Base Station Energy Source Selection Using Radio Traffic Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radio base stations lack efficient methods for selecting and controlling energy sources based on their operational attributes and varying energy needs, leading to suboptimal energy usage and increased carbon emissions.
Innovation Solution
A control node system that uses an offline machine learning model with reinforcement learning to select energy sources based on their energy rates correlated with radio traffic power usage, optimizing operating parameters such as efficiency and cost, and activating the appropriate energy source for use by the base station.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional energy source selection methods are used in radio base stations, then operational simplicity is maintained, but energy efficiency and cost optimization deteriorate
Solution Approach 1:
The control node automatically monitors energy source attributes, correlates them with radio traffic patterns, and performs dynamic selection without manual intervention. The system self-optimizes by continuously analyzing operational data and adjusting energy source allocation based on learned patterns, eliminating the need for manual energy management while improving efficiency
Solution Approach 2:
The system implements closed-loop feedback by monitoring the operational status, energy consumption, and performance metrics of each energy source. This feedback is used to continuously refine the selection strategy, correlating energy source performance with radio traffic patterns and adjusting selections to optimize efficiency while maintaining operational simplicity
2Adaptability or versatility
If multiple energy sources are available with different attributes, then energy source versatility is improved, but selection complexity increases
Solution Approach 1:
The system transforms the complex multi-attribute energy source selection problem into a manageable form by identifying and prioritizing key parameters such as energy rate correlation with radio traffic, operational cost, and efficiency metrics. By focusing on these critical parameters and using machine learning to process them, the system maintains versatility in handling diverse energy sources while reducing selection complexity through parameter-based evaluation
Solution Approach 2:
The control node pre-analyzes and stores operational attributes of all available energy sources, creating a database of energy rate patterns correlated with radio traffic. This preliminary action allows the system to have energy source performance data ready before selection is needed, enabling rapid and informed decisions without complex real-time analysis, thus maintaining versatility while reducing operational complexity
3Loss of energy
If dynamic energy source selection is implemented, then energy cost optimization is improved, but system complexity increases
Solution Approach 1:
The control node autonomously performs energy source selection, monitoring, and optimization without requiring complex external control systems. The system self-manages the complexity by automatically correlating energy rates with radio traffic patterns and making selection decisions based on pre-learned patterns, achieving cost optimization while keeping the control architecture relatively simple
Solution Approach 2:
The patent replaces complex mechanical or manual energy source switching mechanisms with an intelligent control system that uses machine learning algorithms and data correlation. This substitution allows dynamic optimization of energy costs through software-based decision making rather than complex hardware switching mechanisms, reducing physical system complexity while achieving superior cost optimization
4Speed
If energy sources are selected without correlation to radio traffic patterns, then system responsiveness is improved, but energy optimization deteriorates
Solution Approach 1:
The system pre-correlates energy source operational rates with radio traffic patterns during off-peak periods or using historical data, building lookup tables and decision models in advance. When selection is needed, the control node quickly queries these pre-computed results based on current traffic conditions, achieving both rapid responsiveness and optimized energy selection without requiring complex real-time analysis
Data Source
AI summary
A method performed by a control node for a radio access network. The control node may select an energy source from a plurality of energy sources connected to a base station based on selecting an energy rate of one of the energy sources correlated in time with a radio traffic power usage of the base station. The selection may be made from a plurality of energy rates for the plurality of energy rates correlated in time for each energy source with a radio traffic power usage of the base station. The selected energy rate may improve at least one operating parameter of the selected energy source. The control node may activate the selected energy source for use by the base station. A further method performed by a global control node may be provided.