AI Load Prediction Exchange for Consistent Network Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inconsistent AI computing information across network elements in wireless communication systems leads to sub-optimal load balancing decisions, impacting Quality of Service and user experience, and causing inefficiencies in resource allocation and energy consumption.
Innovation Solution
Exchange of AI computing information, including input and configuration details of machine learning models, between network elements to ensure consistent and accurate load prediction, enabling adaptive model updates and optimizing load balancing across the system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AI computing information is exchanged between network elements, then load prediction accuracy is improved, but network complexity increases
Solution Approach 1:
The patent creates a universal message structure that can carry multiple types of AI computing information (model configuration, input data, training parameters) across different network elements. This standardized interface enables multiple functions (load prediction, model updates, information exchange) through a single mechanism, improving accuracy without proportionally increasing complexity
Solution Approach 2:
The AI computing information is segmented into distinct components: model configuration information, input data, and training parameters. This segmentation allows selective exchange of only necessary information between network elements, reducing the overall complexity burden while maintaining prediction accuracy through targeted data sharing
2Productivity
If machine learning models are updated across network elements, then load balancing performance is improved, but information consistency becomes more difficult to maintain
Solution Approach 1:
The patent implements a feedback mechanism where network elements exchange AI computing information including model configuration and training parameters. This feedback loop enables synchronized updates across the network, ensuring that all elements maintain consistent information while adapting to changing load conditions, thus improving performance without sacrificing consistency
Solution Approach 2:
The system performs preliminary actions by pre-configuring and distributing model information to network elements before actual load balancing operations. This advance preparation ensures that when load balancing decisions are made, all network elements already have the necessary consistent information, preventing consistency issues during dynamic operations
Data Source
AI summary
This disclosure describes methods and systems for exchanging AI computing information for load prediction model between network elements of a wireless communication network. The methods include: sending, by a first network element of a wireless communication network, a first message for load prediction to a second network element of the wireless communication network, wherein the first message comprises at least one of an input to a machine learning model for load prediction of the first network element or model configuration information of the machine learning model.