![سامانه نشر مجلات علمی دانشگاه تهران](./data/logo.png)
تعداد نشریات | 162 |
تعداد شمارهها | 6,578 |
تعداد مقالات | 71,072 |
تعداد مشاهده مقاله | 125,681,542 |
تعداد دریافت فایل اصل مقاله | 98,911,707 |
مدلسازی و پیشبینی روند مصرف انرژی برق در ایران | ||
فصلنامه سیستم های انرژی پایدار | ||
دوره 3، شماره 3، تیر 1403، صفحه 323-339 اصل مقاله (1.54 M) | ||
نوع مقاله: مقاله پژوهشی | ||
شناسه دیجیتال (DOI): 10.22059/ses.2024.377117.1081 | ||
نویسندگان | ||
مهسا ابراهیمی نزهمی1؛ محمد میرباقری جم* 2؛ حمیده محرمی1 | ||
1کارشناسی ارشد برنامهریزی سیستمهای اقتصادی، دانشگاه صنعتی شاهرود، شاهرود، ایران | ||
2استادیار، دانشکدۀ مهندسی صنایع و مدیریت، دانشگاه صنعتی شاهرود، شاهرود، ایران | ||
چکیده | ||
پیشبینی روند مصرف انرژی کشور در رفع مشکل ناترازی (شکاف بین عرضه و تقاضا) آن کمککننده است. با توجه به اهمیت نسبی انرژی برق در سبد انرژی مصرفی کشور، در این پژوهش روند مصرف برق در ایران مدلسازی و پیشبینی شده است. عوامل و متغیرهای مؤثر بر روند مصرف برق کشور بر اساس مطالعههای پیشین شناسایی شده و دادههای مربوطه طی دورۀ ۱۳۵۷ تا ۱۴۰۰ برای ساخت مدلهای پیشبینی جمعآوری شده است. در پیشبینی روند مصرف برق از مدل و روشهای متعددی ازجمله روش استفاده از شاخصهای ساده، شدت مصرف انرژی، خط روند مصرف، مدل رگرسیون و شبکۀ عصبی استفاده شده است. نتایج تخمین مدل رگرسیون نشان میدهد روند مصرف برق در کشور تحت تأثیر درآمد سرانه و مصرف دورۀ قبل است و از لحاظ آماری سایر متغیرها مانند قیمت انرژی، دمای هوا و بارندگی اثر معنادار بر روند آن نداشته است. مصرف برق طی سالهای ۱۳۵۷ـ 1400 تقریباً 14/22 برابر شده و رشد متوسط سالیانۀ آن 49/7 درصد است که بر اساس این پیشبینی مصرف برق برای سال ۱۴۰۵ برابر با ۴۵۵۶۰۳ هزار مگاوات است. در حالی که پیشبینی مصرف برق در این سال با مدل رگرسیون برابر ۳۶۸۹۵۹ هزار مگاوات است. مقایسۀ نتایج پیشبینی مصرف برق نشان میدهد دقت پیشبینی مدلها و رویکردهای مختلف یکسان نیست و روش رگرسیون میزان خطای اندازهگیری کمتری نسبت به دیگر روشهای مورد بررسی در پیشبینی روند مصرف برق دارد. | ||
کلیدواژهها | ||
روند مصرف برق؛ مدلهای پیشبینی؛ مدل رگرسیون؛ شبکه عصبی؛ شاخصهای ساده پیشبینی | ||
عنوان مقاله [English] | ||
Modeling and Forecasting the Trend of Electricity Consumption in Iran | ||
نویسندگان [English] | ||
Mahsa Ebrahimi Nezhomi1؛ Mohammad Mirbagherijam2؛ Hamideh Moharrami1 | ||
1. M.A. in Economic Systems Planning, Shahrood University of Technology, Shahrood, Iran | ||
2Assistant Professor, Department of Industrial Engineering and Management, Shahrood University of Technology, Shahrood, Iran | ||
چکیده [English] | ||
Accurate forecasting of a country's energy consumption trend is crucial in addressing the imbalance between supply and demand. Given the significant contribution of electricity to Iran's energy consumption portfolio, this research aims to model and forecast the trend of electricity consumption in Iran. Factors influencing the trend of electricity consumption were identified based on previous studies, and relevant data were collected for the period 1978-2021develop forecast models. Various models and methods were employed to predict the trend of electricity consumption, including simple indicators, energy consumption intensity, trend line analysis, regression modeling, and neural networks. The regression model estimation results indicate that the trend of electricity consumption in Iran is significantly influenced by per capita income and consumption in the previous period. From a statistical perspective, other variables such as energy price, air temperature, and rainfall did not have a significant impact on the trend. The results show that electricity