About this document

Adaptive Hyperparameter Tuning in Federated Learning for Energy Prediction by Pablo Ignacio Contreras Estrada is a document available to read on EtoBox.

This paper presents a novel hierarchical federated learning approach for household energy prediction that incorporates adaptive hyperparameter tuning and clustering techniques. By aggregating models from households with similar energy profiles and optimizing hyperparameters using genetic algorithms and simulated annealing, the proposed method significantly enhances prediction accuracy and reduces communication overhead. The results indicate improved performance compared to traditional federated averaging, p

Author

Pablo Ignacio Contreras Estrada

Language

EN