Enhancing Wind Turbine Power Output Estimation Using Causal Inference and Adaptive Neuro-Fuzzy Inference System ANFIS

Ahmed A. Mostfa; Nawfal  A. Zakar; Rasha  Raad Al-Mola; Abdel-Nasser  Sharkawy

doi:10.30572/2018/KJE/160224

Authors

Ahmed A. Mostfa Dept. of Computer Science. College of Education. University of Al Hamdaniya. Mosul, Iraq https://orcid.org/0000-0001-8722-5306
Nawfal A. Zakar School of Computer Science University of Birmingham, Birmingham, UK
Rasha Raad Al-Mola Dept. of Computer Science. College of Education. University of Al Hamdaniya. Mosul, Iraq
Abdel-Nasser Sharkawy Mechanical Engineering Department, Faculty of Engineering, South Valley University, Qena 83523, Egypt

DOI:

https://doi.org/10.30572/2018/KJE/160224

Keywords:

ANFIS System, Wind Turbine Power, Confounders, Modelling and Estimation, Causal Inference

Abstract

Wind turbines have attracted much attention from scientists who are aiming to achieve a prominent level of performance due to the environmental changes during the year. To meet the demand for renewable energy at the lowest cost, wind energy became the target of machine learning algorithms and was employed to predict the output power of wind turbines. The aim of this study is to utilise a causal inference approach to estimate the power output of wind turbines. Initially, the outcomes derived from numerical prediction are examined using a structural causal model. After causal discovery, we identify potential confounders for the filter factors that have the most significant impact on the outcome and decide whether to include or exclude these prospective confounders in our model. This method guarantees precise predictions using the Adaptive Neuro-Fuzzy Inference System ANFIS. ANFIS is a hybrid learning approach that combines neural network and fuzzy logic system for estimating the output model for nonlinear relationships. ANFIS employed the pressure surface, wind speed and air pressure as input data while the power of the wind turbine served as the output of the predicted model. Various practical experiments were conducted using different membership functions in neuro-fuzzy training to achieve the lowest possible mean square error. The data were gathered over two months on a farm in Egypt on the Suez Gulf. Approximately 85% of the data was utilised to train the three inputs, while the rest was used to evaluate the predicted model and assess the efficiency using Akaike Information Criterion (AIC) to choose the best fit model. A further study showed that changing the ANFIS parameters could deviate from the path of efficient outcomes, compared with the neural network approach.

Downloads

Download data is not yet available.

References

Adedeji, P.A. et al. (2023) ‘Effectiveness of evolutionary-tuned neurofuzzy inference system in predicting wind turbine gearbox oil temperature’, Materials Today: Proceedings [Preprint]. Available at: https://doi.org/10.1016/J.MATPR.2023.08.034. DOI: https://doi.org/10.1016/j.matpr.2023.08.034

Alencar, D.B. et al. (2018) ‘Hybrid approach combining SARIMA and neural networks for multi-step ahead wind speed forecasting in Brazil’, IEEE Access, 6, pp. 55986–55994. Available at: https://doi.org/10.1109/ACCESS.2018.2872720. DOI: https://doi.org/10.1109/ACCESS.2018.2872720

Alyousuf, A.M. and Korkmaz, F. (2023) ‘PERFORMANCE INVESTIGATION OF WIND TURBINES BASED ON DOUBLY FED INDUCTION GENERATORS WITH BACK-TO-BACK CONVERTER’, Kufa Journal of Engineering, 14(1), pp. 1–12. Available at: https://doi.org/10.30572/2018/KJE/140101. DOI: https://doi.org/10.30572/2018/KJE/140101

Atlam, H.F. and Wills, G.B. (2023) ‘ANFIS for risk estimation in risk-based access control model for smart homes’, Multimedia Tools and Applications, 82(12), pp. 18269–18298. Available at: https://doi.org/10.1007/s11042-022-14010-8. DOI: https://doi.org/10.1007/s11042-022-14010-8

Bareinboim, E. et al. (2022) ‘On Pearl’s Hierarchy and the Foundations of Causal Inference’, Probabilistic and Causal Inference, pp. 507–556. Available at: https://doi.org/10.1145/3501714.3501743. DOI: https://doi.org/10.1145/3501714.3501743

Barreiro-Gomez, J. et al. (2019) ‘Data-driven decentralized algorithm for wind farm control with population-games assistance’, Energies, 12(6), pp. 1–14. Available at: https://doi.org/10.3390/en12061164. DOI: https://doi.org/10.3390/en12061164

Bochenek, B. et al. (2021) ‘Day-ahead wind power forecasting in poland based on numerical weather prediction’, Energies, 14(8). Available at: https://doi.org/10.3390/en14082164. DOI: https://doi.org/10.3390/en14082164

Calp, M.H. (2019) ‘A hybrid ANFIS-GA approach for estimation of regional rainfall amount’, Gazi University Journal of Science, 32(1), pp. 145–162.

Chatterjee, S., Naithani, A. and Mukherjee, V. (2016) ‘Small-signal stability analysis of DFIG based wind power system using teaching learning based optimization’, International Journal of Electrical Power & Energy Systems, 78, pp. 672–689. Available at: https://doi.org/https://doi.org/10.1016/j.ijepes.2015.11.113. DOI: https://doi.org/10.1016/j.ijepes.2015.11.113

Chen, J. and Kim, M.H. (2022) ‘Review of Recent Offshore Wind Turbine Research and Optimization Methodologies in Their Design’, Journal of Marine Science and Engineering, 10(1). Available at: https://doi.org/10.3390/jmse10010028. DOI: https://doi.org/10.3390/jmse10010028

Chilton, A. and Rozema, K. (2024) ‘43Causal Inference and Experiments’, Trial by Numbers: A Lawyer’s Guide to Statistical Evidence. Edited by A. Chilton and K. Rozema. Oxford University Press, p. 0. Available at: https://doi.org/10.1093/oso/9780197747858.003.0004. DOI: https://doi.org/10.1093/oso/9780197747858.003.0004

Civelek, Z. et al. (2016) ‘Proportional-integral-derivative parameter optimisation of blade pitch controller in wind turbines by a new intelligent genetic algorithm’, IET Renewable Power Generation, 10(8), pp. 1220–1228. Available at: https://doi.org/10.1049/iet-rpg.2016.0029. DOI: https://doi.org/10.1049/iet-rpg.2016.0029

Ebrahimi, F.M., Khayatiyan, A. and Farjah, E. (2016) ‘A novel optimizing power control strategy for centralized wind farm control system’, Renewable Energy, 86, pp. 399–408. Available at: https://doi.org/10.1016/J.RENENE.2015.07.101. DOI: https://doi.org/10.1016/j.renene.2015.07.101

Farrar, N.O., Ali, M.H. and Dasgupta, D. (2023) ‘Artificial Intelligence and Machine Learning in Grid Connected Wind Turbine Control Systems: A Comprehensive Review’, Energies, 16(3), p. 1530. Available at: https://doi.org/10.3390/en16031530. DOI: https://doi.org/10.3390/en16031530

Galdi, V., Piccolo, A. and Siano, P. (2008) ‘Designing an adaptive fuzzy controller for maximum wind energy extraction’, IEEE Transactions on Energy Conversion, 23(2), pp. 559–569. Available at: https://doi.org/10.1109/TEC.2007.914164. DOI: https://doi.org/10.1109/TEC.2007.914164

GÖKKUŞ, G. (2023) ‘Anfis-Based Real-Time Power Estimation for Wind Turbines’, Konya Journal of Engineering Sciences, 11(1), pp. 136–149. Available at: https://doi.org/10.36306/konjes.1200149. DOI: https://doi.org/10.36306/konjes.1200149

Hadi, A.R.S. et al. (2024) ‘ENHANCING STABILITY AND REGULATION OF OUTPUT VOLTAGE IN BOOST CONVERTERS WITH LEARNING SLIDING MODE CONTROL’, Kufa Journal of Engineering, 15(3), pp. 134–147. Available at: https://doi.org/10.30572/2018/KJE/150308. DOI: https://doi.org/10.30572/2018/KJE/150308

Hafiz, F. and Abdennour, A. (2016) ‘An adaptive neuro-fuzzy inertia controller for variable-speed wind turbines’, Renewable Energy, pp. 136–146. Available at: https://doi.org/10.1016/j.renene.2016.01.100. DOI: https://doi.org/10.1016/j.renene.2016.01.100

Hoyer, P.O. et al. (2008) ‘Nonlinear Causal Discovery’, Advances in Neural Information Processing Systems (NIPS), 21(Proceedings of the 22nd Annual Conference on Neural Information Processing Systems), pp. 689–696.

