Modeling Electrical Energy Consumption in the Residential Sector Based on the Universal Thermal Climate Index (UTCI) in Iran

Document Type : Research Paper

Authors

1 Geographical Sciences Department , University of Hormozgan

2 Geographical sciences department, Faculty of humanities, University of Hormozgan

10.22034/gp.2024.60487.3234

Abstract

The study aimed to introduce the most effective model for estimating energy consumption through the modeling of residential electrical energy consumption. .Reanalysis climate data from ECMWF spanning the years 2003 to 2022 were acquired, along with the annual electrical energy consumption data of the residential sector across Iranian provinces. Pearson correlation coefficient was employed to analyze the relationships between variables, and the Mann-Kendall non-parametric test was utilized to scrutinize trends in these variables. Four regression and Artificial Intelligence (AI)-based models, namely Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and Random Forest (RF), were employed to model electric energy consumption. The performance of these models was assessed using metrics such as Root Mean Squared Error (RMSE), Coefficient of Determination (R2), and Standard Deviation (SD), evaluated‌ through a Taylor diagram. Provinces. In 22 provinces, a positive correlation was observed, whereas in 9 provinces, a negative correlation was identified. Analysis of the temporal changes indicates a consistent increase in minimum and maximum temperatures as well as electrical energy consumption across all provinces. However, it is noteworthy that the UTCI displayed a negative trend in several provinces. The stepwise regression model revealed that in 23 provinces, the sole influential variable is the minimum temperature. Notably, in the provinces of Isfahan, South Khorasan, and Kerman, both minimum temperature and the UTCI were identified as influential variables. Conversely, in Ardabil, Gilan, and Golestan provinces, only the maximum temperature featured in the regression equation. Modeling outcomes underscored the superior performance of the ANN model in comparison to the other three models. The ANN model exhibited the highest correlation coefficient at 0.79, coupled with the RMSE of 360. Following in ranking, the MLR, SVM, and RF models demonstrated progressively lower levels of performance

Keywords

Main Subjects

Full Text

هدف : یکی از پیامدهای گرمایش جهانی، افزایش تنش‌های حرارتی و به تبع آن، افزایش مصرف انرژی الکتریکی در بخش مسکونی می‌باشد. مطالعه حاضر با هدف شناسایی تاثیرگذارترین متغیر اقلیمی بر مصرف انرژی الکتریکی بخش مسکونی و همچنین معرفی بهترین مدل در برآورد مصرف، با استفاده از  مدل‌سازی مصرف انرژی الکتریکی انجام شده است.

روش : داده‌های اقلیمی برای سال‌های 2003 تا 2022 از مرکز پیش‌بینی میان مدت وضع هوا ([1]ECMWF) و همچنین دادهای مصرف سالیانه انرژی الکتریکی بخش مسکونی به تفکیک استان‌های ایران، از توانیر دریافت شد. به منظور بررسی روند، از آزمون ناپارامتریک من-کندال استفاده گردید و برای مدل‌سازی مصرف انرژی الکتریکی، از مدل‌های، رگرسیون خطی چندگانه(MLR[2]) ، شبکه‌های عصبی مصنوعی (ANN[3])، ماشین بردار پشتیبانی (SVM[4]) و جنگل تصادفی (RF[5]) استفاده شد.

 نتایج : همبستگی میان مصرف انرژی الکتریکی بخش مسکونی و دمای‌کمینه و بیشینه، در تمام استان‌های کشور مثبت است. به طوری که در 22 استان همبستگی مثبت و در 9 استان همبستگی منفی می‌باشد. نتایج حاصل از برسی روند تغییرات نشان داد که دمای‌کمینه، دمای بیشینه و انرژی الکتریکی، در همه استان‌ها روند افزایشی داشته‌ است اما شاخص UTCI، روند منفی را هم در تعدادی از استان‌ها ثبت کرده است، به طوری که در 9 استان روند منفی و در 22 استان روند آن مثبت بوده است. همچنین رابطه‌ای که از مدل رگرسیونی گام به گام حاصل شد، نشان داد که در 23 استان، تنها متغیر تاثیرگذار، دمای کمینه می‌باشد. در استان‌های اصفهان، خراسان جنوبی و کرمان، متغیر‌های دمای‌کمینه و شاخص UTCI به عنوان متغیر تاثیرگذار شناخته شد. در استان‌های اردبیل، گیلان و گلستان، تنها دمای بیشینه وارد معادله گردید. نتایج حاصل از مدل‌سازی نشان داد، مدل ANN عملکرد بهتری را نسبت به سه مدل دیگر داشته است. به طوری که بیشترین ضریب همبستگی با 79/0 و حداقل خطا با 360 را ثبت کرده است. مدل‌های MLR، SVM و RF به ترتیب عملکرد بهینه، در رتبه‌های بعدی قرار دارند.

