Machine Learning Link Adaptation for Wireless Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems face inefficiencies in link adaptation due to computationally expensive algorithms, which hinder the speed and efficiency of matching modulation, coding, and other signal parameters to dynamic radio link conditions.
Innovation Solution
Implementing machine learning-based methods, such as k-Nearest Neighbor (k-NN) and deep neural networks (DNNs), for link adaptation in wireless communication systems to improve network efficiency and throughput by optimizing channel quality indicator (CQI) feedback and modulation coding schemes based on real-time channel conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computationally expensive algorithms are used for link adaptation, then accuracy of matching signal parameters to radio link conditions is improved, but processing speed and efficiency deteriorate
Solution Approach 1:
The patent creates a simplified copy of the complex channel state information by using k-NN to find similar historical channel states and their corresponding optimal CQI values. Instead of processing the full complex algorithm in real-time, the system copies and matches against pre-stored channel state patterns, achieving fast and accurate link adaptation decisions.
Solution Approach 2:
The system performs preliminary action by pre-calculating and storing channel state information and corresponding CQI values in a database during periods when processing is not critical. This allows the real-time link adaptation to simply query and match against pre-prepared data, eliminating the need for complex real-time computations.
2Reliability
If traditional link adaptation algorithms are used, then comprehensive analysis of channel conditions is achieved, but computational complexity and processing overhead increase
Solution Approach 1:
The patent uses k-NN to copy and match against pre-stored channel state patterns from a database. This approach maintains reliable link adaptation by comparing current channel conditions with historical patterns, achieving accurate CQI selection without the computational complexity of traditional algorithms.
Solution Approach 2:
The system employs self-service by using the stored channel state information and CQI mappings to automatically determine optimal link adaptation parameters. The k-NN algorithm autonomously queries the database and selects the best matching CQI value without requiring complex real-time processing or external intervention.
3Speed
If real-time processing of channel quality indicator feedback is performed, then responsiveness to changing radio conditions is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary action by pre-processing and storing channel state information and CQI values in a database before real-time operation. During actual link adaptation, the system simply queries and matches against this pre-prepared data, achieving instantaneous responsiveness without real-time computational overhead.
Solution Approach 2:
The patent uses k-NN to copy and match current channel conditions against pre-stored patterns in the database. This copying approach enables the system to instantly retrieve optimal CQI values based on similar historical conditions, achieving fast responsiveness with minimal processing time.
Data Source
AI summary
Aspects for machine learning-based link adaptation are described. For example, an apparatus can determine k-nearest neighbors (K-NNs) based on training data associated with the sub-band and on the signal to interference and noise ratio (SINR) of the sub-band. In aspects, the apparatus can identify a channel quality indicator (CQI) associated with the lowest error rate for the k-NNs and provide the identified CQI to a base station. In aspects, a neural network (NN) can provide labels for CQIs that indicate probability of choosing a CQI, and the CQI having highest probability will be provided to a base station. In aspects, a covariance matrix based on samples of a communication channel can be provided to a NN to determine a rank indicator (RI) corresponding to the channel, and channel state information associated with the (RI) can be sent to the base station. Other aspects are described.