Richard Li, A. Clemm, U. Chunduri, Lijun Dong, K. Makhijani
{"title":"A New Framework and Protocol for Future Networking Applications","authors":"Richard Li, A. Clemm, U. Chunduri, Lijun Dong, K. Makhijani","doi":"10.1145/3229574.3229576","DOIUrl":"https://doi.org/10.1145/3229574.3229576","url":null,"abstract":"Future networking applications place demands on networking services that become increasingly difficult to address using existing internetworking technology. This paper presents a new framework and protocol that is designed to meet this challenge, BPP (Big Packet Protocol). BPP is intended as an enabler for a new generation of networking services that depend on the ability to provide precise service level guarantees while facilitating operations. In addition, BPP allows users to define and customize networking behavior from the network edge for their flows in isolation from other users and without needing to rely on lengthy vendor or network operator product cycles.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123446431","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}
Marc Körner, Torsten M. Runge, Aurojit Panda, S. Ratnasamy, S. Shenker
{"title":"Open Carrier Interface: An Open Source Edge Computing Framework","authors":"Marc Körner, Torsten M. Runge, Aurojit Panda, S. Ratnasamy, S. Shenker","doi":"10.1145/3229574.3229579","DOIUrl":"https://doi.org/10.1145/3229574.3229579","url":null,"abstract":"Edge computing is an emerging technology, which offers manifold performance improvements for applications with low-latency and high-bandwidth requirements. In order to lower the burden for the Network Service Provider to support edge computing, we introduce a generic and platform-agnostic open source edge computing framework implementation called Open Carrier Interface. The implemented prototype provides Application Service Providers with the opportunity to deploy software components directly at the edge of the network and without any operator intervention. We will elaborate and demonstrate that the developed framework and its interfaces (i) are easy to use for all involved parties, (ii) present a unifying abstraction layer for edge-based resource management systems and edge service architectures, (iii) and can deliver a significant performance impact on applications implementing the edge service paradigm.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"467 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115943637","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}
Belma Turkovic, F. Kuipers, Niels L. M. van Adrichem, K. Langendoen
{"title":"Fast network congestion detection and avoidance using P4","authors":"Belma Turkovic, F. Kuipers, Niels L. M. van Adrichem, K. Langendoen","doi":"10.1145/3229574.3229581","DOIUrl":"https://doi.org/10.1145/3229574.3229581","url":null,"abstract":"Along with exciting visions for 5G communications and the Tactile Internet, the networking requirement of attaining extremely low end-to-end latency has appeared. While network devices are typically equipped with buffers to counteract packet loss caused by short-lived traffic bursts, the more those buffers get filled, the more delay is added to every packet passing through. In this paper, we develop congestion avoidance methods that harness the power of fully programmable data-planes. The corresponding programmable switches, through languages such as P4, can be programmed to gather and react to important packet meta-data, such as queue load, while the data packets are being processed. In particular, we enable P4 switches to (1) track processing and queuing delays of latency-critical flows and (2) react immediately in the data-plane to congestion by rerouting the affected flows. Through a proof-of-concept implementation in emulation and on real hardware, we demonstrate that a data-plane approach reduces average and maximum delay, as well as jitter, when compared to non-programmable approaches.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131439021","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}
R. Sedar, Michael Borokhovich, Marco Chiesa, G. Antichi, S. Schmid
{"title":"Supporting Emerging Applications With Low-Latency Failover in P4","authors":"R. Sedar, Michael Borokhovich, Marco Chiesa, G. Antichi, S. Schmid","doi":"10.1145/3229574.3229580","DOIUrl":"https://doi.org/10.1145/3229574.3229580","url":null,"abstract":"Emerging applications expect fast turn-around from in-network failover mechanisms. This paper starts exploring the design space for supporting high availability and low latency using fast reroute in programmable data planes. In particular, we present a primitive for supporting well-known fast reroute mechanisms that is both efficient in terms of packet processing latency, memory requirements, and switch throughput.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134253113","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}
{"title":"AIRCoN-Stack - Introducing Flexibility to Wireless Industrial Real-Time Applications","authors":"Georg von Zengen, Keno Garlichs, L. Wolf","doi":"10.1145/3229574.3229578","DOIUrl":"https://doi.org/10.1145/3229574.3229578","url":null,"abstract":"Wireless networking is a key technology to enable smart production scenarios. It expands the design space for solutions in factory design tremendously. Currently, applications suitable for wireless connections are limited to monitoring purposes due to lacking reliability. This is especially critical when the network needs to adjust to new application needs, environmental conditions or network topologies. In such cases real-time conditions required for certain tasks might break. To overcome those limitations we present AIRCoN-stack. It was specifically designed to perform real-time operations while parts of the network are changing. It uses TDMA with a combined radio- and CPU-scheduler to keep the task execution jitter between nodes in the network as low as possible. We evaluate all components of our network stack in a real-world setup to prove its capabilities.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128659055","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}
{"title":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","authors":"","doi":"10.1145/3229574","DOIUrl":"https://doi.org/10.1145/3229574","url":null,"abstract":"","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132911249","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}
