پیش ‏بینی میزان انرژی مصرفی در ساختمان‏ های با زیرساخت آموزشی موجود با استفاده از شبکه عصبی مصنوعی و اثرات آن بر کاهش دی ‏اکسید‏کربن (مطالعه موردی مدارس مشهد)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه سمنان

2 مهندسی عمران، دانشگاه سمنان، سمنان، ایران

3 دانشیار دانشکده مهندسی عمران، دانشگاه سمنان، سمنان، ایران

چکیده

یکی از مصارف انرژی در بخش‏ ساختمان ‏های در حال بهره‏ برداری و بخصوص ساختمان‏ های با زیرساخت های آموزشی مانند مدارس می ‏باشد. از جمله روش های موثرِ کاهش مصرف انرژی در این ساختمان ‏ها، قبل از ساخت می ‏باشد. لیکن بسیاری از ساختمان ‏ها در حال حاضر ساخته ‏شده و می ‏بایست راهکاری برای کاهش مصرف انرژی در این ساختمان‏ ها پیدا‏نمود. از جمله راهکارهای مهم، پیش ‏بینی میزان انرژی مصرفی در این ساختمان‏ ها است. دراینصورت می‏ توان انرژی مصرفی را قبل و بعداز بعضی تغییرات در ساختمان مورد ارزیابی قرارداد. در این مقاله، به موضوع پیش ‏بینی انرژی در ساختمان‏ های وضع‏ موجود در مدارس که از زیرساخت‌های مهم کشور هستند پرداخته ‏شده ‏است. بدین منظور ابتدا تعدادی از مشخصات مهم فیزیکیِ ساختمان و میزان مصرف انرژی آن براساس قبوض مصرفی، بصورت میدانی جمع ‏آوری شده ‏است. برداشت اطلاعات میدانی از ساختمان‏ های وضع موجود مدارس جهت ارائه مدل پیش ‏بین انرژی تجربه نو در این زمینه بوده و در پژوهش ها کمتر به آن پرداخته شده است. مدلسازی با استفاده از شبکه عصبی مصنوعی انجام شده و نتایج، یک ضریب همبستگی بسیار خوب 0.992 را برای اعتبار سنجی مدل نشان می دهد. در انتها نیز اثرات کاهش دی ‏اکسید‏کربن با توجه به میزان صرفه‏ جویی در انرژی مصرفی مورد بحث قرارگرفته ‏است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of the Amount of Energy Consumed in Existing Educational Buildings Using Artificial Neural Networks and Its Effects on Reducing Carbon Dioxide (Case Study of Mashhad Schools)

نویسندگان [English]

  • Masoud Shamaghdari 1
  • Mohammad Kazem Sharbatdar 2
  • Omid Rezaifar 3
1 Semnan University
2 Faculty of Civil Engineering, Semnan University, Semnan, Iran.
3 Associate Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran
چکیده [English]

One of the major uses of energy is in residential, commercial, educational and other buildings. One of the effective ways to reduce energy consumption in these buildings is before construction. But many buildings are already under construction and a solution must be found to reduce energy consumption in these buildings. One of the important solutions is to predict the amount of energy in these buildings. In this case, the energy consumption can be evaluated before and after some changes in the building. This article addresses the issue of energy prediction in existing school buildings. For this purpose, a number of important physical characteristics of the building and its energy consumption based on consumption bills have been collected in the field. Then an artificial neural network is used for modeling. Using the results of the model, the energy of buildings in schools can be predicted. Finally, the effects of reducing carbon dioxide with respect to energy savings are discussed.

کلیدواژه‌ها [English]

