Short-Term Forecasting of Wind Farm Power Production Using a Modified Artificial Neural Networks Based Algorithm in Python: A Case Study in Manjil
Subject Areas : Power Engineering
Hamid
Jabari
1
(Faculty of Mechanical Engineering, Sahand University of Technology, Tabriz, Iran)
Ardalan
Shafiei-Ghazani
2
(Faculty of Mechanical Engineering, Sahand University of Technology, Tabriz, Iran)
Farkhondeh
Jabari
3
(Power Systems Operation and Planning Research Department, Niroo Research Institute (NRI), Shahrak Ghods, Tehran, Iran)
Keywords: Wind farm, Short time interval, Artificial neural networks (AANs), Root mean squared error (RMSE),
Abstract :
This paper presents a new approach for short-term forecasting of wind farm power generation using artificial neural networks under Python programming language. In this method, weather conditions such as wind speed, wind direction, temperature and air pressure are selected as key features affecting the power production of the wind farm. To achieve a relatively accurate estimate, the root mean squared error of the predicted values is calculated and minimized as the objective function. The speed and accuracy of the proposed algorithm have been evaluated by conducting a case study on a wind farm located in Manjil, Iran. The power production of the wind power plant is predicted for a time horizon of one week and hour by hour using the wind speed, wind direction, temperature and air pressure during 8592 hours (total hours of a year minus hours of a week). The root mean squared error, the highest relative error percentage, the time resolution of the forecasts and the calculation time of the proposed algorithm are compared with other algorithms published in recent years, which shows the effectiveness and high accuracy of the results in a short calculation time. The power production of the wind farm was predicted hour by hour during a week and 168 data points were obtained, the root mean squared error in the optimal scenario is equal to 0.010817. The calculation time of the forecasting algorithm is less than 1 minute, and the maximum relative error in the proposed method is 2.3%, which demonstrates that the uncertainties associated with the power production of the wind farm can be reduced by using this short-term forecasting approach.
A. Soroudi and T. Amraee, "Decision making under uncertainty in energy systems: State of the art," Renewable and Sustainable Energy Reviews, vol. 28, pp. 376-384, 2013.
G. B. Dantzig, "Linear programming under uncertainty," Management Science, vol. 50, no. 12, pp. 1764-1769, 2004.
H. Khorsand and A. R. Seifi, "Probabilistic energy flow for multi-carrier energy systems," Renewable and Sustainable Energy Reviews, vol. 94, pp. 989-997, 2018.
V. Singh, T. Moger, and D. Jena, "Uncertainty handling techniques in power systems: A critical review," Electric Power Systems Research, vol. 203, p. 107633, 2022.
M. Ghahramani, M. Nazari-Heris, K. Zare, and B. Mohammadi-Ivatloo, "A two-point estimate approach for energy management of multi-carrier energy systems incorporating demand response programs," Energy, vol. 249, p. 123671, 2022.
M. Aien, M. G. Khajeh, M. Rashidinejad, and M. Fotuhi‐Firuzabad, "Probabilistic power flow of correlated hybrid wind‐photovoltaic power systems," IET Renewable Power Generation, vol. 8, no. 6, pp. 649-658, 2014.
S. A. Alavi, A. Ahmadian, and M. Aliakbar-Golkar, "Optimal probabilistic energy management in a typical micro-grid based-on robust optimization and point estimate method," Energy Conversion and Management, vol. 95, pp. 314-325, 2015.
M. Järvelä, K. Lappalainen, and S. Valkealahti, "Characteristics of the cloud enhancement phenomenon and PV power plants," Solar Energy, vol. 196, pp. 137-145, 2020.
Z. H. Hulio, W. Jiang, and S. Rehman, "Techno-Economic assessment of wind power potential of Hawke's Bay using Weibull parameter: A review," Energy Strategy Reviews, vol. 26, p. 100375, 2019.
S. Park, Y. Kim, N. J. Ferrier, S. M. Collis, R. Sankaran, and P. H. Beckman, "Prediction of solar irradiance and photovoltaic solar energy product based on cloud coverage estimation using machine learning methods," Atmosphere, vol. 12, no. 3, p. 395, 2021.
F. Jabari, H. Seyedi, S. Najafi Ravadanegh, and B. Mohammadi‐Ivatloo, "Multi‐objective optimal preventive islanding based on stochastic backward elimination strategy considering uncertainties of loads and wind farms," International Transactions on Electrical Energy Systems, vol. 27, no. 12, p. e2451, 2017.
https://geo.libretexts.org/Bookshelves/Meteorology_and_Climate_Science/Practical_Meteorology_(Stull)/10%3A_Atmospheric_Forces_and_Winds/10.04%3A_Section_5
R. Turns Stephen, "An introduction to combustion," ed: McGraw-hill, 2000.
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
https://www.irimo.ir/
S. J. Ghoushchi, S. Manjili, A. Mardani, and M. K. Saraji, "An extended new approach for forecasting short-term wind power using modified fuzzy wavelet neural network: A case study in wind power plant," Energy, vol. 223, p. 120052, 2021.
Y.-Y. Hong and C. L. P. P. Rioflorido, "A hybrid deep learning-based neural network for 24-h ahead wind power forecasting," Applied Energy, vol. 250, pp. 530-539, 2019.
M. G. De Giorgi, A. Ficarella, and M. Tarantino, "Assessment of the benefits of numerical weather predictions in wind power forecasting based on statistical methods," Energy, vol. 36, no. 7, pp. 3968-3978, 2011.
J. Zhang, J. Yan, D. Infield, Y. Liu, and F.-s. Lien, "Short-term forecasting and uncertainty analysis of wind turbine power based on long short-term memory network and Gaussian mixture model," Applied Energy, vol. 241, pp. 229-244, 2019.
P. Zhao, J. Wang, J. Xia, Y. Dai, Y. Sheng, and J. Yue, "Performance evaluation and accuracy enhancement of a day-ahead wind power forecasting system in China," Renewable Energy, vol. 43, pp. 234-241, 2012.
D. M. Teferra, L. M. Ngoo, and G. N. Nyakoe, "Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization," Heliyon, vol. 9, no. 1, 2023.