consumption in Iran has increased by approximately 22.14% over the period 1978-2021, with an average annual growth rate of 7.49%. According to the forecast, electricity consumption is expected to reach 455,603 thousand megawatts by 2026. In contrast, the regression model forecast for this year is 368,959 thousand megawatts. A comparison of the prediction results reveals that the accuracy of different models and approaches varies, with the regression method exhibiting a lower measurement error than the other investigated methods in predicting the electricity consumption trend. | ||
کلیدواژهها [English] | ||
Electricity consumption trend, forecasting models, regression model, neural network, simple predictive indicators | ||
مراجع | ||
[1]. Goto M, Sueyoshi T. Electric power market reform in Japan after Fukushima Daiichi nuclear plant disaster: Issues and future direction. International Journal of Energy Sector Management. 2015; 9(3):336-60. doi:10.1108/IJESM-05-2014-0009.
[2]. Chapagain K, Kittipiyakul S, Kulthanavit P. Short-term electricity demand forecasting: Impact analysis of temperature for Thailand. Energies. 2020; 13(10):2498. doi:10.3390/en13102498.
[3]. Bhatia R. Energy demand analysis in developing countries: a review. The Energy Journal. 1987; 8:1-33.
[4]. Bhattacharyya SC. Energy economics: concepts, issues, markets and governance. Springer Nature; 2019.
[5]. Olaleye SO, Akinbode SO. Analysis of households’ demand for alternative power supply in Lagos State, Nigeria. Curr Res J Soc Sci. 2012; 4(2):121-7.
[6]. Bianco V, Manca O, Nardini S. Electricity consumption forecasting in Italy using linear regression models. Energy. 2009; 34(9):1413-21. doi:10.1016/j.energy.2009.06.034.
[7]. Aguilar Madrid E, Antonio N. Short-term electricity load forecasting with machine learning. Information. 2021; 12(2):50. doi:10.3390/info12020050.
[8]. Mirza FM, Bergland O. The impact of daylight saving time on electricity consumption: Evidence from southern Norway and Sweden. Energy Policy. 2011; 39(6):3558-71.
[9]. Sewdien VN, Preece R, Torres JR, Rakhshani E, van der Meijden MAMM. Assessment of critical parameters for artificial neural networks based short-term wind generation forecasting. Renew Energy. 2020; 161:878-92. doi:10.1016/j.renene.2020.07.117.
[10]. International Energy Agency (IEA). Global energy review 2019. IEA; 2020. Available from: https://www.iea.org/reports/global-energy-review-2019. License: CC BY 4.0.
[11]. Zahedi R, Sadeghitabar E, Khazaee M, Faryadras R, Ahmadi A. Potentiometry of wind, solar and geothermal energy resources and their future perspectives in Iran. Environ Dev Sustain. 2024 Mar 9; 1-27. doi:10.1007/s10668-024-04633-2.
[12]. Ubani O. Determinants of the dynamics of electricity consumption in Nigeria. OPEC Energy Rev. 2013; 37(2):149-61. doi:10.1111/opec.12004.
[13]. Wahid F, Ullah H, Ali S, Jan SA, Ali A, Khan A, Bibi M. The determinants and forecasting of electricity consumption in Pakistan. Int J Energy Econ Policy. 2021; 11(1):241-8.
[14]. Ayasyifa S. Determinants of electricity consumption in Indonesia. Jurnal Ilmu Ekonomi Terapan. 2022; 7(1). doi:10.20473/jiet.v7i1.30777.
[15]. O'Neill BC, Chen BS. Demographic determinants of household energy use in the United States. Popul Dev Rev. 2002; 28:53-88.
[16]. Lin B, Raza MY. Analysis of electricity consumption in Pakistan using index decomposition and decoupling approach. Energy. 2021; 214:118888. doi:10.1016/j.energy.2020.118888.
