Indoor-temperature estimation apparatus, non-transitory computer-readable medium, and indoor-temperature estimation method
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing room temperature estimation models are complex and require a large volume of data and processing time due to the collective treatment of external environmental conditions and temperature control device operations, leading to delayed service initiation.
Innovation Solution
The model is simplified by distinguishing between affected and unaffected periods by the temperature control device, using separate models for each period, and integrating estimates from unaffected and affected room temperatures to predict future room temperatures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a complex model treating external environment and temperature control device effects collectively is used, then the estimation accuracy may be improved, but the model complexity and data processing requirements increase significantly
Solution Approach 1:
The patent segments the estimation model into two distinct components: an unaffected period model that estimates room temperature based solely on external environmental conditions, and an affected period model that estimates temperature changes caused by the air conditioner. This segmentation simplifies each individual model while maintaining overall estimation accuracy by addressing external environment and device effects separately rather than collectively.
2Measurement precision
If a complex model with high data requirements is used, then the estimation accuracy may be improved, but the learning period extends and service start is delayed
Solution Approach 1:
By segmenting the estimation into unaffected and affected periods with separate models, the patent reduces the data requirements for each individual model. The unaffected period model only needs external environment data, while the affected period model only needs air conditioner operation data and temperature differential data. This allows the system to achieve sufficient accuracy with less total data, shortening the learning period and enabling faster service deployment.
3Measurement precision
If a complex model with large data volume is used, then the estimation accuracy may be improved, but the processing load and storage requirements increase
Solution Approach 1:
The patent divides the data processing into two separate streams: external environment data for the unaffected period model and air conditioner operation data for the affected period model. Each model processes only its relevant data type, significantly reducing the volume of data each model must handle and store. This segmentation lowers the overall processing load and storage requirements while maintaining the ability to provide accurate temperature estimates.
Data Source
AI summary
An effect determining unit to specify a learning affected period during which room temperature is affected by a temperature controller and a learning unaffected period during which the room temperature is not affected by the temperature controller; a room-temperature-model generating unit configured to learn a state of an outdoor and room temperature in a learning unaffected period to generate a room temperature model indicating the relationship between the state and the room temperature; an unaffected-room-temperature estimating unit configured to estimate learning temporary room temperature, which is the room temperature presumed to be unaffected by the temperature controller, in the learning affected period by using a room temperature model; and a room-temperature-change-model generating unit configured to learn the room temperature and learning temporary room temperature in the learning affected period, to generate a room temperature change model indicating the change in the room temperature caused by the temperature controller.