Roof photovoltaic potential assessment method based on machine learning

Abstract

The invention discloses a roof photovoltaic potential assessment method based on machine learning. The problems that in the prior art, a roof recognition mode is single, and errors and interference easily exist are solved. The method comprises the following steps: S1, obtaining three-dimensional remote sensing image data of a visual angle at the top of a building through a satellite or aerial photography; s2, inputting one part of data into a trained identification model, and identifying a roof area; carrying out matrix segmentation on one part of data according to rated length and width; s3, boundary identification is carried out on each matrix unit data, a closed boundary curve is obtained after restoration and combination, and a roof area is determined; s4, the roof area is calculated according to coupling of the roof area recognized by the recognition model and the roof area determined by the closed boundary curve, and the photovoltaic potential of the roof is evaluated by combining the energy consumption of the zone area where the building is located and the environment information. Through combination of the identification model and segmentation identification, the roof area is determined through combination of identification results in two modes, the identification modes are diversified, and the accuracy of the identification results is improved.

Description

technical field [0001] The invention relates to the field of photovoltaic potential evaluation, in particular to a roof photovoltaic potential evaluation method based on machine learning. Background technique [0002] With the increasing global energy demand, photovoltaic power generation has received more and more attention due to its advantages of cleanliness, convenience, safety, and suitability for distributed networking, and has become one of the most promising renewable energy power generation methods. . Quantitative evaluation of solar energy resource potential is the basis for formulating energy planning, providing basic data and engineering construction guidance for the development and utilization of regional solar energy resources. The existing method has a single roof identification method, which is prone to interference and errors. [0003] For example, a "distributed photovoltaic resource integration method, system, device and storage medium" disclosed in the C...

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the problem of single roof recognition method in the prior art, which is prone to errors and interference; provides a roof photovoltaic potential evaluation method based on machine learning, through the combination of recognition model and segmentation recognition, and judging the roof from the combination of the recognition results of the two methods Area, various identification methods, improve the accuracy of identification results

Images