Thermodynamic HVAC Modeling for Accurate Indoor Temperature Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current HVAC control systems face challenges in accurately predicting and managing the thermal environment of structures over time due to limitations in the accuracy of thermodynamic models used to characterize changes caused by HVAC system actuation.

Innovation Solution

The development of intelligent network-connected thermostats and thermodynamic models that utilize basis functions to characterize indoor temperature trajectories, incorporating factors like outdoor and indoor temperature differences, time of day, and energy changes, allowing for the generation and updating of thermodynamic models based on historical data to improve predictive accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional thermodynamic models based on structure size and window characteristics are used, then HVAC system sizing and control can be established, but the accuracy of predicting thermal environment changes over time is insufficient

Engineering Contradiction:
Improveaccuracy of thermodynamic modelVSAvoidcomplexity of thermodynamic model
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms the thermodynamic model from a static structure-based model to a dynamic model that incorporates time-varying parameters including outdoor temperature, indoor temperature, structural temperature, time of day, and HVAC actuation state. This allows the model to adapt to changing conditions and improve prediction accuracy without requiring a complete redesign of the modeling approach

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent implements continuous model updating using historical data from the structure's actual thermal response to HVAC actuation. The model learns from past performance and refines its predictions over time, creating a feedback loop that improves accuracy while maintaining a manageable model structure

Inventive Principle:
Principle #23Feedback

2Measurement precision

If simple regression models with limited parameters are used for thermal load forecasting, then the model remains computationally simple, but the accuracy in characterizing complex thermal trajectories is insufficient

Engineering Contradiction:
Improveaccuracy of temperature predictionVSAvoidcomplexity of prediction model
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the thermal response into distinct phases by introducing a 'current stage effect component' that characterizes different portions of the indoor temperature trajectory. This allows the model to handle the complexity of thermal dynamics through modular, manageable segments rather than attempting to model the entire trajectory as a single complex function

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from static regression models to dynamic models that explicitly account for time-varying conditions. The model incorporates temporal dynamics through time-of-day effects, sequential updates based on historical data, and stage-dependent parameters that evolve as the thermal response progresses

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP2987112B1Generating and implementing thermodynamic models of a structure
Publication Date: 2020.02.19 GOOGLE LLC
  • EP2987112B1 patent drawingFigure 1A
  • EP2987112B1 patent drawingFigure 1B
  • EP2987112B1 patent drawingFigure 2

AI summary

Apparatus, systems, methods, and related computer program products for generating and implementing thermodynamic models of a structure. Thermostats disclosed herein are operable to control an HVAC system. In controlling the HVAC system, a need to determine an expected indoor temperature profile for a particular schedule of setpoint temperatures may arise. To make such a determination, a thermodynamic model of the structure may be used. The thermodynamic model may be generated by fitting weighting factors of a set of basis functions to a variety of historical data including time information, temperature information, and HVAC actuation state information. The set of basis functions characterize an indoor temperature trajectory of the structure in response to a change in HVAC actuation state, and include an inertial carryover component that characterizes a carryover of a rate of indoor temperature change that was occurring immediately prior to the change in actuation state.