Dynamic ML Functionality Switching for 5G Resource Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile and wireless telecommunication systems, particularly those using 5G NR technology, lack a mechanism to efficiently switch or manage machine learning functionality based on resource availability, leading to potential performance degradation due to resource constraints.
Innovation Solution
The proposed method involves executing machine learning functionality at a first network element, monitoring machine learning resources impacting performance, and indicating resource availability to a second network element. It also includes receiving a configuration for actions based on resource availability and executing those actions to optimize performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning functionality is executed at a network element, then service quality and intelligence are improved, but resource consumption and system complexity increase
Solution Approach 1:
The patent implements dynamic switching of machine learning functionality based on real-time resource availability monitoring. The network element adaptively activates or deactivates ML features according to current resource conditions, transforming a static resource consumption model into a dynamic one that responds to changing system states.
Solution Approach 2:
The system changes operational parameters by switching between different machine learning functionality states (active/inactive) based on resource availability thresholds. This parameter change allows the system to optimize between service quality and resource consumption by selecting appropriate operational modes.
2Reliability
If machine learning functionality is executed at a network element, then service intelligence is improved, but device complexity increases
Solution Approach 1:
The patent segments machine learning functionality into separate, independently controllable features that can be selectively activated or deactivated. This segmentation allows the system to manage complexity by enabling only the necessary ML features rather than running all possible functions simultaneously.
Solution Approach 2:
The system dynamically adjusts the complexity level by switching ML functionality based on resource availability. When resources are constrained, the system reduces complexity by deactivating ML features, and when resources are abundant, it increases intelligence by activating them.
3Productivity
If machine learning resources are monitored and functionality is switched based on availability, then performance optimization is improved, but control mechanism complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where the network element monitors its own resource availability and uses this information to control machine learning functionality. The performance monitoring entity provides feedback about resource conditions, which triggers appropriate switching actions to optimize performance.
Solution Approach 2:
The network element performs self-monitoring of resource availability and self-adjusts its machine learning functionality based on the monitored conditions. This self-service approach reduces the need for external control complexity while achieving performance optimization.
Data Source
AI summary
Systems, methods, apparatuses, and computer program products for a switching machine learning functionality based on resource availability. A method may include executing a machine learning functionality, feature, or model at a first network element. The method may also include monitoring a machine learning resource at the first network element that impacts performance of the machine learning functionality, feature, or model. The method may further include indicating, to a second network element based on the monitoring, a machine learning-related resource availability impacting performance of the machine learning functionality, feature, or model. In addition, the method may include receiving, from a third network element, a configuration for an action to be executed by the first network element based on the machine learning-related resource availability impacting performance of the machine learning functionality, feature, or model. Further, the method may include executing the action.