Building Data Platform Using Digital Twins for Faster Analytics Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The development of AI and ML models for building systems is time-consuming due to the need for extensive data compilation and integration, requiring significant effort from developers.
Innovation Solution
A building data platform that includes a development platform enabling users to quickly design, develop, and deploy AI and ML models by querying a digital twin, allowing for data point selection, model training, and testing, with features like model templates, user interfaces, and resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If developers manually research and compile data points and generate AI/ML models from scratch, then model accuracy and reliability can be improved, but development time and complexity increase significantly
Solution Approach 1:
The system pre-compiles and organizes building data points, digital twins, and analytics templates before model development is needed. This preliminary preparation of data infrastructure allows developers to quickly build models without manual data compilation, reducing development time while maintaining model reliability through pre-validated data sources
Solution Approach 2:
The system provides pre-built analytics models and digital twins that can be copied and adapted for specific building applications. Instead of generating models from scratch, developers can replicate proven templates and customize them, significantly reducing development time while maintaining reliability through inheritance of validated model structures
2Reliability
If developers manually integrate generated AI/ML models with the building data platform, then model compatibility and system integration can be improved, but integration complexity and effort increase
Solution Approach 1:
The system creates a universal integration layer through the building data platform that can accommodate multiple AI/ML models and building systems through standardized interfaces. The platform's architecture supports various model types and data formats, reducing integration complexity while maintaining compatibility through unified communication protocols and data standards
Solution Approach 2:
The building data platform acts as an intermediary layer between AI/ML models and building systems. This mediator handles data translation, format conversion, and interface standardization, simplifying model integration while ensuring compatibility through centralized data management and standardized communication protocols
3Reliability
If comprehensive data points are collected for AI/ML model training, then model performance and accuracy can be improved, but data processing time and computational resources increase
Solution Approach 1:
The system extracts only the most relevant data points from the comprehensive building data set based on the specific analytics model requirements. By selectively extracting necessary features and parameters rather than processing all available data, the system maintains model performance while significantly improving data processing efficiency and reducing computational overhead
Solution Approach 2:
The system segments the comprehensive building data into organized categories and structures (digital twins, data points, analytics templates) that can be efficiently processed. This segmentation allows the system to retrieve and process only relevant data subsets for each model, improving processing efficiency while maintaining model performance through structured data organization
Data Source
AI summary
A building system can operate to receive an indication from a user device of a user to query a digital twin of one or more buildings, the digital twin including entities including buildings, equipment, spaces, or data of the one or more buildings, the equipment, or the spaces, the digital twin including relationships between the entities. The building system can operate to receive building data from the digital twin by querying the digital twin based on the indication received from the user device. The building system can operate to generate an analytics model based on the building data, wherein the analytics model is trained based on the building data and deploy the analytics model to operate based on data of the one or more buildings and generate one or more analytic results based on the data of the one or more buildings.