Method for controlling air conditioner, and electronic device and computer-readable storage medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for controlling air conditioner startup and shutdown in commercial settings rely on manual operation or time schedules, failing to adjust according to actual building load, leading to energy waste and poor thermal comfort.
Innovation Solution
A method and apparatus that utilize temperature and humidity data to predict optimal startup and shutdown times through a pre-trained prediction model, adjusting parameters based on indoor and outdoor conditions to optimize energy usage and thermal adaptability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If time schedule control is used to automatically start and shut down the air conditioner, then manual operation is eliminated and basic automation is achieved, but the startup and shutdown times cannot adjust according to actual building load, causing energy waste and poor thermal comfort
Solution Approach 1:
The system collects real-time temperature data, humidity data, and occupancy information from sensors, feeds this data into the prediction model, and uses the model's predictions to dynamically adjust startup and shutdown times. This closed-loop feedback mechanism enables the air conditioner to adapt to actual building conditions while maintaining automated control
Solution Approach 2:
The air conditioner system performs self-optimization by using its own collected environmental data and occupancy information to predict optimal operating times. The prediction model, trained on historical data, enables the system to autonomously determine when to start and shut down without external intervention, achieving both automation and adaptability
2Temperature
If the air conditioner is started up too early according to fixed time schedule, then thermal comfort is ensured, but energy consumption increases due to unnecessary early operation
Solution Approach 1:
The system dynamically changes the startup time parameter based on predicted building load, outdoor temperature, humidity, and occupancy patterns. Instead of using a fixed early startup time, the prediction model calculates the optimal startup time that balances thermal comfort requirements with energy consumption, adjusting this parameter in real-time according to environmental conditions
3Use of energy by moving object
If the air conditioner is started up too late to save energy, then energy consumption is reduced, but indoor temperature becomes too high during business hours, degrading thermal comfort
Solution Approach 1:
The system performs preliminary cooling or heating action at the predicted optimal startup time, which is calculated to be just sufficient to reach comfortable temperatures by the time occupants arrive or business hours begin. This preliminary action is precisely timed based on environmental conditions and building thermal characteristics, avoiding both early and late startup problems
Data Source
AI summary
A method includes obtaining temperature data and humidity data of an air conditioner, inputting a mode of the air conditioner, a prediction type of the air conditioner, the temperature data, and the humidity data into a pre-trained prediction model, and controlling a startup or a shutdown of the air conditioner based on a predicted time output by the prediction model. The mode of the air conditioner includes at least one of a cooling mode or a heating mode, the prediction type of the air conditioner includes at least one of a startup-time prediction or a shutdown-time prediction, parameters of the prediction model include an indoor set temperature, an indoor set temperature threshold value, an indoor set humidity, and an indoor set humidity threshold value, and the predicted time includes at least one of a predicted startup time or a predicted shutdown time.