Wind power generation is becoming increasingly essential to the implementation of clean and sustainable energy technologies worldwide. The high demand for wind power means that wind power is required to provide an efficient and reliable output of renewable energy. To reduce the effects of wind farms on the power grid and maintain the balance between energy supply and demand, the accurate forecasting of wind power generation is a crucial aspect of reliable grid operations. However, the intermittent nature of wind resources makes it difficult to forecast wind power accurately, and such forecasts are highly dependent on weather forecasts.
To solve this problem, this thesis proposes an ensemble learner forecasting scheme for improving wind power forecasting (WPF). The scheme comprises metalearning and individual-predictor components. The metalearning component uses a long short-term memory (LSTM) network, whereas the individual predictor component comprises three pretrained individual predictors—fine Gaussian support vector regression, exponential Gaussian process regression, and a nonlinear autoregressive network with exogenous inputs. The innovation of the proposed ensemble WPF model relates to its application of LSTM in metalearning and the use of environmental data as input data to generate weight coefficients for updating the individual predictors.
To illustrate the forecasting performance of the proposed ensemble prediction method for short-term WPF, the prediction results obtained using the proposed ensemble prediction model are compared with those obtained using two ensemble techniques, namely stacking based on a clustered backpropagation neural network (CBPNN) and bootstrap aggregating (bagging). The experimental results obtained using a wind power plant dataset indicate that the proposed model outperforms several state-of-the-art time-series forecasting models. The proposed LSTM ensemble learner scheme achieves significantly better results than the CBPNN and bagging methods. The mean relative error (MRE) of the ensemble LSTM network is 2.67%, whereas the MREs for the CBPNN and bagging methods are 3.45% and 3.42%, respectively.

[1] X. Wang, P. Guo, and X. Huang, "A review of wind power forecasting models," Energy procedia, vol. 12, pp. 770-778, 2011.
[2] J. Hao, C. Zhu, and X. Guo, "Wind Power Short-term Forecasting Model Based on the Hierarchical Output Power and Poisson Re-sampling Random Forest Algorithm," IEEE Access, 2020.
[3] H. Zareipour, D. Huang, and W. Rosehart, "Wind power ramp events classification and forecasting: A data mining approach," in 2011 IEEE Power and Energy Society General Meeting, 2011: IEEE, pp. 1-3.
[4] R. K. Pandit and D. Infield, "SCADA-based wind turbine anomaly detection using Gaussian process models for wind turbine condition monitoring purposes," IET Renewable Power Generation, vol. 12, no. 11, pp. 1249-1255, 2018.
[5] Y.-K. Wu, Y.-C. Wu, J.-S. Hong, L. H. Phan, and D. P. Quoc, "Probabilistic Forecast of Wind Power Generation with Data Processing and Numerical Weather Predictions," in 2020 IEEE/IAS 56th Industrial and Commercial Power Systems Technical Conference (I&CPS), 2020: IEEE, pp. 1-11.
[6] L. Bai, E. Crisostomi, M. Raugi, and M. Tucci, "Wind turbine power curve estimation based on earth mover distance and artificial neural networks," IET Renewable Power Generation, vol. 13, no. 15, pp. 2939-2946, 2019.
[7] P. Guo and D. Infield, "Wind turbine power curve modeling and monitoring with Gaussian Process and SPRT," IEEE Transactions on Sustainable Energy, vol. 11, no. 1, pp. 107-115, 2018.
[8] Y. Wang, Q. Hu, and S. Pei, "Wind power curve modeling with asymmetric error distribution," IEEE Transactions on Sustainable Energy, vol. 11, no. 3, pp. 1199-1209, 2019.
[9] Y. Liu, Y. Sun, D. Infield, Y. Zhao, S. Han, and J. Yan, "A hybrid forecasting method for wind power ramp based on orthogonal test and support vector machine (OT-SVM)," IEEE Transactions on Sustainable energy, vol. 8, no. 2, pp. 451-457, 2016.
[10] M. J. Sanjari and H. Gooi, "Probabilistic forecast of PV power generation based on higher order Markov chain," IEEE Transactions on Power Systems, vol. 32, no. 4, pp. 2942-2952, 2016.
[11] S. Alessandrini, L. Delle Monache, S. Sperati, and J. Nissen, "A novel application of an analog ensemble for short-term wind power forecasting," Renewable Energy, vol. 76, pp. 768-781, 2015.
[12] L. Yang, M. He, J. Zhang, and V. Vittal, "Support-vector-machine-enhanced markov model for short-term wind power forecast," IEEE Transactions on Sustainable Energy, vol. 6, no. 3, pp. 791-799, 2015.
