A wide range of new ultra reliable low latency communication (URLLC) applications in next generation (NG) wireless systems demand real-time radio frequency (RF) data analytics of channel utilization (CU) that can help in making proactive resource allocation decisions. However, such real-time RF data analytics require processing of tens of millions of in-phase and quadrature (IQ) samples per second and sending huge quantities of samples to a resource allocating entity is not practical. We present design and implementation of an RF data analytics system which utilizes field-programmable gate arrays (FPGAs) at the network edge to process real-time streaming IQ samples from RF transceiver. FPGAs process millions of samples per second and output low-overhead descriptive statistics of wireless CU, such as mean CU values, maximum CU values, and entire histograms to obtain probability distribution of CU values, to a resource controller server where a quantile estimation based technique is used to detect congestion in CU in real-time. The FPGA-based modules are implemented on Xilinx’s Zynq-7000 devices mounted with RF transceivers. We evaluate the performance of the implemented analytics system using extensive measurements, testing, and statistical analyses that are performed in both laboratory and over-the-air environments.
Khan Zaheer, Lehtomäki Janne J.
A1 Journal article – refereed
Place of publication:
25 December 2019
Z. Khan and J. J. Lehtomäki, “FPGA-Assisted Real-Time RF Wireless Data Analytics System: Design, Implementation, and Statistical Analyses,” in IEEE Access, vol. 8, pp. 4383-4396, 2020, doi: 10.1109/ACCESS.2019.2962200
Read the publication here: