Dataset for FFT of IQ samples: LTE, NR, and Overlap
Dynamic Spectrum Sharing (DSS) is an enabler for a seamless transition from 4G Long TermEvolution (LTE) to 5G New Radio (NR) by utilizing existing LTE bands without static spectrum re-farming. In this paper, we propose a cross-band DSS scheme that utilizes the Multimedia BroadcastMulticast Service over a Single Frequency Network (MBSFN) feature of an LTE network and theMulticast Broadcast Service (MBS) feature of an NR network. The proposed DSS scheme utilizes LTEand NR resource controllers to assign muted MBSFN subframes on the LTE band and muted MBSsubframes on the NR band based on traffic needs. In contrast to the state-of-the-art, the proposed DSSscheme does not require a coordination signaling channel between the LTE and NR networks. Instead, amachine learning-based Technology Recognition and Traffic Characterization (TRTC) system is used toidentify and characterize traffic patterns. The LTE and NR resource controllers use the TRTC to sensethe muted subframes and offload traffic accordingly. On average, the proposed DSS, as compared tostatic band configuration, improves the LTE throughput, NR throughput, LTE band spectrum utilizationefficiency, and NR band spectrum utilization efficiency by 13.5%, 8.3%, 11.8%, and 20.7%, respectively.
The file "dataset.mat" contains the data and lables. In the matfile there are vectors "data" and "label".
"data" contains a vector of FFT of the IQ samples from LTE, NR, and Overlap and the vector "label" is used to store the corrosponding labels.
The file "data_snr_label.mat" stores the channel SNR corresponding to the stored IQ samples.
The source code used to train the model based on this dataset is available here https://github.com/girmaymerkebu/Technology-Recognition-for-4G-LTE-and-5...