Network Power Saving Estimation From Resource Block Usage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating power savings in networks are costly, time-consuming, and inaccurate, relying on manual analysis and field trials, which are dependent on expert availability and experience, and do not account for network-specific factors.
Innovation Solution
A method using machine learning models to estimate power savings by analyzing the relationship between power consumption and physical resource block usage before and after activating a power saving feature, eliminating the need for manual analysis and providing a more accurate and automated estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If field trials are performed to estimate power savings, then measurement precision is improved, but loss of time and productivity deteriorate due to lengthy trial periods and tight collaboration requirements
Solution Approach 1:
The system performs preliminary analysis of network data to establish baseline power consumption patterns and relationships with traffic parameters before actual power saving feature deployment. This preliminary modeling enables faster post-deployment estimation without requiring lengthy field trials
Solution Approach 2:
The system creates a virtual model/copier of the network's power consumption behavior using machine learning algorithms trained on historical data. This digital twin can simulate power saving outcomes without requiring physical field trials, significantly reducing turnaround time while maintaining estimation accuracy
2Measurement precision
If manual analysis by SMEs is used to estimate power savings, then measurement precision may be improved through expert knowledge, but device complexity and loss of time worsen due to dependency on expert availability and experience
Solution Approach 1:
The system enables self-service estimation by automating the analysis process using machine learning models that independently process network data and generate power saving estimates without requiring manual intervention from subject matter experts. The system serves itself by automatically collecting, analyzing, and interpreting network operational data
Solution Approach 2:
The system replaces the mechanical process of manual expert analysis with an automated computational system using machine learning algorithms. This substitution eliminates dependency on human experts while maintaining or improving estimation accuracy through consistent, data-driven analysis
3Productivity
If power saving features are deployed without accurate estimation, then productivity is improved through faster deployment, but reliability deteriorates due to inability to meet power saving commitments
Solution Approach 1:
The system performs preliminary power saving estimation using machine learning models trained on historical network data before actual power saving feature deployment. This preliminary assessment provides reliable predictions that enable network operators to make informed deployment decisions and set accurate commitments
Solution Approach 2:
The system establishes a feedback mechanism where actual power consumption data from deployed power saving features is continuously collected and used to refine and retrain the machine learning models. This closed-loop feedback improves the accuracy of future estimates and ensures reliability of power saving commitments
Data Source
AI summary
There is provided a method for estimating power saved in a first network. The method is performed by a system. The method includes estimating the power saved in the first network as a difference between: a relationship between power consumption in the first network as a function of physical resource block usage in the first network when a power saving feature is deactivated in the first network, and at least one data point indicative of the power consumption in the first network for a physical resource block usage value when the power saving feature is activated in the first network.