نتیجه گیری : با توجه به نتایج مطالعات متعدد که نشان دهنده روند افزایشی دما به ویژه دمای‌کمینه تا انتهای قرن بیست و یکم می‌باشد و همچنین نتایج تحقیق حاضر که نشان داد، میان پارامتر‌های دمایی به ویژه دمای‌کمینه و مصرف انرژی الکتریکی همبستگی قوی وجود دارد، باید برنامه‌ریزی صحیح و دقیقی به منظور تامین انرژی الکتریکی مورد نیاز ساکنان در آینده صورت گیرد.

 

[1] European Centre for Medium-Range Weather Forecasts

[2] Multiple linear regression

[3] Artificial Neural Networks

[4] Support vector machines

[5] Random Forest

References

gatonovic-Kustrin, S., & Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of Pharmaceutical and Biomedical Analysis, 22(5), 717-727. https://doi.org/https://doi.org/10.1016/S0731-7085(99)00272-1
Alijani, B., Shamsipour, A., Motmaen Arani, A. (2017). Statistical Analysis of Thermal Crisis of Qom in Relation to Energy Consumption. Journal of Geography and Environmental Hazards, 6(1), 1-17. (in persian)
Asgari oskoei, m. r. (2002). time series prediction by neural nets. iranian journal of economic research, 4(12), 69-96. (in persian)
Asgari, H. A., jahangiri, S. (2022). Investigating the Causality of Climate Change and Energy Consumption in the Main Sectors of the Iranian Economy by Toda-Yamamato Method. Geographical Planning of Space, 11(42) (in persian)
babaeian, I. erfani, A. Entezari, A. baaghideh, M. (2017). Future Perspective of Electricity Consumption in Iran during the Period 2011-2100 under Climate Change Scenarios using Downscaling of General Circulation Models. Geography and Environmental Planning, 27(4), 131-144. (in persian)
Biau, G. (2012). Analysis of a random forests model. The Journal of Machine Learning Research, 13, 1063-1095.
Bröde, P., Fiala, D., Blazejczyk, K., Holmér, I., Jendritzky, G., Kampmann, B., Tinz, B., & Havenith, G. (2011). Deriving the operational procedure for the Universal Thermal Climate Index (UTCI). International journal of biometeorology, 56, 481-494. https://doi.org/10.1007/s00484-011-0454-1
Cheng, Y. Ekici, E. Yildiz, G. Yang, Y. Coward, B. Wang, Jiawei. (2023). Applied machine learning for prediction of waste plastic pyrolysis towards valuable fuel and chemicals production. Journal of Analytical and Applied Pyrolysis. 169. 105857. 10.1016/j.jaap.2023.105857. 
Fallah Ghalhari G, Mayvaneh F, Shakeri F. (2015). Evaluation of thermal comfort and human health using Universal Thermal Climate Index (UTCI) Case Study: Kurdistan province. ijhe, 8 (3), 367-378 (in persian)
farajzadeh, M, & ahmad abadi, A. (2010). assessment and zoning of tourism climate of iran using tourism climate index (tci). physical geography research quarterly, 42(71), 31-42. (in persian)
Farhood S, Khoorani A, Eftekharian A. (2023). Detecting Trends in Extreme Temperature and Precipitation events with Different Return Periods in Iran. Journal of Spatial Analysis Environmental Hazards, 10 (2), 149-166 (in persian)
Fiala, D., Havenith, G., Bröde, P., Kampmann, B., & Jendritzky, G. (2012). UTCI-Fiala multi-node model of human heat transfer and temperature regulation. Int J Biometeorol, 56(3), 429-441. https://doi.org/10.1007/s00484-011-0424-7
Figueiredo, D., Júnior, S., & Rocha, E. (2011). What is R2 all about?. Leviathan-Cadernos de Pesquisa Polútica, 3, 60-68. https://doi.org/10.11606/issn.2237-4485.lev.2011.132282
George, S. tavropoulos, Robert van, V. Frederik-Jan van, S. Agnieszka, S.(2020). Random Forest and Ensemble Methods. Elsevier
Heidari, H. Najjar firoozjaee, M. Saeidpour, l. (2011). investigating the relationship between electricity consumption, electricity price and economic growth in iran. journal of economic research and policies, 19(59), 175-199. (in persian)
Hu, Q., Tang, J., Gao, X., Wang, S., Zhang, D., Qin, Y., Wang, Q., Zhou, Y., Huang, N., Penuelas, J., Sardans, J., Canadell, J. G., Ciais, P., Pan, Z., An, P., Xu, L., & Lun, F.. Future hotter summer greatly increases residential electricity consumption in .(2023)
Jahanbakhsh, S. Tadayyoni, M. Salmanpur, R. Jahanbakhsh, E. (2009). the relationship between temperature and heart attack in ahar township. journal of physical geography, 2(5), 29-37. (in persian)
Jianwei, Q., Yang, Z., Han, F., Baoshi, H., & Xuankai, M. (2023). Spatial–Temporal Characteristics of Human Thermal Comfort in Xinjiang: Based on the Universal Thermal Climate Index from 1981 to 2019. Land, 12, 1864. https://doi.org/10.3390/land12101864
Kadkhoda, E. Omidvar, K. Zarrin, A. Mazidi, A. Dadashi-Roudbari, A. (2023). Projected heat stress in Iran based on CMIP6 multi-model ensemble. Iranian Journal of Geophysics, 17(2), 157-173. (in persian)
