Lightweight Machine Learning for Condenser Valve Prediction in a Geothermal Power Plant: A Darajat Case Study

DOI

10.2991/978-94-6463-944-5_25How to use a DOI?

Keywords

condenser; machine learning; linear regression. Random forest; xgboost

Abstract

Improving condenser performance is essential for sustaining the efficiency of geothermal power plants within Indonesia’s Net Zero Emission roadmap. This study investigates the application of machine learning (ML) models to predict condenser valve openings at PLTP Darajat. Three models were evaluated: Linear Regression, Random Forest, and XGBoost. The dataset, comprising 470 hourly operational records, included five key features identified through feature-importance analysis: coolingwater inlet flow, cooling-water inlet temperature, condenser outlet flow, condenser pressure, and generator output. Results show that Linear Regression achieved the best balance between accuracy and computational cost, with R² = 0.8, RMSE = 0.97, MAE = 0.67, and a training time of 0.21 s. In comparison, ensemble models offered marginally higher accuracy but required substantially longer training times. The simplicity and interpretability of Linear Regression enabled accurate valve prediction using only five parameters, improving plant efficiency from 18.62% to 18.90%. These findings demonstrate that lightweight and transparent ML models can provide actionable insights for real-time operation, aligning predictive analytics with operator usability. Future research will expand datasets to capture seasonal dynamics and explore hybrid approaches that combine physics-based and data-driven methods. This work highlights the potential of ML to enhance geothermal plant efficiency and contribute to Indonesia’s long-term clean energy transition.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Opan Ropandi
AU  - Sihana Sihana
AU  - Dwi Joko Suroso
PY  - 2025
DA  - 2025/12/26
TI  - Lightweight Machine Learning for Condenser Valve Prediction in a Geothermal Power Plant: A Darajat Case Study
BT  - Proceedings of the International Conference on Sustainable Energy: Toward Energy Transition and Net-Zero Emission (ICOSE 2025)
PB  - Atlantis Press
SP  - 374
EP  - 388
SN  - 3005-155X
UR  - https://doi.org/10.2991/978-94-6463-944-5_25
DO  - 10.2991/978-94-6463-944-5_25
ID  - Ropandi2025
ER  -