Intelligent Policy Control Engine for 5G Dynamic RAN Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 5G network control systems rely on pre-defined rules, lacking the ability to dynamically adjust based on real-time network data and AI/ML insights, which limits their capacity to optimize network performance and provide differentiated service delivery.
Innovation Solution
An intelligent dynamic RAN policy engine that subscribes to real-time network and UE state databases, dynamically composing and triggering RAN control functions and microservices based on AI/ML results to optimize network performance and service delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If pre-defined rules are used for network control, then system complexity is reduced and ease of operation is improved, but adaptability and network performance optimization are limited
Solution Approach 1:
The patent implements a dynamic policy control engine that transitions from static pre-defined rules to real-time dynamic policies. The system continuously receives network state data, processes it through machine learning models, and generates adaptive policies that adjust to changing network conditions, thereby resolving the contradiction between ease of operation and adaptability.
Solution Approach 2:
The system changes the parameter of policy generation from fixed pre-defined rules to dynamically generated policies based on real-time data. By incorporating machine learning models that process network state data and generate optimized policies, the system transforms the control mechanism from static to adaptive, improving both adaptability and performance while maintaining operational simplicity.
2Productivity
If real-time dynamic policy control with AI/ML is implemented, then network performance optimization and service delivery are improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent segments the policy control function into modular components: data collection modules, machine learning model modules, policy generation modules, and execution modules. This segmentation allows the complex AI/ML-based control system to be broken down into manageable, independently deployable units, reducing overall system complexity while maintaining high network performance.
Solution Approach 2:
The patent introduces an intermediary policy control engine that sits between the raw network data and the control actions. This engine processes complex AI/ML computations and translates them into simplified policy decisions, acting as a mediator that handles the computational complexity while presenting a simpler interface for network control and management.
3Productivity
If real-time data processing and AI-driven decision-making are used, then service delivery and user experience are enhanced, but data processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-training machine learning models offline and preparing policy templates in advance. During real-time operation, the system only needs to process current network state data through pre-configured models and select from pre-generated policy options, significantly reducing data processing time while maintaining AI-driven decision-making capabilities and high service delivery quality.
Data Source
AI summary
An intelligent network policy engine can be utilized to apply dynamic policy changes for microservices. For example, based on outlined service provider policies, user equipment state data, and/or network state data, the intelligent network policy engine can determine which microservices to use and/or what order to use the microservices to increase a performance of the network. The intelligent network policy engine can perform conflict resolution based on how network traffic should be treated in certain scenarios.