Transform model-based photovoltaic power prediction method
A power prediction and model technology, applied in prediction, biological neural network model, instruments, etc., can solve problems such as energy waste, inaccurate photovoltaic power prediction, and difficulty in timing selection.
Active Publication Date: 2021-06-18
JIANGNAN UNIV
View PDF3 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] Photovoltaic power generation is a new type of power generation method that uses the photovoltaic effect of solar cell semiconductor materials to directly convert solar radiation energy into electrical energy. By predicting photovoltaic power, it can be judged when to connect photovoltaics to the grid to achieve energy utilization benefits. However, since the photovoltaic power is affected by various environmental factors, such as irradiance, temperature, humidity, etc., the current forecast of photovoltaic power is not accurate enough. As for when the photovoltaic power will be connected to the grid Selection can also be difficult, resulting in wasted energy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0044] A photovoltaic power prediction method based on the Transformer model, such as figure 1 As shown, a photovoltaic power prediction model is constructed based on the Transformer model. The photovoltaic power prediction model includes a convolutional layer, a position encoding layer, an encoder group, a decoder group, and an activation output layer.
[0045]The convolution layer unifies the dimensions of the input data. The number of convolution kernels used in this application is d, the size of the convolution kernel is 1, and the step size is 1 to perform dimension transformation on the data.
[0046] The position encoding layer performs position encoding on the input data. In order to express the sequence position relationship of the input data, the historical environmental data input to the position encoding layer and the environment...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a photovoltaic power prediction method based on a Transform model, and relates to the technical field of photovoltaic power, and the method comprises the steps: building a photovoltaic power prediction model based on the Transform model, wherein the photovoltaic power prediction model comprises a convolution layer, a position coding layer, an encoder group, a decoder group and an activation output layer; acquiring historical data, inputting the historical data into a convolution layer and a position coding layer, then transmitting to an encoder group after calculation, and the encoder group calculating the data and transmitting the data to a decoder group; obtaining current environment data, inputting the current environment data into a convolution layer and a position coding layer of the photovoltaic power prediction model to calculate data, and transmitting the data to a decoder group, wherein the decoder group obtains initial target data and transmits the initial target data to an activation output layer. The output of the activation output layer is used as current power data, and the access power of photovoltaic grid connection is determined by researching historical data and current data, so that the operation mode of a power grid is determined, and coordinated control of power generation of different energy sources is realized.
Description
technical field [0001] The invention relates to the technical field of photovoltaic power, in particular to a photovoltaic power prediction method based on a Transformer model. Background technique [0002] Photovoltaic power generation is a new type of power generation method that uses the photovoltaic effect of solar cell semiconductor materials to directly convert solar radiation energy into electrical energy. By predicting photovoltaic power, it can be judged when to connect photovoltaics to the grid to achieve energy utilization benefits. However, since the photovoltaic power is affected by various environmental factors, such as irradiance, temperature, humidity, etc., the current forecast of photovoltaic power is not accurate enough. As for when the photovoltaic power will be connected to the grid Selection can also be very difficult, resulting in wasted energy. Contents of the invention [0003] The present inventor proposes a photovoltaic power prediction method b...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/06G06Q10/04G06F30/27G06N3/04
CPCG06Q50/06G06Q10/04G06F30/27G06N3/047G06N3/044
Inventor 沈艳霞沈俊豪赵芝璞
Owner JIANGNAN UNIV