Machine Learning with Variable Sampling Rate for Traffic Prediction in 6G MEC IoT

Table 1

Related works performing prediction of different research objects and by means of different techniques.

[Ref]	Research object	Fine or coarse	Dataset	Simulator	Techniques
[9]	Telcom network	Coarse (15 min)	GEANTWIDE	Not mentioned	ARIMA; SVR; LSTM; RCLSTM; SR-based
[10]	Telcom user traffic and location	Coarse (15 min)	GENAT	Not mentioned	ARIMA; SVR; LSTM; RCLSTM; FFNN
[11]	Telcom. Network	Coarse	Operator data	Python	ARIMA; FFNN; LSTM
[12]	Mobile APP	Fine	MIRAGE-2019	Not mentioned	HMM; RFR
[13]	Mobile APP	Fine	MIRAGE-2019	Not mentioned	LR; K-NNR; RFR; MC; CNN; LSTM; GRU
[14]	Mobile 6G network	Coarse (5 min)	Locally obtained	Edge μ-boxes, jupyter notebook	LSTM-based encoder and decoder
[15]	University campus datacenter	Fine	EDU1 dataset	Python, keras	CNN; RF
[16]	SDN controller (ONOS)	Fine	Ping ARQ message	Not mentioned	DNN; SF; LDA
[17]	Internet	Fine	DNS traffic	Python, TensorFlow	SVR; BPNN; LSTM
[18]	Internet	Fine	User data	MATLAB	GRU; RNN