Traffic Engineering System Using Weighted Cost Multi-Path Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing networks face congestion and packet loss due to link failures and dynamic conditions, such as partial and total span failures, which traditional routing protocols struggle to manage effectively, especially when using equal cost multi-path (ECMP) routing.
Innovation Solution
A traffic engineering (TE) system with a software-defined networking (SDN) architecture that decouples the control plane from the data plane, using weighted cost multi-path (WCMP) routing and tunnel specifications to dynamically re-route traffic based on real-time link capacities and failures, ensuring optimal path utilization and minimizing congestion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If equal cost multi-path (ECMP) routing is used, then network resource utilization is improved, but network reliability deteriorates during link failures
Solution Approach 1:
The patent implements dynamic path selection by transitioning from static ECMP routing to WCMP routing with dynamically calculated weights. The system continuously monitors link status and traffic conditions, adjusting path weights in real-time to adapt to changing network conditions. When link failures occur, the system dynamically recalculates weights to route traffic around failures while maintaining optimal resource utilization.
Solution Approach 2:
The patent changes the routing parameter from equal cost (ECMP) to weighted cost (WCMP) routing. By introducing variable weights based on link capacity, traffic demand, and failure status, the system can optimize both resource utilization and reliability. The weights are adjusted according to current network conditions, allowing the system to handle both normal operation and failure scenarios effectively.
2Device complexity
If traditional routing protocols are used, then device complexity is reduced, but ability to manage dynamic conditions and link failures deteriorates
Solution Approach 1:
The patent segments the routing functionality into two parts: a control plane that performs complex calculations and weight adjustments, and a data plane that executes simplified forwarding decisions. The SDN controller handles the adaptability requirements by calculating optimal paths and weights, while individual network devices focus on executing the configured routing policies. This segmentation allows complex adaptive behavior without overloading individual network devices.
Solution Approach 2:
The patent introduces an SDN controller as an intermediary between network devices and the routing logic. The controller collects network state information, performs complex routing calculations, and distributes routing policies to network devices. This intermediary enables centralized management of dynamic conditions while keeping individual network devices relatively simple, as they only need to execute the controller's instructions.
3Device complexity
If ECMP routing is used during span failures, then device complexity remains low, but packet loss increases
Solution Approach 1:
The patent performs preliminary actions by pre-calculating alternative paths and adjusting routing weights before failures occur. The system continuously monitors link status and proactively adjusts weights to prevent congestion and packet loss. When failures are detected, the system has already prepared alternative routes, enabling rapid rerouting without complex real-time decision-making at network devices.
Data Source
AI summary
The following description is directed to managing a hierarchical network including one or more network zones. In one example, a method of managing a hierarchical network includes collecting network state from respective devices of a network zone; using the collected network state to build an aggregated topology of the network zone; and transmitting the aggregated topology of the network zone to a traffic engineering service.