ML-Based Secondary Cell Selection for Adaptive Carrier Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing carrier aggregation systems fail to optimally distribute user equipment among available cells based on load and radio quality, leading to inefficient use of spectrum resources and suboptimal user experience.
Innovation Solution
A network node device employs machine learning models, specifically reinforcement learning and recurrent neural networks, to predict and dynamically set secondary cell weight parameters for user devices, leveraging input information such as downlink throughput and spectral efficiency to optimize carrier aggregation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If all UEs are assigned the same set of primary and secondary cells, then cell configuration is simplified, but cells quickly become fully loaded and spectrum resources are wasted
Solution Approach 1:
The patent applies local quality by assigning different sets of secondary cells to different UEs based on their individual characteristics. The network determines a specific set of secondary cells for each UE considering factors like UE capabilities, service requirements, and cell load conditions, thereby optimizing spectrum resource utilization while maintaining manageable configuration complexity through automated selection.
2Reliability
If the network manually distributes UEs among available cells, then load balancing is improved, but distribution accuracy and responsiveness deteriorate
Solution Approach 1:
The patent implements self-service by enabling the network to automatically determine optimal secondary cell sets for each UE based on predefined criteria and real-time conditions. The automated selection process considers UE capabilities, service requirements, and current cell load without requiring manual intervention, thereby improving load balancing accuracy while reducing control complexity through algorithmic decision-making.
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the set of secondary cells assigned to each UE based on changing network conditions. The network monitors factors like cell load, radio quality, and UE capabilities, and modifies cell assignments accordingly to maintain optimal load balancing and resource utilization.
3Quantity of substance
If more cells are added to the network, then capacity is increased, but the ability to aggregate cells for individual UEs deteriorates
Solution Approach 1:
The patent applies segmentation by dividing the available cell resources into different sets that can be assigned to different UEs. The network segments the secondary cells into multiple groups and selectively assigns appropriate segments to each UE based on their capabilities and the current network state, thereby maintaining aggregation flexibility even as the total number of cells increases.
Solution Approach 2:
The patent implements dynamics by making cell assignments flexible and adaptive rather than fixed. The network dynamically determines which secondary cells to assign to each UE based on real-time conditions including UE capabilities, service requirements, and cell load, allowing the system to adapt to increasing network capacity while maintaining individual UE aggregation flexibility.
Data Source
AI summary
Devices, methods and computer programs for machine learning (ML)-based secondary cell selection for carrier aggregation (CA) are disclosed. At least some example embodiments may allow dynamically predicting a secondary cell weight parameter which may influence a network node decision in selecting secondary cells for user devices.