Prediksi dan Optimalisasi Konsumsi Energi Smart Atmospheric Water Generator (SAWG) Menggunakan XGBoost Regression
-
Halim Jayakusuma Wiradinata
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
- Heru Agus Santoso Universitas Dian Nuswantoro, Semarang, Indonesia (*) Corresponding Author
Abstract
The decreasing availability of clean water has motivated the use of Smart Atmospheric Water Generator (SAWG) systems as an alternative water source, but their electrical energy consumption fluctuates with ambient conditions and operating patterns. This study develops a predictive model of SAWG energy consumption (kWh) using Extreme Gradient Boosting (XGBoost) and demonstrates a prediction-based operational optimization scheme for energy-efficient scheduling. The SAWG logging dataset (1,601 rows, 9 variables) is preprocessed through missing-value handling, numeric conversion, and noise/outlier detection, resulting in 1,313 usable records. The feature set includes environmental parameters, electrical signals, and time features: hour of day, day of week, and month. Modeling employs chronological time-based splits (80:20 as the main configuration and 60:40 as a robustness check), Time Series Cross-Validation on the training block, and hyperparameter tuning via GridSearchCV. Evaluation on the hold-out test sets shows that the model’s performance in a strict time-series setting remains limited: for the 80:20 split, the test results are approximately MAE = 23.16 kWh, MSE = 648.93 kWh², and R² = −0.22, while for the 60:40 split they are MAE = 27.21 kWh, MSE = 932.17 kWh², and R² = −1.75. Although the model cannot yet explain the overall variance of energy consumption satisfactorily, it can still be used to rank hours by predicted energy. In the prediction-based operational optimization stage, hourly model outputs are fed into a Greedy Scheduler that selects H = 8 operating hours with the lowest predicted energy. Compared with a naive schedule, which yields a total predicted energy of 47.493 kWh over the simulation horizon, the greedy schedule achieves 43.134 kWh, corresponding to an estimated saving of about 9.18%. These results indicate that prediction-based scheduling can reduce SAWG energy consumption without modifying the device hardware and can be further developed as a decision-support component for SAWG operation.
Downloads
References
N. Khan, S. Khan, Q. Khorajiya, J. Sairan, and Prof. M. A. Gulbarga, “Atmospheric Water Generator,” International Journal for Research in Applied Science and Engineering Technology, vol. 10, no. 4, pp. 929–935, Apr. 2022, doi: 10.22214/ijraset.2022.41406.
X. Liu, D. Beysens, and T. Bourouina, “Water Harvesting from Air: Current Passive Approaches and Outlook,” ACS Materials Letters, vol. 4, no. 5, pp. 1003–1024, May 2022, doi: 10.1021/acsmaterialslett.1c00850.
J. Wang, Z. Yang, Z. Li, H. Fu, and J. Chen, “Comprehensive review on atmospheric water harvesting technologies,” Journal of Water Process Engineering, vol. 69, p. 106836, Jan. 2025, doi: 10.1016/j.jwpe.2024.106836.
A. Bhardwaj et al., “Smart IoT and Machine Learning-based Framework for Water Quality Assessment and Device Component Monitoring,” Environmental Science and Pollution Research, vol. 29, no. 30, pp. 46018–46036, Jun. 2022, doi: 10.1007/s11356-022-19014-3.
P. Wang, J. Xu, Z. Bai, R. Wang, and T. Li, “Designing next-generation all-weather and efficient atmospheric water harvesting powered by solar energy,” Energy & Environmental Science, vol. 18, no. 14, pp. 7005–7022, 2025, doi: 10.1039/D5EE01454A.
L. Cattani, P. Cattani, R. Figoni, and A. Magrini, “Performance Assessment of Atmospheric Water Generators: A Review of Evaluation Tools and Proposal for a Novel Advanced Global Evaluation Index for HVAC–AWG Hybrid Solutions,” Applied Sciences, vol. 14, no. 24, p. 11793, Dec. 2024, doi: 10.3390/app142411793.
E. Sadowski, E. Mbonimpa, and C. M. Chini, “Benchmarks of production for atmospheric water generators in the United States,” PLOS Water, vol. 2, no. 6, p. e0000133, Jun. 2023, doi: 10.1371/journal.pwat.0000133.
F. Faraz Ahmad, C. Ghenai, M. al Bardan, M. Bourgon, and A. Shanableh, “Performance analysis of atmospheric water generator under hot and humid climate conditions: Drinkable water production and system energy consumption,” Case Studies in Chemical and Environmental Engineering, vol. 6, p. 100270, Dec. 2022, doi: 10.1016/j.cscee.2022.100270.
I. I. El-Sharkawy, S. Haridy, M. Hassan, A. Radwan, and M. M. Abd-Elhady, “Optimization of atmospheric water harvesting cycles for sustainable water supply in arid regions,” International Journal of Thermofluids, vol. 24, p. 100977, Nov. 2024, doi: 10.1016/j.ijft.2024.100977.
B. Asiabanpour, N. Ownby, M. Summers, and F. Moghimi, “Atmospheric Water Generation and Energy Consumption: An Empirical Analysis,” in 2019 IEEE Texas Power and Energy Conference (TPEC), IEEE, Mar. 2019, pp. 1–6. doi: 10.1109/TPEC.2019.8662164.
