Skip to main content
. 2021 Dec 22;22(1):26. doi: 10.3390/s22010026

Table 9.

The state-of-the-art ML-based solution for 5G network.

Author References Key Contribution ML Applied Network Participants Component 5G Network Application Parameter
RAN Core LB SDN RAN RA SEC
Alave et al. [68] Network traffic prediction LSTM and DNN * X
Bega et al. [15] Network slice admission control algorithm Machine Learning and Deep Learing X X X
Suomalainen et al. [69] 5G Security Machine Learning X
Bashir et al. [70] Resource Allocation Machine Learning X
Balevi et al. [71] Low Latency communication Unsupervised clustering X X X
Tayyaba et al. [72] Resource Management LSTM, CNN, and DNN X
Sim et al. [73] 5G mmWave Vehicular communication FML (Fast machine Learning) X * X
Li et al. [74] Intrusion Detection System Machine Learning X X
Kafle et al. [75] 5G Network Slicing Machine Learning X X
Chen et al. [76] Physical-Layer Channel Authentication Machine Learning X X X X X
Sevgican et al. [77] Intelligent Network Data Analytics Function in 5G Machine Learning X X X * *
Abidi et al. [78] Optimal 5G network slicing Machine Learning and Deep Learing X X *