Edge Computing Layer for Real-Time Industrial Sensor Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional cloud computing infrastructure is inadequate for handling the vast amounts of data generated by industrial machines due to latency, bandwidth, and cost issues, as well as the need for real-time decision-making and predictive maintenance in industrial settings.
Innovation Solution
The implementation of an edge computing platform that processes and analyzes data closer to the source using a software layer hosted on gateway devices or embedded systems, enabling real-time analytics and automated responses through a highly expressive computer language and a complex event processing engine, while also allowing data to be published to the cloud for further machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is sent to cloud storage for processing, then centralized data management is achieved, but latency increases and real-time decision making is compromised
Solution Approach 1:
The system segments data processing functions between edge devices and cloud infrastructure. Edge devices perform local real-time processing of sensor data, while cloud systems handle aggregate analytics and long-term storage. This segmentation enables real-time decisions at the edge without waiting for cloud processing, eliminating latency while maintaining centralized management capabilities.
Solution Approach 2:
The patent introduces an edge computing layer as an intermediary between sensor devices and cloud storage. This intermediate layer processes data locally before sending results to the cloud, acting as a mediator that enables real-time processing while reducing the data transmission burden to cloud systems.
2Reliability
If all sensor data is transmitted to cloud storage, then comprehensive data analysis is enabled, but bandwidth requirements increase and costs become prohibitive
Solution Approach 1:
The system extracts and processes data locally at edge devices, extracting only essential insights and aggregated results for transmission to the cloud. This extraction approach enables comprehensive analysis capabilities while minimizing bandwidth consumption by transmitting only processed findings rather than raw sensor data.
Solution Approach 2:
Instead of transmitting all sensor data to the cloud, the system performs partial processing at the edge, sending only a subset of processed data to cloud systems. This partial action approach maintains comprehensive analysis capability while significantly reducing bandwidth requirements.
3Productivity
If data is processed at the edge, then real-time analytics are enabled, but device complexity increases
Solution Approach 1:
The patent employs containerized applications that can be deployed across diverse edge devices, providing universal real-time analytics capabilities. These multi-functional containers enable various processing tasks on standard hardware, reducing the complexity burden on individual devices while maintaining high productivity.
Solution Approach 2:
The system uses containerization to create portable, copyable units of processing functionality. These standardized containers can be replicated across multiple edge devices, enabling real-time analytics without requiring complex custom implementations on each device.
4Productivity
If cloud infrastructure is used, then economies of scale are achieved, but distance from physical operations reduces responsiveness
Solution Approach 1:
The patent adds a spatial dimension to the computing architecture by deploying edge devices physically close to industrial operations. This dimensional change enables local real-time processing without sacrificing cloud connectivity, effectively reducing the operational distance while maintaining centralized management benefits.
Data Source
AI summary
A method for enabling intelligence at the edge. Features include: triggering by sensor data in a software layer hosted on either a gateway device or an embedded system. Software layer is connected to a local-area network. A repository of services, applications, and data processing engines is made accessible by the software layer. Matching the sensor data with semantic descriptions of occurrence of specific conditions through an expression language made available by the software layer. Automatic discovery of pattern events by continuously executing expressions. Intelligently composing services and applications across the gateway device and embedded systems across the network managed by the software layer for chaining applications and analytics expressions. Optimizing the layout of the applications and analytics based on resource availability. Monitoring the health of the software layer. Storing of raw sensor data or results of expressions in a local time-series database or cloud storage.