The overall theme of our proposed doctoral programme is ECOLE: Experience-based COmputation: Learning to optimisE. It seeks novel synergies between nature inspired optimisation and machine learning to address new challenges that arise in industry due to the increasing complexity of products, product development and production processes. The unique aspect of ECOLE is to study and capture the notion of experience that is associated with expert engineers, who have worked on complex optimisation tasks for a certain time, in a computational framework composed of machine learning and optimisation strategies. We aim at developing cutting-edge optimisation algorithms that can continuously accumulate experience by learning from development projects both over time and across different problem categories. The more such algorithms are used for different optimisation problems, the better they become since their accumulated experience increases. The Consortium consists of two world-leading universities, the University of Birmingham (UK) and the University of Leiden (The Netherlands), both in the top 150 in the 2016-17 Times Higher Education World University Rankings, and two innovative companies, Honda Research Institute Europe GmbH (Germany) in the automotive sector and NEC Europe Ltd (UK) in the ICT sector. All have world-leading research groups with complementary expertise that support ECOLE. ECOLE fills an urgent need in Europe for highly skilled optimisation and machine learning experts who have first-hand industrial experiences allowing sustainable know-how growth for solving future challenges. Its entire training programme is centred around a set of novel research projects proposed for early stage researchers (ESRs), complemented by domain knowledge training, hands-on engineering training and transferable skill training. ESRs will spend 50% of their time in the non-academic beneficiaries and be trained in different academic environments and industrial sectors.

BEBA challenges a very ambitious goal: can we deploy wire-speed-reactive control/processing tasks inside the network switches, while retaining i) centralized control of their specification/operation, ii) high performance and scalability, and - crucial for real world adoption - iii) platform independency, i.e., consistency with the vendors’ need for closed platforms? BEBA’s answer revolves around the identification of a programming abstraction in the form of eXtended Finite State Machines (XFSMs). Via platform-agnostic XFSM “programs”, operators and enterprises will deploy not only static packet forwarding/processing rules (as in current OpenFlow devices), but will be able to specify and wire-speed enforce how such rules shall dynamically adapt to the time-varying flow and traffic behavior, i.e. in reaction to packet-level events, internal statistics changes, link/queue conditions, etc. BEBA holds the promise for future-proof, efficient, and easy to administer network devices capable to be repurposed so as to meet emerging needs. Indeed, BEBA’s approach, extended with node-level processing primitives made usable through our programming abstraction, brings about key benefits in the ability to i) “software-define” middlebox-type network functions well beyond static packet forwarding, with specific project’s attention to the monitoring and network security applications’ domains, and in the possibility to ii) address the current shortcomings revolving around the high latency and large overhead of centralized network control tasks. Finally, BEBA commits to a concrete and pragmatic innovation strategy. Short-time impact and standardization will be attempted by i) casting (part of) the BEBA approach as OpenFlow’s extensions; ii) making its implementation feasible over merchant-silicon chipsets currently found in commodity switches, and iii) releasing an open source virtual BEBA switch for the benefits of the Network Functions Virtualization community.