This talk does not have an abstract.

From virtual reality and teleportation, to telepresence, augmented reality, holograms, and remotely‑controlled robotics, these future network applications promise an unprecedented development for society, economics and culture by revolutionizing the way we live, learn, work and play. Unfortunately, today’s Internet falls short when it comes to providing the stringent performance requirements imposed by such applications. This is due to several fundamental limitations in the design of the current network architecture and communication protocols. As a result, there is a pressing need to rethink the network architecture and protocols, and efficiently harness recent technological advances in terms of virtualization and network softwarization to design the Tactile Internet of the future.

In this talk, we start by analyzing the characteristics and requirements of future networking applications and highlight the limitations of the current network architecture and protocols. We then draw a rough sketch of FlexNGIA, a Flexible Next-Generation Internet Architecture that is able to satisfy the requirements of future Internet applications and services. We also discuss through some use-cases how FlexNGIA could ensure the service level guarantees required by some of the future network applications.

Biography

Mohamed Faten Zhani is an associate professor with the department of software and IT engineering at l’École de Technologie Supérieure (ÉTS Montreal) in Canada. His research interests include cloud computing, network function virtualization, software-defined networking and resource management in large-scale distributed systems. Faten has co‑authored several book chapters and research papers published in renowned conferences and journals including IEEE/IFIP/ACM CNSM, IEEE/IFIP IM/NOMS, IEEE INFOCOM, IEEE transactions on cloud computing and IEEE Journal on Selected Areas in Communications (JSAC). He served as the general or technical program chair of several international workshops and conferences. He is also co-editor of the IEEE Communications Magazine series on "Telecom Software, Network Virtualization, and Software Defined Networks", associate editor of the IEEE Transactions of Network and Service Management, Wiley international journal of network management, and managing editor of the IEEE softwarization newsletter. He is co‑founder and vice-chair of the IEEE Network Intelligence Emerging Technology Initiative and a cluster lead at the IEEE P1916.1 SDN/NFV Performance standard group. Faten recently received the IEEE/IFIP IM 2017 Young Researchers and Professionals Award as a recognition for outstanding research contribution and leadership in the field of network and service management.

More and more applications require end-to-end guaranteed services for bandwidth and latency. Current best-effort based IP Internet cannot provide such services, and new IP-based solution is needed to meet the new service requirements. This paper proposes a framework to support such guaranteed services. It is based on new control plane and data plan. The new control plane could provide flow-based service and program hardware accordingly, and the new data plane can guarantee different services for different flows with agreed bandwidth and latency. The paper focuses on the latency guaranteed service, provides both theoretical per-hop latency estimation and experimental verification.

Due to improving computational capacity of supercomputers, transmitting encrypted packets via one single network path is vulnerable to brute-force attacks. The versatile attackers secretly eavesdrop all the packets, classify packets into different streams, performs an exhaustive search for the decryption key, and extract sensitive personal information from the streams. However, new Internet Protocol (IP) brings great opportunities and challenges for preventing eavesdropping attacks. In this paper, we propose a Programming Protocol-independent Packet Processors (P4) based Network Immune Scheme (P4NIS) against the eavesdropping attacks. Specifically, P4NIS is equipped with three lines of defense to improve the network immunity. The first line is promiscuous forwarding by splitting all the traffic packets in different network paths disorderly. Complementally, the second line encrypts transmission port fields of the packets using diverse encryption algorithms. The encryption could distribute traffic packets from one stream into different streams, and disturb eavesdroppers to classify them correctly. Besides, P4NIS inherits the advantages from the existing encryption based countermeasures which is the third line of defense. Using a paradigm of programmable data planes-P4, we implement P4NIS and evaluate its performances. Experimental results show that P4NIS can increase difficulties of eavesdropping significantly, and increase transmission throughput by 31.7% compared with state-of-the-art mechanisms.

