Edge-Cloud Data Processing Allocation for Manufacturing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing smart manufacturing solutions face limitations in data processing capacity and connectivity on the factory floor, leading to incomplete data analysis and potential disruptions during mission-critical processes due to environmental challenges and connectivity issues.
Innovation Solution
A system that dynamically allocates data processing between edge devices and cloud platforms based on resource availability, data type, user preferences, and parameters such as computational load and network behavior, allowing for flexible processing of manufacturing data either locally or remotely.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is processed on the factory floor using local computing resources, then processing speed and real-time responsiveness are improved, but the amount of data that can be processed is limited due to resource constraints
Solution Approach 1:
The patent segments data processing functions into two categories: real-time processing at the edge device for immediate responsiveness, and batch processing at the cloud platform for handling large volumes of historical data. This segmentation allows the system to simultaneously achieve fast processing speeds for critical operations and the capacity to process extensive datasets for comprehensive analysis.
2Quantity of substance
If data is processed using cloud platforms, then the amount of data that can be analyzed is increased, but connectivity disruptions may prevent mission-critical data processing
Solution Approach 1:
The system performs preliminary action by pre-configuring the edge device with local processing capabilities and caching mechanisms. When connectivity is available, the edge device processes data locally and caches results. When connectivity is lost, the cached data and local processing capabilities enable continuous operation, ensuring mission-critical processes are not interrupted by cloud connectivity disruptions.
3Productivity
If more computing resources are deployed on the factory floor, then data processing capacity is improved, but environmental challenges such as dirt and robustness requirements increase system complexity
Solution Approach 1:
The patent extracts heavy computational tasks and resource-intensive processing functions from the edge device and relocates them to the cloud platform. This extraction allows the edge device to maintain a simpler, more robust design suitable for factory floor environmental conditions, while still achieving high data processing capacity through the cloud's powerful computing resources.
4Loss of time
If data is processed in real-time at the edge device, then latency is reduced, but the complexity of managing distributed processing functions increases
Solution Approach 1:
The system implements feedback mechanisms where the edge device continuously monitors data processing requirements, connectivity status, and performance metrics. Based on this feedback, the system dynamically adjusts the distribution of processing tasks between edge and cloud, optimizing for low latency when possible while managing the complexity of distributed processing through automated decision-making based on real-time conditions.
Data Source
AI summary
Embodiments described herein relate to a system for processing manufacturing data, comprising: an edge device; a cloud platform; a sensing device configured to collect manufacturing data and to provide the collected data to the edge device; wherein the edge device and the cloud platform are each configured to carry out a plurality of data processing functions on the manufacturing data; the system further comprising a resource manager configured to communicate with the edge device and with the cloud platform, wherein the resource manager is further configured to: determine whether each of the plurality of data processing functions is to be carried out at the edge device or at the cloud platform; if it is determined that the plurality of data processing functions is to be carried out at the edge device, instruct the edge device to carry out the plurality of data processing functions; if it is determined that the plurality of data processing functions is to be carried out at the cloud platform, instruct the cloud platform to carry out the plurality of data processing functions; and if it is determined that at least one of the plurality of data processing functions is to be carried out at the edge device and at least one other data processing function is to be carried out at the cloud platform, instruct the edge device to carry out the at least one of the plurality of data processing functions and instruct the cloud platform to carry out the at least one other data processing function.