Andrea Luparello
Synthetic load profile generation for residential users through metadata-driven generative AI in Renewable Energy Community (REC) applications.
Rel. Alfonso Capozzoli, Marco Savino Piscitelli, Rocco Giudice. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Energetica E Nucleare, 2026
|
|
PDF (Tesi_di_laurea)
- Tesi
Accesso limitato a: Solo utenti staff fino al 30 Settembre 2027 (data di embargo). Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (44MB) |
Abstract
The transition toward decentralized and renewable energy systems in buildings increases the need for energy sharing mechanisms that reduce mismatches between local generation and demand while maximizing self sufficiency. Renewable Energy Communities (REC) are legal entities that allow individuals to collectively produce, consume and share renewable electricity within a defined geographical perimeter. Unlike traditional aggregation schemes, where energy flows unidirectionally from large scale producers to end users, RECs enable virtual sharing of locally generated renewable energy through the public distribution grid. By aligning local production with consumption, they enhance self consumption, foster renewable deployment, mitigate variability from distributed generation and reduce dependence on centralized imports, with associated economic benefits for members.
In this context, accurate modeling of residential electricity load profiles is essential to support planning, design and operational management of collective self consumption schemes
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
URI
![]() |
Modifica (riservato agli operatori) |
