ارزیابی توانایی مدل‌های هوشمند در برآورد تابش کل خورشیدی ماهانه

نویسندگان

1 دانشجوی دکتری آبیاری و زهکشی، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه ارومیه

2 دانشیار گروه مهندسی آب، دانشکده کشاورزی، دانشگاه ارومیه

3 استاد گروه آب، دانشکده عمران ، دانشگاه تبریز

4 استاد گروه مهندسی آب، دانشکده کشاورزی، دانشگاه ارومیه

10.22034/ws.2021.11636

چکیده

در این پژوهش، مطالعه­ای مقایسه­ای بین مدل­های شبکه عصبی مصنوعی (ANN)، سیستم استنتاج فازی­- عصبی تطبیقی (ANFIS) و برنامه­ریزی بیان ژن (GEP) برای برآورد تابش خورشیدی ماهانه صورت گرفت. بدین منظور، از داده­های 24 ساله ایستگاه همدیدی تبریز، شامل تابش کل خورشیدی (RS, MJ m−2)، ساعات آفتابی و دمای هوا (°C) بهره گرفته شد. برای اجرای مدل­های هوش مصنوعی، ترکیب جدیدی از ورودی­ها، شامل متوسط ماهانه شاخص صـاف بودن آسمان (KT)، متوسط ماهانه تفاضل دمای بیشینه از دمای کمینه (ΔT)، ساعات آفتابی نسبی ( ) و متوسط ماهانه تـابش فرازمینـی روزانه (Ra)، به کار گرفته شد. با توجه به این­که کمترین مقادیر آماره­های MBE  و RMSE (به ترتیب برابر با 13/0 و 97/1 مگاژول بر متر مربع) و بیشترین مقدار R2 (92/0)، با استفاده از نتایج مدل شبکه عصبی مصنوعی به­دست آمد، لذا ANN به‌عنوان بهترین مدل برای برآورد تابش کل آفتابی ماهانه انتخاب شد. همچنین استفاده از نمودارهای چارک­- چارک، نشان داد که هرچند، شبکه عصبی مصنوعی، بهترین برازش را برای داده­های تابش کل خورشیدی ماهانه ارائه می­کند، اما توانایی این مدل در برآورد مقادیر بالای تابش کل خورشیدی ماهانه کاهش می­یابد.  لذا استفاده از این مدل برای مناطق با میزان تابش دریافتی کمتر توصیه می­شود. عملکرد مدل ANFIS در تحت پوشش قرار دادن مقادیر بالا و پائین (چارک­های چهارم و اول) از سایر مدل­ها بهتر بود. بنابراین مزیت مدل ANFIS را در برآورد دقیق­تر مقادیر بزرگتر تابش خورشیدی است و از این مدل برای برآورد تابش خورشیدی در مناطق با میزان بالای دریافتی تابش خورشیدی می­توان بهره برد. علاوه بر این، بر خلاف نتایج پژوهش­های پیشین که عملکرد مدل GEP برای برآورد تابش آفتابی روزانه را رضایت بخش ارزیابی نکرده بودند، نتایج پژوهش حاضر نشان داد که استفاده از مدل GEP برای برآورد تابش آفتابی کل ماهانه، به ویژه در محدوده 250 تا 800 مگاژول بر متر مربع رضایت‌بخش است. بنابراین می­توان چنین نتیجه گرفت که توانایی مدل GEP در مدل­سازی پدیده­هایی با نوسانات کمتر و محدوده کوچک­تر بیشتر است.

کلیدواژه‌ها


عنوان مقاله [English]

Evaluation of the Capability of Intelligent Models in Estimating Monthly Global Solar Radiation

نویسندگان [English]

  • Seyd Saber Sharifi 1
  • Vahid Rezaverdinejad 2
  • Vahid Nourani 3
  • Javad Behmanesh 4
1 Ph.D. candidate, Water Engin. Dept., Faculty of Agric., Univ. of Urmia, Iran.
2 Assoc. Prof., Water Engin. Dept., Faculty of Agric., Univ. of Urmia, Iran
3 Prof., Water Engin. Dept., Univ. of Tabriz, Tabriz, Iran
4 Prof. Water Engin. Dept., Faculty of Agric., Univ. of Urmia, Iran
چکیده [English]

