Akram Hakiri

Software-Defined Networking

Currently many aspects of the classical architecture of the Internet are etched in stone - a so called ossification of the Internet - which has led to major obstacles in IPv6 deployment and difficulty in using IP multicast services. Yet, there exist many reasons to extend the Internet, e.g., for improving intra-domain and inter-domain routing for high availability of the network, providing end-to-end connectivity for users, and allowing dynamic QoS management of network resources for new applications, such as data center, cloud computing, and network virtualization. To address these requirements, the next-generation architecture for the Future Internet has introduced the concept of Software-Defined Networking (SDN). At the core of this emerging paradigm is the separation and centralization of the control plane from the forwarding elements in the network as opposed to the distributed control plane of existing networks. This decoupling allows deployment of control plane software components (e.g., OpenFlow controller) on computer platforms that are much more powerful than traditional network equipment (e.g., switches/routers) while protecting the data and intellectual property of the vendors of such equipment.A critical understanding of this emerging paradigm is necessary to address the multiple challenges in realizing the Future Internet and to resolve the ossification problem of the existing Internet. To address these requirements, this paper surveys existing technologies and the wide range of recent and state-of-the-art projects on SDN followed by an in-depth discussion of the major challenges in this area.

Software defined networking and virtualization for broadband satellite networks

Satellite networks have traditionally been considered for specific purposes. Recently, new satellite technologies have been pushed to the market enabling high-performance satellite access networks. On the other hand, network architectures are taking advantage of emerging technologies such as software-defined networking (SDN), network virtualization and network functions virtualization (NFV). Therefore, benefiting communications services over satellite networks from these new technologies at first, and their seamless integration with terrestrial networks at second, are of great interest and importance. In this paper, and through comprehensive use cases, the advantages of introducing network programmability and virtualization using SDN and/or NFV in satellite networks are investigated. The requirements to be fulfilled in each use case are also discussed.

Publish/subscribe-enabled software defined networking for efficient and scalable IoT communications

The Internet of Things (IoT) is the result of many different enabling technologies such as embedded systems, wireless sensor networks, cloud computing, big-data, etc., which are used to gather, process, infer, and transmit data. Combining all these technologies requires a research effort to address all the challenges of these technologies, especially for sensing and delivering information from the physical world to cloud-hosted services. In this article we outline the most important issues related to standardization efforts, mobility of objects, networking and gateway access, and QoS support. In particular, we describe a novel IoT network architecture that integrates software defined networking (SDN) and data distribution service (DDS) middleware. The proposed architecture will improve service delivery of IoT systems and will bring flexibility to the network.

Leveraging SDN for The 5G Networks: Trends, Prospects and Challenges

Today 4G mobile systems are evolving to provide IP connectivity for diverse applications and services up to 1Gbps. They are designed to optimize the network performance, improve cost efficiency and facilitate the uptake of mass market IP-based services. Nevertheless, the growing demand and the diverse patterns of mobile traffic place an increasing strain on cellular networks. To cater to the large volumes of traffic delivered by the new services and applications, the future 5G network will provide the fundamental infrastructure for billions of new devices with less predictable traffic patterns will join the network. The 5G technology is presently in its early research stages, so researches are currently underway exploring different architectural paths to address their key drivers. SDN techniques have been seen as promising enablers for this vision of carrier networks, which will likely play a crucial role in the design of 5G wireless networks. A critical understanding of this emerging paradigm is necessary to address the multiple challenges of the future SDN-enabled 5G technology. To address this requirement, a survey the emerging trends and prospects, followed by in-depth discussion of major challenges in this area are discussed.

Supporting End-to-End Quality of Service Properties in OMG Data Distribution Service Publish/Subscribe Middleware over Wide Area Networks

Assuring end-to-end quality-of-service (QoS) in distributed real-time and embedded (DRE) systems is hard due to the heterogeneity and scale of communication networks, transient behavior, and the lack of mechanisms that holistically schedule di erent resources end-to-end. This paper makes two contributions to research focusing on overcoming these problems in the context of wide area network (WAN)-based DRE applications that use the OMG Data Distribution Service (DDS) QoS-enabled publish/subscribe middleware. First, it provides an analytical approach to bound the delays incurred along the critical path in a typical DDS-based publish/subscribe stream, which helps ensure predictable end-to-end delays. Second, it presents the design and evaluation of a policy-driven framework called Velox. Velox combines multi-layer, standards-based technologies—including the OMG DDS and IP Di Serv—to support end-to-end QoS in heterogeneous networks and shield applications from the details of network QoS mechanisms by specifying per-flow QoS requirements. The results of empirical tests conducted using Velox show how combining DDS with Di Serv enhances the schedulability and predictability of DRE applications, improves data delivery over heterogeneous IP networks, and provides network-level di erentiated performance.

