AI Network Resource Selection for Public Safety Service Availability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile communication networks face challenges in optimizing resource selection for user equipment, particularly in public safety networks, due to the lack of user knowledge about application behavior and network characteristics, leading to suboptimal performance and availability.
Innovation Solution
The implementation of artificial intelligence (AI) and machine learning (ML) to assist in selecting frequency bands, infrastructure core networks, and service core networks based on user equipment capabilities and service requirements, ensuring optimal resource allocation and high availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual network configuration is used, then network flexibility is maintained, but service availability and performance optimization are insufficient
Solution Approach 1:
The system enables autonomous network resource selection by having the network automatically choose frequency bands, infrastructure core networks, and service core networks based on AI/ML analysis of user equipment capabilities and service requirements, eliminating manual configuration while improving service availability
Solution Approach 2:
The system continuously monitors network performance and uses this feedback to train AI/ML models that optimize future network resource selections, creating a closed-loop system that improves service availability through data-driven decision-making
2Productivity
If AI/ML-based automated selection is implemented, then service availability and performance are optimized, but system complexity increases
Solution Approach 1:
The AI/ML system performs multiple functions including frequency band selection, infrastructure core network selection, and service core network selection using a unified approach, improving resource allocation efficiency across the entire network without requiring separate complex systems for each function
Solution Approach 2:
The system pre-trains AI/ML models with network characteristics and user equipment capabilities before actual resource selection is needed, enabling fast and efficient automated decisions during network operation without requiring complex real-time computation
3Reliability
If multiple network resources are evaluated, then optimal resource allocation is achieved, but selection time increases
Solution Approach 1:
The system pre-processes and stores network resource information, user equipment capabilities, and service requirements in structured formats before selection is needed, enabling rapid AI/ML-based decisions without time-consuming real-time analysis
Solution Approach 2:
The system transforms complex network selection problems into optimized parameter evaluations by changing the representation of network resources and user requirements into formats that AI/ML models can process efficiently, achieving optimal selection without excessive computation time
Data Source
AI summary
Aspects of the subject disclosure may include, for example, selecting a frequency band for user equipment in a mobile network based on a service to be accessed by the user equipment, selecting an infrastructure core network from a plurality of available infrastructure core networks, selecting a service core network from among a plurality of available service core networks. Artificial intelligence or machine learning may assist in all selections. Other embodiments are disclosed.