مدل‏ سازی پیش ‏بینی کوتاه ‏مدت مصرف برق با استفاده از روش‏های هوش مصنوعی در استان گیلان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد، گروه مهندسی انرژی‏های نو و محیط ‏زیست، دانشکدۀ علوم و فنون نوین، دانشگاه تهران

2 معاونت علم و فناوری ریاست جمهوری

10.22059/ses.2023.350868.1015

چکیده

پیش‏بینی بار از مهم‌ترین جنبه‏های مدیریت مؤثر سیستم‏های قدرت است و به عوامل مختلفی از جمله ابزار و منابع تولید برق توسط هر شرکت، تقاضای بار الکتریکی، عوامل آب‌وهوایی، عوامل اقتصادی و فعالیت‏های انسانی بستگی دارد. براساس افق‏ زمانی، پیش‏بینی بار را می‏توان به سه گروه عمده پیش‏بینی کوتاه‏مدت، میان‏مدت و بلند‏مدت دسته‏بندی کرد. هدف اصلی این مقاله، پیش‏بینی کوتاه‏مدت مصرف برق، در شبکۀ برق منطقه‏ای استان گیلان است. در این پژوهش، پس از جمع‏آوری داده‏ها شامل سرعت باد، رطوبت نسبی، دما، نقطه شبنم، تعطیلات، طول روز و تأثیر کرونا، پیش‏پردازش روی آن‏ها انجام شده و با استفاده از الگوریتم خوشه‏بندی K_Means به پنج خوشه تقسیم می‌شوند. در ادامه روابط بین متغیرهای مستقل و وابسته مصرف برق در استان گیلان با استفاده از الگوریتم‏های رگرسیون خطی1، شبکۀ عصبی مصنوعی2 و رگرسیون بردار پشتیبان3 به همراه روش بهینه‏سازی جستجوی شبکه4، مورد بررسی قرار گرفته و در نرم‏افزار Python و در محیط Google Colab، بررسی و مدل‏سازی شده است. در خوشه‏بندی، الگوریتم‏های یادشده، روی تمامی خوشه‏ها و مجموع آن‏ها اعمال می‏شود. نتایج تحقیق در این مقاله نشان می‏دهد الگوریتم رگرسیون بردار پشتیبان، دقت بالاتر و زمان اجرای بیشتری نسبت به دو الگوریتم شبکۀ عصبی مصنوعی و رگرسیون خطی دارد. الگوریتم شبکۀ عصبی مصنوعی نسبت به رگرسیون خطی دارای خطای کمتر و زمان اجرای بیشتری است.

کلیدواژه‌ها

عنوان مقاله [English]

Modeling short-term forecast of electricity consumption using artificial intelligence methods in Gilan province

نویسندگان [English]

  • Mobina Simaee 1
  • Amirhosein Mirabadi 2
1 Master of Science, Department of Renewable Energies and Environment, Faculty of New Sciences and Technologies, University of Tehran, Iran
2 Science and Technology Vice-Presidency, Tehran, Iran
چکیده [English]

Load forecasting is one of the most important aspects of the effective management of power systems and depends on various factors such as the means and sources of electricity production by each company, electric load demand, weather factors, economic factors and human activities.. The main goal of this article is the STLF in the regional electricity grid of Guilan province. In this research, after collecting data including wind speed, relative humidity, temperature, dew point, holidays, day length and the effect of corona disease, pre-processing is done on them and they are divided into five clusters using K_Means clustering algorithm. In the following, the relationships between the independent and dependent variables of electricity consumption in Guilan province, using linear regression (LR) algorithms, artificial neural network (ANN) and support vector regression (SVR) along with the Grid search optimization method, were investigated and analyzed in Python software and modeled in the Google Colab environment. The results show that the SVR algorithm has higher accuracy and longer implementation time than the two algorithms of ANN and LR.

کلیدواژه‌ها [English]

  • Electricity consumption forecasting
  • short-term electricity forecasting
  • support vector regression
  • linear regression
  • artificial neural network

