Distributed Edge Analytics Architecture for Adaptive Industrial Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current industrial systems lack the capability for real-time predictive and prescriptive analytics close to the point of operation, especially in settings with limited network connectivity and noisy sensor data, and are not effective in generating actionable insights quickly enough to impact system performance optimally.
Innovation Solution
A distributed analytics system with an edge subsystem and an architect subsystem that deploys analytic models to edge processing devices, enabling predictive and prescriptive analytics on sensor data, and modifies these models based on real-time system responses to improve system performance, even in conditions with limited connectivity and noisy data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data is collected and analyzed through centralized network or cloud-based servers, then comprehensive data analysis capability is achieved, but latency increases and real-time responsiveness deteriorates
Solution Approach 1:
The system divides the centralized analytics architecture into distributed edge analytics nodes deployed throughout the industrial system. Each edge node performs local data analysis and control decisions, segmenting the monolithic centralized processing into multiple autonomous units that operate independently, thereby reducing latency while maintaining comprehensive analysis capability.
Solution Approach 2:
The patent introduces a new spatial dimension for data processing by deploying analytics capabilities at the edge of the network rather than concentrating them at the center. This dimensional shift from centralized to distributed architecture enables real-time processing at the source of data generation, eliminating the time delay associated with centralized processing.
2Measurement precision
If big data models are trained and deployed at the data center level, then accurate predictive analytics are achieved, but the system becomes detached from real-time operation and adaptability decreases
Solution Approach 1:
The system implements dynamic model deployment where analytics models are continuously updated and adapted at edge nodes based on real-time operational data. Rather than static models deployed from data centers, the edge analytics dynamically adjust to changing system conditions, maintaining both accuracy and adaptability through continuous learning and model refinement.
Solution Approach 2:
The patent incorporates feedback loops where edge analytics nodes continuously monitor system performance and use real-time data to refine their predictive models. This feedback mechanism enables the system to adapt to changing conditions while maintaining high predictive accuracy, as the models learn from actual operational outcomes and adjust accordingly.
3Speed
If PLC-based real-time control systems are used, then fast response time is achieved, but predictive and prescriptive analytics capability is lost
Solution Approach 1:
The system merges the real-time control capabilities of PLCs with advanced predictive analytics by integrating edge analytics nodes directly into the control architecture. This combination allows the system to maintain fast PLC-style response times while simultaneously performing sophisticated predictive and prescriptive analytics, eliminating the need to choose between speed and analytical capability.
Solution Approach 2:
The edge analytics nodes are designed to perform multiple functions simultaneously: real-time control decisions, predictive analytics, prescriptive recommendations, and data processing. This multi-functionality allows a single system component to provide both fast PLC-style control and advanced analytics capabilities, making the system universally capable of handling diverse operational requirements.
4Loss of information
If centralized data analysis is implemented, then comprehensive system insight is achieved, but network connectivity requirements increase and operational reliability in limited connectivity settings decreases
Solution Approach 1:
The patent extracts the essential analytics processing capability from the centralized network infrastructure and places it at distributed edge nodes. This extraction enables the system to maintain comprehensive system insight through local data analysis while reducing dependence on continuous network connectivity, as each edge node can independently process and analyze data even when disconnected from the central system.
Data Source
AI summary
Distributed analytics system used to control the operation of at least one monitored system; the system includes an architect subsystem and an edge subsystem, wherein the edge subsystem comprises at least one edge processing device associated with at least one monitored system. The architect subsystem deploys at least one analytic model to an edge processing device based on characteristics of a monitored system associated with the edge processing device, the analytic model to be used by the edge processing device to provide control signals to a monitored system; and, receives information related to the monitored system from the edge processing device, the information utilized by the architect subsystem to modify the analytic model deployed to the at least one edge processing device to improve system performance of the monitored system. An edge processing device receives an analytic model from the architect subsystem; provides control signals to the monitored system according to the analytic model; and, sends information related to the monitored system to the architect subsystem, the information to be used by the architect subsystem to modify the analytic model to improve system performance of the monitored system.