Energy consumption prediction method and device
A technology for energy consumption and forecasting methods, applied in forecasting, resources, instruments, etc., to solve problems such as inaccurate energy consumption forecasting
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] figure 1 A schematic diagram of the energy consumption prediction process provided by the embodiment of the present invention, the process includes the following steps:
[0039] S101: Input the acquired first data within the first time length into the pre-trained autoregressive integral moving average ARIMA model, and input the acquired second data within the first time length into the pre-trained support vector machine SVM Model.
[0040] S102: Determine a first predicted energy consumption value based on the ARIMA model, and determine a second predicted energy consumption value based on the SVM model.
[0041] S103: Determine a target energy consumption prediction value at a first prediction time according to the first energy consumption prediction value and the second energy consumption prediction value.
[0042] The energy consumption prediction method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device...
Embodiment 2
[0049] In order to make the determined target energy consumption prediction value more accurate, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, according to the first energy consumption prediction value and the second energy consumption prediction value, determine the first prediction Time-based target energy consumption forecasts include:
[0050] Determining the latest acquired true value of energy consumption;
[0051] determining a first prediction error according to the first predicted value of energy consumption and the actual value of energy consumption; determining a second prediction error according to the second predicted value of energy consumption and the actual value of energy consumption;
[0052] determining a first weight corresponding to the first energy consumption prediction value and a second weight corresponding to the second energy consumption prediction value according to the first prediction error and the se...
Embodiment 3
[0062] On the basis of the above-mentioned embodiments, in the embodiment of the present invention, the training process of the ARIMA model includes:
[0063] For the third data in each second time length in the first training set, input the third data in the second time length and the actual value of energy consumption at the second prediction time corresponding to the second time length into the ARIMA model, The ARIMA model is trained.
[0064] In the embodiment of the present invention, the training set used for training the ARIMA model is used as the first training set, and the data in the first training set is used as the third data. The first data and the third data include energy consumption values. The electronic device divides the third data in the first training set into the third data in each second time length, and the second time length is, for example, three days, then the third data in the first training set can be divided into January 1, 2018 The third data f...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


