Application-Aware SD-WAN Hub Clustering for Traffic Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing software-defined wide area networks (SD-WANs) lack application-awareness in their clustering services, leading to sub-optimal performance and resource underutilization due to fixed scale-out ratios that treat all traffic types equally, resulting in inefficient load balancing and resource allocation.
Innovation Solution
Implement application-aware hub-selection rules in SD-WANs that utilize flow attributes, such as L7 attributes, to prioritize and allocate different forwarding hub nodes based on traffic categories, and a controller to dynamically adjust hub resources based on traffic demand.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed scale-out ratios are used for cluster nodes, then system simplicity is maintained, but network performance and resource utilization deteriorate due to inability to prioritize different traffic types
Solution Approach 1:
The patent segments the cluster nodes into different roles (primary and secondary nodes) and segments traffic into different priority levels. Each segment is handled with appropriate resources and policies, allowing high-priority traffic to receive dedicated attention while maintaining overall system manageability through structured segmentation.
Solution Approach 2:
The patent applies local quality by assigning different characteristics to different parts of the system: primary nodes handle control plane functions and high-priority traffic, while secondary nodes handle data plane functions and lower-priority traffic. This localized differentiation optimizes performance for specific traffic types without requiring complete system redesign.
2Ease of operation
If all traffic flows are treated equally in cluster allocation, then fairness is maintained, but resource utilization deteriorates due to lack of prioritization for high-priority applications
Solution Approach 1:
The patent introduces dynamic traffic engineering policies that allow the system to adaptively allocate resources based on traffic priority and application requirements. The cluster allocation is no longer static but dynamically adjusted according to real-time network conditions and traffic characteristics, enabling both fairness and optimized resource utilization.
Solution Approach 2:
The patent changes the parameter of traffic allocation from uniform distribution to priority-based distribution. By introducing traffic priority as a new parameter and adjusting allocation ratios accordingly, the system achieves better resource utilization while maintaining fairness through policy-based control rather than simple equal division.
3Device complexity
If simple load balancing is used across cluster nodes, then system complexity is reduced, but network efficiency deteriorates due to sub-optimal traffic provisioning
Solution Approach 1:
The patent introduces traffic engineering policies as an intermediary layer between the load balancer and cluster nodes. This intermediary analyzes traffic characteristics, determines priority levels, and makes intelligent routing decisions, thereby improving provisioning efficiency without requiring complex changes to the underlying load balancing mechanism itself.
Solution Approach 2:
The patent performs preliminary classification and prioritization of traffic flows before they reach the load balancing stage. By pre-processing traffic to identify high-priority applications and establishing hub-selection rules in advance, the system enables more efficient load balancing decisions without adding complexity to the core balancing mechanism during real-time operation.
Data Source
AI summary
Some embodiments provide a method for a software-defined wide area network (SD-WAN) connecting first and second sites, with the first site including an edge node and the second site including multiple forwarding hub nodes. At the edge node of the first site, the method receives a packet of a particular flow including a flow attribute. The method uses the flow attribute to identify a hub-selection rule from multiple hub-selection rules, each hub-selection rule identifying at least one forwarding hub node at the second site for receiving one or more flows from the first site, and at least one hub-selection rule identifying at least one forwarding hub node that is not identified by another hub-selection rule. The method uses the identified hub-selection rule to identify a forwarding hub node for the particular flow. The method then sends the packet from the edge node at the first site to the identified forwarding hub node at the second site.