مراجع

[1].          D. Lazos, A. B. Sproul, and M. Kay, “Optimisation of energy management in commercial buildings with weather forecasting inputs: A review,” Renew. Sustain. Energy Rev., vol. 39, pp. 587–603, 2014, doi: 10.1016/j.rser.2014.07.053.
[2].          V. N. Sewdien, R. Preece, J. L. R. Torres, E. Rakhshani, and M. van der Meijden, “Assessment of critical parameters for artificial neural networks based short-term wind generation forecasting,” Renew. Energy, vol. 161, pp. 878–892, 2020, doi: 10.1016/j.renene.2020.07.117.
[3] K. Chapagain, S. Kittipiyakul, and P. Kulthanavit, “Short-term electricity demand forecasting: Impact analysis of temperature for Thailand,” Energies, vol. 13, no. 10, pp. 1–29, 2020, doi: 10.3390/en13102498.
[4].          M. M. Rahman et al., “Prospective methodologies in hybrid renewable energy systems for energy prediction using artificial neural networks,” Sustain., vol. 13, no. 4, pp. 1–28, 2021, doi: 10.3390/su13042393.
[5].          M. J. Gul, G. M. Urfa, A. Paul, J. Moon, S. Rho, and E. Hwang, “Mid-term electricity load prediction using CNN and Bi-LSTM,” J. Supercomput., vol. 77, no. 10, pp. 10942–10958, 2021, doi: 10.1007/s11227-021-03686-8.
[6].          F. C. Torrini, R. C. Souza, F. L. Cyrino Oliveira, and J. F. Moreira Pessanha, “Long term electricity consumption forecast in Brazil: A fuzzy logic approach,” Socioecon. Plann. Sci., vol. 54, pp. 18–27, 2016, doi: 10.1016/j.seps.2015.12.002.
[7].          S. Bissey, S. Jacques, and J. C. Le Bunetel, “The fuzzy logic method to efficiently optimize electricity consumption in individual housing,” Energies, vol. 10, no. 11, 2017, doi: 10.3390/en10111701.
[8].          E. A. Madrid and N. Antonio, “Short-term electricity load forecasting with machine learning,” Inf., vol. 12, no. 2, pp. 1–21, 2021, doi: 10.3390/info12020050.
[9].          L. Suganthi and A. A. Samuel, “Energy models for demand forecasting - A review,” Renew. Sustain. Energy Rev., vol. 16, no. 2, pp. 1223–1240, 2012, doi: 10.1016/j.rser.2011.08.014.
[10]. S. R. Salkuti, “Short-term electrical load forecasting using radial basis function neural networks considering weather factors,” Electr. Eng., vol. 100, no. 3, pp. 1985–1995, 2018, doi: 10.1007/s00202-018-0678-8.
[11]. S. N. Fallah, M. Ganjkhani, S. Shamshirband, and K. wing Chau, “Computational intelligence on short-term load forecasting: A methodological overview,” Energies, vol. 12, no. 3, 2019, doi: 10.3390/en12030393.
[12]. N. Elamin and M. Fukushige, “Modeling and forecasting hourly electricity demand by SARIMAX with interactions,” Energy, vol. 165, pp. 257–268, 2018, doi: 10.1016/j.energy.2018.09.157.
[13]. U. I. Akpan and A. Starkey, “Review of classification algorithms with changing inter-class distances,” Mach. Learn. with Appl., vol. 4, no. November 2020, p. 100031, 2021, doi: 10.1016/j.mlwa.2021.100031.
[14]. H. Li et al., “Classification of electricity consumption behavior based on improved k-means and lstm,” Appl. Sci., vol. 11, no. 16, pp. 1–17, 2021, doi: 10.3390/app11167625.
[15]. E. M. Burger and S. J. Moura, “Gated ensemble learning method for demand-side electricity load forecasting,” Energy Build., vol. 109, pp. 23–34, 2015, doi: 10.1016/j.enbuild.2015.10.019.
[16]. Y. T. Chae, R. Horesh, Y. Hwang, and Y. M. Lee, “Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings,” Energy Build., vol. 111, pp. 184–194, 2016, doi: 10.1016/j.enbuild.2015.11.045.
[17]. I. Shah, H. Iftikhar, and S. Ali, “Modeling and Forecasting Medium-Term Electricity Consumption Using Component Estimation Technique,” Forecasting, vol. 2, no. 2, pp. 163–179, 2020, doi: 10.3390/forecast2020009.
[18]. P. Pełka and G. Dudek, “Pattern-Based Forecasting Monthly Electricity Demand Using Multilayer Perceptron,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11508 LNAI, pp. 663–672, 2019, doi: 10.1007/978-3-030-20912-4_60.
[19]. S. Yu, K. Wang, and Y. M. Wei, “A hybrid self-adaptive Particle Swarm Optimization-Genetic Algorithm-Radial Basis Function model for annual electricity demand prediction,” Energy Convers. Manag., vol. 91, pp. 176–185, 2015, doi: 10.1016/j.enconman.2014.11.059.
 
[20]. "Statistics and information network of Ministry of Energy." https://isn.moe.gov.ir/Accessed: 2023-02-0.
[21]. "guilan regional electric company."https://gilrec.co.ir/ Accessed: 2023-02-01.
[22]. " National Meteorological Organization" https://www.irimo.ir/Accessed: 2023-02-01
[23]. "Sunrise and sunset times in RashtGilan Province", Iran https://sunrise-sunset.org/Accessed: 2022-02-17.
[24]. Maulud D, Abdulazeez AM. A Review on Linear Regression Comprehensive in Machine Learning. JASTT [Internet]. 2020Dec.31 [cited 2022Nov.3];1(4):140-7. Available from: https://jastt.org/index.php/jasttpath/article/view/57.
[25]. J. Moon, S. Park, S. Rho, and E. Hwang, “A comparative analysis of artificial neural network architectures for building energy consumption forecasting,” Int. J. Distrib. Sens. Networks, vol. 15, no. 9, 2019, doi: 10.1177/1550147719877616.
[26]. R. K. Yadav and Anubhav, “PSO-GA based hybrid with Adam Optimization for ANN training with application in Medical Diagnosis,” Cogn. Syst. Res., vol. 64, pp. 191–199, 2020, doi: 10.1016/j.cogsys.2020.08.011.
[27]. K. Mohammadi, S. Shamshirband, M. H. Anisi, K. Amjad Alam, and D. Petković, “Support vector regression based prediction of global solar radiation on a horizontal surface,” Energy Convers. Manag., vol. 91, pp. 433–441, 2015, doi: 10.1016/j.enconman.2014.12.015.
[28]. D. Jap, M. Stöttinger, and S. Bhasin, “Support vector regression: Exploiting machine learning techniques for leakage modeling,” ACM Int. Conf. Proceeding Ser., vol. 14-June-20, 2015, doi: 10.1145/2768566.2768568.
[29]. A. Román-Portabales, M. López-Nores, and J. J. Pazos-Arias, “Systematic review of electricity demand forecast using ann-based machine learning algorithms,” Sensors, vol. 21, no. 13, pp. 1–23, 2021, doi: 10.3390/s21134544.
فصلنامه سیستم های انرژی پایدار
دوره 1، شماره 3
تیر 1401
صفحه 209-230

فایل ها

هم رسانی

ارجاع به این مقاله

آمار