Stacked LSTM for Short-Term Wind Power Forecasting Using Multivariate Time Series Data.

Manisha Galphade; V. B. Nikam; Biplab Banerjee; Arvind W. Kiwelekar; Priyanka Sharma

doi:10.9781/ijimai.2024.07.002

Authors

Manisha Galphade Veermata Jijabai Technological Institute, MIT Art Design & Technology University.
V. B. Nikam Veermata Jijabai Technological Institute.
Biplab Banerjee Center of Studies in Resources Engineering.
Arvind W. Kiwelekar Dr. Babasaheb Ambedkar Technological University.
Priyanka Sharma Director of Software Engineering (HPC AI R&D Lab).

DOI:

https://doi.org/10.9781/ijimai.2024.07.002

Keywords:

Deep Learning, Long Short Term Memory, Multivariate, Renewable Energy , Time Series Data, Wind Power Forecasting

Supporting Agencies

The authors wish to extend their appreciation to the Faculty Development Centre (VJTI-DBATU) focused on Geoinformatics, Spatial Computing, and Big Data Analytics. This center, established under the auspices of PMMMNMTT, MHRD, Government of India, New Delhi, has been involved in enhancing capacity in various fields, including Geoinformatics, AI & Machine Learning, Deep Learning, Big Data Analytics, and related domains. Their support has been invaluable in advancing our research in this study.

Abstract

Currently, wind power is the fast growing area in the domain of renewable energy generation. Accurate prediction of wind power output in wind farms is crucial for addressing the challenges associated the power grid. This precise forecasting enables grid operators to enhance safety and optimize grid operations by effectively managing fluctuations in power generation, ensuring a reliable and stable energy supply. In recent years, there has been a significant rise in research and investigations conducted in this field. This study aims to develop a multivariate short-term wind power forecasting (WPF) model with the objective of enhancing forecasting precision. Among the various prediction models, deep learning models such as Long Short-Term Memory (LSTM) have demonstrated outstanding performance in the field of WPF. By adding multiple layers of LSTM networks, the model can capture more complex patterns. To improve the performance, data preprocessing is carried out using two techniques such as removal of missing values and imputing missing values using Random Forest Regressor (RFR). The comparison between the proposed Stacked LSTM model and other methods including vector autoregressive (VAR), Multiple Linear Regression, Gated Recurrent Unit (GRU) and Bidirectional LSTM (BiLSTM) has been experimented on two datasets. The experimental results show that after imputing missing values using RFR, the Stacked LSTM is optimized model for better performance than above mentioned reference models.

Downloads

Download data is not yet available.

References

S. K. Kim and S. Park, “Impacts of renewable energy on climate vulnerability: A global perspective for energy transition in a climate adaptation framework,” Science of The Total Environment, vol. 859, pp. 160175, Feb. 2023, doi: 10.1016/J.SCITOTENV.2022.160175.

S. M. H. D. Perera, G. Putrus, M. Conlon, M. Narayana, and K. Sunderland, “Wind Energy Harvesting and Conversion Systems: A Technical Review,” Energies, vol. 15, no. 24, p. 1-34, 2022.

T. M. Giannaros, D. Melas, I. Ziomas, “Performance evaluation of the Weather Research and Forecasting (WRF) model for assessing wind resource in Greece,” Renewable Energy, vol. 102, pp. 190–198, 2017.

C. Liu, X. Zhang, S. Mei, Z. Zhen, M. Jia, Z. Li, H. Tang, “Numericalweather prediction enhanced wind power forecasting: Rank ensemble and probabilistic fluctuation awareness,” Applied Energy, vol. 313, p. 118769, 2022.

S. Kumari, S. Sreekumar, S. Singh, D. P. Kothari, “Comparison Among ARIMA, ANN, and SVR Models for Wind Power Deviation Charge Reduction,” in 2022 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON), vol. 1, 2022, pp. 551–557, IEEE.

F. Yao, W. Liu, X. Zhao, L. Song, “Integrated Machine Learning and Enhanced Statistical Approach-Based Wind Power Forecasting in Australian Tasmania Wind Farm,” Complexity, vol. 2020, 2020, doi: 10.1155/2020/9250937.

Z. Wu, G. Luo, Z. Yang, Y. Guo, K. Li, Y. Xue, “A comprehensive review on deep learning approaches in wind forecasting applications,” CAAI Transactions on Intelligence Technology, vol. 7, no. 2, pp. 129–143, 2022.

Y. Wang, R. Zou, F. Liu, L. Zhang, Q. Liu, “A review of wind speed and wind power forecasting with deep neural networks,” Applied Energy, vol. 304, p. 117766, 2021.

H. Zhen, D. Niu, M. Yu, K. Wang, Y. Liang, and X. Xu, “A Hybrid Deep Learning Model and Comparison for Wind Power Forecasting Considering Temporal-Spatial Feature Extraction,” Sustainability, vol. 12, no. 22, pp. 9490, May 2020, doi: 10.3390/SU12229490.

