Route Optimization Engine for Internet Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current routing protocols like BGP do not guarantee optimal performance for routing traffic from multi-homed locations or data centers, as they rely on metrics such as AS_PATH length without considering actual path performance.
Innovation Solution
A route optimization engine that uses linear programming to determine the best performance route by considering cost, capacity, demand, and utilization, incorporating performance data and user-defined constraints to maximize performance values for each network prefix.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If BGP routing protocols use AS_PATH length as the key criterion for route selection, then routing decisions are made based on a simple and standardized metric, but the actual path performance (latency, loss, etc.) is not considered
Solution Approach 1:
The patent introduces an intermediary optimization engine that sits between the BGP routing protocol and the actual traffic flow. This engine collects performance data from multiple sources, processes it through linear programming optimization, and generates optimized routing decisions that override or supplement standard BGP decisions, thereby mediating between simple protocol operation and complex performance requirements
Solution Approach 2:
The system implements feedback mechanisms by continuously collecting actual path performance data (latency, packet loss, utilization) and using this information to dynamically adjust routing decisions. The optimization engine processes this feedback data through linear programming to determine the best routes, creating a closed-loop system where performance information directly influences routing choices
2Reliability
If a routing system considers multiple factors (cost, capacity, demand, performance) to determine optimal routes, then routing performance is maximized, but the complexity of the routing system increases
Solution Approach 1:
The patent replaces complex mechanical or heuristic routing decision-making processes with a mathematical optimization system based on linear programming. Instead of using multiple separate mechanisms to handle different routing factors, the system substitutes them with a unified mathematical model that processes cost, capacity, demand, and performance data through algebraic equations and constraints, achieving optimization through computation rather than complex system architecture
Solution Approach 2:
The system manages complexity by dynamically adjusting parameters within the linear programming model rather than changing the fundamental system structure. By modifying input parameters (performance data, cost metrics, capacity values, demand estimates) and re-running the optimization calculation, the system adapts to changing network conditions without requiring structural modifications to the routing architecture
3Speed
If BGP guarantees the shortest path route to reach the destination, then routing efficiency in terms of hops is improved, but the route may not be optimal in terms of actual performance metrics
Solution Approach 1:
The patent transforms static BGP routing tables into dynamic routing decisions by continuously updating the linear programming optimization with current performance data. The system adapts routing choices in real-time based on changing network conditions, making the routing system flexible and responsive rather than fixed and rigid, allowing it to balance speed and performance optimality dynamically
Data Source
AI summary
A deterministic approach for route selection in the Internet and other multi-homed networks is presented that is based upon a mathematical model that takes into consideration performance and costs while satisfying commitment constraints. The approach is expressed with a linear programming formulation that can be solved with conventional linear programming solver software. Performance metrics can be defined and combined in order to achieve the best route selection depending on requirements. Some of the potential benefits of the approach include: a global optimal solution for routing traffic (using metrics such as performance, cost, and other constraints), a dynamic weight assignment for performance metrics, and a flexible problem definition to add routing rules (e.g. static and restricted routes) to the model.