Network Automation Critic Framework for Predictable Cognitive Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network automation systems lack a flexible mechanism for operators to provide dynamic constraints and pre-action coordination of network automation functions, particularly in cognitive networks, which can lead to unpredictable and potentially adverse effects due to the continuous learning and adaptation of network automation functions from different vendors.
Innovation Solution
Introduce an External Network Automation Critic Framework (ENACF) that allows operators to request and aggregate feedback from Network Automation Critic Functions (NACFs) to evaluate and influence the performance of network automation systems, enabling dynamic deployment of constraints and pre-action coordination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If network automation functions continuously learn and adapt from different vendors, then the system becomes more intelligent and flexible, but the operations become unpredictable and potentially adverse
Solution Approach 1:
The patent implements a feedback mechanism where network automation functions report their learned behaviors and adaptations to a central controller. This feedback loop enables the system to monitor adaptability while maintaining predictability by reviewing and validating learned patterns against predefined safety criteria.
Solution Approach 2:
The system performs preliminary evaluation of learned behaviors before fully implementing them. The controller pre-validates adaptation patterns to ensure they align with operational safety requirements, preventing potentially adverse effects before they occur in the network.
2Productivity
If operators deploy network automation functions without external constraints, then the system achieves higher automation and productivity, but safety and control are reduced
Solution Approach 1:
The patent introduces an intermediary controller that sits between the network automation functions and the network infrastructure. This intermediary layer enables high-level automation while maintaining safety by mediating all actions through predefined safety criteria and constraint validation.
Solution Approach 2:
The system segments automation functions into independent modules that can be deployed and managed separately. Each module operates with defined boundaries and safety constraints, allowing high productivity through modular automation while maintaining overall system safety through isolated control.
3Reliability
If the system aggregates feedback from multiple network critic functions, then the coordination and control improve, but the system complexity increases
Solution Approach 1:
The patent merges the feedback aggregation function into a centralized controller that consolidates inputs from multiple network critic functions. This merging approach improves coordination by providing a unified view of system state while managing complexity through centralized processing rather than distributed aggregation.
Data Source
AI summary
There is provided an apparatus arranged to: receive, from a configuration controller, a request for feedback on a network configuration in a communications network; request feedback on the network configuration from a plurality of network critic functions; aggregate feedback received from at least part of the plurality of network critic functions in response to the request; and provide the aggregated feedback to the configuration controller.