The concern of the present research was to do a comparative study between the GEP, ANN and ANFIS models to estimate monthly global solar radiation. For this purpose, long-term (24-years) monthly data of global solar radiation (RS, MJ m−2), sunshine hours and air temperature (°C), from Tabriz synoptic station were used. To perform the artificial intelligence models, a new combination of inputs including monthly mean clearness index (KT), monthly temperature range (ΔT), relative sunshine hours (n/N) and extraterrestrial global solar radiation (Ra) were employed. Since the lowest values of MBE and RMSE (0. 13 and 1.97 MJ m−2 respectively) and the highest value of R2 (0.92) were obtained for ANN model, and therefore, the ANN model was selected as the best model to estimate the monthly global solar radiation. Using quarter-quarter (Q-Q) plots revealed that although the ANN model generally presents the best fit for monthly global solar radiation data, this model is found to be not successful in estimating the higher values of monthly global solar radiation data. Therefore, the application of ANN model is recommended for regions with lower solar radiation values. The performance of the ANFIS model was better than other models in covering the highest and lowest values (the first and fourth quarter). Therefore, it can be concluded that the ANFIS model gives more accurate results in the areas with the higher values of solar radiation. The findings also show that unlike previous researches which were carried out in daily scale, the performance of GEP technique for modeling monthly global solar radiation is satisfactory especially in the ranges of 250 to 800 MJ m−2. Thus, it can be inferred that GEP can be more powerful in modeling the phenomena which have low fluctuations or a limited range.

کلیدواژه‌ها [English]

