Wireless QoE Parameter Updating Through Reduced-Set MPC Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high dimensionality and complexity of model predictive control (MPC) in managing Quality of Experience (QoE) in wireless communications networks, particularly in standalone non-public networks (SNPNs), lead to instability and inefficiencies in adjusting QoS parameters to maintain optimal QoE.
Innovation Solution
A method and system that reduces complexity by performing root cause analysis to identify a reduced set of QoS parameters impacting QoE deviations, using AI techniques for feature extraction and importance evaluation, and updates these parameters to stabilize QoE through model predictive control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If model predictive control (MPC) is used to manage QoE by adjusting multiple QoS parameters, then QoE optimization capability is improved, but system complexity increases due to high dimensionality of control parameters
Solution Approach 1:
The patent extracts and identifies a reduced set of QoS parameters from the full parameter space that have the most significant impact on QoE deviations. By focusing only on these critical parameters through root cause analysis, the system maintains effective QoE optimization while reducing the dimensional complexity of the control problem.
Solution Approach 2:
The control problem is segmented into two phases: first identifying the reduced parameter set through feature extraction and importance evaluation, then applying MPC only to these selected parameters. This segmentation separates the parameter selection task from the control optimization task, reducing overall system complexity.
2Stability of the object's composition
If a large number of QoS parameters are controlled to reduce QoE deviations, then QoE stability is improved, but computational resources and processing time increase
Solution Approach 1:
The patent extracts only the most influential QoS parameters that actually impact QoE deviations, eliminating redundant parameters from the control loop. This reduction in parameter count directly decreases computational burden and processing time while maintaining the ability to stabilize QoE effectively.
Solution Approach 2:
The system dynamically changes the set of controlled parameters by selecting only those with highest importance scores. This adaptive parameter selection allows the system to maintain QoE stability with fewer parameters, reducing real-time computational requirements and response time.
3Adaptability or versatility
If traditional MPC controls all QoS parameters, then comprehensive QoE management is achieved, but system stability deteriorates due to high dimensionality
Solution Approach 1:
The patent removes unstable or less influential parameters from the MPC control loop by extracting only the critical subset through feature importance analysis. This extraction stabilizes the MPC system by reducing the dimensionality of the control problem while retaining comprehensive QoE management through the selected parameters.
Solution Approach 2:
The system dynamically adapts the parameter set being controlled based on real-time feature importance evaluation. This dynamic selection of parameters allows the MPC system to maintain stability by adjusting the control dimensionality according to current network conditions and QoE deviation patterns.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The disclosure pertains to a method for updating the parameter value of at least one parameter associated with the Quality of Experience (QoE) of an application in a wireless communications system. This method aims to improve the QoE of the application by adjusting relevant QoS parameters based on measured QoE and identified system features. This method is implemented in a network controller device and involves the following steps: - Determining (10) at least one feature related to the wireless communication system that is responsible for a deviation in QoE measurements for the application. - Obtaining (20) at least one Quality of Service (QoS) parameter linked to the deviation from the identified feature. - Updating (30) the parameter value of the QoS parameter linked to the deviation.