Recent developments in orchestration and machine learning have made network automation more feasible, allowing the transition from error-prone and time-consuming manual manipulations to fast and refined automated responses in areas such as security and management. This article investigates the capabilities of a deep reinforcement learning agent to learn how to automatically share prefix announcements of an Autonomous System to its neighbors, in order to mitigate undesired network behaviors and therefore increase network resiliency and security. Our work focuses on network saturation, tackling the problem of network responsiveness in today's massive content delivery context. Results not only prove feasibility of such an agent, but also demonstrate its ability to minimize traffic loss as well as the number of actions to be performed by the automation process.

Improvements in containerization and orchestration have facilitated the management of distributed measurement platforms, helping rationalize networks and services monitoring, a vital but demanding activity. Nonetheless, orchestration in this domain, still requires optimization, which we address in this paper. More precisely, we invest our efforts in the optimization of allocating and scheduling network and service measurement applications, deployed in a pool of physical machines in the network. First, we formulate the problem into an Integer Linear Programming model and prove it to be NP-Hard. Then, we propose an approximate resolution based on the Ant Colony System (ACS) metaheuristic. Finally, we introduce an open-source distributed measurement platform implementing our algorithm. Results show that the ACS algorithm provides efficient orchestration solutions that outperform those provided by a Branch and Bound algorithm and a First Fit Decreasing algorithm.

The Internet is made of almost 50, 000 ASes exchanging routing information thanks to BGP. Inside each AS, information is redistributed via iBGP sessions. This allows each router to map a destination exterior to the AS with a given egress point. The main redistribution mechanisms used today, (iBGP full mesh, Route Reflectors and BGP confederations), either guarantee selection of the best egress point or enhance scalability, but not both. In this paper, we propose a new way to perform iBGP redistribution in an AS based on its IGP topology, conciliating optimality in route selection and scalability. Our contribution is threefold. First, we demonstrate the tractability of our approach and its benefits. Second, we provide an open-source implementation of our mechanism based on Quagga. Third, we illustrate the feasibility of our approach through simulations performed under ns-3 and compare its performance with full mesh and Route Reflection.

The behavior of routing protocols during convergence is critical as it impacts end-to-end performance. Network convergence is particularly important in BGP, the current interdomain routing protocol. In order to decrease the amount of exchanged routing messages and transient routes, BGP routers rely on MRAI timers and route flap damping. These timers are intended to limit the exchange of transient routing messages. In practice, these timers have been shown to be partly ineffective at improving convergence, making it even slower in some situations.In this paper, we propose to add a timer mechanism to routing protocols, that enforces an ordering of the routing messages such that path exploration is drastically reduced while controlling convergence time. Our approach is based on known results in generalized path algorithms and endomorphism semi-rings. Our timers, called MRPC (metrics and routing policies compliant), are set independently by each router and depend only on the metrics of the routes received by the router as well as the routing policies of the router. No sharing of information about routing policies between neighboring ASs is required by our solution. Similarly to the case of routing policies that may lead to BGP convergence problems, arbitrary routing policies can also make it impossible to enforce an ordering of the messages that will prevent path exploration to occur. We explain under which conditions path exploration can be avoided with our timers, and provide simulations to understand how they compare to MRAI.

A large quantity of ERS InSAR data and several scenes of Radarsat InSAR data were used to study historical deformation at Mount Meager in Northern B.C. The Mount Meager Volcanic Complex is a hazardous area showing an anomalously high frequency of catastrophic slope failures. It is also the location of Canada's most recent explosive volcanic eruption (2350 YBP). The primary objective of processing and analysis of the SAR data was to detect and measure small deformation events on the slopes of the mountain. A similarly large number of repeated ERS SAR scenes collected over the urban area of Vancouver between 1992 and 2000 was selected for InSAR processing. The objective of the project was to investigate the potential of detecting and measuring very small deformation rates (better than 1 mm/yr) and deformation events while taking advantage of the large volume of SAR datasets. The following types of deformation were of specific interest: 1. Stability of the Fraser River Delta 2. Tidal loading 3. Subsidence patterns in urban areas 4. Deformation of individual buildings, bridges and infrastructure. This paper provides some information on the processing methodologies that were employed as well as results and interpretation of the results.