A Comparative Study on the Estimation of Wind Speed and Wind Power Density Using Statistical Distribution Approaches and Artificial Neural Network-Based Hybrid Techniques in Çanakkale, Türkiye
Abstract
:1. Introduction
References | Measurement Period/Sampling Interval | Location | Proposed Estimation Method | Error Calculation Technique |
---|---|---|---|---|
[27] | June 2016–May 2017 | Brazil | SARIMA—NN | MAE, MAPE, RMSE |
[28] | 15 min time interval | Liaoning, China | VMD—ANN | MAE, RMSE, R |
[30] | 10 min time interval | China | PSO-SVR-NN | MAE, MAPE, RMSE |
[31] | 2008–2016 | Bushehr, Iran | MLFFNN, SVR-RBF, ANFIS-PSO | RMSE, R, MSE |
[26] | 2007–2016 | Sibu, Malaysia | Terrain-Based ANN | R, MAPE |
[1] | 2013–2014 | Ankara, Türkiye | Weibull Function | - |
[38] | 10 min periods, 30 min periods | Penglai, China | NN-Linear Combination | RMSE, MAE, MAPE |
[24] | April 2006–March 2007 | Coimbatore, Tamil Nadu, India | MLPNN, RBFNN | R2, MSE |
[21] | May 2013–July 2016 | Saudi Arabia | ANN | R, RMSE |
[6] | 2000–2016 | Incheon, South Korea | Weibull and Rayleigh | RMSE, R2, X2 |
[8] | 1995–2002,2012–2013 | Giruliai, Lithuania | Weibull—MLM, Weibull—MSSDM | RMSE, R2, X2 |
[22] | 4 years | Romania | Feedforward ANN | RMSE |
[39] | - | - | ANN with BP, ANN with ELM | RMSE, R2, R |
[32] | - | - | ANFIS-Weibull | RMSE |
[9] | 2004, 2005, 2006, 2009 | Florya, Yalova, Gebze, Biga | MUOM-Weibull | R2, KS, RMSE, X2, PDE |
[40] | 2014, 2016 | Xinjiang, China | SSA, Hybrid Laguerre NN | RMSE, MAE |
[18] | 2016–2018 | Northern Pakistan | MOM, EML, EMJ, EPFM, MMLM, GM | RMSE, R2, MBE |
[10] | 2009–2013 | Hatay, Osmaniye, Türkiye | Weibull with GM, MLM, EML, EPM, MOM | RMSE, R2, MPE |
[5] | January 2008–August 2011 | Osmaniye, Türkiye | Weibull and Rayleigh with GM | - |
[19] | 2013 | Osmaniye, Türkiye | Weibull and Rayleigh with GM, MOM | - |
[11] | 2008–2012 | Jubail, Saudi Arabia | Weibull with MLM, LSR | RMSE, R2, MAE, MBE |
[7] | 12 months | Northern Morocco | Weibull and Rayleigh | RMSE, R2, MBE |
[12] | September 2014 | Southern India | Weibull with GM, MOM, EMJ, EML, LSR, MLM, MMLM, PDM, AMLM | RMSE, MAPE, R2, X2 |
[13] | Period of a year | Saudi Arabia | Weibull with MOM, LSR, MLM | MSE |
[41] | 1971–2000 | Poland | Two and three-parameter Weibull | R2, SE |
[42] | 2010–2014 | Bohawian, China | Weibull-AI (GWO, PSO, CS, EMJ, EML, EPFM, MLM) | RRMSE, R2 |
[43] | September 2014 | Kayathar, Tamil Nadu, India | Weibull with nine different methods | RMSE, MAPE, R2, X2 |
[44] | 1960–1978 | Faya-Largeau, Chad | Weibull | - |
[33] | April 2016–December 2018 | Coastal region ofPakistan | Weibull-AI (GWO, BOA, GA, ABCOA) | RMSE, R2, MBE |
[45] | 2009–2013 | Southern region of Türkiye(Adana, Osmaniye, Hatay) | Weibull with the PDM | R2, MPE, RMSE |
[14] | Period of a year | Hawke’s Bay region of Pakistan | Weibull with EM, MLM, MMLM, EPM, GM | RMSE, R2 |
[15] | 2007–2013 | Bafoussam, Cameroon | Weibull with EMJ, EML, MOM, GM, Mmab, MLM, EPFM, MMLM, EEM, AMLM | RMSE, R2, X2 |
[16] | 2018 | İzmir, Türkiye | Weibull with GM, MLM, EPFM | RMSE, R2, X2 |
[17] | 2014 | Lithuania | MLM, MMLM, WAsP, Rayleigh | MSE, R2, X2, RE |
