Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning

Ridho Hantoro; Gunawan Nugroho; Erna Septyaningrum; Iwan Cony Setiadi; Rasyid Yuniarto Kusuma; Mochammad Arief Febrianto

doi:10.1007/978-981-97-8197-3_37

Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning

Ridho Hantoro, Gunawan Nugroho, Erna Septyaningrum, Iwan Cony Setiadi, Rasyid Yuniarto Kusuma^*, Mochammad Arief Febrianto

^*Corresponding author for this work

Institut Teknologi Sepuluh Nopember

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

Abstract

Overcoming most problems in PV, a monitoring system including data acquisition and data display was created in real-time, and a prediction model for PV power in the next few hours was developed. The highest value of efficiency is when the PV module is configured at a tilled angle of 30°. The input predictions are processed by the stored model. The model used variations of k-NN, k-NN- BPNN, and k-NN-D-BPNN. The model has a MAPE yield of 0.52% for k-NN, 0.95% for k-NN-BPNN and 33.47% for k-NN-D-BPNN, and MSE of 59.84 W2 for k-NN, 225.94 W2 for k-NN-BPNN and 17.701 W2 for k-NN-D-BPNN so that the model is a very good and feasible prediction. The resulting accuracy decreases when the prediction time is added. Therefore, predictions need to be limited to the next 3 h.

Original language	English
Title of host publication	Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023
Editors	Suwarno Suwarno, Triyogi Yuwono, Mohan Kolhe, Muhammad Aziz
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	379-389
Number of pages	11
ISBN (Print)	9789819781966
DOIs	https://doi.org/10.1007/978-981-97-8197-3_37
Publication status	Published - 2025
Event	6th International Conference on Mechanical Engineering, ICOME 2023 - Bali, Indonesia Duration: 30 Aug 2023 → 31 Aug 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1279
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	6th International Conference on Mechanical Engineering, ICOME 2023
Country/Territory	Indonesia
City	Bali
Period	30/08/23 → 31/08/23

Keywords

Power prediction
Real time monitoring
Solar power plants
k-NN-D-BPNN

Access to Document

10.1007/978-981-97-8197-3_37

Cite this

Hantoro, R., Nugroho, G., Septyaningrum, E., Setiadi, I. C., Kusuma, R. Y., & Febrianto, M. A. (2025). Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning. In S. Suwarno, T. Yuwono, M. Kolhe, & M. Aziz (Eds.), Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023 (pp. 379-389). (Lecture Notes in Electrical Engineering; Vol. 1279). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-8197-3_37

Hantoro, Ridho ; Nugroho, Gunawan ; Septyaningrum, Erna et al. / Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning. Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023. editor / Suwarno Suwarno ; Triyogi Yuwono ; Mohan Kolhe ; Muhammad Aziz. Springer Science and Business Media Deutschland GmbH, 2025. pp. 379-389 (Lecture Notes in Electrical Engineering).

@inproceedings{6aa14017afd448208e06cb219b0e49a0,

title = "Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning",

abstract = "Overcoming most problems in PV, a monitoring system including data acquisition and data display was created in real-time, and a prediction model for PV power in the next few hours was developed. The highest value of efficiency is when the PV module is configured at a tilled angle of 30°. The input predictions are processed by the stored model. The model used variations of k-NN, k-NN- BPNN, and k-NN-D-BPNN. The model has a MAPE yield of 0.52% for k-NN, 0.95% for k-NN-BPNN and 33.47% for k-NN-D-BPNN, and MSE of 59.84 W2 for k-NN, 225.94 W2 for k-NN-BPNN and 17.701 W2 for k-NN-D-BPNN so that the model is a very good and feasible prediction. The resulting accuracy decreases when the prediction time is added. Therefore, predictions need to be limited to the next 3 h.",

keywords = "Power prediction, Real time monitoring, Solar power plants, k-NN-D-BPNN",

author = "Ridho Hantoro and Gunawan Nugroho and Erna Septyaningrum and Setiadi, {Iwan Cony} and Kusuma, {Rasyid Yuniarto} and Febrianto, {Mochammad Arief}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 6th International Conference on Mechanical Engineering, ICOME 2023 ; Conference date: 30-08-2023 Through 31-08-2023",

