Terminal AI Function Switching for Low-Overhead Channel Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radio communication technologies lack sufficient studies on life cycle management (LCM) of AI models, leading to inadequate overhead reduction and channel estimation, which hampers communication throughput and quality improvement.
Innovation Solution
A terminal and base station implementation that includes a transmitting section for reporting supported functionalities, a receiving section for indicating activation, deactivation, or switch of functionalities, and a control section for performing these actions based on the indication, utilizing AI technology for efficient LCM.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI-based beam prediction and life cycle management are introduced in radio communication systems, then communication throughput and quality can be improved, but overhead and resource consumption increase due to insufficient LCM studies
Solution Approach 1:
The patent implements dynamic functionality management where the terminal can switch between different AI model functionalities (full AI functionality, partial AI functionality, non-AI functionality) based on network conditions and capabilities. This dynamic adaptation allows the system to optimize communication throughput by enabling AI features when beneficial while reducing overhead by disabling them when unnecessary, directly resolving the technical contradiction between improving productivity and reducing information loss.
Solution Approach 2:
The patent changes the operational parameters of AI models by introducing functionality switching mechanisms. The terminal receives functionality indications from the base station that control whether AI beam prediction, temporal DL beam prediction, and other AI-based features are activated. By changing these operational parameters dynamically, the system can adapt overhead consumption to match actual communication needs, thereby improving throughput while controlling overhead.
2Reliability
If multiple AI model functionalities are activated for beam prediction and channel estimation, then communication quality improves, but device complexity and resource use increase
Solution Approach 1:
The patent segments AI functionalities into distinct, independently controllable components. Instead of treating AI model management as a monolithic complex system, it divides functionality into separable units (spatial domain beam prediction, temporal DL beam prediction, channel estimation) that can be individually activated or deactivated based on network conditions. This segmentation reduces device complexity by allowing selective activation of only necessary functionalities while maintaining communication quality.
Solution Approach 2:
The patent implements feedback mechanisms where the terminal reports supported functionalities to the base station, and the base station responds with functionality indications. This closed-loop feedback system allows the network to control terminal complexity by dynamically adjusting which AI functionalities are activated based on actual network conditions and terminal capabilities, thereby improving communication quality while managing device complexity.
3Measurement precision
If AI-based beam management is implemented without sufficient life cycle management studies, then channel estimation accuracy may improve, but resource consumption increases
Solution Approach 1:
The patent implements periodic functionality reassessment where the terminal and base station periodically evaluate whether AI functionalities should remain activated. Through periodic capability reporting and functionality indication exchanges, the system ensures that channel estimation accuracy is maintained when needed while reducing resource consumption by deactivating AI features when network conditions change or when full AI functionality is no longer beneficial.
Solution Approach 2:
The patent dynamically changes operational parameters of AI models by switching between different functionality modes based on network conditions. When channel estimation accuracy is critical, AI functionalities are activated; when resource conservation is prioritized, functionalities are deactivated or downgraded. This parameter changing approach allows the system to optimize the balance between measurement precision and energy consumption.
Data Source
Figure 1
Figure 2A~2D
Figure 3
AI summary
A terminal according to one aspect of the present disclosure includes a transmitting section that performs reporting of a supported functionality, a receiving section that receives an indication of at least one of activation, deactivation, fallback, and switch of a functionality, and a control section that performs, based on the indication, at least one of the activation, the deactivation, the fallback, and the switch. According to one aspect of the present disclosure, preferable overhead reduction/channel estimation/resource use can be achieved.