Wireless Device Grouping via Machine Learning for Network Resource Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for improving network properties in communications networks have low utilization of available resources, missing opportunities for better resource management and user behavior analysis.
Innovation Solution
A method and system that utilize unsupervised and supervised machine learning to group wireless devices in a communications network, acquiring user network data and cell network data to optimize resource allocation and predict user behavior based on radio characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional clustering techniques are used for resource management, then some network properties can be improved, but the utilization of available resources remains low and many network properties are missed
Solution Approach 1:
The patent segments wireless devices into multiple groups based on their radio characteristics and behavior patterns. By dividing the device population into distinct segments (groups), the system can apply targeted resource management strategies to each segment, improving overall resource utilization while maintaining network performance. This segmentation enables the system to identify and serve different user needs more effectively.
Solution Approach 2:
The patent introduces a new dimension of analysis by grouping devices based on multiple radio characteristics simultaneously (signal strength, data rate, handover behavior, etc.) rather than using single-parameter clustering. This multi-dimensional approach reveals additional patterns and network properties that were previously overlooked, enabling better resource allocation and improving both performance and utilization.
2Productivity
If more machine learning models are implemented for device grouping, then resource management improves, but system complexity increases
Solution Approach 1:
The patent combines unsupervised learning (for initial device grouping based on radio characteristics) with supervised learning (for predicting user behavior and optimizing resources) into a unified system. By merging these approaches, the system leverages the strengths of both methodologies while avoiding the need for separate complex systems, achieving improved resource management with manageable complexity.
Solution Approach 2:
The system performs preliminary unsupervised learning to create initial device groups before applying supervised learning for optimization. This preliminary action establishes a foundation that simplifies subsequent supervised learning tasks, as the data is already organized into meaningful groups. This staged approach reduces the complexity of implementing full supervised learning from scratch.
Data Source
AI summary
There is provided mechanisms for grouping wireless devices of a cell of a communications network. A method is performed by a system in the communications network. The method comprises acquiring user network data for wireless devices in a cell of the communications network and cell network data for the cell. The method comprises determining groups for the wireless devices and assigning each one of the wireless devices to one of the groups using unsupervised machine learning with the user network data and the cell network data as input. The method comprises assigning a wireless device entering the cell to one of the groups using supervised machine learning with user network data of said wireless device and the cell network data as input.