Issa, A.H. and Majeed, A.H. (2012) ‘Intelligent sensor fault detection based on soft computing’, Kufa Journal of Engineering, 4(1), pp. 113–124. Available at: https://doi.org/10.30572/2018/KJE/411246. DOI: https://doi.org/10.30572/2018/KJE/411246

Jamii, J. et al. (2022) ‘Effective artificial neural network-based wind power generation and load demand forecasting for optimum energy management’, Frontiers in Energy Research, 10, p. 898413. Available at: https://doi.org/10.3389/FENRG.2022.898413/BIBTEX. DOI: https://doi.org/10.3389/fenrg.2022.898413

Jović, S. (2020) ‘Prediction of aerodynamics performance of continuously variable-speed wind turbine by adaptive neuro-fuzzy methodology’, Engineering with Computers, 36(2), pp. 597–602. Available at: https://doi.org/10.1007/s00366-019-00716-1. DOI: https://doi.org/10.1007/s00366-019-00716-1

Kadhem, B.T. and Hasan, Y.F. (2021) ‘Calculation of Avr Parameters Using Neural Network To Enhance the Power System Stability’, Kufa Journal of Engineering, 6(1), pp. 79–92. Available at: https://doi.org/10.30572/2018/kje/611309. DOI: https://doi.org/10.30572/2018/KJE/611309

Karaman, Ö.A. (2023) ‘Prediction of Wind Power with Machine Learning Models’, Applied Sciences (Switzerland), 13(20). Available at: https://doi.org/10.3390/app132011455. DOI: https://doi.org/10.3390/app132011455

Mignon, V. (2024) ‘The Multiple Regression Model’, pp. 105–170. Available at: https://doi.org/10.1007/978-3-031-52535-3_3. DOI: https://doi.org/10.1007/978-3-031-52535-3_3

Montero-Hernandez, S. (2019) ‘Learning causal probabilistic graphical models and their application to the analysis of effective connectivity from functional near infrared spectroscopy’. Available at: https://research.birmingham.ac.uk/en/publications/learning-causal-probabilistic-graphical-models-and-their-applicat (Accessed: 10 August 2024).

Nassar, Y.S.N.Y.S. and Khaleel, T. (2019) ‘BUILDING MODEL TO PREDICT LABOUR PRODUCTIVITY USING MULTIPLE LINEAR REGRESSION TECHNIQUE FOR “FORMWORK CONCRETE COLUMNS”’, Kufa Journal of Engineering, 10(2), pp. 12–26. Available at: https://doi.org/10.30572/2018/KJE/100202. DOI: https://doi.org/10.30572/2018/KJE/100202

Pearl, J. (2011) ‘Causality: Models, reasoning, and inference, second edition’, Causality: Models, Reasoning, and Inference, Second Edition, pp. 1–464. Available at: https://doi.org/10.1017/CBO9780511803161. DOI: https://doi.org/10.1017/CBO9780511803161

Pérez, C. et al. (2023) ‘Influence of Atmospheric Stability on Wind Turbine Energy Production: A Case Study of the Coastal Region of Yucatan’, Energies, 16(10). Available at: https://doi.org/10.3390/en16104134. DOI: https://doi.org/10.3390/en16104134

Rahmani, R. et al. (2013) ‘Hybrid technique of ant colony and particle swarm optimization for short term wind energy forecasting’, Journal of Wind Engineering and Industrial Aerodynamics, 123, pp. 163–170. Available at: https://doi.org/10.1016/J.JWEIA.2013.10.004. DOI: https://doi.org/10.1016/j.jweia.2013.10.004

Renewable, I. and Agency, E. (2021) Off-Grid Renewable Energy Statistics 2021 Statistiques D ’ Énergie Renouvelable Hors Réseau 2021 Estadísticas De Energía.

Routray, A., Reddy, Y.S. and Hur, S.H. (2023) ‘Predictive Control of a Wind Turbine Based on Neural Network-Based Wind Speed Estimation’, Sustainability (Switzerland), 15(12). Available at: https://doi.org/10.3390/su15129697. DOI: https://doi.org/10.3390/su15129697

Rubenstein, P.K. et al. (2017) ‘Causal Consistency of Structural Equation Models’, Uncertainty in Artificial Intelligence - Proceedings of the 33rd Conference, UAI 2017 [Preprint]. Available at: https://arxiv.org/abs/1707.00819v1 (Accessed: 10 August 2024).

