HVAC Occupant Tolerance Learning for Demand Response Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building management systems struggle to efficiently manage and process data for HVAC systems, particularly in updating building conditions based on occupant responses and integrating artificial intelligence to generate optimal actions for HVAC operations.
Innovation Solution
A method involving processing circuits that update building conditions of HVAC systems, receive occupant responses, and train an AI model to generate actions for HVAC systems, including updating operating parameters, conditions, and occupancy schedules, using a generative large language model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional building management systems are used to manage HVAC systems, then the system structure is simple and easy to implement, but the system cannot efficiently process occupant responses and generate optimal HVAC actions
Solution Approach 1:
The patent introduces an AI model as an intermediary component between occupant response data and HVAC control actions. The AI model processes unstructured occupant feedback and converts it into structured control decisions, enabling efficient response processing without requiring complex direct integration between all system components.
Solution Approach 2:
The AI model is trained on historical occupant response data to autonomously generate HVAC control actions without requiring constant human intervention or complex rule-based programming. The system learns from past patterns and self-adjusts control strategies, reducing the need for manual system configuration and maintenance.
2Loss of energy
If AI models are integrated to generate optimal HVAC actions, then energy efficiency and occupant comfort are improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The AI model is trained in advance on historical occupant response data and HVAC performance information before deployment. This preliminary training phase allows the model to learn optimal control strategies offline, so that during actual operation, the system can quickly generate energy-efficient HVAC actions without requiring complex real-time computations.
Solution Approach 2:
The system continuously collects occupant responses to HVAC conditions and uses this feedback to retrain and refine the AI model. This closed-loop feedback mechanism allows the system to progressively improve energy efficiency by learning from actual occupant experiences and adjusting control strategies accordingly.
3Adaptability or versatility
If real-time occupant feedback is processed to update building conditions, then adaptability to occupant preferences is improved, but the data processing time and computational resources increase
Solution Approach 1:
The system processes occupant responses selectively based on priority and impact. Not all occupant feedback requires immediate full processing - the AI model identifies and prioritizes the most significant responses that warrant immediate HVAC adjustments, while less critical feedback can be processed during off-peak periods or aggregated with other data.
Data Source
AI summary
A building system of a building, the building system including one or more memory devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to update a building condition of an HVAC system of a space in a building at a time t1, wherein the building condition is updated from a default building condition. The instructions when executed by the one or more processors, cause the one or more processors to update the building condition of the space at a time t2 and receive an occupant response of an occupant from the space. The instructions when executed by the one or more processors, cause the one or more processors to update an artificial intelligence (AI) model based on the occupant response and generate, using the AI model, one or more actions for the HVAC system of a plurality of spaces.