Digital Twin Policy Learning for Adaptive Building Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The development and deployment of analytic and control applications for building systems are time-consuming and lack flexibility to adapt to changing circumstances, as they require significant software development and are not optimized for managing and processing building data effectively.
Innovation Solution
A building system that utilizes a digital twin to create a policy function by selecting entities, inputs, and actions, performing optimizations, and deploying them within the digital twin to control environmental conditions, with the ability to generate combinations of inputs and actions and use simulation models to optimize for objectives like occupant comfort and energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional analytic and control applications are developed and deployed for building systems, then the building can operate with control functionality, but the development and deployment process becomes time-consuming and requires significant software development effort
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the building that includes pre-configured policy functions, entities, and relationships. Instead of developing control applications from scratch for each building, the system copies and adapts proven policy functions from the digital twin, dramatically reducing development time while maintaining control functionality.
Solution Approach 2:
The digital twin is populated with policy functions, entities, and relationships in advance before actual deployment. The optimization process pre-selects and pre-configures the appropriate policy functions and their parameters based on building characteristics, so that when the application is deployed to the actual building, the control functionality is already prepared and requires minimal additional configuration.
2Reliability
If traditional analytic and control applications are used in building systems, then control operations can be performed, but the system lacks flexibility to adapt to changing circumstances
Solution Approach 1:
The patent implements dynamic policy functions that can automatically adjust their behavior based on changing building conditions. The optimization process continuously evaluates building data and adapts the policy function parameters and selections to match current circumstances, enabling the system to remain flexible and responsive while maintaining reliable control operations.
Solution Approach 2:
The system incorporates feedback loops where building data is continuously monitored and fed back into the optimization process. This feedback enables the digital twin to learn from actual building performance and adjust policy functions accordingly, improving adaptability to changing circumstances while maintaining stable control operations.
3Ease of operation
If comprehensive analytic and control applications are deployed to manage all building equipment and data, then complete control capability is achieved, but the system complexity increases significantly
Solution Approach 1:
The patent segments the building control system into discrete, modular policy functions, each responsible for specific control tasks. The digital twin organizes entities and relationships in a structured hierarchy, allowing the system to manage complexity by breaking down comprehensive control capabilities into manageable, independently configurable units that can be selectively applied.
Solution Approach 2:
The patent creates universal policy functions that can be applied across multiple building entities and scenarios. These policy functions are designed to be multi-functional, capable of handling different control situations through parameter adjustment rather than requiring separate custom applications for each control need, thereby reducing overall system complexity.
Data Source
AI summary
A building system of a building operates to select an instance of one or more entities of one or more particular entity types from a digital twin of the building for creating a policy function, the digital twin including representations of entities of the building and relationships between the entities of the building. The building system operates to perform an optimization that selects one or more inputs of inputs associated with the one or more entities for input to the policy function, selects one or more actions of actions associated with the one or more entities that are outputs of the policy function, and identifies one or more parameters for the policy function. The building system operates to deploy the policy function for the one or more entities by causing the digital twin to include the policy function.