Edge Facility Analytics With Source-Level Data Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing facility analytics systems struggle to effectively gather, interpret, and utilize data from various sources, leading to inefficiencies in energy management, maintenance, and cost optimization due to the complexity and volume of data.
Innovation Solution
A computer-based system that tags building automation system (BAS) points with unique identifiers and semantic labels, using machine learning algorithms to analyze dynamic data, provide real-time reporting, predictive maintenance, and automate energy management, while integrating with cloud-based platforms for scalable data storage and visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data from facility is gathered through various techniques to improve analytics capability, then the quantity and variety of data increases, but the difficulty to gather and interpret the data increases
Solution Approach 1:
The patent introduces an intermediary processing layer that receives data from multiple facility sources (sensors, building automation systems, equipment) and automatically tags, standardizes, and organizes the data. This intermediary system handles the complexity of data gathering and interpretation, allowing the core analytics system to work with pre-processed, tagged data without directly dealing with the raw complexity of multiple data sources.
Solution Approach 2:
The system implements self-service through automated data tagging and classification mechanisms that autonomously organize incoming data without requiring manual intervention. The automated tagging system assigns metadata labels to data points based on their source, type, and characteristics, enabling the system to self-organize and interpret data structures.
2Productivity
If existing facility analytics systems are used to manage facility data, then basic analytics are provided, but efficiency in energy management, maintenance, and cost optimization is insufficient
Solution Approach 1:
The system implements feedback mechanisms where tagged facility data is continuously analyzed and fed back to operational systems. This enables real-time adjustments in energy management, predictive maintenance alerts based on equipment performance patterns, and cost optimization recommendations. The feedback loop connects data collection with actionable insights that directly improve facility management efficiency and reduce energy waste.
3Loss of information
If more data is collected from facility sources, then better analytics insights can be obtained, but the complexity of data processing increases
Solution Approach 1:
The patent segments the data processing system into distinct functional modules: data collection from multiple sources, automated tagging and classification, data storage, and analytics processing. Each module handles specific aspects of data management independently, reducing overall system complexity while maintaining complete information processing. The segmentation allows parallel processing and independent optimization of each data handling stage.
Data Source
AI summary
A network edge device includes a local network interface, a remote network interface, a memory and a processor. The local network interface receives data from local data sources over a local network. The remote network interface communicates with a remote computer over a remote network. The processor receives a filter parameter set for each local data source from the remote computer. Each filter parameter set includes a data rate parameter and at least one of a minimum threshold parameter, a maximum threshold parameter or a change-of-value (COV) parameter. For each local data source, the processor compare each data value received from the local data source to at least one of the filter parameters, and sends the data value and subsequent data values to the remote computer at a data rate that is based on the data rate parameter.