Radio Base Station Power Modes for Essential UE Connectivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The power consumption of gNodeB radio in Private 5G networks varies significantly due to fluctuating session counts throughout the day, leading to inefficiencies and increased energy costs, as some base stations remain active even when not needed.
Innovation Solution
Implement a low power operating mode for radio base stations based on connectivity criteria, using machine learning models to classify devices as essential or non-essential, and dynamically adjust power modes to conserve energy by powering down or reducing power to stations with no essential connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radio base stations remain active to ensure connectivity for all devices, then connectivity reliability is maintained, but power consumption increases
Solution Approach 1:
The patent applies local quality by differentiating between essential and non-essential devices through machine learning classification. Different radio base stations are placed in different power modes (full power, reduced power, or sleep mode) based on the specific connectivity needs of devices in their coverage areas, rather than applying a uniform power management policy across the entire network.
Solution Approach 2:
The system dynamically adjusts the power mode of radio base stations based on real-time analysis of device connectivity patterns. The machine learning model continuously evaluates whether devices are essential or non-essential and automatically transitions base stations between operational states, making the power management adaptive rather than static.
2Use of energy by moving object
If radio base stations are powered down to reduce energy costs, then power consumption decreases, but connectivity for essential devices may be compromised
Solution Approach 1:
The system uses machine learning models that analyze device behavior patterns and connectivity requirements to provide feedback on which devices are essential. This feedback loop enables the network to make informed decisions about base station power states, ensuring that essential devices maintain connectivity while non-essential devices can tolerate disconnection during energy-saving modes.
Solution Approach 2:
The machine learning model autonomously determines which devices are essential and which base stations should be powered down or placed in reduced power mode, without requiring manual intervention. The system self-manages the trade-off between energy savings and connectivity requirements by automatically classifying devices and adjusting network configuration.
3Measurement precision
If machine learning models are used to classify devices as essential or non-essential, then power management precision improves, but system complexity increases
Solution Approach 1:
The patent replaces manual or rule-based device classification with machine learning models that automatically analyze device behavior patterns. This substitution enables more precise identification of essential versus non-essential devices, as the ML models can detect complex usage patterns that would be difficult to define with simple rules, despite the increased computational complexity.
Data Source
AI summary
A method, computer system, and computer program product are provided for triggering a low power operating mode for a radio access network. Connectivity criteria are obtained for each of a plurality of user equipment (UEs) connected to a radio access network comprising a plurality of radio base stations. It is determined that at least one radio base station of the plurality of radio base stations can be placed in a low power operating mode based, at least in part, on the connectivity criteria of one or more user equipment connected to the at least one radio base station. The at least one radio base station is caused to enter into the low power operating mode.