Dynamic Link Aggregation for Heterogeneous Packet Flows

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing link aggregation methods face challenges in balancing throughput and latency requirements for heterogeneous applications, often requiring a compromise that may not meet the performance objectives of all applications simultaneously.

Innovation Solution

A dynamic link aggregation system that applies different aggregation policies on a per-packet flow basis, allowing for flexible configuration to meet specific throughput or latency requirements of each application, with the ability to adapt these policies in real-time as conditions change.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If an aggregation policy maximizes throughput by using multiple communication links in parallel, then the aggregate transmission capacity increases, but the latency increases due to packet reordering requirements

Engineering Contradiction:

Improveaggregate transmission capacityVSAvoidend-to-end latency

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent segments packet flows into different categories (real-time vs. non-real-time) and applies different aggregation policies to each segment. Real-time flows use per-flow replication for low latency, while non-real-time flows use load balancing for maximum throughput, thus resolving the contradiction by not applying a single policy to all traffic

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different aggregation policies are applied to different packet flows based on their specific requirements. The system determines quality parameters for each flow and selects appropriate policies (replication for latency-sensitive, load balancing for throughput-sensitive), making the system adaptable to local flow characteristics rather than using a uniform approach

Inventive Principle:

Principle #3Local quality

2Loss of time

If an aggregation policy uses redundant packet transmissions to minimize latency, then the latency decreases, but the maximum throughput is reduced

Engineering Contradiction:

ImprovelatencyVSAvoidmaximum throughput

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The system applies replication (excessive action) only to real-time flows that require it, while using efficient load balancing for non-real-time flows. This partial application of redundancy only where needed resolves the contradiction by avoiding unnecessary replication that would reduce overall throughput

Inventive Principle:

Principle #16Partial or excessive action

3Device complexity

If a single aggregation policy is applied to all packet flows, then the system complexity is reduced, but the ability to meet heterogeneous application requirements is compromised

Engineering Contradiction:

Improveaggregation policy configurationVSAvoidperformance requirement satisfaction

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system changes parameters such as replication factor, load balancing weights, and policy selection based on flow characteristics and quality parameters. This dynamic parameter adjustment allows the system to adapt to heterogeneous requirements without implementing entirely different policies, thus managing complexity while maintaining versatility

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8717885B2Link aggregation methods and devices

Publication Date: 2014.05.06 MUSHROOM NETWORKS INC

AI summary

A method of aggregating a plurality of packet based communication channels is provided by the system. The communication channels connect two common endpoints, and aggregation devices are present at each point to implement an aggregation policy. The system provides a dynamic aggregation system where an aggregation policy is employed on a per packet flow basis. Packet flow can be classified by application type, so that an appropriate aggregation policy can be used for packets belonging to the flow. The selected aggregation policy is used for each flow within the aggregation devices at each endpoint.