RAN Power Optimization via ML Cell Boundary Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radio access networks (RANs) face challenges in managing power consumption, as existing methods for reducing energy usage, such as shutting down non-essential cell sites, are complex and risk impacting network performance and user experience.
Innovation Solution
The use of machine learning (ML) algorithms to predict cell coverage boundaries, energy consumption impact, and performance changes associated with temporary cell site shutdowns or power reduction, allowing for optimized energy management without compromising user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by stationary object
If cell sites are shut down or power is reduced to decrease energy consumption, then power consumption is reduced, but network performance and user experience may be impacted
Solution Approach 1:
The system performs preliminary actions by collecting historical network performance data, traffic patterns, and energy consumption data before making power optimization decisions. Machine learning models are trained in advance to predict the impact of power reduction on network performance, allowing the system to proactively adjust power settings while maintaining performance thresholds.
Solution Approach 2:
The system implements continuous feedback loops where network performance metrics are monitored in real-time after power adjustments. The machine learning models use this feedback to refine predictions and adjust power settings dynamically, ensuring that power consumption is optimized while network performance remains within acceptable ranges.
2Use of energy by stationary object
If machine learning algorithms are used to predict performance changes and energy consumption, then power consumption can be optimized, but system complexity increases
Solution Approach 1:
The machine learning models operate autonomously to predict energy consumption and performance changes without requiring manual intervention. The system self-adjusts power settings based on model predictions, reducing the need for complex manual configuration and ongoing system management while achieving energy optimization.
Solution Approach 2:
The system optimizes energy consumption by dynamically changing operational parameters such as power levels, transmission settings, and resource allocation based on machine learning predictions. This approach allows energy optimization through parameter adjustment rather than requiring complex hardware modifications or system rearchitectures.
Data Source
AI summary
Systems and methods may optimize power consumption for RAN devices. A device obtains field data of user equipment (UE) devices for a group of cells during a time interval. The device computes cell boundaries for each cell and computes a cumulative overlap feature within the geographic area of interest for each cell of the group of cells during a future time period. The device determines updated cell boundaries that correspond to a reduced energy consumption needed to meet service requirements during the future time period.