CSH Talk by Grigore Stamatescu: “Deep impact models for edge characterisation of energy events”

Sep 26, 2019 | 15:0016:00

Loading Events
  • This event has passed.

Event Navigation

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 office@csh.ac.at.




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.



Grigore Stamatescu is an associate professor at the University Politehnica of Bucharest, Romania. His research interests include statistical learning and computational intelligence techniques for sensor data under new paradigms such as (Industrial-) Internet of Things and Cyber-physical Systems, with applications to control of energy systems and smart manufacturing. Between February and September 2019 he was a visiting researcher at the Complexity Science Hub Vienna supported by the Joint Excellence in Science and Humanities program of the Austrian Academy of Sciences.


Sep 26, 2019


Complexity Science Hub Vienna
+43 1 59991 600
View Organizer Website


CSH Vienna
Josefstaedter Straße 39
+ Google Map
+43 1 59991 600
View Venue Website