Cloud/software-based wireless resource controllers have been recently proposed to exploit radio frequency (RF) data analytics for a network control, configuration and management. For efficient resource controller design, tracking the right metrics in real-time (analytics) and making realistic predictions (deep learning) will play an important role to increase its efficiency. This factor becomes particularly critical as radio environments are generally dynamic, and the data sets collected may exhibit shift in distribution over time and/or space. When a trained model is deployed at the controller without taking into account dataset shift, a large amount of prediction errors may take place. This paper quantifies dataset shift in real wireless physical layer data by using a statistical distance method called earth mover's distance (EMD). It utilizes an FPGA to process in real-time the inphase and quadrature (IQ) samples to obtain useful information, such as histograms of wireless channel utilization (CU). We have prototyped the data processing modules on a Xilinx System on Chip (SoC) board using Vivado, Vivado HLS, SDK and MATLAB tools. The histograms are sent as low-overhead analytics to the resource controller server where they are processed to evaluate dataset shift. The presented results provide insight into dataset shift in real wireless CU data collected over multiple weeks in the University of Oulu using the implemented modules on SoC devices. The results can be used to design approaches that can prevent failures due to datashift in deep learning models for wireless networks.

Deep learning (DL) driven proactive resource allocation (RA) is a promising approach for the efficient management of network resources. However, DL models typically have a limitation that they do not capture the uncertainty due to the arrival of new unseen samples with a distribution different than the data distribution available at DL model-training time, leading to wrong resource usage predictions. To address this, we propose a confidence aware DL solution for the robust and reliable predictions of wireless channel utilization (CU) in shared spectrum bands. We utilize an encoder-decoder based Bayesian DL model to generate prediction intervals which capture the uncertainties in wireless CU. We use the CU predictions to design a novel metric score which in turn is utilized to make an adaptive RA algorithm. We show that a DL model capturing uncertainty in CU can achieve higher data rates for a wireless network. Both DL driven predictions and RA models are tested using synthetic data as well as real CU data collected in the University of Oulu. Using analytical and simulations results, we also study the stability of the proposed RA algorithm and show that it converges to a Nash equilibrium (NE). Our results reveal that the proposed algorithm converges to an NE under 2N iterations where N is the number of network access points.

Proactive and intelligent management of network resource utilization (RU) using deep learning (DL) can significantly improve the efficiency and performance of the next generation of wireless networks. However, variations in wireless RU are often affected by uncertain events and change points due to the deviations of real data distribution from that of the original training data. Such deviations which are known as dataset drifts can subsequently lead to a shift in the corresponding decision boundary degrading the DL model prediction performance. To address these challenges, we present hardware-accelerated real-time radio frequency (RF) analytics and drift-awareness modules for robust DL predictions. We have prototyped the proposed design on a Zynq-7000 System-on-Chip which contains an FPGA and an embedded ARM processor. We have used Xilinx Vivado design suite for synthesis and analysis of the HDL design for the proposed solution. To detect dataset drifts, the proposed solution adopts a distance-based technique on FPGA to quantify in real-time the change between the prediction distribution obtained from DL predictions and data distribution of input streaming samples. Using various performance metrics, we have extensively evaluated the performance of the proposed solution and shown that it can significantly improve the DL model robustness in the presence of dataset drifts.

Hardware accelerated modules that can continuously measure/analyze resource (frequency channels, power, etc.) utilization in real-time can help in achieving efficient network control, and configuration in cloud managed wireless networks. As utilization of various network resources over time often exhibits broad and skewed distribution, estimating quantiles of metrics to characterize their distribution is more useful than typical approaches that tend to focus on measuring average values only. In this paper, we describe the development of a real-time quantile-based resource utilization estimator module for wireless networks. The intensive processing tasks run on the FPGA, while the command and control runs on an embedded ARM processor. The module is implemented by using high level synthesis (HLS) on a Xilinx's Zynq-7000 series all programmable system on chip board. We test the performance of the implemented quantile estimator module, and as an example, we focus on forecasting congestion with real frequency channel utilization data. We compare the results from the implemented module against the results from a theoretical quantile estimator. We show that with high accuracy and in real time, the implemented module can perform quantile estimation and can be utilized to perform forecasting of congestion in wireless frequency spectrum utilization.INDEX TERMS 5G, channel resource allocation, wireless channel congestion, forecasting, FPGA, generalized extreme value theory, high level synthesis, URLLC, Xilinx, ZedBoard.