[17]. Park J, Yun SJ. Social determinants of residential electricity consumption in Korea: Findings from a spatial panel model. Energy. 2022; 239:122272. doi:10.1016/j.energy.2021.122272.
[18]. Zhang C, Liao H, Mi Z. Climate impacts: temperature and electricity consumption. Nat Hazards. 2019; 99(3):1259-75. doi:10.1007/s11069-019-03653-w.
[19]. Owoeye T, Olanipekun DB, Ogunsola AJ, Kutu AA. Energy prices, income and electricity consumption in Africa: The role of technological innovation. Int J Energy Econ Policy. 2020; 10(5):392-400.
[20]. Moghadam SS, Gholamian MR, Zahedi R, Shaqaqifar M. Designing a multi-purpose network of sustainable and closed-loop renewable energy supply chain, considering reliability and circular economy. Appl Energy. 2024 Sep 1; 369:123539. doi:10.1016/j.apenergy.2024.123539.
[21]. Khah MV, Zahedi R, Eskandarpanah R, Mirzaei AM, Farahani ON, Malek I, Rezaei N. Optimal sizing of residential photovoltaic and battery system connected to the power grid based on the cost of energy and peak load. Heliyon. 2023 Mar 1; 9(3). doi:10.1016/j.heliyon.2023.e14414.
[22]. Shaghaghi A, Zahedi R, Ghorbani M, Ranjbar Z, Arzhangi SS, Keshavarzzadeh M, Alipour H. State estimation for distribution power systems by applying an advanced optimization approach. Expert Syst Appl. 2024 Apr 15; 240:122325. doi:10.1016/j.eswa.2023.122325.
[23]. Ozoh P, Abd-Rahman S, Labadin J, Apperley M. A comparative analysis of techniques for forecasting electricity consumption. Int J Comput Appl. 2014; 88(15).
[24]. Klyuev RV, Morgoev ID, Morgoeva AD, Gavrina OA, Martyushev NV, Efremenkov EA, Mengxu Q. Methods of forecasting electric energy consumption: A literature review. Energies. 2022; 15(23):8919. doi:10.3390/en15238919.
[25]. Jain PK, Quamer W, Pamula R. Electricity consumption forecasting using time series analysis. In: Advances in Computing and Data Sciences: Second International Conference, ICACDS 2018, Dehradun, India; 2018 Apr 20-21. Revised selected papers, Part II. Singapore: Springer; 2018. p. 327-35. doi:10.1007/978-981-13-1813-9_33.
[26]. Yumuşak R, Özcan EC, Danışan T, Eren T. Electricity consumption forecast by artificial neural networks: The case of Turkey. Proceedings Book. 2019; 31.
[27]. Omidy MR, Omidy N, Asgari H, Jafari Eskandari M. Modeling and forecasting electricity production and consumption in Iran. Futur Stud Manag. 2016; 27(1):71-83. [Persian].
[28]. Fan GF, Wei X, Li YT, Hong WC. Forecasting electricity consumption using a novel hybrid model. Sustainable Cities and Society. 2020; 61:102320. doi:10.5815/ijisa.2021.05.02.
[29]. Yavari K, Zolghadr M. Modeling and forecasting short-term electricity consumption in the country using neural networks and wavelet transform (focusing on environmental and climatic effects). Energy Econ Stud. 2012; 9(33):1-29. [Persian].
[30]. Amiri Domari M, Khateebi Bardsiri O. Forecasting electricity consumption using a combination of neural network and harmony search optimization algorithm. The 5th National Conference on Computer Science and Information Technology; 2018; Babol. Available from: https://civilica.com/doc/810304 [Persian].
[31]. Almuhaini SH, Sultana N. Forecasting long-term electricity consumption in Saudi Arabia based on statistical and machine learning algorithms to enhance electric power supply management. Energies. 2023; 16(4):2035. doi:10.3390/en16042035.
[32]. Botchkarev A. A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdisciplinary Journal of Information, Knowledge, and Management. 2019; 14:45-76. doi:10.28945/4184. | ||
آمار تعداد مشاهده مقاله: 149 تعداد دریافت فایل اصل مقاله: 140 |