Photovoltaic power generation big data prediction method based on feature conversion multi-label learning

A technology of photovoltaic power generation and feature conversion, applied in forecasting, data processing applications, instruments, etc., can solve problems such as ignoring or ignoring the performance of photovoltaic panels and actual operating conditions, and the inability to guarantee the prediction accuracy of power generation, so as to ensure the effectiveness, Guaranteed effect of dissimilarity

Pending Publication Date: 2019-08-02
CHONGQING UNIV OF POSTS & TELECOMM
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the existing methods and photovoltaic power generation prediction technologies only focus on modeling meteorological conditions and historical data, while ignoring the influence of photovoltaic panel body performance and actual operating conditions on power generation efficiency, and the existing technologi

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 big data prediction method based on feature conversion multi-label learning
  • Photovoltaic power generation big data prediction method based on feature conversion multi-label learning
  • Photovoltaic power generation big data prediction method based on feature conversion multi-label learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0044] The technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. The described embodiments are only a part of the embodiments of the present invention.

[0045] The technical solutions of the present invention to solve the above technical problems are:

[0046] figure 1 For the first embodiment of the present invention, a flowchart of a photovoltaic power generation big data prediction method based on feature transformation multi-label learning is provided, which specifically includes:

[0047] 101. The steps for preprocessing the data are as follows:

[0048] 1011. Outlier processing: The outlier processing is blanking out the outliers, the selection time period is 180 days, and the values ​​calculated according to formula (1) are filled; first, the samples are sorted in ascending order, where N is the total number of data, x (i) Indicates that the sam...

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 requests to protect a photovoltaic power generation big data prediction method based on feature conversion multi-label learning. The method comprises the following steps: 101, carrying out preprocessing operation on data; 102, dividing training set data and verification set data according to historical data and time; 103, performing feature engineering operation on the historical data of the photovoltaic power station; 104, performing feature selection based on the AUC maximum value on the data set with the constructed features; 105, establishing a plurality of machine learning models, and constructing an algorithm model based on feature conversion multi-label learning; 106, accurately predicting the power generation condition of the photovoltaic panel according to the data of the photovoltaic power station based on an algorithm model of feature conversion multi-label learning. According to the historical data of the photovoltaic power station, whether the power generation of the photovoltaic panel reaches the standard or not every day in the future week is predicted, the performance of the photovoltaic panel body is effectively guaranteed, and therefore data supportand decision support are provided for national power input.

Description

technical field [0001] The invention belongs to the technical fields of machine learning, multi-label learning, feature conversion learning, and big data processing, in particular, photovoltaic power generation big data prediction based on multiple models. Background technique [0002] In recent years, we have implemented the national strategy of technological innovation and development, built a world-class enterprise with global competitiveness, promoted the deep integration of big data, artificial intelligence and traditional business, and at the same time implemented the innovation-driven development strategy, innovated management models, and aggregated innovative resources. To further stimulate the innovative vitality of employees and enhance the core competitiveness of enterprises, according to the "SPIC Big Data Construction Overall Plan" and "SPIC's Promoting Mass Entrepreneurship and Innovation Industry Plan", photovoltaic power stations are becoming more and more imp...

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): G06Q10/04G06Q50/06
CPCG06Q10/04G06Q50/06Y04S10/50
Inventor 王进余薇许景益孙开伟刘彬邓欣
Owner CHONGQING UNIV OF POSTS & TELECOMM
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