Performance Analysis of ML-Based MTC Traffic Pattern Predictors

Prolonging the lifetime of massive machine-type communication (MTC) networks is key to realizing a sustainable digitized society. Great energy savings can be achieved by accurately predicting MTC traffic followed by properly designed resource allocation mechanisms. However, selecting the proper MTC traffic predictor is not straightforward and depends on accuracy/complexity trade-offs and the specific MTC applications and network characteristics. Remarkably, the related state-of-the-art literature still lacks such debates. Herein, we assess the performance of several machine learning (ML) methods to predict Poisson and quasi-periodic MTC traffic in terms of accuracy and computational cost. Results show that the temporal convolutional network (TCN) outperforms the long-short term memory (LSTM), the gated recurrent units (GRU), and the recurrent neural network (RNN), in that order. For Poisson traffic, the accuracy gap between the predictors is larger than under quasi-periodic traffic. Finally, we show that running a TCN predictor is around three times more costly than other methods, while the training/inference time is the greatest/least.

[1]  Guisong Liu,et al.  MANTA: Multi-Lane Capsule Network Assisted Traffic Classification for 5G Network Slicing , 2022, IEEE Wireless Communications Letters.

[2]  Lindong Zhao,et al.  Quality-of-Decision-Driven Machine-Type Communication , 2022, IEEE Internet of Things Journal.

[3]  Ye Zhang,et al.  Multicell Grant-Free Uplink IoT Networks With Hard Deadline Services in URLLC , 2022, IEEE Wireless Communications Letters.

[4]  David E. Ruíz‐Guirola,et al.  Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction , 2022, IEEE Internet of Things Journal.

[5]  A. Chorti,et al.  Smart Link Adaptation and Scheduling for IIoT , 2022, IEEE Networking Letters.

[6]  Shamik Sengupta,et al.  Modeling and Analyzing Attacker Behavior in IoT Botnet using Temporal Convolution Network (TCN) , 2021, Comput. Secur..

[7]  Hirley Alves,et al.  A Learning-Based Fast Uplink Grant for Massive IoT via Support Vector Machines and Long Short-Term Memory , 2021, IEEE Internet of Things Journal.

[8]  Thomas F. La Porta,et al.  Modeling and Analysis of mMTC Traffic in 5G Base Stations , 2021, 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC).

[9]  Tho Le-Ngoc,et al.  Traffic Prediction for Reconfigurable Access Scheme in Correlated Traffic MTC Networks , 2021, 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

[10]  Yi-Han Xu,et al.  Generative Adversarial LSTM Networks Learning for Resource Allocation in UAV-Served M2M Communications , 2021, IEEE Wireless Communications Letters.

[11]  Matti Latva-aho,et al.  CSI-Free vs CSI-Based Multi-Antenna WET for Massive Low-Power Internet of Things , 2021, IEEE Transactions on Wireless Communications.

[12]  Lianyong Qi,et al.  6G-Enabled Short-Term Forecasting for Large-Scale Traffic Flow in Massive IoT Based on Time-Aware Locality-Sensitive Hashing , 2021, IEEE Internet of Things Journal.

[13]  S. Hu,et al.  Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications , 2020, IEEE Communications Surveys & Tutorials.

[14]  Indika A. M. Balapuwaduge,et al.  Preamble Transmission Prediction for mMTC Bursty Traffic: A Machine Learning based Approach , 2020, GLOBECOM 2020 - 2020 IEEE Global Communications Conference.

[15]  R. M. A. P. Rajatheva,et al.  Event-Driven Source Traffic Prediction in Machine-Type Communications Using LSTM Networks , 2020, GLOBECOM 2020 - 2020 IEEE Global Communications Conference.

[16]  Abdul Ahad,et al.  Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions , 2020, IEEE Access.

[17]  Long Hu,et al.  Intelligent Traffic Adaptive Resource Allocation for Edge Computing-Based 5G Networks , 2020, IEEE Transactions on Cognitive Communications and Networking.

[18]  Eiji Kamioka,et al.  Convolutional Neural Networks for Continuous QoE Prediction in Video Streaming Services , 2020, IEEE Access.

[19]  Frank Y. Li,et al.  Supervised Learning based Arrival Prediction and Dynamic Preamble Allocation for Bursty Traffic , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[20]  Henning Thomsen,et al.  A traffic model for machine-type communications using spatial point processes , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[21]  Lee Gillam,et al.  Energy efficient computing, clusters, grids and clouds: A taxonomy and survey , 2017, Sustain. Comput. Informatics Syst..

[22]  Fathi M. Salem,et al.  Gate-variants of Gated Recurrent Unit (GRU) neural networks , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[25]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.