[13] M. Cui, J. Zhang, Q. Wang, V. Krishnan, and B.-M. Hodge, "A data-driven methodology for probabilistic wind power ramp forecasting," IEEE Transactions on Smart Grid, vol. 10, no. 2, pp. 1326-1338, 2017.
[14] M. J. Sanjari, H. B. Gooi, and N.-K. C. Nair, "Power generation forecast of hybrid PV–Wind system," IEEE Transactions on Sustainable Energy, vol. 11, no. 2, pp. 703-712, 2019.
[15] M. Bouaddi and J. V. Rombouts, "Mixed exponential power asymmetric conditional heteroskedasticity," Cahier de recherche/Working Paper, vol. 7, p. 49, 2007.
[16] M. N. Çankaya, "Asymmetric bimodal exponential power distribution on the real line," Entropy, vol. 20, no. 1, p. 23, 2018.
[17] W. Ching, E. Fung, and M. Ng, "A higher-order Markov model for the Newsboy's problem," Journal of the Operational Research Society, vol. 54, no. 3, pp. 291-298, 2003.
[18] C. Gilbert, J. Browell, and D. McMillan, "Leveraging turbine-level data for improved probabilistic wind power forecasting," IEEE Transactions on Sustainable Energy, vol. 11, no. 3, pp. 1152-1160, 2019.
[19] O. Abedinia, M. Lotfi, M. Bagheri, B. Sobhani, M. Shafie-Khah, and J. P. Catalão, "Improved EMD-based complex prediction model for wind power forecasting," IEEE Transactions on Sustainable Energy, vol. 11, no. 4, pp. 2790-2802, 2020.
[20] H.-Y. Su and C.-R. Huang, "Enhanced Wind Generation Forecast Using Robust Ensemble Learning," IEEE Transactions on Smart Grid, vol. 12, no. 1, pp. 912-915, 2020.
[21] L.-L. Li, X. Zhao, M.-L. Tseng, and R. R. Tan, "Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm," Journal of Cleaner Production, vol. 242, p. 118447, 2020.
[22] H. Rinne, The Weibull distribution: a handbook. CRC press, 2008.
[23] J.-Y. Park, J.-K. Lee, K.-Y. Oh, and J.-S. Lee, "Development of a novel power curve monitoring method for wind turbines and its field tests," IEEE Transactions on Energy Conversion, vol. 29, no. 1, pp. 119-128, 2014.
[24] G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, "Extreme learning machine: theory and applications," Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006.
[25] G.-B. Huang, H. Zhou, X. Ding, and R. Zhang, "Extreme learning machine for regression and multiclass classification," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 2, pp. 513-529, 2011.
[26] A. Juneja and N. N. Das, "Big data quality framework: pre-processing data in weather monitoring application," in 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 2019: IEEE, pp. 559-563.
[27] V. Desai and H. Dinesha, "A Hybrid Approach to Data Pre-processing Methods," in 2020 IEEE International Conference for Innovation in Technology (INOCON), 2020: IEEE, pp. 1-4.
[28] C. Rabbath and D. Corriveau, "A comparison of piecewise cubic Hermite interpolating polynomials, cubic splines and piecewise linear functions for the approximation of projectile aerodynamics," Defence Technology, vol. 15, no. 5, pp. 741-757, 2019.
[29] C. Savas and F. Dovis, "The impact of different kernel functions on the performance of scintillation detection based on support vector machines," Sensors, vol. 19, no. 23, p. 5219, 2019.
[30] J. Wang, H. Zhong, X. Lai, Q. Xia, Y. Wang, and C. Kang, "Exploring key weather factors from analytical modeling toward improved solar power forecasting," IEEE Transactions on Smart Grid, vol. 10, no. 2, pp. 1417-1427, 2017.
[31] I. A. Basheer and M. Hajmeer, "Artificial neural networks: fundamentals, computing, design, and application," Journal of microbiological methods, vol. 43, no. 1, pp. 3-31, 2000.
[32] O. Abedinia, M. Bagheri, M. S. Naderi, and N. Ghadimi, "A new combinatory approach for wind power forecasting," IEEE Systems Journal, vol. 14, no. 3, pp. 4614-4625, 2020.
[33] M. Massaoudi et al., "An effective hybrid NARX-LSTM model for point and interval PV power forecasting," IEEE Access, vol. 9, pp. 36571-36588, 2021.
[34] Y. A. Alsariera, V. E. Adeyemo, A. O. Balogun, and A. K. Alazzawi, "Ai meta-learners and extra-trees algorithm for the detection of phishing websites," IEEE Access, vol. 8, pp. 142532-142542, 2020.
