Predictive Radio Resource Allocation Across 5G Cells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication networks face challenges in efficiently allocating resources to idle user equipment (UE) transitioning to active mode, leading to attach failures and delays due to misallocation and lack of beam-steering, especially with mmWave frequencies experiencing higher path loss and interference.
Innovation Solution
A system that predicts the transition of idle UE to active mode by collecting signal propagation information and preemptively allocating radio resources, including creating and adjusting energy beams to cover idle UEs, using a multi-connectivity framework that supports NR and LTE, and implementing load balancing across base stations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network resources are allocated reactively after idle UE transitions to active mode, then resource allocation simplicity is maintained, but attach failures and delays increase due to misallocation
Solution Approach 1:
The system performs preliminary actions by predicting which idle UEs are likely to transition to active mode and preemptively allocating radio resources before the actual transition occurs. The network collects signal propagation information and uses machine learning models to predict transition probability, then proactively establishes connections and allocates beams to reduce attach failures and delays.
2Reliability
If beam-steering is implemented for idle UE, then connection reliability improves, but network overhead and complexity increase
Solution Approach 1:
The system performs preliminary beam steering actions by predicting idle UE transitions and pre-positioning beams in the directions where idle UEs are located. The network calculates predicted locations based on signal propagation data and machine learning models, then proactively steers beams to those locations before actual connections are needed, reducing the overhead of reactive beam adjustment.
Solution Approach 2:
The system applies local quality by directing beam-steering and resource allocation specifically toward areas where idle UEs are predicted to transition, rather than uniformly managing all network resources. The network identifies local hotspots with high transition probability and concentrates beam-steering operations in those specific geographic areas, reducing overall network complexity.
3Speed
If mmWave frequencies are used for high-speed connections, then data rate improves, but path loss and interference increase
Solution Approach 1:
The system performs preliminary actions by predicting which idle UEs will need high-speed mmWave connections and preemptively establishing mmWave beams and allocating resources before transitions occur. This allows the network to optimize mmWave beam directions and power levels in advance, compensating for the higher path loss characteristic of mmWave frequencies by ensuring optimal transmission paths are already in place.
4Measurement precision
If network collects and processes signal propagation information for prediction, then resource allocation accuracy improves, but processing overhead and time increase
Solution Approach 1:
The system performs preliminary data collection and processing by continuously gathering signal propagation information during idle UE periods and pre-processing it through machine learning models to generate transition predictions. The network pre-calculates resource allocation decisions based on this predicted information, so when actual transitions occur, the processing is already complete or minimal, reducing real-time processing time overhead.
Data Source
AI summary
The technologies described herein are generally directed to providing radio resources to facilitate a predicted transition to active mode by idle user equipment in a fifth generation (5G) network or other next generation networks. An example method can include predicting that a user equipment of a group of user equipment in an idle mode will transition to an active mode during a time duration. The method can further include, identifying base station equipment that are able to provide coverage to the group of user equipment during the time duration. Further, the method can include, based on predicting the user equipment will transition to active mode, prioritizing allocation among the base station equipment, of resources to provide coverage to facilitate an active mode connection by the user equipment to the base station equipment.