[20] | 2014–2018 | Punjab, Pakistan | Weibull with EPFM | RMSE, R2 |
[25] | 4 years | Niğde, Cesme, Mamak, Bozcaada, and Silivri, Türkiye | Machine Learning Algorithms(LASSO, KNN, xGBoost, SVR, RFR) | RMSE, R2, MAE |
[34] | - | - | Hybrid Deep Learning Models(RKF, FS, WNN, ANN) | MAPE, nRMSE |
[35] | January 2017–December 2017 | Taiwan | DBNGA, SARIMA, LSSVRTSGA, LSSVRGA | MAPE, RMSE |
[36] | Period of a year with 1 h intervals | Tehran, Iran | ANN-RBF, ANFIS, ANN-GA, ANN-PSO | RMSE, MSE |
[37] | May 2014–April 2015 | Madura Strait, Java Sea | Hybrid NN-GA, NN-PSO | RMSE, MAPE, SDE, SSE |
[46] | 24 h ahead | Beijing, China | PSO-ANN | - |
[47] | March–May 2009 | Mongolia | ANN, Hybrid Model | RMSE |
[23] | Period of a year | Western region of India | GRNN, MLP | MSE |
[29] | 3 months | Türkiye | SHWIP | nMAE |
2. Methodology
2.1. Information about Study Region
2.2. Weibull and Rayleigh Distribution Functions
2.2.1. Weibull Distribution
2.2.2. Rayleigh Probability Density Function
2.3. Calculations of Wind Power
2.4. ANN-Based Hybrid Models for Wind Speed Estimation
3. Results and Discussions
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
ABCOA | Artificial Bee Colony Algorithm |
AI | Artificial Intelligence |
AMLM | Alternative Maximum Likelihood Method |
ANFIS | Adaptive Neuro-Fuzzy Inference System |
ANN | Artificial Neural Network |
BOA | Bat Optimization Algorithm |
BP | Back-Propagation |
CS | Cuckoo Search Algorithm |
DBNGA | Deep Belief Network with Genetic Algorithms |
EEM | Equivalent Energy Method |
ELM | Extreme Learning Machine |
EM | Empirical Method |
EMJ | Empirical Method of Justus |
EML | Empirical Method of Lysen |
EPFM | Energy Pattern Factor Method |
EPM | Energy Pattern Method |
FS | Fourier Series |
GA | Genetic Algorithm |
GM | Graphical Method |
GRNN | Generalized Regression Neural Network |
GWO | Gray Wolf Optimizer |
KNN | K-Nearest Neighbor |
KS | Kolmogorov–Smirnov Distance |
LASSO | Least Absolute Shrinkage Selector Operator |
LSR | Least-Squares Regression |
LSSVRGA | Least-Squares Support Vector Regression with Genetic Algorithms |
LSSVRTSGA | Least-Squares Support Vector Regression for Time Series with Genetic Algorithms |
MAE | Mean Absolute Error |
MAPE | Mean Absolute Percentage Error |
MBE | Mean Bias Error |
MLFFNN | Multi-Layer Feed-Forward Neural Network |
MLM | Maximum Likelihood Method |
MLP | Multi-Layer Perceptron |
MLPNN | Multi-Layer Perceptron Neural Network |
Mmab | Mabchour’s Method |
MMLM | Modified Maximum Likelihood Method |
MOM | Method of Moments |
MPE | Mean Percentage Error |
MSE | Mean Square Error |
MSSDM | Mean Speed and Standard Deviation Method |
MUOM | Method of Multi-Objective Moments |
nMAE | Normalized Mean Absolute Error |
NN | Neural Network |
NWP | Numerical Weather Prediction |
nRMSE | Normalized Root Mean Square Error |
PDE | Power Density Error |
Probability Distribution Function | |
PDM | Power Density Method |
PSO | Particle Swarm Optimization |
R | Correlation Coefficient |
R2 | Coefficient of Determination |
RBF | Radial Basis Function |
RBFNN | Radial Basis Function Neural Network |
RE | Relative Error |
