A domestic research team has developed a method for analyzing and predicting frequency usage based on machine learning, which is expected to become an international standard.

The Electronics and Telecommunications Research Institute (ETRI) announced on the 30th that the 'Machine Learning-Based Spectrum Availability Prediction Method' developed by ETRI was adopted as a draft working document for a new report at the 'International Telecommunication Union Radiocommunication Sector Spectrum Management Study Group (ITU-R SG1) Meeting' held for two weeks from the 25th of last month.

'Spectrum availability' is an indicator of the extent to which radio communication services can be used in a specific frequency band.

Accurate analysis of spectrum availability is essential to understanding frequency usage and saturation.

This allows for efficient management of radio resources, such as reclaiming and reallocating unused frequencies.

Until now, spectrum availability has been analyzed through simplified mathematical models, making it difficult to analyze complex radio environments.

In addition, there is no standard document that organizes analysis methods according to various frequency types and usage patterns, so there is no guideline to refer to. It was a situation.

ETRI has systematically organized methods for analyzing spectrum availability by frequency type and usage pattern.

Furthermore, we proposed a methodology for evaluating and predicting spectrum availability using machine learning, reflecting the complex radio environment centered on the most frequently used mobile communication frequencies.

The research team also evaluated and predicted the actual availability of LTE frequency spectrum in Korea using this method.

Based on actual traffic data, the supply-demand balance of LTE frequencies is evaluated and future usage rates are predicted.

This analysis is significant because it is the first of its kind in the world.

Based on this data and methodology, each country will be able to analyze frequencies and efficiently manage radio resources, significantly enhancing the status of ETRI and the Republic of Korea's international standardization activities.

The research team had already proposed a research project related to this working document at the 2019 ITU-R SG1 meeting and received approval as a new SG1 research project through the UN member state circulation process.

This achievement is a culmination of ETRI's leading role throughout the standardization process.

ETRI Radio Resources Research Lab Director Park Seung-geun, who led the standardization effort, said, “Based on the data and machine learning-based spectrum availability assessment and prediction method developed this time, we will continue to strive to secure leadership in next-generation mobile communication frequency research.”

Going forward, the research team plans to actively participate in international standardization work related to radio waves and information and communications, while continuing to research analysis methodologies suited to Korea's radio environment to support the establishment of effective national radio resource management policies.