Adaptive AR Model Order for Channel Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing channel prediction techniques for wireless networks face challenges in accurately estimating channel state information (CSI) due to channel estimation errors and outdating caused by mobility and TDD transmission patterns, leading to degraded beamforming performance.
Innovation Solution
A method for determining the autoregressive (AR) model order for a channel prediction filter based on CSI quality, which involves monitoring CSI quality, estimating current channel conditions, determining the AR model order, and performing channel prediction using the AR model with the determined order.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If uplink reference signals transmission periodicity is increased to allow more user equipment transmission opportunities, then the number of user equipment that can transmit reference signals increases, but the CSI outdating becomes more severe for each user equipment
Solution Approach 1:
The patent applies dynamics by making the AR model order adaptive rather than fixed. The system dynamically adjusts the model order based on current channel conditions, allowing the prediction mechanism to respond to changing mobility patterns and CSI quality. This resolves the contradiction by enabling the system to handle varying numbers of users and mobility conditions without being constrained by a static configuration.
Solution Approach 2:
The patent changes the parameter of AR model order based on CSI quality metrics and channel conditions. By monitoring CSI quality and adjusting the model order accordingly, the system can maintain accurate channel predictions even when reference signal periodicity increases. This parameter adaptation allows the system to compensate for CSI outdating while supporting more user equipment.
2Productivity
If TDD configuration has more downlink transmission timeslots than uplink transmission timeslots, then downlink capacity increases, but the estimated channel becomes outdated for downlink transmission
Solution Approach 1:
The patent applies preliminary action by performing channel predictions using the AR model before actual downlink transmission occurs. The system uses available uplink reference signals to predict future channel states, preparing the downlink precoders in advance. This allows the system to maintain reliable channel estimates even in TDD configurations where downlink slots significantly outnumber uplink slots.
Solution Approach 2:
The patent implements feedback by monitoring CSI quality metrics and using this information to adjust the AR model order and prediction parameters. The system continuously evaluates the accuracy of channel estimates and adapts the prediction mechanism accordingly, ensuring that downlink capacity is maximized while maintaining sufficient channel estimation accuracy despite the asymmetry in TDD configuration.
3Adaptability or versatility
If user equipment mobility increases, then network coverage and user access improve, but channel estimation errors and CSI outdating increase
Solution Approach 1:
The patent makes the AR model adaptive to user equipment mobility by dynamically adjusting the model order based on observed channel conditions and CSI quality. The system can increase the model order for highly mobile users to capture faster channel variations, while using lower model orders for stationary users. This dynamic adaptation allows the system to support high mobility while maintaining channel estimation accuracy.
Solution Approach 2:
The patent changes the AR model parameters (particularly the model order) based on mobility-induced channel conditions. By monitoring CSI quality and channel variation rates, the system adjusts the prediction model complexity to match the actual channel dynamics, thereby maintaining measurement precision across a wide range of mobility scenarios.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
There is provided mechanisms for CSI quality triggered determination of AR model order for a channel prediction filter. A method is performed by a network node. The method comprises obtaining an indication of declining CSI quality in a radio environment. The method comprises, in response thereto, obtaining an estimation of current channel conditions in the radio environment. The method comprises determining the AR model order based on the estimation of current channel conditions. The method comprises performing channel prediction of the radio environment using the channel prediction filter. The channel prediction filter is defined by an AR model having the determined AR model order.