Decoupled modeling methods and systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for forecasting the ON/OFF status of thermostatically controlled appliances (TCAs) like HVAC units are inaccurate due to unforeseeable factors such as construction material variations and lack of high-resolution sub-metered data, leading to inefficiencies in energy management and demand response programs.
Innovation Solution
A data-driven, decoupled equivalent thermal parameter (ETP) model processor is used to derive thermal resistance (R), capacitance (C), and heat flow (Q) parameters by processing power consumption data into activated and non-activated time cycles, minimizing errors and adjusting for outdoor temperature variations to improve energy parameter estimation and reduce total energy load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If physics-based methods are used to model house thermal dynamics in detail, then model completeness is improved, but manufacturing precision deteriorates due to unforeseeable factors like construction material variations and tree covers
Solution Approach 1:
The patent transitions from physics-based parameters (material thickness, thermal conductivity, construction details) to data-driven parameters (thermal resistance R, capacitance C, heat flow Q) that are derived from actual power consumption measurements. This parameter transformation allows the model to adapt to real-world variations without requiring precise knowledge of construction details, thereby resolving the contradiction between model completeness and accuracy.
Solution Approach 2:
The patent replaces the physics-based mechanical modeling approach with a data-driven statistical approach. Instead of using differential equations based on physical principles, the system uses machine learning algorithms to learn thermal dynamics patterns from historical power consumption data, substituting mechanical modeling with empirical pattern recognition to achieve better accuracy despite unforeseeable factors.
2Adaptability or versatility
If data-driven methods are used to derive ETP parameters from power consumption data, then adaptability is improved, but measurement precision deteriorates due to lack of high-resolution sub-metered data
Solution Approach 1:
The patent performs preliminary data processing by aggregating power consumption data into thermal cycles (heating/cooling cycles) before parameter estimation. This preliminary action transforms raw, noisy power consumption data into meaningful thermal patterns, enabling accurate parameter derivation even from low-resolution data. The system prepares the data in advance to make it suitable for robust parameter estimation.
Solution Approach 2:
The patent introduces thermal cycle detection as an intermediary step between raw power consumption data and ETP parameter estimation. This intermediary process identifies heating and cooling cycles, extracts relevant features, and transforms the data into a form that is more amenable to accurate parameter estimation, thereby bridging the gap between low-resolution input data and high-precision parameter requirements.
3Productivity
If decoupled modeling is used to separate daytime and nighttime parameters, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent segments the thermal modeling into distinct daytime and nighttime models with separate parameter sets. This segmentation allows each model to capture the specific thermal dynamics characteristics of its respective period, improving overall model accuracy and energy management productivity. The system divides the complex 24-hour thermal behavior into manageable segments that can be independently optimized and managed.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
A decoupled ETP model processor is configured to store power consumption data retrieved from power systems; convert the power consumption data into power activated time cycles and power non-activated time cycles; derive a thermal resistance (R) parameter and a capacitance (C) parameter for a predetermined heat flow (Q) parameter at each of the outdoor temperatures; compare the converted power activated time cycles to the actual power activated time cycles; compare the converted power non-activated time cycles to the actual power non-activated time cycles; calculate a first improved resistance-capacitance-heat flow (RCQ) parameter set and a respective first outdoor temperature for the compared and converted power activated time cycles to the actual power activated time cycles; calculate the Q parameter at each outdoor temperature during the power activated time cycles; and calculate the R parameter and the C parameter at each outdoor temperature during the power non-activated time cycles.