Hybrid Traffic Flow Simulation for Dynamic Bandwidth Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional flow propagation analysis techniques are unsuitable for determining flows in networks with dynamic bandwidth links, such as contention-based wireless links, due to variable bandwidth allocation and interference from neighboring links, which complicates the prediction of effective throughput.

Innovation Solution

A method and system that simulate traffic flow at the OSI network layer for fixed bandwidth links and at the discrete-packet level for dynamic bandwidth links, processing discrete-packet reception events to determine effective bandwidth and allocation among individual flows, allowing for accurate reconstruction of traffic flow parameters and simulation across links.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional flow propagation analysis techniques are used, then analysis speed is maintained, but accuracy of flow prediction in networks with dynamic bandwidth links deteriorates

Engineering Contradiction:
Improveflow prediction accuracyVSAvoidsimulation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The network links are segmented into two distinct categories: fixed bandwidth links and dynamic bandwidth links. This segmentation allows the simulation to apply different modeling approaches to each type, using conventional flow propagation for fixed links and packet-level simulation for dynamic links, thereby improving overall accuracy without uniformly increasing complexity across the entire network.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The simulation model dynamically adapts its complexity based on link characteristics. For dynamic bandwidth links where accuracy is critical, the model employs packet-level simulation that captures variable bandwidth and interference effects. For fixed bandwidth links, the simpler conventional flow propagation is used. This dynamic approach to modeling resolves the contradiction by applying complexity only where necessary.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If packet-level simulation is used for dynamic bandwidth links, then flow prediction accuracy improves, but computational complexity increases

Engineering Contradiction:
Improveeffective throughput prediction accuracyVSAvoidsimulation computation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The network is segmented into regions requiring packet-level simulation (dynamic bandwidth links) and regions where conventional flow propagation suffices (fixed bandwidth links). This segmentation limits the computational burden of packet-level simulation to only those portions of the network where dynamic bandwidth effects occur, rather than applying it universally, thus reducing overall computation time while maintaining accuracy where needed.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different simulation qualities are applied locally based on link characteristics. Packet-level simulation with high computational detail is applied locally at dynamic bandwidth links where accuracy is critical, while conventional flow propagation is used elsewhere. This local quality approach ensures high prediction accuracy for effective throughput at dynamic links without incurring the computational cost across the entire network.

Inventive Principle:
Principle #3Local quality

3Productivity

If conventional flow propagation analysis is used, then computational efficiency is maintained, but ability to handle variable bandwidth and interference effects deteriorates

Engineering Contradiction:
Improveanalysis efficiencyVSAvoidhandling of dynamic bandwidth conditions
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The simulation model dynamically switches between two operational modes: conventional flow propagation for fixed bandwidth links and packet-level simulation for dynamic bandwidth links. This dynamic adaptability allows the system to maintain computational efficiency for the majority of fixed links while accurately capturing variable bandwidth and interference effects at dynamic links, resolving the contradiction between efficiency and adaptability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The hybrid simulation model serves multiple functions: it performs conventional flow propagation analysis for fixed bandwidth links and packet-level analysis for dynamic bandwidth links within a unified framework. This multi-functionality allows the system to maintain computational efficiency for standard cases while adapting to handle dynamic bandwidth conditions when required, improving versatility without sacrificing overall efficiency.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS9253045B2Modeling and simulating flow propagation in dynamic bandwidth systems
Publication Date: 2016.02.02 RIVERBED TECH LLC
  • US9253045B2 patent drawing
  • US9253045B2 patent drawing
  • US9253045B2 patent drawing

AI summary

In a network that includes static bandwidth and dynamic bandwidth links, traffic flow at the OSI network layer is simulated at a traffic-flow level at interfaces to fixed bandwidth links, and simulated at a discrete-packet level at interfaces to dynamic bandwidth links. The resultant discrete-packet reception events at the receiving interface(s) of the dynamic bandwidth link are processed to determine the effective bandwidth/throughput of the link, as well as the allocation of this bandwidth among the individual flows through the link. The discrete-packet level receptions are used to reconstruct the parameters of the traffic flow at the network layer of the receiving interface, and this determined traffic flow is simulated accordingly at the next link, depending upon whether the next link is a static or dynamic bandwidth link.