Connection Selection via Evaluation Packets

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing communication devices face challenges in efficiently selecting the most suitable WAN network interfaces, access connections, or end-to-end connections for data packet transmission due to varying performance over time, which affects overall network performance and requires periodic re-evaluation to ensure optimal data transfer.

Innovation Solution

A method where evaluation packets are transmitted through multiple connections to determine performance, allowing for the selection of the best connection based on latency and other criteria, and data packets are routed through connections with lower latency to ensure efficient data transfer, with the option to aggregate connections for improved bandwidth.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple WAN interfaces and connections are available for data transmission, then bandwidth aggregation and network reliability are improved, but connection selection complexity and latency determination overhead increase

Engineering Contradiction:
Improvebandwidth aggregationVSAvoidconnection selection complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary latency evaluation by transmitting test packets through multiple connections before actual data transmission. This advance assessment establishes a performance baseline that guides subsequent connection selection, eliminating the need for complex real-time decision-making during data transfer.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors connection performance by transmitting evaluation packets and receiving feedback on latency and throughput. This feedback mechanism enables dynamic adjustment of connection selection strategies, allowing the system to adapt to changing network conditions without increasing operational complexity.

Inventive Principle:
Principle #23Feedback

2Reliability

If connection performance is re-evaluated periodically, then optimal data transmission paths are maintained, but network overhead and processing time increase

Engineering Contradiction:
Improveoptimal path maintenanceVSAvoidevaluation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system implements periodic evaluation of connection performance at predetermined intervals rather than continuously. This approach maintains optimal path selection while significantly reducing the processing overhead and time consumption associated with constant monitoring and re-evaluation.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system evaluates only a subset of connections periodically rather than all available connections continuously. By selecting representative samples for evaluation, the system maintains reliable path selection with minimized evaluation overhead and processing time.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If evaluation packets are transmitted through all connections, then accurate performance comparison is achieved, but network bandwidth consumption increases

Engineering Contradiction:
Improveperformance comparison accuracyVSAvoidbandwidth consumption
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The system transmits evaluation packets with different characteristics (size, protocol, payload type) through different connections based on their intended usage. This localized optimization ensures accurate performance measurement for specific traffic types while minimizing overall bandwidth consumption by not uniformly evaluating all connections with all packet types.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system transmits evaluation packets through only a subset of connections or uses reduced packet sizes for evaluation purposes. This partial action approach maintains sufficient measurement precision for connection comparison while significantly reducing the bandwidth consumption associated with comprehensive evaluation packet transmission.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS9602412B2Methods and systems for transmitting data packets
Publication Date: 2017.03.21 PISMO LABS TECH
  • US9602412B2 patent drawing
  • US9602412B2 patent drawing
  • US9602412B2 patent drawing

AI summary

The present invention discloses a method carried out by a first communications device for determining performance of a plurality of connections and selecting at least one first connection from the plurality of connections substantially based on performance. Data packets are then transmitted through the at least one first connection. The plurality of connections are aggregated to form an aggregated connection. The determining of performance is performed by transmitting evaluation packets through the plurality of connections. The evaluation packets are based on data packets that are received by the first communication device but have not yet been transmitted through the aggregated connection. The data packets may be designated for a host or node reachable through the aggregated connection. Alternatively, the evaluation packets may be based on predefined information when there are no data packets to be transmitted through the aggregated connection. The performance may be determined periodically.