Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

The SmartEMS project will develop data analysis and machine learning approaches suitable for incorporationx000D
in non-residential building energy management systems, and test them in real buildings. Dramatic recentx000D
improvements in the power of machine learning have made it possible to train and deploy such algorithms tox000D
solve practical challenges. Complex energy systems in buildings present many such challenges, from set-pointx000D
optimization to predictive control. SES Inc. has the capabilities and client-base to take advantage of this.x000D
There are two core approaches: offline learning from data, and real-time predictive control. The former willx000D
identify underlying trends and areas of concern by analysis of operational data; the latter will develop and trainx000D
machine learning controllers that will improve operation based on weather predictions. The two together canx000D
deliver a highly flexible, robust solution.x000D
SmartEMS will use open-source systems and protocols (VOLTTRON, BACnet) that have been successfullyx000D
used by SES Inc. on previous projects. Open-source state of the art machine learning libraries based in Pythonx000D
(scikit-learn, TensorFlow) will be used, along with other Python-based data analysis and visualisation libraries.x000D
Remotely accessible interface hardware (bare-bones PCs; Raspberry Pi) will be deployed in 3 test buildingsx000D
(one university campus and two clients of SES Inc.). Cloud computing from CANARIE will be used forx000D
computationally intensive parts of the process.x000D
The output will be a commercially deployable solution based on the latest academic research; parts of this willx000D
also be released as open-source. This will form the basis for an ongoing collaboration. The concept hasx000D
significant potential to improve energy use, emissions and comfort in commercial buildings.