Air conditioning control evaluation device, air conditioning system, air conditioning control evaluation method and program
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air-conditioning control evaluation systems fail to automatically select the most accurate building models for estimating power consumption and indoor comfort changes, particularly when considering factors like building geometry and sensor placement, leading to inaccurate energy-saving and comfort evaluations.
Innovation Solution
An air-conditioning control evaluation apparatus that automatically selects a building model from a set of models based on available data and distribution types, using a candidate-model selection criterion to determine input data and estimate parameters, thereby minimizing the number of necessary parameters and improving the accuracy of energy-saving and comfort evaluations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed building model is used for power consumption estimation, then the device complexity is reduced, but the measurement precision of energy-saving evaluation deteriorates
Solution Approach 1:
The system dynamically selects building models based on available sensor data and distribution types rather than using a fixed model. The model selection adapts to different operational conditions and data availability, resolving the contradiction between system complexity and estimation accuracy.
Solution Approach 2:
The system changes the parameter set used in power consumption estimation based on the selected building model. Different models use different combinations of building parameters, sensor data, and distribution types, allowing accurate estimation without requiring all parameters to be always available.
2Adaptability or versatility
If multiple building models are maintained for different scenarios, then the adaptability to various building configurations is improved, but the device complexity increases
Solution Approach 1:
The system performs preliminary classification of building models into categories (first building models with fewer parameters, second building models with more parameters) based on anticipated data availability. This pre-organization allows efficient model selection without complex real-time analysis, balancing adaptability with manageable complexity.
Solution Approach 2:
The system uses statistical distribution types (normal distribution, log-normal distribution, etc.) as simplified representations of complex building thermal behaviors. These distribution-based models capture essential building characteristics without requiring detailed physical models, reducing complexity while maintaining adaptability.
3Measurement precision
If building models with more parameters are used, then the measurement precision of comfort evaluation is improved, but the quantity of required input data increases
Solution Approach 1:
The system dynamically selects between first building models (fewer parameters) and second building models (more parameters) based on the quantity and quality of available sensor data. When data is limited, simpler models are used; when data is abundant, more comprehensive models provide higher precision comfort evaluation.
Solution Approach 2:
The system changes the effective parameter set by selecting different building models based on data availability. The same physical building can be represented by different parameter sets depending on what sensor data is available, allowing accurate evaluation without requiring all possible input parameters.
4Manufacturing precision
If statistical distribution types are determined for observed data, then the manufacturing precision of parameter estimation is improved, but the difficulty of detecting and measuring distribution types increases
Solution Approach 1:
The system uses standard statistical distribution types (normal distribution, log-normal distribution, uniform distribution, etc.) as simplified models to represent complex observed data patterns. These well-known distributions provide accurate parameter estimation without requiring complex custom distribution identification, reducing measurement difficulty while maintaining precision.
Data Source
Figure 1A~1B
Figure 1C~2
Figure 3
AI summary
An air-conditioning control evaluation apparatus according to the present invention 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 building information is information related to a building where an air-conditioning related device is disposed. The input information includes device information and observed data. The control information is information on a control to be executed for the air-conditioning related device. The candidate selection criterion represents the correspondence between an item included in the input information and a building model. The computing unit determines an item available as input data for a building model, identifies the distribution of the observed data, selects a plurality of candidate building models from the set of building models based on the available item and the 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.