A Method for Predicting the Power of Photovoltaic Power Generation
A photovoltaic power generation technology, applied in the direction of forecasting, data processing applications, instruments, etc., can solve the problems of limited forecasting accuracy and insufficient consideration of the principle of photovoltaic power generation, and achieve the effect of improving forecasting accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] A method 100 for constructing a photovoltaic power generation prediction model, such as figure 1 shown, including:
[0046] Step 110. Obtain the low-dimensional feature matrix m*n of the power trend item and the power fluctuation item respectively, and perform nonlinear transformation between the features of each dimension in each low-dimensional feature matrix according to the principle of photovoltaic power generation, and construct the low-dimensional feature matrix m*n that affects the low-dimensional feature matrix. The high-dimensional feature matrix m*N of the power trend item or power fluctuation item corresponding to the dimensional feature matrix, where m is the number of historical time points, N and n are the number of feature dimensions, and N>n;
[0047] Step 120, based on each high-dimensional feature matrix, using the forward feature selection method, train the long-term short-term memory network prediction sub-model with compensation bias for predicting...
Embodiment 2
[0082] A photovoltaic power generation power prediction model, which is constructed by any construction method of the photovoltaic power generation power prediction model described in the first embodiment above, including: a long-short-term memory network prediction sub-model with compensation bias of the power trend item and a power Long Short-Term Memory Network Prediction Submodels with Compensation Bias for Volatility Term.
[0083] It is obtained by adopting the construction method of the aforementioned photovoltaic power generation prediction model, and the prediction performance is high, so the prediction reliability is high.
[0084] The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.
Embodiment 3
[0086] A photovoltaic power generation prediction method 200, comprising:
[0087] Step 210, based on the preferred dimension sets of power trend items and power fluctuation items in any of the methods for constructing photovoltaic power generation forecasting models described in the first embodiment, construct a power trend for predicting the time to be predicted in a one-to-one correspondence The optimal dimension characteristic matrix of item and power fluctuation item;
[0088] Step 220, based on the sub-models of a photovoltaic power generation power prediction model as described in the second embodiment above, using the preferred dimension feature matrix in one-to-one correspondence to obtain the predicted value of the power trend item and the predicted value of the power fluctuation item;
[0089] Step 230: Obtain a predicted power value based on the predicted value of the power trend item and the predicted value of the power fluctuation item.
[0090] It should be not...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More