RAN Parameter Tuning Using Edge Device Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for optimizing radio access networks (RANs) are inefficient and costly due to repetitive testing and require expertise, making it difficult to optimize performance.
Innovation Solution
Implementing a computing device that uses a trained classifier model to classify edge devices and adjust operational parameters for radio networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive testing approaches are used to optimize RAN performance, then optimization accuracy is improved, but time consumption and cost increase significantly
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the RAN that replicates the physical network's behavior and characteristics. This digital twin can be tested and optimized without affecting the actual network, allowing comprehensive optimization analysis to be performed on the copy while the physical network remains operational and unaffected by testing disruptions
Solution Approach 2:
The system performs preliminary optimization actions by first testing and validating parameter adjustments in the digital twin environment before applying them to the physical RAN. This preliminary action in the virtual model ensures that optimization accuracy is achieved through thorough testing while preventing time loss from failed field experiments
2Measurement precision
If comprehensive testing approaches are used to optimize RAN performance, then optimization accuracy is improved, but cost increases due to specialized equipment and personnel requirements
Solution Approach 1:
By creating a virtual digital twin of the RAN, the patent eliminates the need for expensive specialized testing equipment and highly paid expert personnel that would otherwise be required for comprehensive physical network testing. The digital twin can be created and manipulated using standard computing resources, dramatically reducing the cost of achieving high optimization accuracy
Solution Approach 2:
The patent replaces the mechanical and physical testing system (requiring specialized equipment and manual expert operation) with a computational simulation system. The digital twin uses software-based models and algorithms to replicate network behavior, substituting expensive physical testing infrastructure with more affordable computational resources
3Productivity
If traditional RAN optimization methods are used, then performance improvements can be achieved, but the process becomes complex and requires expert knowledge
Solution Approach 1:
The digital twin system enables self-service optimization where the virtual model automatically tests, evaluates, and determines optimal parameter configurations without requiring external expert intervention. The system serves itself by using its own simulated environment to identify improvements, reducing the complexity burden on human operators while maintaining high productivity
Solution Approach 2:
The system implements continuous feedback loops where the digital twin simulates parameter changes, automatically measures performance outcomes, and uses this feedback to guide further optimization iterations. This automated feedback mechanism simplifies the optimization process by eliminating the need for experts to manually analyze complex interactions and determine next steps
4Measurement precision
If repetitive testing is performed to optimize RAN, then optimization thoroughness is improved, but efficiency deteriorates
Solution Approach 1:
By performing all repetitive testing iterations in the digital twin copy rather than the physical network, the patent achieves thorough optimization validation without the efficiency penalties of repeated physical deployments. Multiple testing iterations in the virtual environment take minimal time compared to equivalent physical testing, maintaining both thoroughness and efficiency
Solution Approach 2:
The digital twin allows continuous optimization testing and validation to occur without interruption to normal RAN operations. While the physical network continues its useful action of serving customers, the digital twin simultaneously performs exhaustive repetitive testing, eliminating the need to stop network operations for testing purposes
Data Source
AI summary
A computing device, method, and computer readable media that provide radio access network improvements or optimization. A data port of a computing device receives communication data wirelessly communicated between wireless devices and a node in a telecommunications infrastructure, and receives a batch of operational parameters for the node. A processor in communication with the data port provides the communication data to a trained model configured to classify devices. The processor further obtains, from the trained model when the processor applies the communication data to the trained model, a classification for each of the wireless devices including a device type and a mobility state for each of the wireless devices. The processor further generates, based on the classifications, an adjustment for the batch of operational parameters.