Optimal sizing and costing of solar system for automotive industrial in Thailand base on seasonal load forecasting with NARX model
DOI:
https://doi.org/10.18686/cest546Keywords:
load forecasting; Nonlinear AutoRegressive with eXogenous inputs model (NARX model); solar system; Battery Energy Storage Systems (BESS)Abstract
This research presents the optimal sizing and costing of the solar system and battery energy storage system for automotive industrial base on load forecasting with nonlinear autoregressive using exogenous inputs of neural networks. The model uses hourly electricity consumption data from industrial plants, local temperature, and working or holiday days as training, validation, and testing data. For the annual and seasonal electricity forecasting models, the electricity consumption data is divided by season in Thailand, namely summer season (February–May), rainy season (June–September), and winter season (October–January). The experimental results found that the seasonal forecasting model was more effective, with a mean squared error (MSE) of 0.014, which is lower than the annual forecasting model with an MSE of 0.0161. The data obtained from seasonal electricity forecasting will be used in the design of solar systems and Battery Energy Storage Systems (BESS) using PVsyst software. The results from the system simulation show that the system consists of 336 solar panels with a total capacity of 208 kWp and a BESS system with a capacity of 1,565.4 kWh. It can produce 310,201 kWh of electricity per year and deliver 77,983 kWh of energy to the grid. Finally, this project can pay back within 7.2 years.
References
1. Yang C, Yin C, Wu Y, et al. Atomic insights into the deformation mechanism of an amorphous wrapped nanolamellar heterostructure and its effect on self-lubrication. Journal of Materials Research and Technology. 2023; 26: 4206–4218. doi: 10.1016/j.jmrt.2023.08.215
2. Zhou Q, Jiao Z, Huang Z, et al. Wear-resistant CrCoNi nanocrystalline film via friction-driven surface segregation. Acta Materialia. 2024; 279: 120299. doi: 10.1016/j.actamat.2024.120299
3. Dong Y, Jiao Z, Ma Y, et al. A systematic review on advanced surface coating technologies for high-pressure piston pumps. Defence Technology. 2025; S2214914725003423. doi: 10.1016/j.dt.2025.10.018
4. Hua D, Xia Q, Li J, et al. Atomistic insights into the role of graphene sheets in CoCrNi/graphene composites. Acta Materialia. 2025; 287: 120809. doi: 10.1016/j.actamat.2025.120809
5. Office of the National Economic and Social Development Council. The Thirteenth National Economic and Social Development Plan (2023–2027). Office of the Prime Minister; 2023.
6. Mikayilov J, Alyamani R, Darandary A, et al. Modeling and Forecasting Industrial Electricity Demand for Saudi Arabia: Uncovering Regional Characteristics. The Electricity Journal. 2023; 36(8). doi: 10.30573/KS--2021-DP22
7. Habbak H, Mahmoud M, Metwally K, et al. Load Forecasting Techniques and Their Applications in Smart Grids. Energies. 2023; 16(3): 1480. doi: 10.3390/en16031480
8. Mediavilla MA, Dietrich F, Palm D. Review and analysis of artificial intelligence methods for demand forecasting in supply chain management. Procedia CIRP. 2022; 107: 1126–1131. doi: 10.1016/j.procir.2022.05.119
9. Tarmanini C, Sarma N, Gezegin C, et al. Short term load forecasting based on ARIMA and ANN approaches. Energy Reports. 2023; 9: 550–557. doi: 10.1016/j.egyr.2023.01.060
10. Song X, Chen Z, Wang J, et al. A multi-stage LSTM federated forecasting method for multi-loads under multi-time scales. Expert Systems with Applications. 2024; 253: 124303. doi: 10.1016/j.eswa.2024.124303
