ML-Based Carrier Aggregation for Channel-Matched Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing carrier aggregation mechanisms often result in UEs being assigned to carriers that are mismatched to the channel conditions, leading to inefficient data throughput and latency issues.
Innovation Solution
Implementing a machine learning model to dynamically re-evaluate carrier aggregation based on real-time channel conditions, UE capabilities, and location, using parameters like RSRP, RSRQ, SINR, and CQI, to optimize the assignment of primary and secondary component carriers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional carrier aggregation assignment based on UE capabilities and load is used, then device compatibility and network management are simplified, but data throughput efficiency and latency performance deteriorate due to carrier-channel mismatch
Solution Approach 1:
The patent implements dynamic carrier aggregation assignment that adapts to changing channel conditions in real-time. The system continuously monitors channel state information and adjusts carrier assignments dynamically, transitioning from static traditional methods to adaptive dynamic allocation, thereby improving data throughput while managing complexity through automated algorithms
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring channel conditions, UE capabilities, and performance metrics. This feedback loop enables the network to make informed decisions about carrier aggregation assignments, optimizing throughput by matching carriers to actual channel states rather than relying on predetermined static assignments
2Loss of time
If traditional static carrier aggregation assignment is used, then system complexity is reduced, but latency increases due to inability to adapt to changing channel conditions
Solution Approach 1:
The patent implements dynamic carrier aggregation assignment that adapts to changing channel conditions in real-time. The system continuously monitors channel state information and adjusts carrier assignments dynamically, transitioning from static traditional methods to adaptive dynamic allocation, thereby improving data throughput while managing complexity through automated algorithms
Solution Approach 2:
The system performs preliminary evaluation of multiple candidate carriers before making assignments. By pre-assessing channel conditions and UE capabilities, the system can make optimal carrier aggregation decisions in advance, reducing latency caused by reactive adjustments and enabling proactive optimization of resource allocation
Data Source
AI summary
Methods and systems for carrier aggregation based on channel conditions using a machine learning model are disclosed. According to an implementation, a computing system may receive, from a user equipment (UE), a request to increase a data transmission rate. The computing system may be associated with an access point of a wireless network. The computing device may request the UE to report a measured first parameter associated with a carrier assigned to the UE. Further, the computing device may obtain, from a network device, a second parameter associated with the carrier, the second parameter being measured by the network device. Based at least in part on the first parameter and the second parameter, and using a machine learning model, the computing device may determine a new carrier. The computing device may further assign, to the UE, the new carrier in response to the request to increase the data transmission rate.