Air-conditioning control evaluation apparatus, air-conditioning control evaluation method, and computer readable medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air-conditioning control evaluation systems struggle to automatically select optimal models that accurately represent thermal and humidity characteristics of buildings, leading to inaccurate energy-saving and comfort evaluations due to reliance on predetermined physical and statistical models, and difficulties in handling unavailable data and complex computation models.
Innovation Solution
An air-conditioning control evaluation apparatus that automatically selects a building model from a set of models based on available data, using a candidate-model selection criterion to determine input data, estimate parameters, and calculate residuals, thereby minimizing parameters and improving accuracy in energy-saving and comfort evaluations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If predetermined physical and statistical models are used for air-conditioning control evaluation, then the evaluation system can be established, but the accuracy of energy-saving and comfort evaluations deteriorates due to inability to automatically select optimal models
Solution Approach 1:
The system automatically selects optimal building models and parameter estimation methods based on available data characteristics without requiring manual intervention. The model selection unit autonomously evaluates data distribution types and selects appropriate models, while the parameter estimation unit automatically chooses estimation methods based on identified data characteristics, enabling the system to serve itself in optimizing evaluation accuracy.
Solution Approach 2:
The system changes parameters related to model selection and parameter estimation based on the identified type of distribution of observed data. When data follows different distribution patterns (normal, log-normal, gamma, etc.), the system dynamically adjusts which building model to use and which parameter estimation method to apply, thereby adapting to different building conditions and data characteristics to maintain high evaluation accuracy.
2Reliability
If multiple parameters are used to represent building thermal and humidity characteristics, then the evaluation comprehensiveness is improved, but the number of necessary parameters increases making the system more complex
Solution Approach 1:
The system dynamically determines the number and type of parameters to be estimated based on the identified data distribution type and selected building model. Rather than always estimating all possible parameters, the system adaptively selects only the necessary parameters for the current evaluation context, reducing the quantity of parameters while maintaining comprehensive evaluation capability through dynamic parameter selection.
3Adaptability or versatility
If complex computation models are used to handle unavailable data, then the data handling capability is improved, but the computation complexity and time increase
Solution Approach 1:
The system performs preliminary identification of the type of distribution of observed data before proceeding with parameter estimation and model selection. This preliminary action enables the system to pre-determine the appropriate building model and parameter estimation method, avoiding the need for complex iterative computations to handle unavailable data later in the process, thereby reducing overall computation time while maintaining versatile data handling capability.
Data Source
AI summary
An air-conditioning control evaluation apparatus includes a storage unit and a computing unit. The storage unit stores building information, input information, control information, a set of building models, and a candidate selection criterion. The computing unit determines an item available as input data for a building model, identifies the distribution of observed data, selects a plurality of candidate building models from the set of building models based on the available item and candidate selection criterion, estimates each parameter based on a method corresponding to the distribution, determines one building model based on a predetermined statistic calculated for the plurality of building models and the residual between estimated and observed values calculated for each of the building models, and evaluates, by use of the determined building model, energy saving and comfort for a plurality of controls to be evaluated.