Evaluation method of rooftop photovoltaic resources of distributed buildings based on the fusion of ResFAUnet and MAS-PointMLP

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings Pub Date : 2025-03-28 DOI:10.1016/j.enbuild.2025.115680

Xiaobin Xu , Zerun Sun , Zhiyuan Mao , Yajuan Feng , Haojie Zhang , Jianbo Bai , Jian Yang , Yingying Ran , Zhiying Tan

{"title":"Evaluation method of rooftop photovoltaic resources of distributed buildings based on the fusion of ResFAUnet and MAS-PointMLP","authors":"Xiaobin Xu , Zerun Sun , Zhiyuan Mao , Yajuan Feng , Haojie Zhang , Jianbo Bai , Jian Yang , Yingying Ran , Zhiying Tan","doi":"10.1016/j.enbuild.2025.115680","DOIUrl":null,"url":null,"abstract":"<div><div>To accurately evaluate roof resources for distributed PV systems, a method based on the fusion of laser and image is proposed. First, ResFAUnet, which integrates transfer learning and multi-scale features, is used to segment the exterior outline of the building roof. Then, the building roof is finely segmented using MAS-PointMLP. Finally, the characteristics of the roof are calculated based on the point cloud processing algorithm, the arrangement of photovoltaic modules is realized based on the image processing algorithm, and the solar radiation and power generation are calculated based on the SHORTWAVE-C model. The proposed ResFAUnet can effectively segment the outer contour of the building roof, and the improved MAS-PointMLP network achieves 87.78% in the Mean Intersection over Union (MIoU), 1.14% higher than the original PointMLP. The average error between the annual total radiation of the roof and that of the database of Copernicus atmospheric monitoring service is 7.4%, verifying the effectiveness of the proposed algorithm.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115680"},"PeriodicalIF":6.6000,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and Buildings","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378778825004104","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

To accurately evaluate roof resources for distributed PV systems, a method based on the fusion of laser and image is proposed. First, ResFAUnet, which integrates transfer learning and multi-scale features, is used to segment the exterior outline of the building roof. Then, the building roof is finely segmented using MAS-PointMLP. Finally, the characteristics of the roof are calculated based on the point cloud processing algorithm, the arrangement of photovoltaic modules is realized based on the image processing algorithm, and the solar radiation and power generation are calculated based on the SHORTWAVE-C model. The proposed ResFAUnet can effectively segment the outer contour of the building roof, and the improved MAS-PointMLP network achieves 87.78% in the Mean Intersection over Union (MIoU), 1.14% higher than the original PointMLP. The average error between the annual total radiation of the roof and that of the database of Copernicus atmospheric monitoring service is 7.4%, verifying the effectiveness of the proposed algorithm.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Energy and Buildings 工程技术-工程：土木

CiteScore

12.70

自引率

11.90%

发文量

863

审稿时长

38 days

期刊介绍： An international journal devoted to investigations of energy use and efficiency in buildings Energy and Buildings is an international journal publishing articles with explicit links to energy use in buildings. The aim is to present new research results, and new proven practice aimed at reducing the energy needs of a building and improving indoor environment quality.