Wireless Device ML Reporting for Signaling Overhead Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless network architectures face challenges in fully utilizing machine learning potential due to variable data transfer costs, particularly in over-the-air signaling, which increases signaling overhead and affects intelligence distribution between devices and networks.
Innovation Solution
Implementing intelligent wireless communication devices capable of predicting and reporting values using machine learning models, allowing for optimized data transfer and reduced signaling by activating reporting only when necessary, based on device capabilities and network requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If device reporting is extended to include machine learning predicted values and additional information types, then network intelligence is improved, but signaling overhead increases
Solution Approach 1:
The patent extracts only the most relevant predicted values and device information needed for network optimization, rather than transmitting all available device data. The machine learning model at the device selectively identifies and reports only significant measurements and predictions, reducing signaling overhead while maintaining network intelligence.
Solution Approach 2:
The patent changes the parameter being reported from raw measurements to machine learning-processed predicted values. This transformation compresses multiple raw measurements into fewer, more meaningful predicted parameters, reducing signaling overhead while improving network intelligence through actionable insights.
2Quantity of substance
If machine learning models are deployed at the device, then data transfer costs are reduced, but device complexity increases
Solution Approach 1:
The patent implements partial machine learning functionality at the device, where only specific prediction tasks are performed locally rather than full ML pipelines. This selective deployment reduces data transfer costs for critical measurements while keeping device complexity manageable through focused, task-specific models.
Solution Approach 2:
The patent uses simplified copies or surrogate models at the device that approximate complex network-side machine learning functionality. These lighter-weight models perform essential predictions locally, reducing data transfer requirements while maintaining acceptable accuracy without requiring full device complexity.
Data Source
AI summary
Systems and methods for activating intelligent wireless communication device reporting in a wireless network are disclosed. Embodiments of a method performed by a wireless communication device for machine-learned optimization of wireless networks is proposed. In one embodiment, the method includes sending, to a network node, information that indicates one or more capabilities of the wireless communication device for reporting of predicted values that are predicted by the wireless communication device using one or more machine learning capabilities of the wireless communication device. The method further includes receiving, from the network node, a request. The request includes (a) a request to start reporting predicted values, (b) a request to start training a machine learning model for generating predicted values, or (c) both (a) and (b). The method further includes performing one or more actions in response to receiving the request.