RES | Renewable Energy Sources |
RFR | Random Forest Regression |
RKF | Recurrent Kalman Filter |
RMSE | Root Mean Square Error |
RRMSE | Relative Root Mean Square Error |
SARIMA | Seasonal Autoregressive Integrated Moving Average |
SDE | Standard Deviation of Error |
SE | Standard Error |
SHWIP | Statistical Hybrid Wind Power |
SSA | Singular Spectrum Analysis |
SSE | Sum Squared Error |
SVM | Support Vector Machine |
SVR | Support Vector Regression |
VMD | Variational Mode Decomposition |
WNN | Wavelet Neural Network |
X2 | Chi-Square Error |
xGBoost | Extreme Gradient Boost |
References
- Kaplan, O.; Temiz, M. A Novel Method Based on Weibull Distribution for Short-Term Wind Speed Prediction. Int. J. Hydrogen Energy 2017, 42, 17793–17800. [Google Scholar] [CrossRef]
- Foley, A.M.; Leahy, P.G.; Marvuglia, A.; McKeogh, E.J. Current Methods and Advances in Forecasting of Wind Power Generation. Renew. Energy 2012, 37, 1–8. [Google Scholar] [CrossRef]
- Santhosh, M.; Venkaiah, C.; Kumar, D.V. Short-Term Wind Speed Forecasting Approach Using Ensemble Empirical Mode Decomposition and Deep Boltzmann Machine. Sustain. Energy Grids Netw. 2019, 19, 100242. [Google Scholar] [CrossRef]
- Al-Yahyai, S.; Charabi, Y.; Gastli, A. Review of the Use of Numerical Weather Prediction (NWP) Models for Wind Energy Assessment. Renew. Sustain. Energy Rev. 2010, 14, 3192–3198. [Google Scholar] [CrossRef]
- Yaniktepe, B.; Koroglu, T.; Savrun, M.M. Investigation of Wind Characteristics and Wind Energy Potential in Osmaniye, Turkey. Renew. Sustain. Energy Rev. 2013, 21, 703–711. [Google Scholar] [CrossRef]
- Ali, S.; Lee, S.M.; Jang, C.M. Statistical Analysis of Wind Characteristics Using Weibull and Rayleigh Distributions in Deokjeok-do Island–Incheon, South Korea. Renew. Energy 2018, 123, 652–663. [Google Scholar] [CrossRef]
- Bidaoui, H.; El Abbassi, I.; El Bouardi, A.; Darcherif, A. Wind Speed Data Analysis Using Weibull and Rayleigh Distribution Functions, Case Study: Five Cities Northern Morocco. Procedia Manuf. 2019, 32, 786–793. [Google Scholar] [CrossRef]
- Katinas, V.; Marčiukaitis, M.; Gecevičius, G.; Markevičius, A. Statistical Analysis of Wind Characteristics Based on Weibull Methods for Estimation of Power Generation in Lithuania. Renew. Energy 2017, 113, 190–201. [Google Scholar] [CrossRef]
- Usta, I.; Arik, I.; Yenilmez, I.; Kantar, Y.M. A New Estimation Approach Based on Moments for Estimating Weibull Parameters in Wind Power Applications. Energy Convers. Manag. 2018, 164, 570–578. [Google Scholar] [CrossRef]
- Kaplan, Y.A. Determination of the Best Weibull Methods for Wind Power Assessment in the Southern Region of Turkey. IET Renew. Power Gener. 2017, 11, 175–182. [Google Scholar] [CrossRef]
- Baseer, M.A.; Meyer, J.P.; Rehman, S.; Alam, M.M. Wind Power Characteristics of Seven Data Collection Sites in Jubail, Saudi Arabia Using Weibull Parameters. Renew. Energy 2017, 102, 35–49. [Google Scholar] [CrossRef]
- Chaurasiya, P.K.; Ahmed, S.; Warudkar, V. Study of Different Parameters Estimation Methods of Weibull Distribution to Determine Wind Power Density Using Ground Based Doppler SODAR Instrument. Alex. Eng. J. 2018, 57, 2299–2311. [Google Scholar] [CrossRef]