[35] Y. Chi, H. Wang, P. S. Yu, and R. R. Muntz, "Moment: Maintaining closed frequent itemsets over a stream sliding window," in Fourth IEEE International Conference on Data Mining (ICDM'04), 2004: IEEE, pp. 59-66.
[36] Y. Yu, Y. Zhu, S. Li, and D. Wan, "Time series outlier detection based on sliding window prediction," Mathematical problems in Engineering, vol. 2014, 2014.
[37] M. Tan, S. Yuan, S. Li, Y. Su, H. Li, and F. He, "Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning," IEEE transactions on power systems, vol. 35, no. 4, pp. 2937-2948, 2019.
[38] M. H. D. M. Ribeiro and L. dos Santos Coelho, "Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series," Applied Soft Computing, vol. 86, p. 105837, 2020.
[39] X. Du, H. Zhang, H. Van Nguyen, and Z. Han, "Stacked LSTM deep learning model for traffic prediction in vehicle-to-vehicle communication," in 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), 2017: IEEE, pp. 1-5.
[40] Z. Shi, H. Liang, and V. Dinavahi, "Direct interval forecast of uncertain wind power based on recurrent neural networks," IEEE Transactions on Sustainable Energy, vol. 9, no. 3, pp. 1177-1187, 2017.
[41] Z. Sun and M. Zhao, "Short-term wind power forecasting based on VMD decomposition, ConvLSTM networks and error analysis," IEEE Access, vol. 8, pp. 134422-134434, 2020.
[42] A. Ahmadi, M. Nabipour, B. Mohammadi-Ivatloo, A. M. Amani, S. Rho, and M. J. Piran, "Long-Term Wind Power Forecasting Using Tree-Based Learning Algorithms," IEEE Access, vol. 8, pp. 151511-151522, 2020.
[43] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," nature, vol. 323, no. 6088, pp. 533-536, 1986.
[44] Z. Yuan, W. Wang, and X. Fan, "Back propagation neural network clustering architecture for stability enhancement and harmonic suppression in wind turbines for smart cities," Computers & Electrical Engineering, vol. 74, pp. 105-116, 2019.
[45] Y. Hu et al., "Short term electric load forecasting model and its verification for process industrial enterprises based on hybrid GA-PSO-BPNN algorithm—A case study of papermaking process," Energy, vol. 170, pp. 1215-1227, 2019.
[46] J. M. Bright, "Solcast: Validation of a satellite-derived solar irradiance dataset," Solar Energy, vol. 189, pp. 435-449, 2019.
[47] H.T. Yang, C.M. Huang, Y.C. Huang, and Y.S. Pai, "A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output," IEEE transactions on sustainable energy, vol. 5, no. 3, pp. 917-926, 2014.
[48] S. Singh, T. Bhatti, and D. Kothari, "Wind power estimation using artificial neural network," Journal of Energy Engineering, vol. 133, no. 1, pp. 46-52, 2007.
[49] R. K. Dash, T. N. Nguyen, K. Cengiz, and A. Sharma, "Fine-tuned support vector regression model for stock predictions," Neural Computing and Applications, pp. 1-15, 2021.
[50] M.-S. Ko, K. Lee, J.-K. Kim, C. W. Hong, Z. Y. Dong, and K. Hur, "Deep Concatenated Residual Network With Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting," IEEE Transactions on Sustainable Energy, vol. 12, no. 2, pp. 1321-1335, 2020.
[51] B. Kosko, "Bidirectional associative memories: unsupervised hebbian learning to bidirectional backpropagation," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 51, no. 1, pp. 103-115, 2021.
[52] V. B. Krishna, W. S. Wadman, and Y. Kim, "NowCasting: Accurate and precise short-term wind power prediction using hyperlocal wind forecasts," in Proceedings of the Ninth International Conference on Future Energy Systems, 2018, pp. 63-74.
[53] M. Sun, C. Feng, and J. Zhang, "Multi-distribution ensemble probabilistic wind power forecasting," Renewable Energy, vol. 148, pp. 135-149, 2020.
[54] S. Lu, "Multi-Step Ahead Ultra-Short-Term Wind Power Forecasting Based on Time Series Analysis," in 2020 International Conference on Computer Information and Big Data Applications (CIBDA), 2020: IEEE, pp. 430-434.
[55] H. Cheng, P.-N. Tan, J. Gao, and J. Scripps, "Multistep-ahead time series prediction," in Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2006: Springer, pp. 765-774.