Adaptive IIoT Edge Provisioning for Context-Aware Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial Internet of Things (IIoT) edge nodes lack adaptability and intelligence, leading to inefficiencies and high maintenance costs due to the need for manual software updates and static analytics models, which fail to handle changing data patterns and context-aware functionality.
Innovation Solution
An adaptive edge platform that performs situation analysis to determine required changes in analytical models and functional blocks, automatically provisioning updated edge containers with micro containers including rules sets, complex domain expressions, and protocol decoders, enabling context-aware functionality and dynamic scaling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If IIoT edge nodes use fixed static analytics models and software, then device complexity is reduced and ease of manufacture is improved, but adaptability to changing data patterns and contexts deteriorates, requiring manual software updates and causing equipment downtime
Solution Approach 1:
The patent implements dynamic analytics models that automatically adapt to changing data patterns and contexts at the edge node. The system transitions from static, fixed software to dynamic, self-adjusting analytics models that can respond to varying industrial processes and data characteristics without manual intervention, thereby improving adaptability while managing complexity through automated mechanisms
Solution Approach 2:
The edge node incorporates self-service capabilities through automated model selection and adaptation mechanisms. The system automatically detects changes in data patterns, selects appropriate analytics models, and adjusts its behavior without requiring manual software updates or human intervention, enabling the edge node to serve itself in adapting to changing conditions
2Adaptability or versatility
If manual software updates are performed on edge nodes, then adaptability to new functions is improved, but productivity deteriorates due to substantial manual effort and equipment downtime
Solution Approach 1:
The system implements automated software update and model deployment mechanisms at the edge node. The edge node automatically receives, validates, and deploys new analytics models and software updates without requiring manual intervention, thereby maintaining high adaptability to new functions while eliminating productivity losses associated with manual updates and equipment downtime
Solution Approach 2:
The patent employs preliminary action by pre-configuring and pre-validating analytics models and software updates before deployment to the edge node. The system prepares update packages in advance, validates their compatibility, and stages them for deployment, enabling seamless updates that minimize downtime and maintain continuous productivity while improving adaptability
3Reliability
If data is sent to the cloud for analytics, then analytics capabilities are improved, but loss of energy increases due to heavy bandwidth utilization
Solution Approach 1:
The patent implements local quality by deploying analytics capabilities directly at the edge node rather than relying solely on cloud-based analytics. The edge node performs context-aware analytics locally on industrial data, processing and analyzing data where it is generated. This local processing reduces the need to transmit large volumes of data to the cloud, thereby maintaining reliable analytics capabilities while significantly reducing bandwidth utilization and associated energy losses
Solution Approach 2:
The system segments analytics functions between the edge node and the cloud. Routine, context-aware analytics are performed locally at the edge node, while only aggregated results, anomalies, or data requiring advanced cloud-based analysis are transmitted to the cloud. This segmentation of analytics responsibilities maintains comprehensive analytics capability while minimizing the energy-consuming data transmission to the cloud
Data Source
AI summary
Computer-implemented methods for configuring an Industrial Internet of Things (IIoT) edge node in an IIoT network to perform one or more functions, comprising: performing a situation analysis to determine a required change in one or more of an analytical model, a runtime component, and a functional block of the IIoT edge node based on a change in the one or more functions; and automatically provisioning a new or updated functional module to the IIoT edge node, based on the situation analysis, the new or updated functional module including one or more components, wherein each component includes at least one of a rules set, a complex domain expression with respect to a process industry, an analytical model, and a protocol decoder.