Federated and split learning models were applied to forecast power consumption in smart grids, with a focus on integrating renewable energy sources while prioritizing data privacy, computational efficiency, and accuracy. The study conducted a comparative evaluation of these two methods, investigating various parameters influencing the performance of split learning.
Anotace v angličtině
-
Klíčová slova
-
Klíčová slova v angličtině
-
Rozsah průvodní práce
71P
Jazyk
AN
Anotace
Federated and split learning models were applied to forecast power consumption in smart grids, with a focus on integrating renewable energy sources while prioritizing data privacy, computational efficiency, and accuracy. The study conducted a comparative evaluation of these two methods, investigating various parameters influencing the performance of split learning.
Anotace v angličtině
-
Klíčová slova
-
Klíčová slova v angličtině
-
Zásady pro vypracování
-
Zásady pro vypracování
-
Seznam doporučené literatury
-
Seznam doporučené literatury
-
Přílohy volně vložené
-
Přílohy vázané v práci
-
Převzato z knihovny
Ne
Plný text práce
Přílohy
Posudek(y) oponenta
Hodnocení vedoucího
Záznam průběhu obhajoby
The second opponent suggested also 2
Presentation of the diploma thesis
Methods
Quantile regression
Federated learning - several houses
Data are sent to a server.
Supervisor review, opponent review, opponent2 review - references are missing