Received Power Correction Models for 5G Base Station Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing estimation models for received power of communication devices in 5G networks are inaccurate, failing to provide precise estimates in actual operation environments.
Innovation Solution
A learning program that combines a physical model with a correction model using deep neural networks to refine received power estimates, incorporating reinforcement learning to derive optimal control rules for base station operation, thereby improving estimation accuracy and reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a physical model is used to estimate received power, then the estimation process is simple and fast, but the estimation accuracy is insufficient in actual operation environments
Solution Approach 1:
The estimation system is segmented into two independent components: a physical model for basic estimation and a correction model for refining accuracy. The physical model handles the bulk estimation while the correction model processes only the residual errors, achieving high accuracy without requiring the entire system to be complex.
Solution Approach 2:
The correction model acts as an intermediary that receives the output from the physical model and adjusts it based on actual measurement data. This intermediary component bridges the gap between simple physical estimation and complex real-world conditions, improving accuracy without replacing the entire physical model.
2Measurement precision
If manual parameter adjustments are made to improve estimation accuracy, then the estimation can be optimized for specific environments, but the operation complexity and time consumption increase
Solution Approach 1:
The correction model performs self-adjustment by automatically learning from historical data between physical model estimates and actual measurements. It autonomously optimizes its parameters without human intervention, eliminating the need for manual parameter tuning while maintaining high accuracy across different environments.
Solution Approach 2:
The system incorporates feedback mechanisms where actual measurement data is continuously fed back to train and refine the correction model. This feedback loop enables the model to automatically adapt to changing environmental conditions, removing the need for manual reconfiguration when conditions change.
3Reliability
If base station transmission power is increased to ensure communication quality, then communication reliability improves, but power consumption increases
Solution Approach 1:
The system dynamically adjusts base station transmission power based on real-time received power estimates and actual communication conditions. Instead of using fixed high power levels, the system continuously optimizes power settings to maintain communication quality while minimizing energy consumption, adapting to changing channel conditions and user requirements.
Solution Approach 2:
The correction model enables precise parameter estimation of received power under various transmission conditions. This accurate parameter knowledge allows the system to optimize transmission power settings by changing power levels adaptively based on actual channel conditions, achieving reliable communication with reduced power consumption compared to conservative fixed power settings.
Data Source
AI summary
A non-transitory computer-readable recording medium stores a learning program for causing a computer to execute a process including: calculating, by using a first model that estimates a value of received power of a radio wave received by a communication device from a base station based on position information of the base station and position information of the communication device, an estimated value of the received power of the radio wave; and training a second model that outputs a correction value for correcting the estimated value of the first model based on an actually measured value of the received power of the communication device in an operation environment using the first model, and the estimated value.