logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-03062024-123825


Tipo di tesi
Tesi di laurea magistrale
Autore
FAETI, COSIMO
URN
etd-03062024-123825
Titolo
Causal Impact Analysis
Dipartimento
INFORMATICA
Corso di studi
DATA SCIENCE AND BUSINESS INFORMATICS
Relatori
relatore Prof. Frangioni, Antonio
Parole chiave
  • Bayesian Structural Time Series
  • causal inference
  • counterfactual estimators
  • data science
  • energy consumption
  • energy efficiency
  • energy insights platform
  • Interrupted Time Series
  • sustainability
Data inizio appello
12/04/2024
Consultabilità
Non consultabile
Data di rilascio
12/04/2094
Riassunto
This thesis explores the application of causal inference methodologies to measure the impact of Eliq's energy management solutions on end-users' electricity consumption. With the increasing demand for electricity and the imperative to reduce greenhouse gas emissions, understanding the causal effects of energy management solutions becomes indispensable. Leveraging causal inference techniques, this research investigates whether Eliq's solutions lead to changes, particularly reductions, in energy consumption among customers. Through counterfactual estimators such as Bayesian Structural Time Series and Interrupted Time Series models, the study analyzes multi-dimensional data collected from various locations to estimate the causal impact. Results demonstrate a significant negative causal impact in the majority of cases, indicating a reduction in electricity consumption attributed to Eliq's insights platform. However, a smaller portion of locations exhibit a positive causal impact, suggesting an increase in consumption due to factors not always controllable by Eliq. Overall, this research contributes to advancing the understanding of energy management solutions' effectiveness and their role in promoting energy efficiency and sustainability.
File