Supporting SIP-based end-to-end Data Distribution Service QoS in WANs

Assuring end-to-end QoS in enterprise distributed real-time and embedded (DRE) systems is hard due to the heterogeneity and transient behavior of communication networks, the lack of integrated mechanisms that schedule communication and computing resources holistically, and the scalability limits of IP multicast in wide-area networks (WANs). This paper makes three contributions to research on overcoming these problems in the context of enterprise DRE systems that use the OMG Data Distribution Service (DDS) quality-of-service (QoS)-enabled publish/subscribe (pub/sub) middleware over WANs. First, it codifies the limitations of conventional DDS implementations deployed over WANs. Second, it describes a middleware component called Proxy DDS that bridges multiple, isolated DDS domains deployed over WANs. Third, it describes the NetQSIP framework that combines multi-layer, standards-based technologies including the OMG-DDS, Session Initiation Protocol (SIP), and IP DiffServ to support end-to-end QoS in a WAN and shield pub/sub applications from tedious and error-prone details of network QoS mechanisms. The results of experiments using Proxy DDS and NetQSIP show how combining DDS with SIP in DiffServ networks significantly improves dynamic resource reservation in WANs and provides effective end-to-end QoS management.

QoS-Enabled ANFIS Dead Reckoning Algorithm for Distributed Interactive Simulation

Dead Reckoning mechanisms are usually used to estimate the position of simulated entity in virtual environment. However, this technique often ignores available contextual information that may influence to the state of an entity, sacrificing remote predictive accuracy in favor of low computational complexity. A novel extension of Dead Reckoning is suggested in this paper to increase the network availability and fulfill the required Quality of Service in large scale distributed simulation application. The proposed algorithm is referred to as ANFIS Dead Reckoning, which stands for Adaptive-Network-based Fuzzy Inference Systems Dead Reckoning is based on a fuzzy inference system which is trained by the learning algorithm derived from the neuronal networks and fuzzy inference theory. The proposed mechanism is based on the optimization approach to calculate the error threshold violation in networking games. Our model shows it primary benefits especially in the decision making of the behavior of simulated entities and preserving the consistence of the simulation.

A DDS/SDN Based Communication System for Efficient Support of Dynamic Distributed Real-Time Applications

Many distributed real-time applications have dynamic requirements regarding communication delay and bandwidth. The Data Distribution Service (DDS) middleware is a key enabling technology used to support such applications. Indeed, the publish/subscribe distribution model of DDS with the ability to assign dynamic QoS (Quality of Service) parameters to DDS distribution services is able to take into account changes in the exchanged data flows and in the required QoS. This variability is taken into account at the middleware level to adjust some of DDS QoS mechanisms but is rarely propagated to the network layer to provide dynamic network communication services that fit the varying DDS distribution service needs. Usually, an over provisioned network is used, leading to network resource wastage. This paper addresses this issue and proposes a communication architecture that combines DDS with a new emerging class of communication networks named Software Defined Networks (SDN) to support efficiently dynamic distributed applications. SDN bring flexibility to the network and enable the provision of on-demand dynamic network communication services.

A SIP-based network QoS provisioning framework for cloud-hosted DDS applications

The growing trend towards running publish/subscribe (pub/sub)-based distributed real-time and embedded (DRE) systems in cloud environments motivates the need to achieve end-to-end quality-of-service (QoS) over wide-area networks (WANs). The OMG Data Distribution Service (DDS) is a data-centric middleware that provides fast, scalable and predictable distribution of real-time critical data. The DDS standard, however, provides QoS control mechanisms that are confined only to the middleware residing at end-systems, which makes it hard to support DRE pub/sub systems over WANs. A promising solution to this problem is to integrate DDS with the Session Initiation Protocol (SIP), which is an IP-based signaling protocol that supports real-time applications involving voice, video, and multimedia sessions via the QoS mechanisms in IP networks. This paper describes our approach to bridge the SIP protocol and DDS to realize DDS-based applications over QoS-enabled IP WANs by overcoming both inherent and accidental complexities in their integration. An exemplar of the proposed approach for IP DiffServ networks is described, which uses the Common Open Policy Server (COPS) protocol to assure QoS for cloud-hosted DRE pub/sub applications. To distinguish the DDS traffic from other best-effort traffic in the cloud environment, our approach uses the COPS-DRA protocol as a generic protocol for automatic service-level negotiation and the integration of this protocol in an overall QoS management architecture to manage service levels over multiple domains deploying different QoS technologies.

Data-centric publish/subscribe routing middleware for realizing proactive overlay software-defined networking

Software Defined Networking (SDN) has emerged as an attractive solution to allow cloud-to-cloud interconnection and federation. SDN technologies, such as OpenFlow, use both reactive hop-by-hop and proactive approaches to program the switches. The reactive strategy incurs substantial scalability problems for large networks due to the hop-by-hop behavior while the proactive approach is hard to implement in practice due to the need to forecast all possible forwarding rules ahead-of-time. An attractive and more realistic alternative is the proactive overlay SDN approach, however, many challenges must first be overcome to realize it. Existing techniques to program the switches use low-level programming abstractions, which are error-prone and cannot scale. Middleware-based solutions, e.g., using XMPP, are stateful and hence also incur substantial scalability issues. Although content-based publish/subscribe (pub/sub) solutions have been used in the past for SDN, they rely on brokers, which is problematic and incurs unnecessary additional infrastructure elements that pollute the SDN architecture. To address these issues, this paper demonstrates how the strengths of the data-centric, broker-less pub/sub paradigm can be exploited to realize proactive overlay SDN for inter cloud domain federation. To that end, we first present the design rationale and architecture of our solution called POSEIDON (Proactive brOkerless SubscribEr Interest-Defined Overlay Networking). Second, we present the messaging protocol between the controller and switches. Finally, we present results of evaluating POSEIDON and illustrate how it improves data delivery and provides high performance at the network-level in proactive overlay SDN.