- Salah, M.M.; Abo-khalil, A.G.; Praveen, R.P. Wind Speed Characteristics and Energy Potential for Selected Sites in Saudi Arabia. J. King Saud Univ.-Eng. Sci. 2021, 33, 119–128. [Google Scholar] [CrossRef]
- Hulio, Z.H.; Jiang, W.; Rehman, S. Techno-Economic Assessment of Wind Power Potential of Hawke’s Bay Using Weibull Parameter: A Review. Energy Strategy Rev. 2019, 26, 100375. [Google Scholar] [CrossRef]
- Kapen, P.T.; Gouajio, M.J.; Yemélé, D. Analysis and Efficient Comparison of Ten Numerical Methods in Estimating Weibull Parameters for Wind Energy Potential: Application to the City of Bafoussam, Cameroon. Renew. Energy 2020, 159, 1188–1198. [Google Scholar] [CrossRef]
- Gungor, A.; Gokcek, M.; Uçar, H.; Arabacı, E.; Akyüz, A. Analysis of Wind Energy Potential and Weibull Parameter Estimation Methods: A Case Study from Turkey. Int. J. Environ. Sci. Technol. 2020, 17, 1011–1020. [Google Scholar] [CrossRef]
- Katinas, V.; Gecevicius, G.; Marciukaitis, M. An Investigation of Wind Power Density Distribution at Location with Low and High Wind Speeds Using Statistical Model. Appl. Energy 2018, 218, 442–451. [Google Scholar] [CrossRef]
- Saeed, M.K.; Salam, A.; Rehman, A.U.; Saeed, M.A. Comparison of Six Different Methods of Weibull Distribution for Wind Power Assessment: A Case Study for A Site in the Northern Region of Pakistan. Sustain. Energy Technol. Assess. 2019, 36, 100541. [Google Scholar] [CrossRef]
- Kaplan, Y. Rayleigh ve Weibull Dağılımları Kullanılarak Osmaniye Bölgesinde Rüzgar Enerjisinin Değerlendirilmesi. Süleyman Demirel Üniversitesi Fen Bilim. Enstitüsü Derg. 2016, 20, 62–71. [Google Scholar] [CrossRef]
- Sumair, M.; Aized, T.; Gardezi, S.A.R.; Ur Rehman, S.U.; Rehman, S.M.S. Wind Potential Estimation and Proposed Energy Production in Southern Punjab Using Weibull Probability Density Function and Surface Measured Data. Energy Explor. Exploit. 2021, 39, 2150–2168. [Google Scholar] [CrossRef]
- Brahimi, T.; Alhebshi, F.; Alnabilsi, H.; Bensenouci, A.; Rahman, M. Prediction of Wind Speed Distribution Using Artificial Neural Network: The Case of Saudi Arabia. Procedia Comput. Sci. 2019, 163, 41–48. [Google Scholar] [CrossRef]
- Dumitru, C.D.; Gligor, A. Daily Average Wind Energy Forecasting Using Artificial Neural Networks. Procedia Eng. 2017, 181, 829–836. [Google Scholar] [CrossRef]
- Kumar, G.; Malik, H. Generalized Regression Neural Network Based Wind Speed Prediction Model for Western Region of India. Procedia Comput. Sci. 2016, 93, 26–32. [Google Scholar] [CrossRef]
- Navas, R.K.B.; Prakash, S.; Sasipraba, T. Artificial Neural Network Based Computing Model for Wind Speed Prediction: A case study of Coimbatore, Tamil Nadu, India. Phys. A Stat. Mech. Its Appl. 2020, 542, 123383. [Google Scholar] [CrossRef]
- Demolli, H.; Dokuz, A.S.; Ecemis, A.; Gokcek, M. Wind Power Forecasting Based on Daily Wind Speed Data Using Machine Learning Algorithms. Energy Convers. Manag. 2019, 198, 111823. [Google Scholar] [CrossRef]
- Lawan, S.M.; Abidin, W.A.W.Z.; Masri, T. Implementation of A Topographic Artificial Neural Network Wind Speed Prediction Model for Assessing Onshore Wind Power Potential in Sibu, Sarawak. Egypt. J. Remote Sens. Space Sci. 2020, 23, 21–34. [Google Scholar] [CrossRef]
