Fig. 1. MFH architecture based on the XG-PON system.

Fig. 2. LSTM neural network architecture used in the proposed method.

Fig. 3. LSTM cell and its unfolding in time.

Fig. 4. Detailed structure of the LSTM cell memory block. The sigmoid function is denoted as σ and the pointwise multiplication is denoted as × in the figure.

Fig. 5. MSE in the training process.

Fig. 6. Upstream delay performance comparison of RR-DBA, FNN-DBA, and LSTM-DBA.

Fig. 7. Upstream jitter performance comparison of RR-DBA, FNN-DBA, and LSTM-DBA.

Fig. 8. Upstream packet loss ratio performance comparison of RR-DBA, FNN-DBA, and LSTM-DBA.

Fig. 9. Upstream delay performance comparison of RR-DBA, FNN-DBA, LSTM-DBA, and FBA for one active ONU case.