Method and system for building and predicting air conditioner load prediction model in office building
An air-conditioning load and forecasting model technology, which is applied in neural learning methods, biological neural network models, information technology support systems, etc., can solve problems such as insufficient forecasting accuracy, long cycle, and large resource occupation, so as to achieve accurate forecasting results and reduce Accuracy requirements, high universality effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0076] This embodiment discloses a method for establishing an air-conditioning load forecasting model in an office building. The training data set includes more than 14,000 sets of data for training a single air-conditioning load forecasting model. More than 7,000 sets of data are used to test the model and train the model. The set and test set include environmental data and actual air-conditioning load data for each hour between 8:00 am and 20:00 pm every day for a month, and the data set is input into the prediction network to train the model. According to the established RBF model and the combined residual correction model, the air-conditioning load of 12 hours during the daytime on a certain day in summer is predicted. The actual value, absolute error and average relative error predicted by various methods are as follows: Figure 5 , Figure 6 , Figure 7 shown
[0077] According to the simulation results of air-conditioning load forecasting by different methods, the av...
Embodiment 2
[0085] This embodiment discloses an air-conditioning load forecasting system in an office building. On the basis of the above embodiments, the following technical features are also disclosed:
[0086] The indoor and outdoor temperature and humidity sensor selects the digital temperature and humidity sensor model HTU21D(F). It is a plug-and-play temperature and humidity measurement component. The sensor is matched by the OEM to make the measurement more reliable and accurate. It directly uses an MCU without Other peripheral circuits can output temperature and humidity as digital signals. Its temperature measurement range is: -40~+125℃, and the humidity measurement range is: 0~100%RH. Because this invention is mainly aimed at load forecasting for office buildings in cold regions, the measurement range of the sensor needs to be considered. In some areas in northern my country, the lowest temperature in winter can reach minus 30 to 40 degrees, so it is necessary to select a sensor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