  • Artificial neural network
  • Adaptive Neuro-Fuzzy Inference System
  • Monthly global solar radiation
  • Gene expression programming
  • Tabriz
Allen RG, Pereira LS, Raes D and Smith M, 1998. Crop Evapotranspiration – Guidelines for Computing Crop Water Requirements. FAO Irrigation and Drainage Paper. 56. FAO, Rome.
Behrang M, Assareh E, Ghanbarzadeh A and Noghrehabadi A, 2010. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data. Solar Energy 84(8): 1468-1480.
Behmanesh J, Mortazavi N and Mohammadnezhad B, 2015. Estimation of reference evapotranspiration using full and limited data (Case study: Tabriz and Urmia synoptic stations), Water and Soil Science. 25(3): 13-27. (In Persian with English abstract)
Behrang M, Assareh E, Noghrehabadi A and Ghanbarzadeh A, 2011. New sunshine-based models for predicting global solar radiation using PSO (particle swarm optimization) technique. Energy 36(5): 3036-3049.
Benghanem, M, Mellit A and Alamri S, 2009. ANN-based modelling and estimation of daily global solar radiation data: A case study. Energy Conversion and Management 50(7): 1644-1655.
Besharat F, Dehghan AA and Faghih AR, 2013. Empirical models for estimating global solar radiation: A review and case study. Renewable and Sustainable Energy Reviews 21: 798-821.
Bishop CM, 1995. Neural Networks for Pattern Recognition, Oxford University Press.
Daneshyar M, 1978. Solar radiation statistics for Iran. Solar Energy. 21(4): 345-349.
Erfanian M and Babaei Hesar S, 2013. Evaluation of hybrid model for estimating daily solar radiation in some solar sites of Iran, Journal of Water and Soil 27(1): 158-168. (In Persian with English abstract)
Fallah Ghalhari Q and Shakeri F, 2016. Calibration of Angstrom- Prescott coefficients for selected stations of Khorasan-e Razavi province, Water and Soil Science. 26(3-2): 229-241. (In Persian with English abstract)
Ferreira C, 2001. Gene expression programming: A new adaptive algorithm for solving problems. Complex Systems 13(2): 87-129.
Fogel LJ, 1964. On the organization of intellect. Doctoral dissertation, University of California, Los Angeles-Engineering.
Hasni A, Sehli A, Draoui B, Bassou A and Amieur B, 2012. Estimating global solar radiation using artificial neural network and climate data in the south-western region of Algeria. Energy Procedia 18: 531-537.
Haykin S and Network N, 2004. A comprehensive foundation. Neural Networks 2: 41.
Jang JS, 1993. ANFIS: adaptive-network-based fuzzy inference system, IEEE Transactions on Systems. Man, and Cybernetics 23(3): 665-685.
Kholghi M, Ashrafzadeh A and Maalmir M, 2009. Monthly low-flow forecasting using a stochastic model and adaptive network based fuzzy inference system. Iran-Water Resources Research 5(2): 16-26. (In Persian with English abstract)
Khorasanizadeh H and Mohammadi K, 2013. Introducing the best model for predicting the monthly mean global solar radiation over six major cities of Iran. Energy 51: 257-266.
Koza JR, 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection, Vol 1. MIT Press.
Landeras G, López JJ, Kisi O and Shiri J, 2012. Comparison of gene expression programming with neuro-fuzzy and neural network computing techniques in estimating daily incoming solar radiation in the Basque Country (Northern Spain). Energy Conversion and Management 62: 1-13.
Li MF, Tang XP, Wu W and Liu HB, 2013. General models for estimating daily global solar radiation for different solar radiation zones in mainland China. Energy Conversion and Management 70: 139-148.
Majnooni-Heris A, Zand-Parsa S, Sepaskhah A and Nazemosadat M, 2009. Development and evaluation of global solar radiation models based on sunshine hours and meteorological data. Journal of Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources) 12(46): 491-499. (In Persian with English abstract)
Mehdizadeh S, Behmanesh J and Khalili K, 2016. Comparison of artificial intelligence methods and empirical equations to estimate daily solar radiation. Journal of Atmospheric and Solar-Terrestrial Physics 146:215-27.
Mohammadi K, Shamshirband S, Tong CW, Alam KA and Petković D, 2015. Potential of adaptive neuro-fuzzy system for prediction of daily global solar radiation by day of the year. Energy Conversion and Management 93: 406-413.
Mohanty S, Patra PK and Sahoo SS, 2016. Prediction and application of solar radiation with soft computing over traditional and conventional approach–A comprehensive review. Renewable and Sustainable Energy Reviews 56: 778-796.
Moieni S, Javadi S, Kokabi M and Manshadi M, 2010. Estimating the solar radiation in Iran by using the optimal model. Iranian Journal of Energy 13(2): 1-10. (In Persian with English abstract)
Mostafavi ES, Ramiyani SS, Sarvar R, Moud HI and Mousavi SM, 2013. A hybrid computational approach to estimate solar global radiation: an empirical evidence from Iran. Energy 49: 204-210.
Mubiru J, 2008. Predicting total solar irradiation values using artificial neural networks. Renewable Energy 33(10): 2329-2332.
Noorian, AM, Moradi I and Kamali GA, 2008. Evaluation of 12 models to estimate hourly diffuse irradiation on inclined surfaces. Renewable Energy 33(6): 1406-1412.
Ozoegwu CG, 2019. Artificial neural network forecast of monthly mean daily global solar radiation of selected locations based on time series and month number. Journal of Cleaner Production 216: 1-13.
Rahimikhoob A, 2010. Estimating global solar radiation using artificial neural network and air temperature data in a semi-arid environment. Renewable Energy 35(9): 2131-2135.
Sabziparvar AA and Khataar B, 2015. Evaluation of artificial neural network (ANN) and Irmak experimental models to predict daily solar net radiation (Rn) in cold semi-arid climate (Case study: Hamedan). Water and Soil Science 25(2): 37-50. (In Persian with English abstract)
Sabziparvar AA and Olyaie E, 2011. Evaluation of the performance of artificial neural networks (ANN) in predicting the daily global solar radiation and comparison with results from the Angström model (case study: Tabriz Synoptic Station). Iranian Journal of Geophysics 5(3): 30-41. (In Persian with English abstract)
Sabziparvar AA and Shetaee H, 2007. Estimation of global solar radiation in arid and semi-arid climates of East and West Iran. Energy 32(5): 649-655.
Shafaei S and Dinpashoh Y, 2018. Analysis of drought characteristics of Tabriz (1951-2015). Water and Soil Science 28(3): 117-130. (In Persian with English abstract)
Sharifi SS, Delirhasannia R, Nourani V, Sadraddini AA and Ghorbani A, 2013. Using artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) for modeling and sensitivity analysis of effective rainfall. Recent Advances in Continuum Mechanics, Hydrology and Ecology 4: 133-139.
Sharifi SS, Rezaverdinejad V and Nourani V, 2016. Estimation of daily global solar radiation using wavelet regression, ANN, GEP and empirical models: A comparative study of selected temperature-based approaches. Journal of Atmospheric and Solar-Terrestrial Physics 149: 131-145.
Sumithira T, Kumar AN and Rameshkumar R, 2012. An adaptive neuro-fuzzy inference system (ANFIS) based Prediction of Solar Radiation. Journal of Applied Sciences Research 8(1): 346-351.
Wu CL, Chau KW and Li YS, 2009. Methods to improve neural network performance in daily flows prediction. Journal of Hydrology 372(1–4): 80-93.
Yacef R, Benghanem M and Mellit A, 2012. Prediction of daily global solar irradiation data using Bayesian neural network: a comparative study. Renewable Energy 48: 146-154.
Zhao N, Zeng X and Han S, 2013. Solar radiation estimation using sunshine hour and air pollution index in China. Energy Conversion and Management 76: 846-851.