Photovoltaic output ultra-short-term prediction method and system based on multi-source heterogeneous data

A multi-source heterogeneous data and ultra-short-term prediction technology, applied in the field of electronic information, can solve the problems of complex image feature extraction algorithm design, low precision, and difficulty in applying natural scenes, so as to reduce or eliminate adverse effects and improve utilization rate , to avoid the effect of light abandonment phenomenon

Active Publication Date: 2021-03-16
UNIV OF SCI & TECH BEIJING
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a method and system for ultra-short-term forecasting of photovoltaic output based on multi-source heterogeneous data to solve the problem that the existing photovoltaic output forecasting method has low accuracy, and the image feature extraction algorithm is relatively complicated in algorithm design, and there are relatively strong problems. Due to the limitation of conditions, it is difficult to apply to the technical problems of complex natural scenes

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 output ultra-short-term prediction method and system based on multi-source heterogeneous data
  • Photovoltaic output ultra-short-term prediction method and system based on multi-source heterogeneous data
  • Photovoltaic output ultra-short-term prediction method and system based on multi-source heterogeneous data

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0051] This embodiment provides a method for ultra-short-term prediction of photovoltaic output based on multi-source heterogeneous data. The method can be implemented by electronic equipment, and the electronic equipment can be a terminal or a server. The execution process of the ultra-short-term prediction method of photovoltaic output based on multi-source heterogeneous data is as follows: figure 1 shown, including the following steps:

[0052] S101. Obtain a time series of ground-based cloud images and historical photovoltaic output data, and extract cloud image features from the time series through a deep neural network; obtain historical data features based on the historical photovoltaic output data;

[0053] It should be noted that due to its good generalization and convenience in feature extraction, deep neural network (DNN) occupies a dominant position in computer vision tasks such as image classification and target detection. In this embodiment, by introducing a dee...

no. 2 example

[0072] This embodiment provides a photovoltaic output ultra-short-term forecasting system based on multi-source heterogeneous data. The composition of the photovoltaic output ultra-short-term forecast system based on multi-source heterogeneous data is as follows figure 2 As shown, the following modules are included:

[0073] Ground-based cloud image feature extraction module, which takes the ground-based cloud image as input and is used to extract cloud image features from the time series composed of ground-based cloud images through a deep neural network;

[0074] A historical photovoltaic output feature extraction module, which takes historical photovoltaic output data as input and is used to obtain historical data features based on historical photovoltaic output data;

[0075] The feature fusion and photovoltaic output prediction module is used to splicing the cloud image features extracted by the ground-based cloud image feature extraction module and the historical data f...

no. 3 example

[0088] This embodiment provides an electronic device, which includes a processor and a memory; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor, so as to implement the method of the first embodiment.

[0089] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) and one or more memories, wherein at least one instruction is stored in the memory, so The above instruction is loaded by the processor and executes the above method.

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 output ultra-short-term prediction method and system based on multi-source heterogeneous data. The method comprises the steps of extracting cloud atlas featuresfrom a foundation cloud atlas through a deep neural network; extracting historical data features from the historical photovoltaic output data; splicing the cloud picture features and the historical data features; and finally, based on the spliced features, generating predicted photovoltaic output data through a one-dimensional convolutional network. According to the invention, the deep neural network and the ultra-short-term photovoltaic output prediction are combined, the advantages of the deep neural network in image feature extraction are utilized, the features are extracted from the foundation cloud atlas and then fused with the photovoltaic output historical data, and the photovoltaic output prediction is realized. The combination of the image and the historical data overcomes the defects of single input data and low information amount of the prediction model, and the deep neural network automatically extracts the cloud image features to overcome the defects of low information utilization rate and weak generalization ability of the artificially designed image features.

Description

technical field [0001] The invention relates to the field of electronic information technology, in particular to a method and system for ultra-short-term forecasting of photovoltaic output based on multi-source heterogeneous data. Background technique [0002] As one of the most important ways to utilize solar energy, photovoltaic power generation has a global installed capacity of 400 million kilowatts by the end of 2017. Photovoltaic power generation has made outstanding contributions to reducing carbon emissions and addressing climate warming. It is of great significance to promote the comprehensive and sustainable development of society. However, since photovoltaic power generation is easily affected by geographical location and weather conditions, it has strong instability and volatility, which brings huge challenges to the grid connection of large-scale photovoltaic power generation: 1) The photovoltaic output is not consumed in time , the photovoltaic utilization rat...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04
CPCG06Q10/04G06Q50/06G06N3/045
Inventor 黄超阳昊王龙罗熊
Owner UNIV OF SCI & TECH BEIJING
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap