Abstract
A user equipment (UE) in a wireless communication network uses a deep learning network model to infer whether a Fifth Generation (5G) New Radio (NR) random-access channel (RACH) failure is likely to occur at a given network location given current Fourth Generation (4G) or 5G measurable key performance indicators (KPIs) at its modem. The KPIs are recorded by the UE as training features during daily usage when NR RACH failure or NR RACH success is detected. The deep learning model is trained based on the recorded features and labels using, for example, supervised learning. The UE implements the trained deep learning network model to infer whether an NR RACH failure is likely to occur based on the features, such as the measurable 4G/5G KPIs, at the current location so that the UE can avoid triggering an NR RACH procedure.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Kuo, Gordon, "Applying Deep Learning in User Equipment Measurable KPIs to Avoid Unnecessary NR RACH Procedures", Technical Disclosure Commons, (July 19, 2021)
https://www.tdcommons.org/dpubs_series/4460