Network Device Utilization Analysis via Traffic Graphing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying underutilized network devices in complex data communications networks is challenging due to the complexity and cost of monitoring individual devices, and the lack of accurate inventory data, which hinders energy efficiency improvements in IT environments.
Innovation Solution
A method that utilizes network traffic data to create a graph representing connections between devices, filters out non-semantic connections, and analyzes islands of interconnected nodes to identify underutilized devices by associating traffic rate data with links outside the network, reducing the need for extensive monitoring and inventory maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual device monitoring is performed to track utilization, then device utilization can be measured, but the monitoring process becomes complex and time-consuming to set up
Solution Approach 1:
The patent uses network traffic data as an intermediary to indirectly measure device utilization. Instead of directly monitoring individual devices, the system analyzes traffic patterns and connection data that naturally flow through the network, using this intermediary data to infer utilization levels without complex monitoring infrastructure
Solution Approach 2:
The patent replaces complex mechanical monitoring systems with a simpler data analysis approach. Rather than deploying sophisticated monitoring agents on each device, the system substitutes this with analysis of existing network traffic data, which is already being collected for other purposes, thereby simplifying the overall system
2Measurement precision
If detailed analysis of IT inventory is performed to assess device utilization, then utilization can be evaluated, but maintaining an accurate inventory requires significant effort and expense
Solution Approach 1:
The system uses network traffic data that is naturally generated and collected by the network itself during normal operation. This self-service approach eliminates the need for separate inventory maintenance efforts, as the data is already being collected for network management purposes rather than requiring dedicated inventory management resources
3Ease of manufacture
If network traffic data is analyzed to identify underutilized devices, then device identification can be performed with minimal monitoring infrastructure, but the method requires processing and analyzing network data
Solution Approach 1:
The patent applies partial action by analyzing only the portions of network traffic data that are relevant to utilization assessment, such as connection establishment patterns and traffic flow characteristics, rather than processing every detail of network traffic. This selective analysis reduces processing requirements while maintaining effectiveness
Data Source
AI summary
A method, article of manufacture, and system for indicating underutilized network devices that provide services in a data communications network. The method includes: receiving network traffic data; filtering the network traffic data to eliminate data for predefined connections; producing, from the filtered network traffic data, a graph representing a connection between a first device and a second device within the data communications network; analyzing the graph to identify a set of interconnected nodes that is outside the data communications network; and indicating an underutilized network device by producing an output dependent on traffic rate data associated with a link to the identified set of interconnected nodes that is outside the data communications network.