Balancing Data Privacy and 5G VNFs Security Monitoring: Federated Learning with CNN + BiLSTM + LSTM Model

Table 5

Optimal hyperparameters for FL and CL with the CICIDS2017 dataset.

Parameters	Federated learning	Centralized learning
Learning rate	0.01	0.01
Number of rounds	10	—
Number of epochs	40	200
Batch size	120	120
Number of clients	3, 6, 9, 12	—
Loss function	Adam	Adam