COST ASSESSMENT FOR GRID-EXPORT PV SYSTEMS USING LONG-TERM FORECASTING: A PRE-INVESTMENT STUDY FOR BESS DEPLOYMENT
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.389Keywords:
Long-term PV forecasting, Baseline revenue, Curtailment, Investment feasibility, Gradient Boosted Trees, Techno-economic analysisAbstract
Long-term energy yield estimation plays a critical role in evaluating the financial feasibility of Photovoltaic (PV) projects, particularly for grid-export-only systems where revenue depends entirely on the amount of energy delivered to the grid. Unlike short-term forecasting used for operational control, long-horizon prediction enables investors and system planners to quantify expected annual energy generation, revenue under Power Purchase Agreement (PPA) or Time-of-Use (TOU) pricing, and project payback time. This study develops a forecast-driven economic evaluation framework to assess the baseline profitability of a grid-export-only PV plant and evaluate the pre-investment feasibility of Battery Energy Storage System (BESS) deployment. Historical PV output and meteorological variables are used to train a Gradient Boosted Trees (GBT) model, generating reliable aggregated PV predictions. These forecasts are applied to compute baseline revenue, expected curtailment, and the overall profitability of various PV-BESS capacities under PPA and TOU tariffs. Results from a 720.9 kWp/600 kW AC PV system show that combining forecasting with scenario-based assessment provides a robust estimation of economic viability. The study identifies that moderate BESS sizing (e.g., 535–750 kWh) under TOU tariffs significantly maximizes net present value (NPV) and shortens the payback period, laying a solid foundation for optimal BESS integration.
References
[1] P. Singla, M. Duhan, and S. Saroha, “A comprehensive review and analysis of solar forecasting techniques,” Front. Energy, vol. 16, no. 2, pp. 187–223, Mar. 2021, doi: https://doi.org/10.1007/s11708-021-0722-7.
[2] A. Mellit, A. M. Pavan, E. Ogliari, S. Leva, and V. Lughi, “Advanced methods for photovoltaic output power forecasting: A review,” Appl. Sci., vol. 10, no. 2, p. 487, Jan. 2020, doi: https://doi.org/10.3390/app10020487.
[3] M. Gupta, A. Arya, U. Varshney, J. Mittal, and A. Tomar, “A review of PV power forecasting using machine learning techniques,” Prog. Eng. Sci., vol. 2, no. 1, p. 100058, Mar. 2025, doi: https://doi.org/10.1016/j.pes.2025.100058.
[4] J. Yu et al., “Deep Learning Models for PV Power Forecasting: Review,” Energies, vol. 17, no. 16, p. 3973, Aug. 2024, doi: https://doi.org/10.3390/en17163973.
[5] A. A. Hassan, D. M. Atia, H. T. El-Madany, and F. ElGhannam, “Multi-label machine learning for power forecasting of a grid-connected photovoltaic solar plant over multiple time horizons,” Sci. Rep., vol. 15, no. 1, p. 32676, Sep. 2025, doi: https://doi.org/10.1038/s41598-025-20251-y.
[6] Y. Xu, X. Ji, and Z. Zhu, “A photovoltaic power forecasting method based on the LSTM-XGBoost-EEDA-SO model,” Sci. Rep., vol. 15, no. 1, p. 30177, Aug. 2025, doi: https://doi.org/10.1038/s41598-025-16368-9.
[7] A. Mollasalehi and A. Farhadi, “Solar and Wind Power Forecasting: A Comparative Review of LSTM, Random Forest, and XGBoost Models,” arXiv preprint arXiv:2509.24059, Sep. 2025, doi: https://doi.org/10.48550/arXiv.2509.24059.
[8] A. S. Ahmad, S. K. Chattopadhyay, and B. K. Panigrahi, “A Quantitative Assessment of the Economic Viability of Photovoltaic Battery Energy Storage Systems,” Energies, vol. 17, no. 24, p. 6279, Dec. 2024, doi: https://doi.org/10.3390/en17246279.
[9] H. N. Hokmabad, O. Husev, J. Kurnitski, and J. Belikov, “Optimizing size and economic feasibility assessment of photovoltaic and energy storage setup in residential applications,” Sustain. Energy Grids Netw., vol. 38, p. 101385, Jun. 2024, doi: https://doi.org/10.1016/j.segan.2024.101385.
[10] Altair, “Altair RapidMiner Documentation.” [Online]. Available: https://docs.rapidminer.com/
[11] NASA, “NASA POWER | Data Access Viewer (DAV).” [Online]. Available: https://power.larc.nasa.gov/data-access-viewer/
[12] Altair, “Gradient Boosted Trees - Altair RapidMiner Documentation.” [Online]. Available: https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/trees/gradient_boosted_trees.html
[13] Altair, “Performance (Regression) - Altair RapidMiner Documentation.” [Online]. Available: https://docs.rapidminer.com/latest/studio/operators/validation/performance/predictive/performance_regression.html
[14] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geosci. Model Dev., vol. 15, no. 14, pp. 5481–5487, 2022, doi: https://doi.org/10.5194/gmd-15-5481-2022.
[15] K. J. Iheanetu, “Solar Photovoltaic Power Forecasting: A Review,” Sustainability, vol. 14, no. 24, p. 17005, Dec. 2022, doi: https://doi.org/10.3390/su142417005.
[16] Sungrow Power Supply Co., Ltd., “Home | SUNGROW.” [Online]. Available: https://vietnam.sungrowpower.com/.
