Recommendation Policy Manager for Predictive Networking Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive networking systems in SD-WANs lack the ability to selectively limit recommendations to specific portions of the network, which can be necessary due to regulatory or criticality concerns, or for evaluating performance, as they are typically designed to provide recommendations for the entire network.
Innovation Solution
A recommendation policy manager that obtains network characteristics and allows administrators to define constraints via a user interface to limit recommendations by the predictive networking engine for selected portions of the network, preventing it from generating recommendations based on set constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the predictive networking engine provides recommendations for the entire network, then the coverage and comprehensiveness of recommendations is improved, but the ability to address specific regulatory or criticality concerns for certain network portions deteriorates
Solution Approach 1:
The patent divides the network into different portions or segments, allowing the predictive networking engine to apply different recommendation policies to each segment. Network administrators can select specific network portions for which recommendations should be generated, thereby addressing regulatory or criticality concerns for certain areas while maintaining comprehensive coverage for other areas.
2Reliability
If the predictive networking engine generates recommendations for all network portions, then the system's monitoring capability is improved, but the complexity of managing and controlling recommendations deteriorates
Solution Approach 1:
The patent enables network administrators to define different characteristics and constraints for different network portions. Each network segment can have its own recommendation policies, constraints, and parameters, allowing for localized control and management while maintaining overall system monitoring capability.
3Measurement precision
If the predictive networking system evaluates performance for the entire network, then the evaluation comprehensiveness is improved, but the ability to focus on specific network portions for evaluation deteriorates
Solution Approach 1:
The patent makes the network portion selection dynamic, allowing administrators to flexibly select, add, or remove network portions for evaluation based on changing requirements. The system can adapt to different evaluation scenarios, focusing on specific network portions when needed while maintaining the capability for comprehensive network evaluation when required.
Data Source
AI summary
In one embodiment, a device obtains a plurality of characteristics of different portions of a network for which a predictive networking engine is available. The device provides the plurality of characteristics of the different portions of a network to a user interface. The device receives, via the user interface, a set of one or more constraints to limit recommendations by the predictive networking engine for a selected portion of the network from among the different portions of the network. The device configures the predictive networking engine to prevent it from generating recommendations for the selected portion of the network according to the set of one or more constraints.