ML-Based Radio Access Technology Selection for Network Energy Savings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current multi-radio access technology (RAT) networks face challenges in optimizing energy efficiency while maintaining quality of service, due to the coexistence of different generations of mobile networks and the need for dynamic power allocation.
Innovation Solution
The implementation of a method that uses machine learning to determine the most energy-efficient radio access technology for cellular broadband communications by processing signal strengths and resource allocation metrics, thereby optimizing energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple radio access technologies are used for cellular broadband communications, then service coverage and capability are improved, but energy consumption increases
Solution Approach 1:
The system dynamically changes operational parameters by using machine learning to select different radio access technologies based on real-time conditions. The ML model processes signal strengths and resource allocation metrics to determine the optimal RAT, thereby adapting energy consumption parameters to match current network conditions while maintaining service coverage.
Solution Approach 2:
The patent implements dynamic RAT selection where the system continuously monitors signal strengths and resource allocation across multiple radio access technologies. The machine learning model enables the system to dynamically switch between different RATs (such as LTE and 5G NR) based on changing network conditions, ensuring energy-efficient operation while maintaining adaptability to various service requirements.
2Use of energy by moving object
If machine learning models are used to optimize radio access technology selection, then energy efficiency is improved, but system complexity increases
Solution Approach 1:
The patent introduces a machine learning model as an intermediary component that sits between the raw network parameters (signal strengths, resource allocation) and the RAT selection decision. This ML intermediary processes the complex multi-parameter input and outputs a simplified recommendation, thereby managing system complexity while achieving energy efficiency optimization.
Solution Approach 2:
The machine learning model is trained to autonomously make RAT selection decisions based on processed network parameters. Once trained, the model serves itself by continuously learning from network conditions and making independent optimization decisions, reducing the need for complex manual configuration and external control systems.
Data Source
AI summary
A method can comprise receiving, by a system, a service request from a user equipment. The method can further comprise, based on the service request, determining respective signal strengths of respective radio access technologies of multiple radio access technologies being used for cellular broadband communications. The method can further comprise, identifying a subset of the respective radio access technologies for which a signal strength criterion is satisfied. The method can further comprise processing a subset of the respective signal strengths corresponding to the subset of the respective radio access technologies using a machine learning model to determine a selected radio access technology, wherein the machine learning model is trained to determine the selected radio access technology based on an energy efficiency metric of the system and based on resource allocation of the system. The method can further comprise communicating with the user equipment via the selected radio access technology.