xavier, Danilo R. B. Araújo","doi":"10.1109/HPSR.2017.7968679","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968679","url":null,"abstract":"This paper proposes a decision model based on fuzzy logics to assign the route between source-destination nodes in elastic optical networks. The route is chosen dynamically based on the lowest cost criterion, which is calculated based on a weighted summation of three metrics, called availability of contiguous slots on the route, average availability of slots on the route and physical length of the lightpath. To accomplish this task, we use the Takagi-Sugeno defuzzification process to calculate the cost of the route under analysis. By using our proposal in three different scenarios, we obtained a better network performance regarding blocking probability and an increase in the throughput when compared to other well-known routing algorithms, such as Shortest Path, Minimum Hop, Congested Aware Shortest Path and Spectrum Continuity based Shortest Path.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115024588","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968672
Fadoua Hassen, L. Mhamdi
We propose a highly scalable packet-switching architecture that suits for demanding Data Center Networks (DCNs). The design falls into the category of buffered multistage switches. It affiliates the three-stage Clos-network and the Networks-on-Chip (NoC) paradigm. We also suggest a congestion-aware routing algorithm that shares the traffic load among the switch's central modules via interleaved connecting links. Unlike conventional switches, the current proposal provides better path diversity, simple scheduling, speedup and robustness to load variation. Simulation results show that the switch scales well with the port-count and traffic fluctuation and that it outperforms different switches under many traffic patterns.
{"title":"High-radix packet-switching architecture for Data Center Networks","authors":"Fadoua Hassen, L. Mhamdi","doi":"10.1109/HPSR.2017.7968672","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968672","url":null,"abstract":"We propose a highly scalable packet-switching architecture that suits for demanding Data Center Networks (DCNs). The design falls into the category of buffered multistage switches. It affiliates the three-stage Clos-network and the Networks-on-Chip (NoC) paradigm. We also suggest a congestion-aware routing algorithm that shares the traffic load among the switch's central modules via interleaved connecting links. Unlike conventional switches, the current proposal provides better path diversity, simple scheduling, speedup and robustness to load variation. Simulation results show that the switch scales well with the port-count and traffic fluctuation and that it outperforms different switches under many traffic patterns.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117301247","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968689
Ze Yang, K. Yeung
We consider a software defined network (SDN) with a single controller communicating with all switches through a spanning tree rooted at the controller, or a controller tree. When a switch fails, its immediate downstream switch(es) will detect the failure. A downstream switch is protected if it has a neighbor whose path to the controller is not affected by this failure. By rerouting its traffic to this neighbor, the protected switch will bypass the failure (of its parent). On the other hand, an unprotected switch cannot bypass the failure using the local rerouting above; and the subtree rooted at the unprotected switch will be disconnected from the controller. Let the weight of an unprotected switch be the number of switches in the subtree. Then the weight of a controller tree is the total weight of all unprotected switches. In this paper, we focus on the problem of finding the minimum weight controller tree (mwCT). We first introduce a new switch protection mechanism called sibling protection. We then prove that the mwCT problem is NP-hard. To solve it, we formulate the first Integer Linear Programming (ILP). We show that the solutions obtained by an existing heuristic are far from optimal.
{"title":"ILP formulation for controller tree design in SDN","authors":"Ze Yang, K. Yeung","doi":"10.1109/HPSR.2017.7968689","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968689","url":null,"abstract":"We consider a software defined network (SDN) with a single controller communicating with all switches through a spanning tree rooted at the controller, or a controller tree. When a switch fails, its immediate downstream switch(es) will detect the failure. A downstream switch is protected if it has a neighbor whose path to the controller is not affected by this failure. By rerouting its traffic to this neighbor, the protected switch will bypass the failure (of its parent). On the other hand, an unprotected switch cannot bypass the failure using the local rerouting above; and the subtree rooted at the unprotected switch will be disconnected from the controller. Let the weight of an unprotected switch be the number of switches in the subtree. Then the weight of a controller tree is the total weight of all unprotected switches. In this paper, we focus on the problem of finding the minimum weight controller tree (mwCT). We first introduce a new switch protection mechanism called sibling protection. We then prove that the mwCT problem is NP-hard. To solve it, we formulate the first Integer Linear Programming (ILP). We show that the solutions obtained by an existing heuristic are far from optimal.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127021168","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 : 2017-06-01DOI: 10.1109/HPSR.2017.7968683
Alaelson C. Jatoba-Neto, Christian Esteve Rothenberg, D. Mello, Sercan Ö. Arik, J. Kahn
Accommodating sustained exponential traffic growth in optical networks requires scaling the spatial dimension using space-division multiplexing. Numerous uncoupled spatial channels may be realized by activating multiple parallel fibers or cores in multicore fibers. A multiplicity of uncoupled spatial channels will render the granularity provided by multiple wavelength channels less essential in enabling optical switching. In this paper, we investigate a possible paradigm shift in optical node architectures, in which nodes based on wavelength-selective switching are replaced by those based on simple spatial switching. We compare spatial switching of full-spectrum superchannels to wavelength switching of uncoupled spatial superchannels, considering the evolution of traffic over time. Our results show that spatial switching may achieve more efficient scaling than wavelength switching in roughly 10 to 17 years, depending on the traffic growth rate assumed.
{"title":"Scaling optical networks using full-spectrum spatial switching","authors":"Alaelson C. Jatoba-Neto, Christian Esteve Rothenberg, D. Mello, Sercan Ö. Arik, J. Kahn","doi":"10.1109/HPSR.2017.7968683","DOIUrl":"https://doi.org/10.1109/HPSR.2017.7968683","url":null,"abstract":"Accommodating sustained exponential traffic growth in optical networks requires scaling the spatial dimension using space-division multiplexing. Numerous uncoupled spatial channels may be realized by activating multiple parallel fibers or cores in multicore fibers. A multiplicity of uncoupled spatial channels will render the granularity provided by multiple wavelength channels less essential in enabling optical switching. In this paper, we investigate a possible paradigm shift in optical node architectures, in which nodes based on wavelength-selective switching are replaced by those based on simple spatial switching. We compare spatial switching of full-spectrum superchannels to wavelength switching of uncoupled spatial superchannels, considering the evolution of traffic over time. Our results show that spatial switching may achieve more efficient scaling than wavelength switching in roughly 10 to 17 years, depending on the traffic growth rate assumed.","PeriodicalId":169489,"journal":{"name":"2017 IEEE 18th International Conference on High Performance Switching and Routing (HPSR)","volume":"49 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122836676","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：