ITU-R SM.2542-0 (06/2024)

TABLE OF CONTENTS
1 Terms, definitions and abbreviations
1.1 Big data
1.2 Artificial intelligence
1.3 Machine learning
1.4 Radio frequency machine learning
1.5 Abbreviations
2 Introduction
3 Distributed spectrum monitoring
3.1 Elements of a distributed spectrum monitoring system
3.1.1 Local/edge processing at monitoring receivers
3.1.2 Data security
3.2 Big data challenges of a distributed spectrum monitoring system
3.2.1 Monitoring data types and impact on network bandwidth
3.2.2 ML algorithms applied to spectrum monitoring
3.2.3 Common types of ML algorithms
3.2.4 Metadata and time synchronization
3.2.5 Sensor data format
3.2.6 Heterogeneity in spectrum monitoring equipment
3.2.7 Local and central databases
4 Big data spectrum monitoring
4.1 Big data spectrum monitoring benefits
4.2 Big data spectrum monitoring solution
4.3 RF collection layer: example big data spectrum monitoring network
4.4 Data storage layer
4.4.1 Collection of big data (definition of collected data)
4.4.2 Data pre-processing
4.4.3 Data analysis and visualization
4.5 Data management layer
5 Realtime data-driven spectrum awareness using RFML
6 Summary
7 References
Annex 1 Solution for data-driven AI and big data spectrum monitoring in Korea (Republic of)
Annex 2 Mobile public transport based big data acquisition for spectrum mapping

There have been many advancements on the application of ML and AI to spectrum monitoring and there is a large volume of technical papers outlining the use, the algorithms, and the limitations of the technology, as well as commercially available software solutions.

This Report applies new trends in data sciences including artificial intelligence and big data technologies to the automation of spectrum monitoring.