Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Photovoltaic power short-term prediction method and device based on machine learning, and storage medium

A machine learning and short-term forecasting technology, applied in machine learning, forecasting, instruments, etc., can solve problems such as insufficient accuracy of photovoltaic power forecasting, and achieve the effects of accurate power forecasting, large profit space, and rapid development

Pending Publication Date: 2022-01-28
西安化奇数据科技有限公司
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a short-term photovoltaic power prediction method, device and storage medium based on machine learning, which solves the technical problem of insufficient photovoltaic power prediction accuracy in the prior art under short-term conditions

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 short-term prediction method and device based on machine learning, and storage medium
  • Photovoltaic power short-term prediction method and device based on machine learning, and storage medium
  • Photovoltaic power short-term prediction method and device based on machine learning, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] This embodiment relates to a computer-based photovoltaic power short-term prediction method, and the step can be performed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases Next, it can be performed in the order different from here. like figure 1 , Includes the following steps:

[0040] Step S101, historical data integration: data from the historical power, climate meteorology, geographic location, electrical station design, electrical efficiency, management operations, etc., and integrated it as a time series with time as an index. data.

[0041]Light resources and photovoltaic power affect factors and affect the complicacy. Different factors have different degrees of influence in different environments, so integrated data from multi-dimensional collection. Specifically, climate meteorological data mainly includes atmospheric radiation, aerosol optical thickness, sun flange, spati...

Embodiment 2

[0056] This embodiment relates to a device for short-term prediction of photovoltaic power, which can be implemented in hardware or software for completing the short-term prediction method of photovoltaic power. like image 3 As shown, the prediction device 100 includes a historical data integration module 101, a data set pretreatment module 102, a timing trend decomposition module 103, an optimal feature filter module 104, a machine learning modeling module 105, a prediction of trend fusion module 106.

[0057] The historical data integration module 101 is configured to collect data from a plurality of photovoltaic power plants, and integrate them as a time series data at time as an index; corresponding to the content of step S101 in Example 1;

[0058] The data set pre-processing module 102 is used to make a split box processing in the data in the data, and perform data cleaning of the missing value and an abnormal value; corresponding to the content of step S102 in the first emb...

Embodiment 3

[0064] This embodiment relates to an electronic device for short-term prediction of photovoltaic power. Figure 4 The electronic device of the electronic device provided by the embodiment of the present invention, the electronic device may include a processor 301, a communication interface (Communications Interface 302, a memory (Memory) 303, and bus 304, wherein the processor 301, Communication interface 302, memory 303 performs communication between each other through bus 304. The processor 301 can invoke a computer program stored on the memory 303 and can run on the processor 301 to perform the short-term prediction method provided by the above-described Embodiment 1. For example,: historical data integration: collect data from the photovoltaic power station, and integrate them as a time series data at time as an index; data collection pre-processing: the characteristics of the continuous value in the data are split box processing, and Data cleaning of missing values ​​and abnor...

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 relates to a photovoltaic power short-term prediction method and device based on machine learning and a storage medium. The method comprises the steps of historical data integration, data set preprocessing, time sequence trend decomposition, optimal feature screening, machine learning modeling, prediction trend fusion and the like. Comprising the following steps: integrating and cleaning multi-dimensional data of a photovoltaic power station under a certain spatial-temporal scale by adopting a trend decomposition and machine learning algorithm; performing trend decomposition of the power data by using a time sequence data trend decomposition method; carrying out modeling prediction on each trend term by comparing and using a plurality of machine learning regression algorithms and autoregression models; and finally, combining the decomposition model to carry out trend prediction fusion on a prediction result to complete short-term prediction of the photovoltaic power. According to the invention, modeling is carried out on each trend term after power data decomposition, the prediction precision is effectively improved, more accurate power prediction and larger income space are brought to new energy station owners, and scientific planning and reasonable application of new energy are facilitated.

Description

Technical field [0001] The present invention belongs to the field of electrical output prediction techniques, and more particularly to a short-term prediction method, apparatus, and storage medium based on a machine-learning based photovoltaic power. Background technique [0002] In the new energy subsidy, the challenges faced by the new energy station owners are more severe, one is the discounted economic benefit of the subsidy, one side is the economic burden brought by strict assessment. . Only continuously optimize prediction technology and service levels, enhance prediction accuracy, can really reduce the assessment, bringing greater income space for the site. [0003] At present, my country's standard for power forecasting and control technology is relatively old, with traditional physical and statistical methods, physical methods based on the solar irradiation transmission equation, photovoltaic module operation equations, etc., the photovoltaic power station needs the det...

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): G06Q10/04G06N20/00G06Q50/06G06Q10/00
CPCG06Q10/04G06N20/00G06Q50/06G06Q10/20
Inventor 王晓妮
Owner 西安化奇数据科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products