AI/ML Model for Random Access Procedure Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current random access procedures in wireless communication networks, such as those in LTE and NR, face challenges in optimizing preamble transmission power and beam selection, leading to increased latency and potential collisions, which can jeopardize the quality of service, especially in Ultra-Reliable Low-Latency Communication scenarios.
Innovation Solution
A computer-implemented method using an AI/ML model to predict the success of a random access procedure based on input parameters, allowing for adaptation of RA parameters such as initial power level, beam selection, and power ramping, to optimize the random access configuration and avoid unnecessary retransmissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional random access procedures are used with fixed power levels and beam selection, then the system maintains simplicity in configuration, but latency increases and collision probability rises
Solution Approach 1:
The system performs preliminary actions by predicting random access outcomes and determining optimal power levels and beam selections before the actual random access procedure executes. This advance preparation reduces latency by eliminating trial-and-error retries while the model cache stores pre-computed recommendations for rapid deployment.
Solution Approach 2:
An AI/ML model acts as an intermediary between the traditional random access configuration and the actual access procedure. The model receives input parameters, predicts success probability, and outputs optimized recommendations for power levels and beam selections, mediating between fixed configurations and dynamic optimization needs.
2Reliability
If multiple preamble transmissions are performed to ensure successful access, then reliability improves, but latency increases due to retransmissions
Solution Approach 1:
The system performs preliminary prediction and optimization of transmission parameters before the random access procedure. By determining optimal power levels and beam selections in advance using the AI model, the system achieves high reliability on the first attempt, eliminating the need for multiple retransmissions and reducing overall access duration.
Solution Approach 2:
The patent replaces the mechanical retry mechanism (multiple preamble transmissions) with an intelligent prediction system. Instead of blindly retransmitting and hoping for success, the AI/ML model substitutes the trial-and-error mechanical approach with data-driven optimization, achieving reliable first-attempt success.
3Reliability
If higher transmission power is used to ensure successful preamble detection, then access reliability improves, but energy consumption increases
Solution Approach 1:
The AI model dynamically changes the transmission power parameter based on predicted success probability and channel conditions. Instead of using fixed high power for all cases, the system adjusts power levels optimally for each specific scenario, ensuring reliable detection while minimizing energy consumption by avoiding unnecessarily high power transmissions.
4Reliability
If beam selection is optimized for each random access attempt, then access success probability improves, but computational complexity increases
Solution Approach 1:
The system performs preliminary beam selection optimization using the AI model before the random access procedure. The model predicts which beams are most likely to succeed based on historical data and current conditions, preparing recommendations in advance. This eliminates the need for complex real-time beam searching during the actual access attempt.
Solution Approach 2:
The system uses a model cache that stores pre-computed beam selection recommendations and input parameters. Instead of performing complex computations for every random access attempt, the system copies and applies pre-validated beam selections from the cache that match current conditions, significantly reducing computational complexity while maintaining accuracy.
Data Source
AI summary
Systems and methods of the present disclosure are directed to a computer implemented method performed by a Wireless Communication Device (WCD). The method includes receiving information from a network node. The information includes an Artificial Intelligence (AI)/Machine Learning (ML) model that outputs a set of output parameters that represent whether a Random Access (RA) procedure to be performed by the WCD will be successful based on a set of input parameters. Or the information includes information about or that characterizes the AI/ML model that enables the WCD to build the AI/ML model that outputs the set of output parameters that represent whether the RA procedure to be performed by the WCD will be successful based on the set of input parameters. The method includes adapting one or more RA parameters for the RA procedure based on the AI/ML model.