Smart Edge MPC Control for Resource-Limited Building Equipment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building environmental control systems face challenges in maintaining comfortable conditions while minimizing costs, especially when resources such as computing power are limited, making it difficult to implement complex control systems effectively.
Innovation Solution
A smart edge controller that adjusts the complexity of optimization based on available processing resources, using sensor data to generate setpoints for building equipment, and optionally connects to a cloud system for enhanced control when resources allow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex control systems are implemented to optimize building environmental control, then cost optimization and comfort maintenance improve, but device complexity and computing resource requirements increase
Solution Approach 1:
The patent implements dynamic adaptation of MPC complexity by detecting available computing resources and automatically adjusting optimization parameters such as prediction horizon, control horizon, and model order. This allows the control system to maintain optimal performance while adapting to varying computational constraints in real-time.
Solution Approach 2:
The system changes operational parameters of the MPC algorithm based on available resources. When computing resources are abundant, more complex models and longer optimization horizons are used. When resources are limited, the system reduces model complexity and optimization depth, ensuring the control system remains functional across different device capabilities.
2Productivity
If complex optimization algorithms are used to generate setpoint trajectories, then cost function optimization improves, but processing resource consumption increases
Solution Approach 1:
The patent dynamically adjusts the complexity of optimization algorithms based on detected processing resources. The system monitors available computing power and memory, then adapts the MPC configuration accordingly - using simpler algorithms when resources are constrained and more sophisticated optimization when resources are abundant.
Solution Approach 2:
The system implements partial optimization by selectively reducing the optimization horizon or model complexity when resources are limited, rather than abandoning optimization entirely. This allows the system to perform simplified but still effective cost function optimization that consumes fewer processing resources while maintaining acceptable performance.
3Measurement precision
If full complexity model predictive control is implemented at edge devices, then control accuracy improves, but device complexity and resource requirements worsen
Solution Approach 1:
The patent enables edge devices to dynamically adapt the complexity of MPC implementations based on their specific computational capabilities. The system detects available resources and automatically configures the appropriate level of model complexity, prediction horizon, and optimization depth, allowing accurate control on resource-constrained devices.
Solution Approach 2:
The system applies different levels of MPC complexity to different building equipment or zones based on local resource availability. Each edge device can independently configure its MPC implementation to match its specific computational capabilities, allowing high accuracy where resources permit and acceptable performance where resources are constrained.
Data Source
AI summary
A smart edge controller for building equipment that operates to affect a variable state or condition within a building. The controller includes processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations including obtaining sensor data indicating environmental conditions of the building and include determining an amount of available processing resources at the smart edge controller or at the building equipment. The operations include automatically scaling a level of complexity of an optimization of a cost function based on the available processing resources and include performing the optimization of the cost function at the automatically scaled level of complexity to generate a first setpoint trajectory. The first setpoint trajectory includes operating setpoints for the building equipment at time steps within an optimization period. The operations include operating the building equipment based on the first setpoint trajectory.