Load image inpainting: An improved U-Net based load missing data recovery method

Liqi Liu and Yanli Liu

Applied Energy, 2022, vol. 327, issue C, No S0306261922012454

Abstract: Dealing with large percentage data missing is always a challenge for load data recovery. This paper, drawing on ideas from image inpainting, formulates load missing data recovery problem as load image inpainting and the improved U-Net is proposed to restore the load image. First, the 1-dimensional load data is constructed into 2-dimensional load image. Additionally, missing data presents as irregular black holes on the load image. Then, the improved U-Net which introduces residual network (ResNet) and convolutional block attention module (CBAM) is proposed to specifically restore the incomplete load image. Meanwhile, mean absolute error (MAE) and structural similarity (SSIM) are utilized to evaluate data recovery accuracy and load pattern recovery similarity respectively. Load missing data recovery results based on the actual industrial load dataset are presented to verify the effectiveness of the proposed method.

Keywords: Load data; Missing data recovery; Load image; U-Net; ResNet; CBAM; SSIM (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261922012454
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:327:y:2022:i:c:s0306261922012454

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2022.119988

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().