A Nonlinear Autoregressive Neural Network for Interference Prediction and Resource Allocation in URLLC Scenarios

Ultra reliable low latency communications (URLLC) is a new service class introduced in 5G which is characterized by strict reliability (1–10−5) and low latency requirements (1 ms). To meet these requisites, several strategies like overprovisioning of resources and channel-predictive algorithms have been developed. This paper describes the application of a Nonlinear Autoregressive Neural Network (NARNN) as a novel approach to forecast interference levels in a wireless system for the purpose of efficient resource allocation. Accurate interference forecasts also grant the possibility of meeting specific outage probability requirements in URLLC scenarios. Performance of this proposal is evaluated upon the basis of NARNN predictions accuracy and system resource usage. Our proposed approach achieved a promising mean absolute percentage error of 7.8 % on interference predictions and also reduced the resource usage in up to 15 % when compared to a recently proposed interference prediction algorithm.

[1]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[2]  Luís Guilherme Barbosa Rolim,et al.  A Control-Oriented Model of a PEM Fuel Cell Stack Based on NARX and NOE Neural Networks , 2015, IEEE Transactions on Industrial Electronics.

[3]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[4]  Pengxiang Qiu,et al.  Nonlinear Autoregressive Neural Networks to Predict Hydraulic Fracturing Fluid Leakage into Shallow Groundwater , 2020, Water.

[5]  Nurul H. Mahmood,et al.  Multi-Channel Access Solutions for 5G New Radio , 2019, 2019 IEEE Wireless Communications and Networking Conference Workshop (WCNCW).

[6]  Christos Masouros,et al.  Rethinking the role of interference in wireless networks , 2014, IEEE Communications Magazine.

[7]  Christian Bettstetter,et al.  Interference Prediction in Wireless Networks: Stochastic Geometry Meets Recursive Filtering , 2019, IEEE Transactions on Vehicular Technology.

[8]  Maria del Carmen Pegalajar Jiménez,et al.  An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings , 2016 .

[9]  H. Vincent Poor,et al.  Channel Coding Rate in the Finite Blocklength Regime , 2010, IEEE Transactions on Information Theory.

[10]  Youcef Messlem,et al.  Daily global solar radiation forecasting over a desert area using NAR neural networks comparison with conventional methods , 2015, 2015 International Conference on Renewable Energy Research and Applications (ICRERA).

[11]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[12]  Wen Tong Chong,et al.  A Comparative Study of Activation Functions of NAR and NARX Neural Network for Long-Term Wind Speed Forecasting in Malaysia , 2019, Mathematical Problems in Engineering.

[13]  David A. Cartes,et al.  Application of artificial intelligence to stator winding fault diagnosis in Permanent Magnet Synchronous Machines , 2013 .

[14]  Martin Haenggi,et al.  Mean Interference in Hard-Core Wireless Networks , 2011, IEEE Communications Letters.

[15]  Shubham Varma,et al.  A machine learning algorithm for interference removal from a signal , 2015, 2015 National Conference on Recent Advances in Electronics & Computer Engineering (RAECE).

[16]  Robert Baldemair,et al.  5G Radio Network Design for Ultra-Reliable Low-Latency Communication , 2018, IEEE Network.

[17]  Matti Latva-aho,et al.  A Predictive Interference Management Algorithm for URLLC in Beyond 5G Networks , 2020, IEEE Communications Letters.