Another job talk with some machine learning in it, more, hopefully.

---------- Forwarded message ---------- From: Pierre McKenzie mckenzie@iro.umontreal.ca Date: 2017-01-26 18:54 GMT-05:00 Subject: Colloque DIRO, *lundi* 30 janvier, François Fouquet (Luxembourg) To: seminaires@iro.umontreal.ca

*Enabling Model-Driven Analytics for Cyber Physical systems *

par

* François Fouquet *

University of Luxembourg

*Lundi 30 janvier, 15:30-16:30*, *Salle 3195*, Pavillon André-Aisenstadt

Université de Montréal, 2920 Chemin de la Tour

Café avant 15:00-15:30

*Cette présentation sera donnée en français.*

*Résumé:*

Advances in software, embedded computing, sensors, and networking technologies will lead to a new generation of smart cyber-physical systems. Such systems have to continuously monitor and collect data from physical processes in order to make decisions fast, i.e., in live. However, the complex nature combined with the massive amount of data generated by such systems impose fundamental challenges. Smart grids are excellent illustrations of such systems. They combine novel country-wide communication medias together with many energy sensors to enable the next generation of sustainable infrastructure, including renewable energies. For instance, on-field grid operators can now leverage these newly collected data to empower live simulation tools that allow them to foresee the impacts of maintenance actions before their actual application on the real grid. However, developing such software systems, at the crossroad of big data, modelling and simulation is very challenging. In collaboration with the main electricity grid operator in Luxembourg, we have developed a novel analytic approach to process such complex data in live.

During this talk, I will present what we call model-driven live analytics. I will focus on the key enablers to make this approach scalable to the size of country-wide CPSs. The main contribution of this work is a multi-dimensional graph data model that brings raw data, domain knowledge, and machine learning together in a single model, which can drive live analytic processes. Firstly, data handled by cyber-physical systems is usually dynamic and changes frequently and at different paces. I will present a temporal graph data model and storage system, which consider time as a first-class property and allow to analyse frequently changing data. Additionally, I will present how a continuous sequence of sensor values can be efficiently encoded using live mathematical model inference. Secondly, making sustainable decisions requires to anticipate which impacts certain actions could have. In some cases, hundreds or thousands of such hypothetical actions must be explored ahead before any solid decision can be taken. I will present our approach to deal with such need - a multi-dimensional model that efficiently represent, store and analyse many different alternatives of the same system in live. Thirdly, to make smart decisions, cyber-physical systems must continuously refine behavioural models that are known at design time, with what can only be learned from live data. During this talk, I will present how we have combined machine learning and the multi-dimensional graph data model to empower live analytics for cyber-physical systems. Finally, I will conclude this talk with details about the open source project, which is developed around these research ideas, and share the lessons learned with respect to high-performance Java and big data.