Photovoltaic power generation power control method based on gating convolution and attention mechanism

A technology of photovoltaic power generation and control methods, which is applied in photovoltaic power generation, power generation prediction in AC networks, electrical components, etc., can solve problems such as incapable of parallel acceleration, only utilization, and difficult models, and achieve voltage balance maintenance and energy saving Energy and economic loss reduction effects

Active Publication Date: 2020-12-01
TIANJIN UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although RNNs can effectively extract time series features, there are the following problems: 1. The sequence data is calculated moment by moment. The calculation at the current moment depends on the previous results and cannot be a...

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Photovoltaic power generation power control method based on gating convolution and attention mechanism
  • Photovoltaic power generation power control method based on gating convolution and attention mechanism
  • Photovoltaic power generation power control method based on gating convolution and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0040] In order to solve the technical problems in the background technology, a specific convolutional neural network can be designed to predict time series data. Among them, the Gated Convolutional Neural Network (GCNN) can be used to extract short-term temporally dependent connections. The Global Attention Mechanism (Global Attention Mechanism) can directly learn long-distance timing dependencies without sequential memory like LSTM, so it can be used to learn long-term dependencies of sequences.

[0041] The present invention describes an end-to-end deep learning model BiGCNN. The network structure of the model is summarized as figure 1 shown. The entire network consists of three parts: the network layer stacked by the Conv+Pool layer, the BiGLU network layer, and the Attenti...

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

No PUM Login to view more

Abstract

The invention discloses a photovoltaic power generation power control method based on gating convolution and an attention mechanism. The method comprises the steps that an end-to-end deep learning model BiGCNN composed of a Conv + Pool layer stacked network layer, a BiGLU network layer and an Attention network layer is constructed; wherein the BiGLU network layer and the Attention network layer are respectively used for extracting short-term and long-term time sequence dependence relations; weather data collected by sensors and meteorological satellites installed near photovoltaic equipment toa computer is transmitted through a wireless network; the computer loads the deep learning model BiGCNN to predict the power generation power at a certain moment in the future according to the numerical weather data in a past period of time and the historical power generation power of the photovoltaic equipment; based on the predicted power generation power, a photovoltaic power generation and planning system is helped to take positive defensive measures. By controlling the prediction result, the photovoltaic power generation and planning system can be helped to take positive defense measures.

Description

technical field [0001] The present invention relates to the field of time series data control of machine learning, in particular to a control method of photovoltaic power generation based on gated convolution and global attention mechanism, through the analysis of weather data collected in the past period of time and historical power generation And use it to predict the photovoltaic power generation power at a certain time in the future, and then realize the effective control of photovoltaic power generation power. Background technique [0002] Power forecasting for renewable energy power plants has been a very active research area in recent years. Forecasting electricity generation for some time in the future ensures safe operation of the grid and helps minimize the operating costs of renewable energy. Solar energy is one of the best renewable clean energy to replace traditional energy, and photovoltaic power generation has become a very important topic. The main influenc...

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
no application Login to view more
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04H02J3/00H02J3/38
CPCG06Q10/04G06Q50/06H02J3/004H02J3/381H02J2300/24G06N3/048G06N3/045G06N3/044Y04S10/50Y02E10/56
Inventor 孙美君陈颖鉴王征
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products