Wireless Link Adaptation With Machine-Learned MCS Offsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently implementing link adaptation and power control, which are crucial for optimizing modulation and coding schemes and signal-to-interference ratios, leading to suboptimal system throughput and increased transmit power.
Innovation Solution
A method and apparatus utilizing machine learning, specifically reinforcement learning, to determine modulation and coding scheme (MCS) levels and signal-to-interference ratio adjustments by transmitting reference signals, receiving channel quality indications, and adjusting MCS levels based on machine learning processes, including Q-learning and unequally quantized block error rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional link adaptation and power control methods are used, then the system operation is simple and device complexity is low, but system throughput is suboptimal and transmit power is increased
Solution Approach 1:
The system employs machine learning models that automatically learn and optimize link adaptation and power control parameters without requiring manual configuration or complex centralized control. The base station and user equipment autonomously adjust MCS levels and power settings based on learned patterns from channel conditions, achieving high throughput while keeping device complexity manageable through decentralized intelligence
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting MCS (modulation and coding scheme) levels and power control parameters based on machine learning predictions. The system transforms static parameter settings into dynamic, adaptive parameters that change according to channel conditions, thereby improving system throughput without proportionally increasing device complexity
2Reliability
If machine learning-based link adaptation is implemented, then system throughput is enhanced and transmit power is reduced, but device complexity and processing requirements increase
Solution Approach 1:
The machine learning-based link adaptation process is segmented into distinct functional modules: channel quality measurement, feature extraction, machine learning inference, and parameter determination. This segmentation allows each module to be optimized independently and distributed across different processing units, reducing overall processing complexity while maintaining high link adaptation accuracy
Solution Approach 2:
The patent introduces intermediate representations and feature vectors that bridge raw channel measurements and final MCS/power control decisions. These intermediaries simplify the machine learning processing by transforming complex channel state information into compact, meaningful features that are easier to process, thereby reducing computational complexity while preserving accuracy
3Reliability
If conventional power control is used, then transmit power is increased to ensure reliable communication, but energy efficiency deteriorates
Solution Approach 1:
The system implements feedback-based power control where the base station receives ACK/NACK feedback from user equipment and uses machine learning to adjust transmit power accordingly. This feedback loop enables the system to maintain communication reliability by increasing power only when necessary (on NACK) while reducing power when transmissions are successful (on ACK), thereby significantly improving energy efficiency compared to conventional continuous high-power transmission
Solution Approach 2:
The patent applies dynamics by making transmit power adaptive rather than static. The power control mechanism dynamically adjusts power levels based on real-time channel conditions and machine learning predictions, transitioning from fixed power settings to flexible, condition-dependent power allocation. This dynamic approach ensures reliable communication at the lowest necessary power levels, improving energy efficiency
Data Source
AI summary
A method for transmitting data by a base station in a wireless communication system according to the present disclosure comprises: transmitting a reference signal (RS) to one or more user equipments (UEs); receiving, from the one or more UEs, channel quality indication (CQI) information based on the reception of the RS; determining a modulation and coding scheme (MCS) level on the basis of the CQI information; transmitting data to the one or more UEs in accordance with the MCS level; and receiving, from the one or more UEs, an acknowledgment/negative acknowledgment (ACK/NACK) with respect to the transmitted data, wherein the MCS level is determined on the basis of the CQI information and an offset determined according to a machine learning process, and the machine learning process for determining the offset is performed by configuring the selecting of one of a plurality of MCS offset values as an operation value of machine learning, configuring an error rate for the operation value as a state value of the machine learning, and configuring a processing rate at a level where the error rate satisfies a predetermined reference, as a compensation value of the machine learning.