Machine Learning Management Orchestration for Lower Message Exchange
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of numerous machine learning (ML) entities in networks leads to increased message exchange and untimely updates, affecting network performance due to inefficient workflows and data exchange between operator and vendor management systems.
Innovation Solution
A method where a first network element determines and sends management and control information to a second network element, enabling the orchestration and execution of ML procedures, reducing message exchange and improving efficiency by leveraging ML step capability information and interface model objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If each ML entity frequently executes ML workflows with extensive data exchange between operator management system and vendor management system, then the network can perform adaptive change in real time, but a large quantity of messages are exchanged through interfaces causing untimely update and low efficiency
Solution Approach 1:
The patent merges the management and control functions into a unified workflow orchestration mechanism. The first network element determines management and control information that includes both ML entity information and ML step requirement information, then sends this consolidated information to the second network element. This merging reduces the number of separate messages exchanged between operator and vendor management systems while maintaining real-time adaptive change capabilities.
Solution Approach 2:
The patent introduces management and control information as an intermediary structure between the operator management system and vendor management system. This intermediary contains standardized fields (ML entity information and ML step requirement information) that facilitate efficient data exchange without requiring extensive point-to-point communication for each ML workflow execution, thereby reducing message volume and update time.
2Adaptability or versatility
If a large quantity of ML entities are introduced into the network with frequent workflow execution, then network adaptability is improved, but the complexity of message exchange and data processing increases
Solution Approach 1:
The patent creates a universal management and control information structure that can handle multiple types of ML entities through standardized fields. The first network element determines management and control information using a consistent template that works across different ML entity types, and the second network element processes this information uniformly. This universality reduces the complexity of managing diverse ML entities by providing a single standardized interface for workflow orchestration.
Solution Approach 2:
The patent segments the management and control information into distinct, manageable fields: ML entity information (containing entity identifier, type, version) and ML step requirement information (containing step identifier, parameter requirements). This segmentation allows the system to handle complex ML workflows by processing information in structured segments rather than as monolithic data structures, reducing processing complexity while supporting network adaptability.
3Reliability
If extensive data exchange is performed for each ML workflow between operator and vendor systems, then complete ML workflow control is achieved, but interface message volume increases and update efficiency decreases
Solution Approach 1:
The patent performs preliminary action by determining complete management and control information upfront before workflow execution. The first network element determines all necessary ML entity information and ML step requirement information in advance, then sends this pre-prepared information to the second network element. This preliminary determination ensures complete workflow control is achieved without requiring extensive data exchange during actual workflow execution, thereby maintaining reliability while improving update efficiency.
Data Source
AI summary
This application relates to the field of wireless communication technologies, and provides a machine learning management and control method and an apparatus. In the method, a first network element determines management and control information of a target ML entity and sends the management and control information of the target ML entity to a second network element, where the management and control information of the target ML entity includes target ML entity information and ML step requirement information. The first network element. The second network element manages and controls a machine learning procedure of the target ML entity based on the ML step requirement information.