A European cellular company uses machine learning to predict radio link failures five days in advance to maintain a reliable, high-speed 5G network. Operators are required to minimize service disruption, maintain reliability, and comply with industry standards such as ultra-reliable low latency communication (URLLC).
Lack of visibility into radio link failure caused by weather conditions such as clouds, rain, and snow can pose major threats to reliability and latency of a 5G network, resulting in poor customer experience.
RapidCanvas worked with the company’s teams to create a predictive model.
Use of historical data, weather data, and tower configuration data
Create an ML model to predict RLF events five days into the future
Flexible model to update the configuration for each tower and receive predictions even in a live production setting.
The company is able to make hardware and software configuration changes, as needed
Through this process, the company is able to provide a reliable, high-speed 5G network to its customers.
A Latin American renewable energy company optimized its maintenance schedules and reduced its risks and costs, extending the useful life of each turbine
A Brazilian company that builds solar farms identified the most optimum land parcels for new farm development to be evaluated quickly and efficiently.
A European telecommunications company leveraged ML to predict RLF caused by weather conditions and maintain consistent, reliable 5G service.