Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes

Leire Hernandez-Lecuona; Ricardo Alonso; Ainhoa Pereda; Sergio Gil; J. David Nuñez-Gonzalez; Manuel Graña

doi:10.1007/978-3-032-19763-4_12

Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes

Leire Hernandez-Lecuona
, Ricardo Alonso
, Ainhoa Pereda
, Sergio Gil
, J. David Nuñez-Gonzalez^*
, Manuel Graña

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The increasing deployment of photovoltaic (PV) systems demands advanced supervision tools to ensure optimal performance and minimize maintenance costs. This work presents a novel methodology for detecting and classifying inverter-related anomalies—specifically inverter clipping and thermal power derating—using synthetic SCADA data from a simulated PV plant. The proposed approach integrates linear regression, residual filtering, and Gaussian Mixture Models to identify non-MPP operating conditions, enabling improved accuracy in performance analysis. Results demonstrate high detection accuracy. The lightweight, unsupervised nature of the method makes it suitable for real-time SCADA integration and future application to diverse PV configurations, paving the way for more reliable and condition-based maintenance strategies in PV asset management.

Original language	English
Title of host publication	Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings
Editors	Emilio Corchado, Héctor Quintián, Esteban Jove, Alicia Troncoso Lora, Francisco Martínez Álvarez, Pablo García Bringas, Paolo Fosci
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	128-139
Number of pages	12
ISBN (Print)	9783032197627
DOIs	https://doi.org/10.1007/978-3-032-19763-4_12
Publication status	Published - 2026
Event	20th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2025 - Salamanca, Spain Duration: 16 Oct 2025 → 17 Oct 2025

Publication series

Name	Communications in Computer and Information Science
Volume	2806 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	20th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2025
Country/Territory	Spain
City	Salamanca
Period	16/10/25 → 17/10/25

UN SDGs

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

SDG 7 Affordable and Clean Energy

Access to Document

10.1007/978-3-032-19763-4_12

Cite this

Hernandez-Lecuona, L., Alonso, R., Pereda, A., Gil, S., Nuñez-Gonzalez, J. D., & Graña, M. (2026). Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes. In E. Corchado, H. Quintián, E. Jove, A. Troncoso Lora, F. Martínez Álvarez, P. García Bringas, & P. Fosci (Eds.), Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings (pp. 128-139). (Communications in Computer and Information Science; Vol. 2806 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-032-19763-4_12

Hernandez-Lecuona, Leire ; Alonso, Ricardo ; Pereda, Ainhoa et al. / Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes. Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings. editor / Emilio Corchado ; Héctor Quintián ; Esteban Jove ; Alicia Troncoso Lora ; Francisco Martínez Álvarez ; Pablo García Bringas ; Paolo Fosci. Springer Science and Business Media Deutschland GmbH, 2026. pp. 128-139 (Communications in Computer and Information Science).

@inproceedings{8495f9328cfc48c5b7186902f81200bf,

title = "Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes",

abstract = "The increasing deployment of photovoltaic (PV) systems demands advanced supervision tools to ensure optimal performance and minimize maintenance costs. This work presents a novel methodology for detecting and classifying inverter-related anomalies{\textemdash}specifically inverter clipping and thermal power derating{\textemdash}using synthetic SCADA data from a simulated PV plant. The proposed approach integrates linear regression, residual filtering, and Gaussian Mixture Models to identify non-MPP operating conditions, enabling improved accuracy in performance analysis. Results demonstrate high detection accuracy. The lightweight, unsupervised nature of the method makes it suitable for real-time SCADA integration and future application to diverse PV configurations, paving the way for more reliable and condition-based maintenance strategies in PV asset management.",

author = "Leire Hernandez-Lecuona and Ricardo Alonso and Ainhoa Pereda and Sergio Gil and Nu{\~n}ez-Gonzalez, \{J. David\} and Manuel Gra{\~n}a",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 20th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2025 ; Conference date: 16-10-2025 Through 17-10-2025",

year = "2026",

doi = "10.1007/978-3-032-19763-4\_12",

language = "English",

isbn = "9783032197627",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "128--139",

