Machine learning solutions for rlc sdu construction in non-ip data delivery transmission over non-terrestrial networks

A method for communication in a non-terrestrial communication system, comprising:

• sending, by an application layer, metadata associated with one data transmission unit of a plurality of data transmission units, the metadata indicating that the one data transmission unit comprises a last data transmission unit associated with a particular application payload;
• receiving, by a Radio Link Control (RLC) layer, the metadata associated with the one data transmission unit;
• applying a Machine Learning (ML) model, using historical values of model parameters of the ML model, to determine a likelihood of data loss;
• and
• setting, by the RLC layer, a poll bit in the last data transmission unit when the likelihood of data loss exceeds a threshold.

Non-transitory computer-readable storage media having instructions encoded thereon, the instructions configured to cause processing circuitry to:

• send, by an application layer, metadata associated with one data transmission unit of a plurality of data transmission units, the metadata indicating that the one data transmission unit comprises a last data transmission unit associated with a particular application payload;
• receive, by a Radio Link Control (RLC) layer, the metadata associated with the one data transmission unit;
• apply a Machine Learning (ML) model, using historical values of model parameters of the ML model, to determine a likelihood of data loss;
• and
• set, by the RLC layer, a poll bit in the last data transmission unit when the likelihood of data loss exceeds a threshold.