| KEYWORD |
ELECTRONIC DESIGN AUTOMATION - EDA
Machine learning for anomalous detection of household appliances
Thesis in external company
keywords ANOMALY DETECTION, ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORKS, DEEP NEURAL NETWORKS, MACHINE LEARNING, NON-INTRUISIVE LOAD MONITORING, SMART GRID
Reference persons EDOARDO PATTI
External reference persons Marco Castangia (marco.castangia@polito.it), Christian Camarda (christian@midorisrl.eu)
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, Energy Center Lab, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description The detection of anomalous behaviors in the power consumption of appliances can help in reducing energy wastage in households. Malfunctioning appliances usually show a power signature statistically different from their normal behavior, which can lead to higher energy consumption or more serious damages. Alternatively, anomalous behaviors can be caused by negligent users exhibiting bad habits in the usage of their appliances. This thesis aims at detecting anomalous behaviors in the power consumption of various appliances by means of machine learning techniques for anomaly detection. In detail, the candidate will analyze the power consumption of different appliances in order to detect significant outliers. The ideal candidate should be familiar with Python. The knowledge of basic machine learning algorithms is a plus.
Required skills python programming language
Deadline 10/02/2025
PROPONI LA TUA CANDIDATURA