Video streaming takes a dominant percentage of rapidly-increasing mobile Internet traffic in Wireless Local Area Networks (WLAN). As consumers may often request the same contents, such as popular videos and live videos, using multicast transmissions under Named Data Networking (NDN) architecture can significantly reduce the network cost.
However, in order to guarantee the wireless multicast data reliability, the existing multicast schemes use a lower data rate (e.g., 1 Mbps for IEEE 802.11b, and 6 Mbps for IEEE 802.11a) to transmit the multicast data, inevitably reducing the best possible quality of experience (QoE) for those high-speed consumers.
In this paper, under the Scalable Video Coding (SVC) mechanism, we propose an adaptive video streaming scheme by using the NDN multicast (named NM-ABR), where NDN multicast groups are dynamically formed due to the varying network conditions and SVC characteristics.
In NM-ABR, after detecting a multicast group, we first devise a multicast data rate selection algorithm in order to maximize the consumer receiving throughput for multicast transmission. Then, we integrate the transmission data rate into the adaptive bit rate (ABR) algorithm to request the most suitable bitrate for video segments. At last, for those low-speed consumers, we propose an SVC-based multiple-layer control approach to reduce the retransmission of video segments in enhancement layers.
We implement the proposed NM-ABR in NS3 via the ndnSIM module, and conduct extensive experiments to demonstrate its efficacy in terms of video bitrate, startup delay, and stalling time.

IP experiences dramatic development since its birth and has become the fundamental protocol of the Internet. However, IP faced more and more prominent problems in the past years, such as address exhaustion, low flexibility and low packet space efficiency. The root cause of these problems is that IP protocol is designed with fixed-length address and fixed-length delimited packet format, lacking of extensibility and flexibility. In order to solve these problems, we firstly propose a hierarchical network architecture where network is able to extend naturally without limitation. Then we adopt an addressing scheme based on the hierarchical network architecture. The address reflects the hierarchical levels of network and has no quantity limit. Benefiting from the hierarchical network architecture, flexible packet forwarding which improves the flexibility of address is described, and it helps improve packet space efficiency and interconnect heterogenous networks as well. Implementation and experiments illustrate the feasibility and flexibility of our scheme compared to conventional IP protocol.

Previous work on service oriented networking has mainly focused on the requirements of network operators and other service providers. This document proposes a new, backwards-compatible, approach to the topic that is directly aimed at end users and their requirements, but also has significant benefits for operators. It describes a proposed new mechanism for packet forwarding in edge networks, where the service required rather than an IP address acts as the vector for routing packets. Deeper in the network, the user's traffic is dispatched to specific services using conventional mechanisms.

Internet protocols have developed significantly over the last 50 years but have reached a point where the further improvements in performance, resilience, security and privacy cannot be achieved by simple incremental changes. This paper proposes a new IP protocol that puts the user's end host at the centre of major algorithmic decisions. It consist of three new mechanisms: a private source routing establishment protocol that allows inter-domain traffic routes to be decided by the user and kept private from the providers; a mechanism to control reception of packets that mitigates denial-of-service attacks and a new directory system that puts the end user at the core of the decisions enabling anycast and mobility with a pub-sub mechanism with fine grain capabilities for describe resources.These changes allow end nodes to have a much tighter control of how they send and receive their traffic and provide a paradigm shift for the Internet ecosystem.

Deterministic networks have been proposed recently, where networks are expected to provide data transmission with bounded latency and very low packet loss rate to applications. In this paper, we analyze the requirements of various applications in deterministic networks, and propose a data forwarding mechanism for applications with bounded latency requirements. The proposed mechanism considers jointly the bound latency requirement, network states and different resource usages, aiming at optimizing the resource usage of the whole network while satisfying the requirements of as many applications as possible. Deep reinforcement learning technique is used to connect the transmission latency with network states. Simulation results show that our mechanism can effectively adjust the data transmission for deterministic applications according to the resource usage of the networks.

In this paper, we present InBlock4, an alternative to RPKI to provide Route Origin validation for BGP. InBlock4 is based in blockchain technology, embedding an alternative trust model, where an entity obtaining a resource allocation is protected also from errors and abuses from other entities in the allocation hierarchy. InBlock4 is compatible with BGPsec. Moreover, InBlock4 can be bootstrapped using the information in the RPKI and it can coexists with RPKI-based route origin validation. In the paper, we also present a working implementation of InBlock4 for Ethereum and we quantify its performance. \end{abstract}