PIUL-DERs: Physics-informed pseudo-labeling unsupervised learning for smart homes with distributed energy resources

Yihan Huang; Jing Jiang; Zhilin Gao; Hongjian Sun; Zhiwei Gao

doi:10.1016/j.apenergy.2025.127045

PIUL-DERs: Physics-informed pseudo-labeling unsupervised learning for smart homes with distributed energy resources

Yihan Huang, Jing Jiang^*, Zhilin Gao, Hongjian Sun, Zhiwei Gao

^*Corresponding author for this work

School of Engineering Physics and Mathematics

Research output: Contribution to journal › Article › peer-review

7 Downloads (Pure)

Abstract

This article proposes a novel algorithm PIUL-DERs, physics-informed pseudo-labeling unsupervised learning for the residential distributed energy resources (DERs) management of smart homes with electric vehicles (EVs) and photovoltaic (PV) systems. A self-optimizing pseudo-labeling unsupervised learning framework is developed to predict EV usage and PV generation, where a physics-informed model specifically captures PV generation uncertainties by embedding solar irradiance model, weather characteristics, and thermal efficiency. Then, based on residential DERs predictions, the carbon-aware centralized energy management scheme (CEMS) addresses the challenges of energy storage coordination in smart homes, considering dynamic power grid carbon intensity to reduce grid dependence of individual smart homes and thus facilitate real-time carbon emissions reductions. The simulation results validate the reliability and efficiency of the PIUL-DERs. The proposed PIUL-DERs accurately predicts PV/EV profiles with 73 % less complexity than that of the existing method and realizes carbon-aware CEMS between smart homes, reducing carbon emissions by 46 %

Original language	English
Article number	127045
Number of pages	15
Journal	Applied Energy
Volume	403
Issue number	Part A
DOIs	https://doi.org/10.1016/j.apenergy.2025.127045
Publication status	Published - 15 Jan 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Carbon intensity
Centralized energy management scheme (CEMS)
Distributed energy resources (DERs)
Pseudo-labeling unsupervised learning
physics-informed model

Access to Document

10.1016/j.apenergy.2025.127045Licence: CC BY

Revised_PIUL_DERs_Manuscript_Round2_with_No_Changes_MarkedAccepted author manuscript, 8.9 MBLicence: CC BY
1-s2.0-S0306261925017751-mainFinal published version, 5.5 MBLicence: CC BY

Cite this

@article{7052bab62e2c4e599414d5a7df9222bc,

title = "PIUL-DERs: Physics-informed pseudo-labeling unsupervised learning for smart homes with distributed energy resources",

abstract = "This article proposes a novel algorithm PIUL-DERs, physics-informed pseudo-labeling unsupervised learning for the residential distributed energy resources (DERs) management of smart homes with electric vehicles (EVs) and photovoltaic (PV) systems. A self-optimizing pseudo-labeling unsupervised learning framework is developed to predict EV usage and PV generation, where a physics-informed model specifically captures PV generation uncertainties by embedding solar irradiance model, weather characteristics, and thermal efficiency. Then, based on residential DERs predictions, the carbon-aware centralized energy management scheme (CEMS) addresses the challenges of energy storage coordination in smart homes, considering dynamic power grid carbon intensity to reduce grid dependence of individual smart homes and thus facilitate real-time carbon emissions reductions. The simulation results validate the reliability and efficiency of the PIUL-DERs. The proposed PIUL-DERs accurately predicts PV/EV profiles with 73 \% less complexity than that of the existing method and realizes carbon-aware CEMS between smart homes, reducing carbon emissions by 46 \%",

keywords = "Carbon intensity, Centralized energy management scheme (CEMS), Distributed energy resources (DERs), Pseudo-labeling unsupervised learning, physics-informed model",

author = "Yihan Huang and Jing Jiang and Zhilin Gao and Hongjian Sun and Zhiwei Gao",

year = "2026",

month = jan,

day = "15",

doi = "10.1016/j.apenergy.2025.127045",

language = "English",

volume = "403",

journal = "Applied Energy",

issn = "0306-2619",

publisher = "Elsevier B.V.",

number = "Part A",

}

TY - JOUR

T1 - PIUL-DERs: Physics-informed pseudo-labeling unsupervised learning for smart homes with distributed energy resources

AU - Huang, Yihan

AU - Jiang, Jing

AU - Gao, Zhilin

AU - Sun, Hongjian

AU - Gao, Zhiwei

PY - 2026/1/15

Y1 - 2026/1/15

N2 - This article proposes a novel algorithm PIUL-DERs, physics-informed pseudo-labeling unsupervised learning for the residential distributed energy resources (DERs) management of smart homes with electric vehicles (EVs) and photovoltaic (PV) systems. A self-optimizing pseudo-labeling unsupervised learning framework is developed to predict EV usage and PV generation, where a physics-informed model specifically captures PV generation uncertainties by embedding solar irradiance model, weather characteristics, and thermal efficiency. Then, based on residential DERs predictions, the carbon-aware centralized energy management scheme (CEMS) addresses the challenges of energy storage coordination in smart homes, considering dynamic power grid carbon intensity to reduce grid dependence of individual smart homes and thus facilitate real-time carbon emissions reductions. The simulation results validate the reliability and efficiency of the PIUL-DERs. The proposed PIUL-DERs accurately predicts PV/EV profiles with 73 % less complexity than that of the existing method and realizes carbon-aware CEMS between smart homes, reducing carbon emissions by 46 %

AB - This article proposes a novel algorithm PIUL-DERs, physics-informed pseudo-labeling unsupervised learning for the residential distributed energy resources (DERs) management of smart homes with electric vehicles (EVs) and photovoltaic (PV) systems. A self-optimizing pseudo-labeling unsupervised learning framework is developed to predict EV usage and PV generation, where a physics-informed model specifically captures PV generation uncertainties by embedding solar irradiance model, weather characteristics, and thermal efficiency. Then, based on residential DERs predictions, the carbon-aware centralized energy management scheme (CEMS) addresses the challenges of energy storage coordination in smart homes, considering dynamic power grid carbon intensity to reduce grid dependence of individual smart homes and thus facilitate real-time carbon emissions reductions. The simulation results validate the reliability and efficiency of the PIUL-DERs. The proposed PIUL-DERs accurately predicts PV/EV profiles with 73 % less complexity than that of the existing method and realizes carbon-aware CEMS between smart homes, reducing carbon emissions by 46 %

KW - Carbon intensity

KW - Centralized energy management scheme (CEMS)

KW - Distributed energy resources (DERs)

KW - Pseudo-labeling unsupervised learning

KW - physics-informed model

UR - https://www.scopus.com/pages/publications/105022425714

U2 - 10.1016/j.apenergy.2025.127045

DO - 10.1016/j.apenergy.2025.127045

M3 - Article

SN - 0306-2619

VL - 403

JO - Applied Energy

JF - Applied Energy

IS - Part A

M1 - 127045

ER -

PIUL-DERs: Physics-informed pseudo-labeling unsupervised learning for smart homes with distributed energy resources

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this