ML-Based QoS Policy for Wireless Remote Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication networks face challenges in efficiently utilizing radio resources for remote control of devices like robots, requiring high precision, which is hindered by manual tagging of Quality of Service (QoS) levels and increased latency, leading to suboptimal radio resource allocation.
Innovation Solution
A network node applies machine learning to train a communication policy that automatically adjusts QoS modes based on communication phases, minimizing radio resource usage while maintaining precision by determining a performance score and applying optimized policies between the network node and the control node operating a remotely controlled device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual tagging of QoS levels is used to ensure high precision in remote control, then communication reliability is improved, but device complexity and time consumption increase
Solution Approach 1:
The system performs self-service by automatically determining QoS levels through machine learning models without requiring manual tagging. The network node autonomously analyzes communication phases and selects appropriate QoS levels, eliminating the need for complex manual configuration while maintaining high communication reliability
Solution Approach 2:
The invention changes the parameter determination approach from static manual tagging to dynamic machine learning-based determination. The system continuously adapts QoS parameters based on real-time communication phase analysis, transforming the system from a manually configured state to an autonomously adapting state
2Reliability
If manual tagging of QoS levels is applied to maintain precision, then communication reliability is improved, but the time required for configuration increases
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models with communication phase data before actual operation. This preparation enables the system to automatically and rapidly determine QoS levels during runtime without time-consuming manual configuration, achieving both high reliability and fast deployment
Solution Approach 2:
The automated machine learning-based QoS determination performs self-service configuration without human intervention. The system independently analyzes communication requirements and selects appropriate QoS levels, eliminating manual configuration time while maintaining communication reliability
3Device complexity
If traditional radio resource allocation is used, then system simplicity is maintained, but radio resource efficiency deteriorates
Solution Approach 1:
The invention introduces dynamics into radio resource allocation by using machine learning models that adapt QoS levels based on real-time communication phase analysis. Instead of static allocation, the system dynamically adjusts resource allocation to match actual communication needs, significantly improving radio resource efficiency while adding manageable system complexity
Solution Approach 2:
The system changes resource allocation parameters from fixed traditional values to dynamically determined values based on machine learning analysis. By transforming parameters like QoS levels and resource allocation decisions into adaptive variables, the system achieves superior radio resource efficiency
4Reliability
If QoS levels are increased to ensure precision in remote control, then communication reliability is improved, but radio resource consumption increases
Solution Approach 1:
The invention applies local quality by determining appropriate QoS levels for specific communication phases rather than uniformly high QoS for all communications. The machine learning model identifies which communication phases require high precision and allocates resources accordingly, ensuring reliability only where needed and reducing overall radio resource consumption
Solution Approach 2:
The system changes QoS parameter levels dynamically based on communication phase requirements. Instead of maintaining consistently high QoS parameters, the system adjusts parameters to match actual needs, achieving necessary communication reliability while minimizing radio resource consumption
Data Source
AI summary
A method and a network node for applying machine learning for training a communication policy controlling radio resources for communication of messages between the network node and a control node operating a remotely controlled device is provided. The network node obtains said messages during one or more communication phases communicated when an initial first communication policy is applied for controlling a Quality of Service, QoS, mode. The network node trains a machine learning model based on said messages and the first communication policy. The network node produces a second communication policy including at least one adjusted QoS mode for at least one communication phase. The network node determines a performance score for the second communication policy in the communication phase(s) based on the radio resources used when communicating using the second communication policy.