Wireless Receiver BP Detection With Learned Iteration Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Belief Propagation (BP) algorithms in large-scale multi-user MIMO systems face challenges in determining optimal damping and scaling factors, as well as node selection, which affects detection performance and convergence, making it difficult to achieve near-optimal settings for each iteration.
Innovation Solution
A wireless receiver apparatus using deep learning techniques to learn and store sets of scaling and damping factors, or node selection factors, allowing the BP detector to execute an iterative BP algorithm with near-optimal parameters for each iteration, thereby improving multi-user detection performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If damping factor and scaling factor are determined individually through empirical methods, then the determination process is simple, but the detection performance and convergence are poor
Solution Approach 1:
The patent transforms the parameter determination problem from empirical trial-and-error to a learned parameter selection process. Deep learning models are trained to predict optimal damping factors and scaling factors based on input signal characteristics, thereby improving detection performance while automating the previously complex manual tuning process
Solution Approach 2:
The system implements feedback mechanisms where the deep learning model continuously learns from detection outcomes and adjusts parameter selection accordingly. The model uses past detection performance and current signal conditions to dynamically select optimal parameters, creating a closed-loop system that improves reliability through iterative learning
2Measurement precision
If the number of BP iterations is increased to improve detection performance, then detection accuracy improves, but the processing time increases
Solution Approach 1:
The patent applies dynamic parameter adjustment where damping factors and scaling factors are changed adaptively across different iterations based on signal conditions and convergence status. This dynamic approach allows the system to achieve high detection accuracy with fewer iterations by optimizing parameters at each step rather than using fixed values throughout
Solution Approach 2:
The deep learning model performs preliminary analysis of input signals to predict optimal parameter sequences before the BP detection process begins. This preliminary action enables the system to pre-determine the most effective parameter combinations, reducing the number of iterations needed to achieve target detection accuracy
3Reliability
If node selection is used to counteract fading spatial correlations, then detection performance improves, but it becomes difficult to determine optimal subsets per iteration
Solution Approach 1:
The deep learning model autonomously performs node selection by automatically identifying and selecting optimal antenna subsets for each iteration based on learned patterns from training data. This self-service approach eliminates the need for manual subset configuration and adapts to varying signal conditions dynamically, making the complex node selection process transparent and automated
Data Source
AI summary
A BP detector of a wireless receiver apparatus reads a first parameter set or a second parameter set. The first parameter set includes a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique. The second parameter set includes a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique from a memory. The BP detector executes an iterative BP algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.