- Alencar, D.B.; Affonso, C.M.; Oliveira, R.C.; Jose Filho, C.R. Hybrid Approach Combining SARIMA and Neural Networks for Multi-Step Ahead Wind Speed Forecasting in Brazil. IEEE Access 2018, 6, 55986–55994. [Google Scholar] [CrossRef]
- Mohammed, G.; Zhang, Y.; Han, A. Performance Comparison of ANNs Model with VMD for Short-Term Wind Speed Forecasting. IET Renew. Power Gener. 2018, 12, 1424–1430. [Google Scholar] [CrossRef]
- Ozkan, M.B.; Karagoz, P. A Novel Wind Power Forecast Model: Statistical Hybrid Wind Power Forecast Technique (SHWIP). IEEE Trans. Ind. Inform. 2015, 11, 375–387. [Google Scholar] [CrossRef]
- Zhang, Y.; Sun, H.; Guo, Y. Wind Power Prediction Based on PSO-SVR and Grey Combination Model. IEEE Access 2019, 7, 136254–136267. [Google Scholar] [CrossRef]
- Khosravi, A.; Koury, R.N.N.; Machado, L.; Pabon, J.J.G. Prediction of Wind Speed and Wind Direction Using Artificial Neural Network, Support Vector Regression and Adaptive Neuro-Fuzzy Inference System. Sustain. Energy Technol. Assess. 2018, 25, 146–160. [Google Scholar] [CrossRef]
- Asghar, A.B.; Liu, X. Estimation of Wind Speed Probability Distribution and Wind Energy Potential Using Adaptive Neuro-Fuzzy Methodology. Neurocomputing 2018, 287, 58–67. [Google Scholar] [CrossRef]
- Saeed, M.A.; Ahmed, Z.; Yang, J.; Zhang, W. An Optimal Approach of Wind Power Assessment Using Chebyshev Metric for Determining the Weibull Distribution Parameters. Sustain. Energy Technol. Assess. 2020, 37, 100612. [Google Scholar] [CrossRef]
- Aly, H.H. A Novel Deep Learning İntelligent Clustered Hybrid Models for Wind Speed and Power Forecasting. Energy 2020, 213, 118773. [Google Scholar] [CrossRef]
- Lin, K.P.; Pai, P.F.; Ting, Y.J. Deep Belief Networks with Genetic Algorithms in Forecasting Wind Speed. IEEE Access 2019, 7, 99244–99253. [Google Scholar] [CrossRef]
- Fazelpour, F.; Tarashkar, N.; Rosen, M.A. Short-Term Wind Speed Forecasting Using Artificial Neural Networks for Tehran, Iran. Int. J. Energy Environ. Eng. 2016, 7, 377–390. [Google Scholar] [CrossRef]
- Arifin, S.; Mahistha, D.S.P.; Ukhti, M.F.; Kurniawan, M.R.; Aisjah, A.S. Optimization of Neural Network Based on Hybrid Method of Genetic Algorithm and Particle Swarm Optimization for Maritime Weather Forecasting in Buoyweather Station Type II. AIP Conf. Proc. 2019, 2088, 020035. [Google Scholar] [CrossRef]
- Wang, J.; Zhang, N.; Lu, H. A Novel System Based on Neural Networks with Linear Combination Framework for Wind Speed Forecasting. Energy Convers. Manag. 2019, 181, 425–442. [Google Scholar] [CrossRef]
- Petković, D.; Nikolić, V.; Mitić, V.V.; Kocić, L. Estimation of Fractal Representation of Wind Speed Fluctuation by Artificial Neural Network with Different Training Algorothms. Flow Meas. Instrum. 2017, 54, 172–176. [Google Scholar] [CrossRef]
- Wang, C.; Zhang, H.; Ma, P. Wind Power Forecasting Based on Singular Spectrum Analysis and A New Hybrid Laguerre Neural Network. Appl. Energy 2020, 259, 114139. [Google Scholar] [CrossRef]