{"title":"Bridging the ICN Deployment Gap with IPoC: An IP-over-ICN protocol for 5G Networks","authors":"Susmit Shannigrahi, Chengyu Fan, G. White","doi":"10.1145/3229574.3229575","DOIUrl":"https://doi.org/10.1145/3229574.3229575","url":null,"abstract":"Information-centric networking (ICN) is a new networking model that addresses content directly rather than addressing end-hosts. An ICN-based networking layer aligns better with application needs; it provides content-centric security, caching, and intelligent packet forwarding making it useful to both users and service providers alike in terms of efficiency, security, and mobility. ICN has recently received considerable attention; researchers have explored its benefits for diverse use cases such as large-data applications, building automation systems, vehicular networks, and IoT applications. While ICN provides significant benefits to all these application areas, one significant challenge that remains to be addressed is real-world deployment. An ICN-only network will require all IP applications to be rewritten to use ICN natively, a tall order in a world with millions of applications connected to the Internet. Though this problem affects all IP applications, we use mobile applications as the driving example for this work. An ICN based network can benefit smartphone users with higher throughput and lower service interruptions and at the same time, allow mobile service providers to utilize their network better and reduce protocol complexity. In this paper, we propose IPoC, a general purpose tunneling protocol that enables all IP applications to utilize ICN networks. We implement the IPoC protocol using Named Data Networking (NDN) semantics and using mobile communication as the driving example, compare our protocol performance with native IP. We show that the protocol overhead and performance degradation of IPoC is minimal which makes it suitable for immediate deployment. In return, we show how NDN and IPoC can bring ICN benefits to 5G mobile networks by simplifying the mobility plane, introducing intelligent functionality, and reducing network complexity.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132971688","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}
Shreyasee Mukherjee, R. Ravindran, D. Raychaudhuri
{"title":"A Distributed Core Network Architecture for 5G Systems and Beyond","authors":"Shreyasee Mukherjee, R. Ravindran, D. Raychaudhuri","doi":"10.1145/3229574.3229583","DOIUrl":"https://doi.org/10.1145/3229574.3229583","url":null,"abstract":"This paper presents a distributed core network architecture for use in future cellular systems. The proposed architecture addresses the performance bottlenecks and latency associated with the centralized control and data gateways used in today's mobile core networks. A fully distributed architecture for the mobile core is realized through the use of identifier-based protocol extensions to IP which run on base stations (eNodeB) and routers without the need for centralized gateways. The resulting \"flat\" mobile core network is capable of supporting a variety of mobility and IoT services with significantly lower latency and improved throughput relative to current solutions. Specific data plane service examples including service chaining and local VOIP are given. The paper concludes with an evaluation of control and data-plane overhead for a large US-scale cellular network operator in the proposed architecture.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"436 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126114271","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}
{"title":"FEC Killed The Cut-Through Switch","authors":"Omer S. Sella, A. Moore, Noa Zilberman","doi":"10.1145/3229574.3229577","DOIUrl":"https://doi.org/10.1145/3229574.3229577","url":null,"abstract":"Latency penalty in Ethernet links beyond 10Gb/s is due to forward error correction (FEC) blocks. In the worst case a single-hop penalty approaches the latency of an entire cut-through switch. Latency jitter is also introduced, making latency prediction harder, with large peak to peak variance. These factors stretch the tail of latency distribution in Rack-scale systems and Data Centers, which in turn degrades performance of distributed applications. We analyse the underlying mechanisms, calculate lower bounds and propose a different approach that would reduce the penalty, allow control over latency and feedback for application level optimisation.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116008059","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}
Guangyu Li, Qiang Shen, Yong Liu, Houwei Cao, Zifa Han, Feng Li, Jin Li
{"title":"Data-driven Approaches to Edge Caching","authors":"Guangyu Li, Qiang Shen, Yong Liu, Houwei Cao, Zifa Han, Feng Li, Jin Li","doi":"10.1145/3229574.3229582","DOIUrl":"https://doi.org/10.1145/3229574.3229582","url":null,"abstract":"Content caching at network edge is a promising solution for serving emerging high-throughput low-delay applications, such as virtual reality, augmented reality and Internet-of-Things. The traditional caching algorithms need to adapt to the edge networking environment since old traffic assumptions may no longer hold. Meanwhile, user/group content interest as a new important element should be considered to improve the caching performance. In this work, we propose two novel caching strategies that mine user/group interests to improve caching performance at network edge. The static user-group interest patterns are handled by the Matrix Factorization method and the temporal content request patterns are handled by the Least-Recently-Used or Nearest-Neighbor algorithms. Through empirical experiments with a large-scale real IPTV user traces, we demonstrate that the proposed caching algorithms outperform the existing caching algorithms and approach the caching performance upper bound in the large cache size regime. Leveraging on offline computation, we can limit the online computation cost and achieve good caching performance in realtime.","PeriodicalId":113231,"journal":{"name":"Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132881261","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}