MPLS Packet Prediction via OAM Messaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
MPLS networks face challenges in efficiently managing packet flow due to limited cache memory, which affects bandwidth and routing speed, especially in the absence of comprehensive OAM monitoring and prediction mechanisms.
Innovation Solution
Implementing a packet prediction learning algorithm in MPLS switches that generates and communicates packet prediction information via OpenFlow and OAM messages to preload packet flow data in high-speed memory, reducing the need for frequent access to lower-speed memory and optimizing routing speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the entire flow table is stored in lower speed memory, then memory capacity is sufficient, but routing speed is reduced due to frequent access to lower speed memory
Solution Approach 1:
The patent applies preliminary action by predicting future packet flows and pre-loading corresponding flow table entries into high-speed cache memory before they are actually needed. The packet prediction algorithm analyzes historical flow patterns and proactively loads anticipated flows into the fast memory buffer, allowing the switch to process packets at high speed without waiting for slow memory access. This resolves the contradiction by preparing data in advance, enabling both sufficient memory capacity and high routing speed.
2Speed
If flow entries are loaded from lower speed memory to high speed local memory, then routing speed improves, but bandwidth is reduced due to the time required for memory transfer
Solution Approach 1:
The system performs preliminary action by predicting which flow entries will be needed soon and pre-loading them into high-speed cache memory during periods of low packet arrival rate. This allows the switch to maintain high routing speed when packets arrive without experiencing bandwidth reduction from frequent memory transfers. The prediction algorithm identifies optimal moments to load flow entries proactively, decoupling routing speed from bandwidth consumption.
Solution Approach 2:
The patent implements self-service by having the switch autonomously generate packet prediction information and automatically load flow entries into cache memory without external intervention. The switch monitors its own packet flows, predicts future needs, and manages its own memory loading, eliminating the need for continuous external control and reducing overhead that would otherwise limit bandwidth efficiency.
3Productivity
If packet prediction information is communicated to multiple switches, then routing optimization improves, but device complexity increases due to coordination requirements
Solution Approach 1:
The patent introduces an intermediary mechanism where the switch generates packet prediction information and communicates it to the controller, which then distributes instructions to other switches. This intermediary approach simplifies coordination by centralizing the decision-making logic in the controller, which handles the complexity of synchronizing prediction information across multiple switches. The controller acts as a mediator that manages the communication overhead and coordination requirements, allowing routing optimization without proportionally increasing device complexity at individual switches.
Data Source
AI summary
A first switch in a MPLS network receives a plurality of packets that are part of a pair of flows. The first switch performs a packet prediction learning algorithm on the first plurality of packets and generates packet prediction information that is communicated to a second switch within the MPLS network utilizing an Operations, Administration, and Maintenance (OAM) packet (message). In a first example, the first switch communicates a packet prediction information notification to a Network Operations Center (NOC) that in response communicates a packet prediction control signal to the second switch. In a second example, the first switch does not communicate a packet prediction information notification. In the first example, the second switch utilizes the packet prediction control signal to determine if the packet prediction information is to be utilized. In the second example, second switch independently determines if the packet prediction information is to be used.