Digital Twin Control for Resource Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for managing resource consumption in physical environments, such as electric power, are labor-intensive and fail to account for the complexity of machines or processes, requiring skilled analysts and frequent updates when changes occur or when used in new contexts.
Innovation Solution
A computing technology that maintains environment information and sensor data to generate forecast data using machine-trained models, then creates a control plan to optimize resource usage in physical environments, leveraging local energy devices to reduce external resource consumption and minimize environmental impact, using a declarative-based solver component like mixed integer linear programming.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If custom logic is used to model a single machine or process, then control can be achieved, but the approach is labor-intensive and requires skilled analysts
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the physical system that captures its behavior and relationships. This digital model can be analyzed and controlled without requiring skilled analysts to manually model the physical system, reducing labor intensity while maintaining control capability.
Solution Approach 2:
The digital twin framework provides a universal modeling approach that can represent multiple machines, processes, and their interrelationships in a single integrated model. This eliminates the need for separate custom logic for each machine and enables automated analysis across the entire system.
2Ease of operation
If custom logic is used to model machines or processes, then control is possible, but the logic fails to adequately account for complexity
Solution Approach 1:
The digital twin framework nests multiple levels of detail and complexity within a unified model structure. It can represent individual components, subsystems, and the overall system simultaneously, capturing complex interrelationships that single-machine custom logic cannot adequately represent.
Solution Approach 2:
The patent adds the dimension of virtual/digital representation to the physical system, creating a two-dimensional view (physical + virtual) that enables comprehensive analysis of complex relationships without overwhelming the control logic with physical complexity.
3Ease of operation
If custom logic is used for controlling machines, then control can be implemented, but updating logic when changes occur is labor-intensive
Solution Approach 1:
The digital twin framework enables the system to automatically update its own model when changes occur in the physical environment. Sensors and data feeds continuously refresh the digital representation, eliminating the need for manual logic updates by skilled analysts.
Solution Approach 2:
The system continuously receives feedback from sensors and operational data, automatically updating the digital twin to reflect current system states and changes. This feedback loop enables adaptive control without requiring manual intervention to update the control logic.
4Device complexity
If narrow modeling of individual machines is used, then simple control logic can be created, but contextual information is ignored
Solution Approach 1:
The patent merges individual machine models into a comprehensive digital twin that captures not only each component's behavior but also their interrelationships and contextual factors. This unified model preserves contextual information while maintaining analytical simplicity through standardized representation.
Data Source
AI summary
A technique is described herein for using computing technology to intelligently manage the consumption of a resource in a physical environment and/or controlling the physical environment in other ways. The technique maintains environment information that describes entities within the physical environment, together with the relationships among the entities. The technique leverages the environment information and collected sensor data to generate forecast data using one or more machine-trained models. The technique then leverages the environment information, sensor data, and forecast data to generate a control plan. The control plan provides a strategy for controlling the physical environment that satisfies a specified optimization objective. In one use case, the technique contributes to the efficient consumption of power provided by a distribution system by avoiding consumption of power in periods in which the distribution system is expected to experience high loads.