Khoorani, A., & Monjazeb Marvdashti, S. (2014). Investigating the Effects of Climate Change on the Number of Visitors in Hengam Island. Physical Geography Research, 46(1), 109-122. doi: 10.22059/jphgr.2014.50622 (in persian)
Khoorani, A., Moradi, A., & Moradi, A. (2023). Projecting changes in the thermal comfort of coastal tourists in Hormozgan province. Physical Geography Research, 55(2), 71-87. doi: 10.22059/jphgr.2023. 359547.1007773 (in persian)
Khorshiddoust, A. M., jahanbakhshasl, S., abbasighasrik, Z., & abbasighasrik, F. (2023). Analysis and Prediction of Minimum Temperatures in Kurdistan Province Using Climatic Scenarios. Journal of Geography and Planning, 27(86), 149-166. doi: 10.22034/gp.2021.44023.2762(in persian)
Kim, M. K., Kim, Y.-S., & Srebric, J. (2020). Predictions of electricity consumption in a campus building using occupant rates and weather elements with sensitivity analysis: Artificial neural network vs. linear regression. Sustainable Cities and Society, 62, 102385.
Kyaw, A. K., Hamed, M. M., & Shahid, S. (2023). Spatiotemporal changes in Universal Thermal Climate Index over South Asia. Atmospheric Research, 292, 106838. https://doi.org/https://doi. org/10.1016/j. atmosres. 2023.106838
lukić, m., & djuric, d. (2023). thermal comfort in belgrade, serbia: utci-based seasonal and annual analysis for the period 1991-2020. 28, 77-88. https://doi.org/10.59456/afts.2023.1528.077l
Mahdavian, S., Zeynali, B., & Salahi, B. (2023). Evaluation of land use changes in Kiwi Chay Basin and analysis of precipitation and temperature changes in future periods with CMIP5 models. Journal of Geography and Planning, 27(85), 133-143. doi: 10.22034/gp.2022.50623.2977
Ministry of Energy, (2019). Dialogue with the ministry of energy information base. Retrieved from https://news.moe.gov.ir/News-List/40791. (in persian)
Mizban, H. Faramarzi, A. Mohebalipour, N. Khayavi, M. (2016). Stepwise regression analysis of independent variables in the experiment of investigating some agronomic traits of eight new varieties of rainfed safflower in zanjan province. The First National Conference on New Achievements in Agricultural and Natural Resource Research. (in persian)
Mohammadi, M., Khoorani, A. 2024. Spatiotemproal changes and hot spots of UTCI index over Iran. Urban Climate, 56, 102031. https://doi.org/10.1016/j.uclim.2024.102031.
Molodi, G. khorani, A. moradi, A. (2016) Impacts of climate change on heat waves in northern coast of Persian Gulf. Journal of Spatial Analysis Environmental Hazards, 3 (1), 1-14. (in persian)
Roffe, S., Van der Walt, A., & Fitchett, J. (2023). Spatiotemporal characteristics of human thermal comfort across southern Africa: an analysis of the Universal Thermal Climate Index (UTCI) for 1971–2021. International Journal of Climatology, 43. https://doi.org/10.1002/joc.8009
Salmani, A., Mojarrad, F.(2019). Analysis of Relationship between Climatic Variables and Electricity Consumption and Estimated Demand by General Circulation Models in Western Iran. Physical Geography Research, 51(2), (in persian)
Schonlau, M., & Zou, R. Y. (2020). The random forest algorithm for statistical learning. The Stata Journal, 20(1), 3-29.
Shin, J., Yang, H., & Kim, C. (2019). The relationship between climate and energy consumption: The case of South Korea. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 45, 1-16. https://doi.org/10.1080/15567036.2019.1673853
Shokri Ganjavi, H. & Nazarzadeh, J. (2005). Study of the Effect of air temperature changes on the average daily electricity consumption in the country. Energy of Iran, 9(20). (in persian)
Valizadeh, M., & Khoorani, A. (2022). The impact of climate change on the outdoor tourism with a focus on the outdoor tourism climate index (OTCI) in Hormozgan province, Iran. Theoretical and Applied Climatology, 150, 1-8. https://doi.org/10.1007/s00704-022-04248-5
Wang, F., Shao, W., Yu, H., Kan, G., He, X., Zhang, D., Ren, M., & Wang, G. (2020). Re-evaluation of the Mann-Kendall test power for detecting monotonic trends in hydro-meteorological time series. Frontiers in Earth Science, 8. https://doi.org/10.3389/feart.2020.00014
Zandi, R., & Shahriyar, F. (2024). Evaluation of time series relationship between land use changes and land surface temperature in desert cities (case study: Yazd city). Journal of Geography and Planning, (), -. doi: 10.22034/gp.2024.60544.3237. (in persian)
Zhang, C., Liao, H., & Mi, Z. (2019). Climate impacts: temperature and electricity consumption. Natural Hazards, 99(3), 1259-1275. https://doi.org/DOI:101007/s11069-019-03653-w

Files

Share

How to cite

Statistics