11. Zhou B, Zhang Y, Fei C, et al. Short-term forecasting of building heating load based on MVMD-SSA-LSTM. Clean Energy Science and Technology. 2025; 3(1): 297. doi: 10.18686/cest297
12. Rangel E, Cadenas E, Campos-Amezcua R, et al. Enhanced Prediction of Solar Radiation Using NARX Models with Corrected Input Vectors. Energies. 2020; 13(10): 2576. doi: 10.3390/en13102576
13. Ali M, Syed MA, Khalid M. NARX Recurrent Neural Network Based Short Term Residential Load Forecasting Considering the Effects of Multiple Weather Features. In: Proceedings of the 2022 IEEE IAS Global Conference on Emerging Technologies (GlobConET); 20 May 2022; Arad, Romania. pp. 557–561. doi: 10.1109/GlobConET53749.2022.9872509
14. Zuazo IZ, Boussaada Z, Aginako N, et al. Short-Term Load Forecasting of building electricity consumption using NARX Neural Networks model. In: Proceedings of the 2021 6th International Conference on Smart and Sustainable Technologies (SpliTech); 8 September 2021; Bol and Split, Croatia, pp. 1–6. doi: 10.23919/SpliTech52315.2021.9566440
15. Anrizal Akbar MA, Yunus AMS, Tangko J. PVSYST-Based Solar Power Plant Planning. INTEK: Jurnal Penelitian. 2022; 9(1): 89–92. doi: 10.31963/intek.v9i1.3789
16. Islam MS, Islam F, Habib MA. Feasibility Analysis and Simulation of the Solar Photovoltaic Rooftop System Using PVsyst Software. International Journal of Education and Management Engineering. 2022; 12(6): 21–32. doi: 10.5815/ijeme.2022.06.03
17. Singh TSD, Shimray BA, Singh AB, et al. Performance measurement of 5 kWp rooftop grid-connected SPV system in moderate climatic region of Imphal, Manipur, India. Energy for Sustainable Development. 2023; 73: 292–302. doi: 10.1016/j.esd.2023.02.009
18. Alkahtani MM, Kamari NAM, Zainuri MAAM, et al. Design of Grid-Connected Solar PV Power Plant in Riyadh Using PVsyst. Energies. 2024; 17(24): 6229. doi: 10.3390/en17246229
19. Hanni JR, Bukya M, Kumar P, et al. Analysis and Modeling of 581 kWp Grid-Integrated Solar Photovoltaic Power Plant of Academic Institution Using PVsyst. Engineering Proceedings. 2023; 59(1): 142. doi: 10.3390/engproc2023059142
20. Slouma S, Boulaares W, Maity S, et al. Optimal design of stand-alone photovoltaic system based on battery storage system: A case study of Borj Cedria in Tunisia. Clean Energy Science and Technology. 2023; 1(1). doi: 10.18686/cest.v1i1.28
21. Touahri T, Laribi S, Maouedj R, et al. Feasibility Analysis of a Solar PV Grid-Connected System Using PVsyt Software Tools. In: Smart Energy Empowerment in Smart and Resilient Cities, Lecture Notes in Networks and Systems. Springer International Publishing; 2020. pp. 425–433. doi: 10.1007/978-3-030-37207-1_45
22. Azeem A, Ismail I, Jameel SM, et al. Electrical Load Forecasting Models for Different Generation Modalities: A Review. IEEE Access. 2021; 9: 142239–142263. doi: 10.1109/ACCESS.2021.3120731
23. Tsalikidis N, Mystakidis A, Tjortjis C, et al. Energy load forecasting: one-step ahead hybrid model utilizing ensembling. Computing. 2024; 106(1): 241–273. doi: 10.1007/s00607-023-01217-2
24. Zor K, Timur O, Teke A. A state-of-the-art review of artificial intelligence techniques for short-term electric load forecasting. In: Proceedings of the 2017 6th International Youth Conference on Energy (IYCE); 21–24 June 2017; Budapest, Hungary, pp. 1–7. doi: 10.1109/IYCE.2017.8003734
25. Groß A, Lenders A, Schwenker F, et al. Comparison of short-term electrical load forecasting methods for different building types. Energy Informatics. 2021; 4(S3): 13. doi: 10.1186/s42162-021-00172-6
26. Liao Z, Pan H, Huang X, et al. Short-term load forecasting with dense average network. Expert Systems with Applications. 2021; 186: 115748. doi: 10.1016/j.eswa.2021.115748
