The lecture by Grigore Stamatescu from University Politehnica of Bucharest will take place at the Complexity Science Hub Vienna in Room 201.
If you are interested in participating, please email to firstname.lastname@example.org.
The talk will discuss a hierarchical energy system architecture with embedded control which pushes prediction models to edge devices to address the challenge of managing demand-side response locally. We employ a two-step approach: At an upper level of hierarchy, we adopt a conventional machine learning pipeline to build load prediction models using automated domain-specific feature extraction and selection.
On a lower level of hierarchy, computed labels are used to train impact models realized by LSTM networks running on edge devices to infer the probability that the power consumption of the player contributes to the upper level prediction failure event. The system is evaluated on clustered and aggregated public energy traces of academic buildings. I will use the Matrix Profile, an efficient technique for time series exploratory analysis and data mining, to visualize the obtained results.