Intent-Based Policy Routing for SD-WAN SLA Satisfaction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current load balancing techniques in communication networks, such as Software-Defined Wide Area Networks (SD-WAN), struggle to efficiently balance traffic across multiple paths while ensuring Quality of Service (QoS) and Service Level Agreements (SLA) requirements, often requiring frequent communication between devices and controllers, which leads to slow reaction times to network changes and inadequate support for global network intents.
Innovation Solution
Implementing an intent-based policy routing method within network devices, such as access routers, that allows them to make routing decisions based on policy information including global intents and SLA requirements, reducing the need for frequent communication with controllers and enhancing SLA satisfaction by using traffic and SLA prediction models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If frequent communication between devices and controllers is implemented for path selection, then SLA requirements can be satisfied, but reaction time to network changes increases and communication overhead increases
Solution Approach 1:
The patent implements prediction models (traffic prediction model and SLA prediction model) that perform preliminary analysis of network conditions and potential SLA violations. By predicting future network states before they occur, the system can proactively adjust routing decisions without waiting for actual SLA breaches or continuous controller communication, thus maintaining SLA satisfaction while reducing reaction time.
Solution Approach 2:
The access router is equipped with embedded prediction models that enable it to autonomously make routing decisions based on local network condition analysis. This self-service capability allows the device to independently predict traffic patterns and SLA compliance without frequent controller intervention, reducing communication overhead while maintaining reliable SLA satisfaction through locally-informed decisions.
2Ease of operation
If controller-managed path selection is used, then centralized policy control is achieved, but communication overhead increases and device autonomy decreases
Solution Approach 1:
The patent segments the routing decision-making function into two parts: centralized policy definition (remaining with the controller) and local prediction-based execution (implemented at the access router). The controller sends high-level policy intentions, while the access router uses its embedded prediction models to autonomously determine specific routing actions. This segmentation reduces communication overhead by eliminating frequent detailed path selection messages while maintaining centralized policy oversight.
Solution Approach 2:
The controller performs preliminary policy configuration and intent definition, then the access router uses prediction models to autonomously execute routing decisions based on those policies. This preliminary action at the controller level, combined with autonomous local execution, reduces the need for continuous communication while maintaining centralized policy control.
3Productivity
If link utilization-based load balancing is implemented, then network capacity is optimized, but SLA guarantees cannot be ensured
Solution Approach 1:
The patent implements a feedback mechanism where the SLA prediction model continuously monitors predicted SLA compliance and adjusts routing decisions accordingly. The system uses predicted traffic patterns and network conditions to anticipate SLA violations before they occur, providing feedback that guides load balancing decisions to maintain both network capacity optimization and SLA guarantees.
Solution Approach 2:
The patent changes the decision-making parameters from simple link utilization metrics to multi-parameter predictions including traffic patterns, network conditions, and SLA compliance probability. By incorporating these additional parameters through prediction models, the system can make routing decisions that optimize network capacity while ensuring SLA guarantees are maintained.
Data Source
AI summary
The present disclosure relates to smart policy routing in a network. To this end, a network entity is configured to obtain policy information from a controller. The policy information can include one or more global intents and information about at least one SLA requirement for each of the plurality of flow groups. Furthermore, each global intent is indicative of one requirement of a network operator. The network entity further makes one or more routing decisions for the plurality of flow groups based on the policy information. In some examples, a controller is configured to provide policy information to the network entity.