27. Matrenin P, Safaraliev M, Dmitriev S, et al. Medium-term load forecasting in isolated power systems based on ensemble machine learning models. Energy Reports. 2022; 8: 612–618. doi: 10.1016/j.egyr.2021.11.175
28. Lindberg KB, Seljom P, Madsen H, et al. Long-term electricity load forecasting: Current and future trends. Utilities Policy. 2019; 58: 102–119. doi: 10.1016/j.jup.2019.04.001
29. Agrawal RK, Muchahary F, Tripathi MM. Long term load forecasting with hourly predictions based on long-short-term-memory networks. In: Proceedings of the 2018 IEEE Texas Power and Energy Conference (TPEC); 8–9 February 2018; College Station, TX, USA. pp. 1–6. doi: 10.1109/TPEC.2018.8312088
30. Huang Q, Li Y, Liu S, et al. Hourly Load Forecasting Model Based on Real-Time Meteorological Analysis. In: Proceedings of the 2016 8th International Conference on Computational Intelligence and Communication Networks (CICN); 23–25 December 2016; Tehri, India. pp. 488–492. doi: 10.1109/CICN.2016.101
31. Som T. Time Load Forecasting: A Smarter Expertise Through Modern Methods. In: Prediction Techniques for Renewable Energy Generation and Load Demand Forecasting, Lecture Notes in Electrical Engineering. Springer Nature; 2023. pp. 153–176. doi: 10.1007/978-981-19-6490-9_9
32. Chavan M. Time Series Analysis in Electrical Load Forecasting. Panamerican Mathematical Journal. 2024; 35(1s): 210–219. doi: 10.52783/pmj.v35.i1s.2307
33. Eljazzar MM, Hemayed EE. Impact of Economic, Social and Meteorological Factors on Load Forecasting in Different Timeframes—A Survey. In: 2020 5th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE); 1 December 2020; Jaipur, India. pp. 1–6. doi: 10.1109/ICRAIE51050.2020.9358323
34. Yang J, Tuo M, Lu J, et al. Analysis of Weather and Time Features in Machine Learning-aided ERCOT Load Forecasting. In: Proceedings of the 2024 IEEE Texas Power and Energy Conference (TPEC); 12 February 2024; College Station, TX, USA. pp. 1–6. doi: 10.1109/TPEC60005.2024.10472183
35. Lindèn M, Helbrink J, Nilsson M, et al. Categorisation of electricity customers based upon their demand patterns. CIRED—Open Access Proceedings Journal. 2017; 2017(1): 2628–2631. doi: 10.1049/oap-cired.2017.0878
36. Jiang Z, Lin R, Yang F, et al. Comparing Electricity Consumer Categories Based on Load Pattern Clustering with Their Natural Types. In: Algorithms and Architectures for Parallel Processing, Lecture Notes in Computer Science. Springer International Publishing; 2017. pp. 658–667. doi: 10.1007/978-3-319-65482-9_51
37. Al Sarhan FF. Design an on-grid PV system to supply electricity to a school in Babil city using PVsyst software. Journal of Applied Research and Technology. 2024; 22(5): 617–626. doi: 10.22201/icat.24486736e.2024.22.5.2411
38. Zar JH. Spearman Rank Correlation: Overview. In: Wiley StatsRef: Statistics Reference Online. Wiley; 2014. doi: 10.1002/9781118445112.stat05964
39. Bishara AJ, Hittner JB. Testing the significance of a correlation with nonnormal data: Comparison of Pearson, Spearman, transformation, and resampling approaches. Psychological Methods. 2012; 17(3): 399–417. doi: 10.1037/a0028087
40. Brydges CR. Effect Size Guidelines, Sample Size Calculations, and Statistical Power in Gerontology. Innovation in Aging. 2019; 3(4): igz036. doi: 10.1093/geroni/igz036
41. Climate of Thailand. Available online: https://www.tmd.go.th/info/ (accessed on 24 January 2025). (in Thai)
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Siamrat Phonkaphon, Ekawit Songkohb, Karun Sirichunchuen, Pramuk Unahalekhaka
This work is licensed under a Creative Commons Attribution 4.0 International License.
.jpg)
.jpg)
