Data Plane Protocol for Network Routing Arc Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network systems face unacceptably long reconfiguration delays in responding to link failures due to the time-consuming nature of control plane OAM messages traveling between network controllers and deep-seated nodes within the network topology.
Innovation Solution
Implementing a data plane protocol that enables nodes within a routing arc to exchange data plane management frames, such as JOAN frames, to autonomously detect and reroute network traffic without relying on control plane communications, thereby reversing links and freezing incoming edges to bypass failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If control plane OAM messages are used to reconfigure network links, then network connectivity can be restored after link failures, but reconfiguration delays become unacceptably long due to the time required for messages to travel between network controllers and deep-seated nodes
Solution Approach 1:
The patent introduces data plane management frames as an intermediary mechanism between nodes. These frames enable direct node-to-node communication for failure detection and link reconfiguration, eliminating the need for messages to traverse the entire path to remote network controllers and back. The management frames act as a local mediator that resolves the time delay issue while maintaining connectivity restoration capability.
Solution Approach 2:
The patent segments the network control function by separating failure detection and reconfiguration capabilities from the central network controller. Individual nodes are empowered to autonomously detect failures and reconfigure their own links using data plane management frames. This segmentation distributes the control function, allowing parallel local responses instead of sequential centralized control, thereby reducing reconfiguration delays.
2Ease of operation
If control plane communications are used for failure detection and reconfiguration, then network links can be reconfigured after failures, but the process becomes slow due to the distance and topology of the network
Solution Approach 1:
The patent implements self-service by enabling nodes to autonomously detect failures and reconfigure their own links without requiring external control plane instructions. Nodes use data plane management frames to automatically identify failed links and execute reconfiguration locally. This self-service capability maintains ease of operation while dramatically improving reconfiguration speed by eliminating communication delays with remote controllers.
Solution Approach 2:
The patent employs preliminary action by pre-configuring nodes with the capability to autonomously detect and respond to failures. Nodes are equipped with data plane management frame functionality that enables immediate local response to failures without waiting for control plane instructions. This preliminary empowerment of nodes allows rapid automatic reconfiguration while maintaining operational simplicity.
3Reliability
If nodes deep inside the network topology respond to failures using control plane messages, then link failures can be detected and repaired, but the response time becomes unacceptably long
Solution Approach 1:
The patent transitions from the traditional vertical control plane dimension to a horizontal data plane dimension for failure management. Instead of messages traveling vertically through multiple network layers to reach remote controllers, nodes communicate horizontally using data plane management frames. This dimensional change in communication approach enables deep-seated nodes to respond quickly to failures without being constrained by their distance from the network controller.
Data Source
AI summary
A network includes routing arcs for routing network traffic to a destination. Each arc comprising nodes connected in sequence by reversible links oriented to direct network traffic to first and second edge nodes through which the network traffic exits the arc. The nodes in the arc detect a first failure. In response, the nodes exchange first management frames to reverse links in the arc so that the network traffic in the arc is directed away from the first failure toward the first edge node of the arc through which the network traffic exits the arc. The nodes detect a second failure in the arc that is spaced apart from the first failure. In response, the nodes exchange second management frames to freeze incoming edges of parent arcs to prevent network traffic in the corresponding parent arc from entering the arc.