editor = "Emilio Corchado and H{\'e}ctor Quinti{\'a}n and Esteban Jove and \{Troncoso Lora\}, Alicia and \{Mart{\'i}nez {\'A}lvarez\}, Francisco and \{Garc{\'i}a Bringas\}, Pablo and Paolo Fosci",

booktitle = "Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings",

address = "Germany",

}

Hernandez-Lecuona, L, Alonso, R , Pereda, A , Gil, S, Nuñez-Gonzalez, JD & Graña, M 2026, Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes. in E Corchado, H Quintián, E Jove, A Troncoso Lora, F Martínez Álvarez, P García Bringas & P Fosci (eds), Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings. Communications in Computer and Information Science, vol. 2806 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 128-139, 20th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2025, Salamanca, Spain, 16/10/25. https://doi.org/10.1007/978-3-032-19763-4_12

Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes. / Hernandez-Lecuona, Leire; Alonso, Ricardo ; Pereda, Ainhoa et al.
Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings. ed. / Emilio Corchado; Héctor Quintián; Esteban Jove; Alicia Troncoso Lora; Francisco Martínez Álvarez; Pablo García Bringas; Paolo Fosci. Springer Science and Business Media Deutschland GmbH, 2026. p. 128-139 (Communications in Computer and Information Science; Vol. 2806 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes

AU - Hernandez-Lecuona, Leire

AU - Alonso, Ricardo

AU - Pereda, Ainhoa

AU - Gil, Sergio

AU - Nuñez-Gonzalez, J. David

AU - Graña, Manuel

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - The increasing deployment of photovoltaic (PV) systems demands advanced supervision tools to ensure optimal performance and minimize maintenance costs. This work presents a novel methodology for detecting and classifying inverter-related anomalies—specifically inverter clipping and thermal power derating—using synthetic SCADA data from a simulated PV plant. The proposed approach integrates linear regression, residual filtering, and Gaussian Mixture Models to identify non-MPP operating conditions, enabling improved accuracy in performance analysis. Results demonstrate high detection accuracy. The lightweight, unsupervised nature of the method makes it suitable for real-time SCADA integration and future application to diverse PV configurations, paving the way for more reliable and condition-based maintenance strategies in PV asset management.

AB - The increasing deployment of photovoltaic (PV) systems demands advanced supervision tools to ensure optimal performance and minimize maintenance costs. This work presents a novel methodology for detecting and classifying inverter-related anomalies—specifically inverter clipping and thermal power derating—using synthetic SCADA data from a simulated PV plant. The proposed approach integrates linear regression, residual filtering, and Gaussian Mixture Models to identify non-MPP operating conditions, enabling improved accuracy in performance analysis. Results demonstrate high detection accuracy. The lightweight, unsupervised nature of the method makes it suitable for real-time SCADA integration and future application to diverse PV configurations, paving the way for more reliable and condition-based maintenance strategies in PV asset management.

UR - https://www.scopus.com/pages/publications/105042509657

U2 - 10.1007/978-3-032-19763-4_12

DO - 10.1007/978-3-032-19763-4_12

M3 - Conference contribution

AN - SCOPUS:105042509657

SN - 9783032197627

T3 - Communications in Computer and Information Science

SP - 128

EP - 139

BT - Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings

A2 - Corchado, Emilio

A2 - Quintián, Héctor

A2 - Jove, Esteban

A2 - Troncoso Lora, Alicia

A2 - Martínez Álvarez, Francisco

A2 - García Bringas, Pablo

A2 - Fosci, Paolo

PB - Springer Science and Business Media Deutschland GmbH

T2 - 20th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2025

Y2 - 16 October 2025 through 17 October 2025

ER -

Hernandez-Lecuona L, Alonso R , Pereda A , Gil S, Nuñez-Gonzalez JD, Graña M. Detection of Photovoltaic Generator Underperformance Due to Inverter Operation Modes. In Corchado E, Quintián H, Jove E, Troncoso Lora A, Martínez Álvarez F, García Bringas P, Fosci P, editors, Soft Computing Models in Industrial and Environmental Applications - 20th International Conference, SOCO 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 128-139. (Communications in Computer and Information Science). doi: 10.1007/978-3-032-19763-4_12