Edge Data Federation for Telemetry Bandwidth Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data communication networks face strain due to redundant telemetry data transmission, which consumes bandwidth and power, leading to reduced performance and increased resource burden, especially as the number of connected devices increases.
Innovation Solution
Client systems tag telemetry data as 'passthrough' or 'federatable', with edge devices federating redundant data into a smaller, optimized federated data set, and backend systems analyze both types to optimize network operations and resource allocation using AI/ML mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all telemetry data is transmitted to the backend system for analysis, then complete data availability for network optimization is achieved, but network bandwidth and power consumption increase significantly
Solution Approach 1:
The patent segments telemetry data into two distinct categories: federatable data (redundant, can be processed at edge) and passthrough data (unique, requires backend processing). This segmentation allows the system to apply different handling strategies to different data types, transmitting only necessary data to the backend while processing redundant data locally at edge devices, thereby reducing overall data transmission volume and energy consumption.
Solution Approach 2:
The patent extracts and removes redundant information from the telemetry data stream at the edge devices through federation processing. By identifying and eliminating duplicate data before transmission, the system extracts only the essential unique information that requires backend analysis, significantly reducing the volume of data that needs to be transmitted across the network and consumed in terms of bandwidth and power.
2Adaptability or versatility
If telemetry data volume increases with more connected devices, then network coverage and data diversity improve, but network performance and resource efficiency deteriorate
Solution Approach 1:
The patent merges redundant telemetry data from multiple client systems at the edge devices through a federation process. Instead of allowing each device to transmit its data independently to the backend, edge devices combine and deduplicate data streams, merging redundant information into a single processed output. This approach maintains comprehensive network coverage by accepting data from all devices while improving performance by reducing the total volume of data requiring backend processing.
3Loss of information
If redundant telemetry data is transmitted across the network, then data completeness is maintained, but bandwidth consumption and power usage increase
Solution Approach 1:
The patent introduces edge devices as intermediary components between client systems and the backend system. These intermediaries perform federation processing on telemetry data, identifying and removing redundant information before data reaches the backend. The edge devices act as intelligent mediators that preserve data completeness by ensuring all unique information is captured while eliminating duplicate transmissions, thereby reducing overall data traffic volume without sacrificing information integrity.
Data Source
AI summary
A data communication network includes client systems and an edge device. The client systems each provide telemetry data to the data communication network, tags a first portion of the telemetry data with first metadata, and tags a second portion of the telemetry data with second metadata. The first metadata indicates that the first portion is passthrough data, and the second metadata indicates that the second portion is federatable data. The edge device receives the federatable data from each of the client systems, federates the federatable data into federated data, and provides the federated data. The federated data is of a smaller quantity than the received federatable data. The backend system receives the passthrough data from the client systems, receives the federated data from the edge device, analyzes the passthrough data and the federated data, and configures the data communication network based upon the analysis.