F. Gaggini, R. N. F. Crespo, M. Calò, V. M. Gentile, A. Macii, and E. Patti, “An Internet of Things Ecosystem for Atmospheric Water Generators,” IEEE Access, vol. 13, pp. 77565–77581, Apr. 2025, doi: 10.1109/ACCESS.2025.3562742.
M. Lowe, R. Qin, and X. Mao, “A Review on Machine Learning, Artificial Intelligence, and Smart Technology in Water Treatment and Monitoring,” Water, vol. 14, no. 9, p. 1384, Apr. 2022, doi: 10.3390/w14091384.
G. Barletta, S. Moitra, S. Derrible, A. Mathew, A. M. Nair, and C. M. Megaridis, “Exploring machine learning models to predict atmospheric water harvesting with an ion deposition membrane,” Journal of Water Process Engineering, vol. 72, p. 107476, Apr. 2025, doi: 10.1016/j.jwpe.2025.107476.
M. S. Islam and B. Asiabanpour, “Machine Learning-Based Optimization of Surface Temperature in TPMS Geometries for Atmospheric Water Generation Systems,” in Proc. IISE Annual Conference & Expo 2025, Atlanta, GA, USA, 2025, doi: 10.5281/zenodo.15644127.
L. Li, Z. Shi, H. Liang, J. Liu, and Z. Qiao, “Machine Learning-Assisted Computational Screening of Metal-Organic Frameworks for Atmospheric Water Harvesting,” Nanomaterials, vol. 12, no. 1, p. 159, Jan. 2022, doi: 10.3390/nano12010159.
C. Cuevas, A. Cendoya, D. Sacasas, and M. Pezo, “Evaluation of the Potential of Atmospheric Water Generators to Mitigate Water Scarcity in Northern Chile,” Processes, vol. 13, no. 9, p. 3003, Sep. 2025, doi: 10.3390/pr13093003.
C. Rincón, J. Alencastre, E. Barrantes, and C. Carbajal, “Atmospheric water generator: design for rural zones with low and medium humidity level,” South Florida Journal of Development, vol. 5, no. 7, p. e4081, Jul. 2024, doi: 10.46932/sfjdv5n7-002.
E. Fosso-Kankeu, A. Al Alili, H. Mittal, and B. Mamba, Eds., Atmospheric Water Harvesting: Development and Challenges. Cham: Springer, 2023, doi: 10.1007/978-3-031-21746-3.
S. D. Deshmukh and A. V. Deshmukh, Atmospheric Water Generation (AWG): Engineering Principles, Technologies and Applications. Lulu.com, 2025.
N. Maleki, O. Lundström, A. Musaddiq, J. Jeansson, T. Olsson, and F. Ahlgren, “Future energy insights: Time-series and deep learning models for city load forecasting,” Applied Energy, vol. 374, p. 124067, Nov. 2024, doi: 10.1016/j.apenergy.2024.124067.
L. Ren, L. Zhang, H. Wang, and Q. Guo, “An Extreme Gradient Boosting Algorithm for Short-Term Load Forecasting Using Power Grid Big Data,” 2019, pp. 479–490. doi: 10.1007/978-981-13-2288-4_46.
S. G. Kangalli Uyar, B. K. Ozbay, and B. Dal, “Interpretable building energy performance prediction using XGBoost Quantile Regression,” Energy and Buildings, vol. 340, p. 115815, Aug. 2025, doi: 10.1016/j.enbuild.2025.115815.
E. L. Alba, G. A. Oliveira, M. H. D. M. Ribeiro, and É. O. Rodrigues, “Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations,” Forecasting, vol. 6, no. 3, pp. 839–863, Sep. 2024, doi: 10.3390/forecast6030042.
Z. Mustaffa and M. H. Sulaiman, “Advanced forecasting of building energy loads with XGBoost and metaheuristic algorithms integration,” Energy Storage and Saving, Aug. 2025, doi: 10.1016/j.enss.2025.03.005.
A. Muqtadir, B. Li, Z. Ying, C. Songsong, and S. N. Kazmi, “Nowcasting the next hour of residential load using boosting ensemble machines,” Scientific Reports, vol. 15, no. 1, p. 7157, Feb. 2025, doi: 10.1038/s41598-025-91767-6.
H. Abbasimehr, R. Paki, and A. Bahrini, “A novel XGBoost-based featurization approach to forecast renewable energy consumption with deep learning models,” Sustainable Computing: Informatics and Systems, vol. 38, p. 100863, Apr. 2023, doi: 10.1016/j.suscom.2023.100863.
I. Hussain, K. B. Ching, C. Uttraphan, K. G. Tay, and A. Noor, “Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study,” Scientific Reports, vol. 15, no. 1, p. 16124, May 2025, doi: 10.1038/s41598-025-94946-7.
A. T. Mustafa and O. S. A.-D. Al-Yozbaky, “Forecasting Energy Demand and Generation Using Time Series Models: A Comparative Analysis of Classical, Grey, Fuzzy, and Intelligent Approaches,” Franklin Open, p. 100350, Aug. 2025, doi: 10.1016/j.fraope.2025.100350.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Prediksi dan Optimalisasi Konsumsi Energi Smart Atmospheric Water Generator (SAWG) Menggunakan XGBoost Regression
Pages: 1730-1742
Copyright (c) 2025 Halim Jayakusuma Wiradinata, Heru Agus Santoso
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