- Wais, P. Two and Three-Parameter Weibull Distribution in Available Wind Power Analysis. Renew. Energy 2017, 103, 15–29. [Google Scholar] [CrossRef]
- Wang, J.; Huang, X.; Li, Q.; Ma, X. Comparison of Seven Methods for Determining the Optimal Statistical Distribution Parameters: A Case Study of Wind Energy Assessment in the Large-Scale Wind Farms of China. Energy 2018, 164, 432–448. [Google Scholar] [CrossRef]
- Chaurasiya, P.K.; Ahmed, S.; Warudkar, V. Comparative Analysis of Weibull Parameters for Wind Data Measured from Met-Mast and Remote Sensing Techniques. Renew. Energy 2018, 115, 1153–1165. [Google Scholar] [CrossRef]
- Soulouknga, M.H.; Doka, S.Y.; Revanna, N.; Djongyang, N.; Kofane, T.C. Analysis of Wind Speed Data and Wind Energy Potential in Faya-Largeau, Chad, Using Weibull Distribution. Renew. Energy 2018, 121, 1–8. [Google Scholar] [CrossRef]
- Kaplan, Y.A. Performance Assessment of Power Density Method for Determining the Weibull Distribution Coefficients at Three Different Locations. Flow Meas. Instrum. 2018, 63, 8–13. [Google Scholar] [CrossRef]
- Eseye, A.T.; Zhang, J.; Zheng, D.; Li, H.; Jingfu, G. A Double-Stage Hierarchical Hybrid PSO-ANN Model for Short-Term Wind Power Prediction. In Proceedings of the 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), Chengdu, China, 28–30 April 2017; pp. 489–493. [Google Scholar] [CrossRef]
- Peng, H.; Liu, F.; Yang, X. A Hybrid Strategy of Short Term Wind Power Prediction. Renew. Energy 2013, 50, 590–595. [Google Scholar] [CrossRef]
- Duden Örgen, F.K.; Altıntaş, A.; Yaşar, S.; Öztürk, M.; Çiftçi, E.; Tuncer, A.D. Software-Based Wind Energy Potential Assessment: A Case Study from Western Turkey. J. Polytech. 2023, 26, 303–309. [Google Scholar] [CrossRef]
- Available online: https://repa.enerji.gov.tr/REPA/ (accessed on 30 December 2023).
- Karsli, V.M.; Gecit, C. An Investigation on Wind Power Potential of Nurdaǧı-Gaziantep, Turkey. Renew. Energy 2003, 28, 823–830. [Google Scholar] [CrossRef]
- Arslan, O. Technoeconomic Aanalysis of Electricity Generation from Wind Energy in Kutahya, Turkey. Energy 2010, 35, 120–131. [Google Scholar] [CrossRef]
- Altay, A.; Turkoglu, A. An Intelligent Prediction of Self-Produced Energy. In Sustainable Future Energy Technology and Supply Chains; Springer: Cham, Switzerland, 2015; pp. 25–45. [Google Scholar] [CrossRef]
- Boga, C.; Koroglu, T. Proper Estimation of Surface Roughness Using Hybrid Intelligence Based on Artificial Neural Network and Genetic Algorithm. J. Manuf. Process. 2021, 70, 560–569. [Google Scholar] [CrossRef]
- Xiong, D.; Fu, W.; Wang, K.; Fang, P.; Chen, T.; Zou, F. A Blended Approach Incorporating TVFEMD, PSR, NNCT-Based Multi-Model Fusion and Hierarchy-Based Merged Optimization Algorithm for Multi-Step Wind Speed Prediction. Energy Convers. Manag. 2021, 230, 113680. [Google Scholar] [CrossRef]
- Fu, W.; Zhang, K.; Wang, K.; Wen, B.; Fang, P.; Zou, F. A Hybrid Approach for Multi-Step Wind Speed Forecasting Based on Two-Layer Decomposition, Improved Hybrid DE-HHO Optimization and KELM. Renew. Energy 2021, 164, 211–229. [Google Scholar] [CrossRef]
