Comparative Study of Forecasting Schemes for IoT Device Traffic in Machine-to-Machine Communication

We present a comparative study of Autoregressive Integrated Moving Average (ARIMA), Multi-Layer Perceptron (MLP), 1-Dimensional Convolutional Neural Network (1-D CNN), and Long-Short Term Memory (LSTM) models on the problem of forecasting the traffic generation patterns of individual Internet of Things (IoT) devices in Machine-to-Machine (M2M) communication. We classify IoT traffic into four classes: Fixed-Bit Periodic (FBP), Variable-Bit Periodic (VBP), Fixed-Bit Aperiodic (FBA), and Variable-Bit Aperiodic (VBA). We show that LSTM outperforms all of the other models significantly in the symmetric Mean Absolute Percentage Error (sMAPE) measure for devices in the VBP class in our simulations. Furthermore, we show that LSTM has almost the same performance in this metric for the FBA class as MLP and 1-D CNN. While the training time per IoT device is the highest for LSTM, all of the forecasting models have reasonable training times for practical implementation. Our results suggest an architecture in which an IoT Gateway predicts the future traffic of IoT devices in the FBP, VBP and FBA classes and pre-allocates the uplink wireless channel for these classes in advance in order to alleviate the Massive Access Problem of M2M communication.

[1]  Raouf Boutaba,et al.  A comprehensive survey on machine learning for networking: evolution, applications and research opportunities , 2018, Journal of Internet Services and Applications.

[2]  Min Chen,et al.  Machine-to-Machine Communications: Architectures, Standards and Applications , 2012, KSII Trans. Internet Inf. Syst..

[3]  Katia Obraczka,et al.  Collision-free medium access based on traffic forecasting , 2012, 2012 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM).

[4]  Jorge Martínez-Bauset,et al.  Reinforcement Learning-Based ACB in LTE-A Networks for Handling Massive M2M and H2H Communications , 2018, 2018 IEEE International Conference on Communications (ICC).

[5]  Marco Pavone,et al.  Cellular Network Traffic Scheduling With Deep Reinforcement Learning , 2018, AAAI.

[6]  Jun-Bae Seo,et al.  Recursive Pseudo-Bayesian Access Class Barring for M2M Communications in LTE Systems , 2017, IEEE Transactions on Vehicular Technology.

[7]  Katia Obraczka,et al.  Smart Experts for Network State Estimation , 2016, IEEE Transactions on Network and Service Management.

[8]  Vicent Pla,et al.  Performance Analysis and Optimal Access Class Barring Parameter Configuration in LTE-A Networks With Massive M2M Traffic , 2018, IEEE Transactions on Vehicular Technology.

[9]  Kwang-Cheng Chen,et al.  Cooperative Access Class Barring for Machine-to-Machine Communications , 2012, IEEE Transactions on Wireless Communications.

[10]  Chia-han Lee,et al.  PRADA: Prioritized Random Access With Dynamic Access Barring for MTC in 3GPP LTE-A Networks , 2014, IEEE Transactions on Vehicular Technology.

[11]  Lu Xu,et al.  A Cluster-Based Congestion-Mitigating Access Scheme for Massive M2M Communications in Internet of Things , 2018, IEEE Internet of Things Journal.

[12]  Jianlong Liu,et al.  A Novel Congestion Reduction Scheme for Massive Machine-to-Machine Communication , 2017, IEEE Access.

[13]  Hsiao-Hwa Chen,et al.  M2M Communications in 3GPP LTE/LTE-A Networks: Architectures, Service Requirements, Challenges, and Applications , 2015, IEEE Communications Surveys & Tutorials.

[14]  Katia Obraczka,et al.  The case for using traffic forecasting in schedule-based channel access , 2011, 2011 IEEE Consumer Communications and Networking Conference (CCNC).