Mohamed Lamine Lamali

End-to-end quality of service in pseudo-wire networks

Carrier-grade networks are complex systems that include several heterogeneous domains and support various types of services under specific Quality of Service (QoS) requirements. To tackle the problem of setting end-to-end connections across heterogeneous domains, the Pseudo-Wire architecture [1] allows to emulate some protocols (e.g. SDH, Ethernet, ATM, etc.) over MPLS. This emulation is achieved by encapsulation and decapsulation functions called adaptation functions. A path crossing heterogeneous domains must involve compatible functions so that datagrams are understandable by the source and target nodes (e.g. if Ethernet is encapsulated in MPLS by a node, it must be decapsulated by another).

Path computation in multi-layer multi-domain networks: A language theoretic approach

Multi-layer networks are networks in which several protocols may coexist at different layers. The Pseudo-Wire architecture provides encapsulation and decapsulation functions of protocols over Packet-Switched Networks. In a multi-domain context, computing a path to support end-to-end services requires the consideration of encapsulation and decapsulation capabilities. It appears that graph models are not expressive enough to tackle this problem. In this paper, we propose a new model of heterogeneous networks using Automata Theory. A network is modeled as a Push-Down Automaton (PDA) which is able to capture the encapsulation and decapsulation capabilities, the PDA stack corresponding to the stack of encapsulated protocols. We provide polynomial algorithms that compute the shortest path either in hops or in the number of encapsulations and decapsulations along the inter-domain path, the later reducing manual configurations and possible loops in the path.

Reputation-Aware learning for SLA negotiation

Assuring Quality of Service (QoS) over multiple Network Service Providers (NSPs) requires to negotiate QoS contracts as Service Level Agreements (SLAs) between NSPs. The goal of an NSP is to maximize its revenues by selling as much as possible SLAs. However, provisioning too much SLAs might increase the risk of violations of the committed QoS thus impacting the NSPs reputation. In order to determine the appropriate provisioning strategies, we propose to extend existing solutions based on Reinforcement Learning with reputation-awareness so that NSPs maximize their revenues.

Adaptive multicast streaming for videoconferences on software-defined networks

Abstract Real-time applications, such as video conferences, have strong Quality of Service requirements for ensuring a decent Quality of Experience. Nowadays, most of these conferences are performed over wireless devices. Thus, an appropriate management of both heterogeneous mobile devices and network dynamics is necessary. Software Defined Networking enables the use of multicasting and stream layering inside the network nodes, two techniques able to enhance the quality of live video streams. In this paper, we propose two algorithms for building and maintaining multicast sessions in a software-defined network. The first algorithm sets up the initial multicast trees for a given call. It optimally places the stream layer adaptation function inside the core network in order to minimize the bandwidth consumption. This algorithm has two versions: the first one, based on shortest path trees is minimizing the latency, while the second one, based on spanning trees is minimizing the bandwidth consumption. The second algorithm adapts the multicast trees according to the network changes occurring during a call. It does not recompute the trees, but only relocates the stream layer adaptation functions. It requires very low computation at the controller, thus making our proposal fast and highly reactive. Extensive simulation results confirm the efficiency of our solution in terms of processing time and bandwidth savings compared to existing solutions such as multiple unicast connections, Multipoint Control Unit solutions and application layer multicast.

Path computation in multi-layer networks: Complexity and algorithms

Carrier-grade networks comprise several layers where different protocols coexist. Nowadays, most of these networks have different control planes to manage routing on different layers, leading to a suboptimal use of the network resources and additional operational costs. However, some routers are able to encapsulate, decapsulate and convert protocols and act as a liaison between these layers. A unified control plane would be useful to optimize the use of the network resources and automate the routing configurations. Software-Defined Networking (SDN) based architectures, such as OpenFlow, offer a chance to design such a control plane. One of the most important problems to deal with in this design is the path computation process. Classical path computation algorithms cannot resolve the problem as they do not take into account encapsulations and conversions of protocols. In this paper, we propose algorithms to solve this problem and study several cases: Path computation without bandwidth constraint, under bandwidth constraint and under other Quality of Service constraints. We study the complexity and the scalability of our algorithms and evaluate their performances on real topologies. The results show that they outperform the previous ones proposed in the literature.