year = "2025",

doi = "10.1007/978-981-97-8197-3_37",

language = "English",

isbn = "9789819781966",

series = "Lecture Notes in Electrical Engineering",

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

pages = "379--389",

editor = "Suwarno Suwarno and Triyogi Yuwono and Mohan Kolhe and Muhammad Aziz",

booktitle = "Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023",

address = "Germany",

}

Hantoro, R , Nugroho, G , Septyaningrum, E , Setiadi, IC, Kusuma, RY & Febrianto, MA 2025, Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning. in S Suwarno, T Yuwono, M Kolhe & M Aziz (eds), Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023. Lecture Notes in Electrical Engineering, vol. 1279, Springer Science and Business Media Deutschland GmbH, pp. 379-389, 6th International Conference on Mechanical Engineering, ICOME 2023, Bali, Indonesia, 30/08/23. https://doi.org/10.1007/978-981-97-8197-3_37

Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning. / Hantoro, Ridho ; Nugroho, Gunawan ; Septyaningrum, Erna et al.
Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023. ed. / Suwarno Suwarno; Triyogi Yuwono; Mohan Kolhe; Muhammad Aziz. Springer Science and Business Media Deutschland GmbH, 2025. p. 379-389 (Lecture Notes in Electrical Engineering; Vol. 1279).

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

TY - GEN

T1 - Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning

AU - Hantoro, Ridho

AU - Nugroho, Gunawan

AU - Septyaningrum, Erna

AU - Setiadi, Iwan Cony

AU - Kusuma, Rasyid Yuniarto

AU - Febrianto, Mochammad Arief

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - Overcoming most problems in PV, a monitoring system including data acquisition and data display was created in real-time, and a prediction model for PV power in the next few hours was developed. The highest value of efficiency is when the PV module is configured at a tilled angle of 30°. The input predictions are processed by the stored model. The model used variations of k-NN, k-NN- BPNN, and k-NN-D-BPNN. The model has a MAPE yield of 0.52% for k-NN, 0.95% for k-NN-BPNN and 33.47% for k-NN-D-BPNN, and MSE of 59.84 W2 for k-NN, 225.94 W2 for k-NN-BPNN and 17.701 W2 for k-NN-D-BPNN so that the model is a very good and feasible prediction. The resulting accuracy decreases when the prediction time is added. Therefore, predictions need to be limited to the next 3 h.

AB - Overcoming most problems in PV, a monitoring system including data acquisition and data display was created in real-time, and a prediction model for PV power in the next few hours was developed. The highest value of efficiency is when the PV module is configured at a tilled angle of 30°. The input predictions are processed by the stored model. The model used variations of k-NN, k-NN- BPNN, and k-NN-D-BPNN. The model has a MAPE yield of 0.52% for k-NN, 0.95% for k-NN-BPNN and 33.47% for k-NN-D-BPNN, and MSE of 59.84 W2 for k-NN, 225.94 W2 for k-NN-BPNN and 17.701 W2 for k-NN-D-BPNN so that the model is a very good and feasible prediction. The resulting accuracy decreases when the prediction time is added. Therefore, predictions need to be limited to the next 3 h.

KW - Power prediction

KW - Real time monitoring

KW - Solar power plants

KW - k-NN-D-BPNN

UR - http://www.scopus.com/inward/record.url?scp=105007513851&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-8197-3_37

DO - 10.1007/978-981-97-8197-3_37

M3 - Conference contribution

AN - SCOPUS:105007513851

SN - 9789819781966

T3 - Lecture Notes in Electrical Engineering

SP - 379

EP - 389

BT - Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023

A2 - Suwarno, Suwarno

A2 - Yuwono, Triyogi

A2 - Kolhe, Mohan

A2 - Aziz, Muhammad

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th International Conference on Mechanical Engineering, ICOME 2023

Y2 - 30 August 2023 through 31 August 2023

ER -

Hantoro R , Nugroho G , Septyaningrum E , Setiadi IC, Kusuma RY, Febrianto MA. Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning. In Suwarno S, Yuwono T, Kolhe M, Aziz M, editors, Smart Innovation in Green and Sustainable Energy - Select Proceedings of ICOME 2023. Springer Science and Business Media Deutschland GmbH. 2025. p. 379-389. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-8197-3_37

Development of a Real Time Monitoring and Power Prediction System for Solar Power Plants Using Machine Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this