- Duan, J.; Chang, M.; Chen, X.; Wang, W.; Zuo, H.; Bai, Y.; Chen, B. A Combined Short-Term Wind Speed Forecasting Model Based on CNN–RNN and Linear Regression Optimization Considering Error. Renew. Energy 2022, 200, 788–808. [Google Scholar] [CrossRef]
- Emeksiz, C.; Tan, M. Wind Speed Estimation Using Novelty Hybrid Adaptive Estimation Model Based on Decomposition and Deep Learning Methods (ICEEMDAN-CNN). Energy 2022, 249, 123785. [Google Scholar] [CrossRef]
Jan | Feb | Mar | Apr | May | Jun | Jul | Aug | Sep | Oct | Nov | Dec | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
vm (m/s) | 2019 | 4.06 | 4.06 | 3.90 | 3.06 | 3.05 | 2.89 | 3.08 | 3.85 | 3.32 | 2.73 | 3.03 | 3.23 |
σ (m/s) | 2019 | 2.66 | 2.34 | 2.12 | 1.79 | 2.06 | 1.61 | 1.59 | 1.58 | 1.64 | 1.74 | 2.52 | 2.90 |
c (m/s) | 2019 | 4.04 | 3.81 | 3.38 | 2.89 | 2.67 | 2.58 | 2.88 | 3.64 | 3.10 | 2.45 | 2.46 | 2.68 |
k | 2019 | 1.41 | 1.57 | 1.47 | 1.50 | 1.28 | 1.50 | 1.78 | 2.12 | 1.59 | 1.31 | 0.95 | 0.98 |
Parameter | Specifications |
---|---|
Neural network type | Feed-forward backpropagation |
Number of neurons in input layer | 12 |
Number of neurons in output layer | 1 |
Number of hidden layers | 2 |
Data division | 70% Training, 30% Testing |
Learning Rate | [0.7] |
Transfer function | logsig (Log–sigmoid function) tansig (Tangent sigmoid function) |
Training function | trainlm (Levenberg–Marquardt) |
Performance function | Mean squared error (MSE) |
Iteration number | 70 |
Normalized range | [–1, 1] |
Error Metrics | Definitions | Formulas |
---|---|---|
R2 | Coefficient of Determination | |
MSE | Mean Square Error | |
RMSE | Root Mean Square Error | |
MAE | Mean Absolute Error | |
MAPE | Absolute Percentage Error |
Method | Statistical Error Performance Result | |||||
---|---|---|---|---|---|---|
R | R2 | MSE | RMSE | MAE | MAPE | |
Presented ANN-PSO | 0.94042 | 0.866 | 0.4721 | 0.6871 | 0.4304 | 17.07% |
Presented ANN-GA | 0.94839 | 0.896 | 0.3653 | 0.6044 | 0.3994 | 16.66% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Koroglu, T.; Ekici, E. A Comparative Study on the Estimation of Wind Speed and Wind Power Density Using Statistical Distribution Approaches and Artificial Neural Network-Based Hybrid Techniques in Çanakkale, Türkiye. Appl. Sci. 2024, 14, 1267. https://doi.org/10.3390/app14031267
Koroglu T, Ekici E. A Comparative Study on the Estimation of Wind Speed and Wind Power Density Using Statistical Distribution Approaches and Artificial Neural Network-Based Hybrid Techniques in Çanakkale, Türkiye. Applied Sciences. 2024; 14(3):1267. https://doi.org/10.3390/app14031267
Chicago/Turabian StyleKoroglu, Tahsin, and Elanur Ekici. 2024. "A Comparative Study on the Estimation of Wind Speed and Wind Power Density Using Statistical Distribution Approaches and Artificial Neural Network-Based Hybrid Techniques in Çanakkale, Türkiye" Applied Sciences 14, no. 3: 1267. https://doi.org/10.3390/app14031267
APA StyleKoroglu, T., & Ekici, E. (2024). A Comparative Study on the Estimation of Wind Speed and Wind Power Density Using Statistical Distribution Approaches and Artificial Neural Network-Based Hybrid Techniques in Çanakkale, Türkiye. Applied Sciences, 14(3), 1267. https://doi.org/10.3390/app14031267