Unified ensemble federated learning with cloud computing for online anomaly detection in energy-efficient wireless sensor networks

Journal of Cloud Computing

Advances, Systems and Applications

Table 2 Comparison of EFL with state-of-the-art federated learning models

Model	Model Acccuracy	Communication Overhead	Privacy Preservation	Training Convergence
Federated Learning with Secure Agg [16]	91%	1.2 MB	High	34 epochs
Federated Averaging (FedAvg) [32]	88%	1.5 MB	Low	28 epochs
EFL	95%	1.0 MB	High	9 epochs