  • "energy prediction"
  • "artificial neural network"
  • "school building"
  • "carbon dioxide"
[1] Ghafari Jabari, S., Ghafari Jabari, S. & Saleh E. (2013). “Review strategies for improving the design and construction of settlements in Tehran”, Quarterly Journal of Energy Policy and Planning Research, 1(1), 115-132.
[2] Plessis, G. E. D., Liebenberg, L., Mathews, E. H. & Plessis, J. N. D. (2013). “A versatile energy management system for large iIntegrated cooling Systems”, Energy Conversion and Management, 66, 312-325.
[3] Harvey, D. (2009). “Reducing energy use in the buildings sector: measures, costs and examples”, Energy Efficiency, 2, 139-163.
[4] Tian, W., Song, J., Li, Z., & Wlide, P. D. (2014). “Bootstrap techniques for sensitivity analysis and model selection in building thermal performance analysis”, Applied Energy, 135, 320–328.
[5] Iranian Fuel Conservation Company, www.ifco.ir
[6] Error! Hyperlink reference not valid., www.iea.org
[7] Renewable Energy and Energy Efficiency Organization (SATBA), Iran, www.satba.gov.ir
[8] Sarkardehee, E., Saghafi, M. R., & Nasrollahi, F. (2019). “Effects of southern wall angle on heating performance and energy consumption of residential buildings in Yazd”, Quarterly Journal of Energy Policy and Planning Research, 5(1), 197-227.
[9] Madahi, M., & Tavanaiee, F. (2019). “Optimization of thermal performance of external walls of residential building in cold and dry climate by utilizing the energy simulation software (A case study: Mashhad, Iran)”, JEM, 9(3), 108-121.
[10] Shaeri, J., Yaghoubi, M., & Vakilinazhad, R. (2020). “The impact of using electro chromic on the cooling load in offices at hot and dry, hot and humid, and cold climates in Iran”, JEM, 10(3), 90-99.
[11] Azadeh, A., Ghaderi, S. F., & Sohrabkhani, S. (2014). “A simulated-based neural network algorithm for forecasting electrical energy consumption in Iran”, Energy Policy, 36, 2637-2644. 
[12] Tso, G., & Yau, K. (2003). “A study of domestic energy usage pattern in Hong Kong”, Energy, 28, 1671-1682.
[13] Ridwana, I., Nassif, N., & Choi, W. (2020). “Modeling of building energy consumption by integrating regression analysis and artificial neural network with Data classification”, Buildings, 10(11), 198.
[14] Frenay, L. D. F., & Fiorelli, F. A. S. (2011). “Use of neural networks for evaluation of energy consumption of air conditioning systems”, 21st International Congress of Mechanical Engineering, Natal, RN, Brazil.
[15] Khoshtinat, A., Shieh baygi, A. (2017). “Predicting building energy consumption using multilayer perceptron neural networkˮ, Emerging Trends in Energy conservation Sixth Conference, Iran.  
[16] Argiriou, A. A., Bellas-Velidis, I., & Balaras, C. A. (2000). “Development of a neural network heating controller for solar  buildings”, Neural Networks, 13, 811-820.
[17] Moon, J. W., Jung, S. K., & Kim, J. J. (2009). “Application of ANN (artificial neural network) in residential thermal control”, Proceeding of Eleventh International IBPSA Conference, Glasgow, Scotland, 64-71.
[18] Kumar, R., Aggarwal, R. K., & Sharma, J. D. (2013). “Energy analysis of a building using artificial neural network: a review”, Energy and Buildings, 65, 352-358.
[19] Jovanović, R. Z., Sretenović, A. A., & Živković, B. D. (2015). “Ensemble of various neural networks for prediction of heating energy consumptionˮ, Energy and Buildings, 94, 189-199.
[20] Deb, C., Eang, L. S., Yang, J., & Santamouris, M. (2016). “Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks”, Energy and Buildings, 121, 284-297.
[21] Runge, J. & Zmeureanu, R. (2019). “Forecasting energy use in buildings using artificial neural networks: a review”, Energies, 12(17), 3254.
[22] Seyedzadeh, S., Rahimian, F. P., Glesk, I., & Roper, M. (2018). “Machine learning for estimation of building energy consumption and performance: a Rreview”, Visualization in Engineering, 6(5).
[23] Pino-Mejías, R., Pérez-Fargallo, A., Rubio-Bellido, C., & Pulido-Arcas, J. A. (2017). “Comparison of linear regression and artificial neural networks models to predict heating and cooling Energy Demand, energy consumption and CO2 emissions”, Energy, 118, 24-36.
[24] Demuth, H., & Beale, M. (2002). “Neural network toolbox user`s guide”, Math Works Inc., Natick, MA, U.S.A.
[25] Islamic Parliament Research Center of IRAN (IPRC). (2019). “About energy subsidies in Iran”, N:16654.
[26] Energy News Agency. (2017). “Bargh news”, www.barghnews.com
[27] Dashtbayzi, M. R., & Ghanbarian, M. (2016). “Comparison of artificial neural network methods for modeling of turning of polymer Matrix composite”, Journal of Mechanical Engineering Amirkabir, 47(2), 83-98.
[28] Naderpour, H., Hoseini Vaez, S. R., & Malekshahi, N. (2021). “Predicting the behavior of concrete dams using artificial neural networks (case study of Dez dam)”, Civil Infrastructure Researches, 6(2), 123-132.
CAPTCHA Image