Shah, P. and Shah, T. (2024) ‘Adaptive Neuro Fuzzy Inference System based classifier in diagnosis of breast cancer’, Results in Control and Optimization, 14(October 2023), p. 100358. Available at: https://doi.org/10.1016/j.rico.2023.100358. DOI: https://doi.org/10.1016/j.rico.2023.100358

Sharkawy, A.N. et al. (2024) ‘Design, Assessment, and Modeling of Multi-Input Single-Output Neural Network Types for the Output Power Estimation in Wind Turbine Farms’, Automation 2024, Vol. 5, Pages 190-212, 5(2), pp. 190–212. Available at: https://doi.org/10.3390/AUTOMATION5020012. DOI: https://doi.org/10.3390/automation5020012

Simon, G.J. and Sisi Ma, A. (2024) ‘Advancing Causal Analytics Using Biomedical Data’. Available at: https://conservancy.umn.edu/handle/11299/262885 (Accessed: 18 September 2024).

Song, D. et al. (2024) ‘Review on the Application of Artificial Intelligence Methods in the Control and Design of Offshore Wind Power Systems’, Journal of Marine Science and Engineering, 12(3). Available at: https://doi.org/10.3390/jmse12030424. DOI: https://doi.org/10.3390/jmse12030424

Tchakoua, P. et al. (2013) ‘A review of concepts and methods for wind turbines condition monitoring’, 2013 World Congress on Computer and Information Technology, WCCIT 2013, 2(1). Available at: https://doi.org/10.1109/WCCIT.2013.6618706. DOI: https://doi.org/10.1109/WCCIT.2013.6618706

Tchakoua, P. et al. (2014) ‘Wind turbine condition monitoring: State-of-the-art review, new trends, and future challenges’, Energies, 7(4), pp. 2595–2630. Available at: https://doi.org/10.3390/en7042595. DOI: https://doi.org/10.3390/en7042595

Ulkat, D. and Günay, M.E. (2018) ‘Prediction of mean monthly wind speed and optimization of wind power by artificial neural networks using geographical and atmospheric variables: case of Aegean Region of Turkey’, Neural Computing and Applications, 30(10), pp. 3037–3048. Available at: https://doi.org/10.1007/S00521-017-2895-X. DOI: https://doi.org/10.1007/s00521-017-2895-x

Wang, Y. et al. (2019) ‘A review of applications of artificial intelligent algorithms in wind farms’, Artificial Intelligence Review, 53(5), pp. 3447–3500. Available at: https://doi.org/10.1007/S10462-019-09768-7. DOI: https://doi.org/10.1007/s10462-019-09768-7

Wang, Y. et al. (2023a) ‘A Wind Power Forecasting Method Using Causal Inference’, 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023, pp. 1828–1832. Available at: https://doi.org/10.1109/EI259745.2023.10513267.

Wang, Y. et al. (2023b) ‘A Wind Power Forecasting Method Using Causal Inference’, 2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023, pp. 1828–1832. Available at: https://doi.org/10.1109/EI259745.2023.10513267. DOI: https://doi.org/10.1109/EI259745.2023.10513267

Xu, Y. et al. (2023) ‘Iterative Neuro-Fuzzy Hammerstein Model Based Model Predictive Control for Wind Turbines’, IEEE Transactions on Industry Applications, 59(5), pp. 6501–6512. Available at: https://doi.org/10.1109/TIA.2023.3284784. DOI: https://doi.org/10.1109/TIA.2023.3284784

Yang, Y. et al. (2016) ‘Modelling a combined method based on ANFIS and neural network improved by DE algorithm: A case study for short-term electricity demand forecasting’, Applied Soft Computing Journal, 49, pp. 663–675. Available at: https://doi.org/10.1016/J.ASOC.2016.07.053. DOI: https://doi.org/10.1016/j.asoc.2016.07.053

Yin, X. and Zhao, X. (2021) ‘Deep Neural Learning Based Distributed Predictive Control for Offshore Wind Farm Using High-Fidelity les Data’, IEEE Transactions on Industrial Electronics, 68(4), pp. 3251–3261. Available at: https://doi.org/10.1109/TIE.2020.2979560. DOI: https://doi.org/10.1109/TIE.2020.2979560

Yin, X., Jiang, Z. and Pan, L. (2020) ‘Recurrent neural network based adaptive integral sliding mode power maximization control for wind power systems’, Renewable Energy, 145, pp. 1149–1157. Available at: https://doi.org/10.1016/j.renene.2018.12.098. DOI: https://doi.org/10.1016/j.renene.2018.12.098

Zhang, J. et al. (2019) ‘Short-term forecasting and uncertainty analysis of wind turbine power based on long short-term memory network and Gaussian mixture model’, Applied Energy, 241, pp. 229–244. Available at: https://doi.org/10.1016/j.apenergy.2019.03.044. DOI: https://doi.org/10.1016/j.apenergy.2019.03.044