K.-S. Chen, K.-P. Lin, J.-X. Yan, and W.-L. Hsieh, “Renewable Power Output Forecasting Using Least-Squares Support Vector Regression and Google Data,” Sustainability, vol. 11, no. 11, pp. 3009, May 2019, doi: 10.3390/SU11113009.

J. Zhou, X. Yu, and B. Jin, “Short-Term Wind Power Forecasting: A New Hybrid Model Combined Extreme-Point Symmetric Mode Decomposition, Extreme Learning Machine and Particle Swarm Optimization,” Sustainability, vol. 10, no.9, pp. 3202, May 2018, doi: 10.3390/SU10093202.

B. Xiong, L. Lou, X. Meng, X. Wang, H. Ma, Z. Wang, “Short-term wind power forecasting based on Attention Mechanism and Deep Learning,” Electric Power Systems Research, vol. 206, 2022.

L. Ye, B. Dai, M. Pei, P. Lu, J. Zhao, M. Chen, B. Wang, “Combined approach for short-term wind power forecasting based on wave division and Seq2Seq model using deep learning,” IEEE Transactions on Industry Applications, vol. 58, no. 2, pp. 2586–2596, 2022.

A. Alkesaiberi, F. Harrou, Y. Sun, “Efficient wind power prediction using machine learning methods: A comparative study,” Energies, vol. 15, no. 7, p. 2327, 2022.

J. Jamii, M. Mansouri, M. Trabelsi, M. F. Mimouni, W. Shatanawi, “Effective artificial neural network- based wind power generation and load demand forecasting for optimum energy management,” Frontiers in Energy Research, vol. 10, 2022.

D.-D. Yuan, M. Li, H.-Y. Li, C.-J. Lin, B.-X. Ji, “Wind power prediction method: Support vector regression optimized by improved jellyfish search algorithm,” Energies, vol. 15, no. 17, p. 6404, 2022.

X. Shi, X. Lei, Q. Huang, S. Huang, K. Ren, Y. Hu, “Hourly Day-Ahead Wind Power Prediction Using the Hybrid Model of Variational Model Decomposition and Long Short-Term Memory,” Energies 2018, Vol. 11, Page 3227, vol. 11, p. 3227, may 2018, doi: 10.3390/EN11113227.

K. Qu, G. Si, Z. Shan, X. Kong, X. Yang, “Short- term forecasting for multiple wind farms based on transformer model,” Energy Reports, vol. 8, pp. 483–490, 2022.

E. G. S. Nascimento, T. A. de Melo, D. M. Moreira, “A transformer-based deep neural network with wavelet transform for forecasting wind speed and wind energy,” Energy, vol. 278, pp. 127–678, 2023.

A. Lagos, J. E. Caicedo, G. Coria, A. R. Quete, M. Martz’zinez, G. Suvire, J. Riquelme, “State-of-the- Art using bibliometric analysis of Wind-Speed and- Power forecasting methods applied in power systems,” Energies, vol. 15, no. 18, p. 6545, 2022.

A. Tascikaraoglu, M. Uzunoglu, “A review of combined approaches for prediction of short-term wind speed and power,” 2014, doi: 10.1016/j.rser.2014.03.033.

E. López, C. Valle, H. Allende, E. Gil, H. Madsen, “Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory,” Energies 2018, Vol. 11, Page 526, vol. 11, p. 526, may 2018, doi: 10.3390/EN11030526.

F. Shahid, A. Zameer, A. Mehmood, M. A. Z. Raja, “A novel wavenets long short term memory paradigm for wind power prediction,” Applied Energy, vol. 269, pp. 115098, may 2020, doi: 10.1016/J.APENERGY.2020.115098.

J. F. Toubeau, P. D. Dapoz, J. Bottieau, A. Wautier, Z. D. Grève, F. Vallée, “Recalibration of recurrent neural networks for short-term wind power forecasting,” Electric Power Systems Research, vol. 190, pp. 106639, may 2021, doi: 10.1016/J.EPSR.2020.106639.

Z. Sun, M. Zhao, “Short-Term Wind Power Forecasting Based on VMD Decomposition, ConvLSTM Networks and Error Analysis,” IEEE Access, vol. 8, pp. 134422– 134434, 2020, doi: 10.1109/ACCESS.2020.3011060.

S. Siami-Namini, N. Tavakoli, A. S. Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, pp. 1394–1401, may 2019, doi: 10.1109/ICMLA.2018.00227.

H. S. Dhiman, P. Anand, D. Deb, “Wavelet transform and variants of SVR with application in wind forecasting,” Advances in Intelligent Systems and Computing, vol. 757, pp. 501–511, 2019, doi: 10.1007/978-981-13-1966-245.

Y. Zhang, J. Le, X. Liao, F. Zheng, Y. Li, “A novel combination forecasting model for wind power integrating least square support vector machine, deep belief network, singular spectrum analysis and locality- sensitive hashing,” Energy, vol. 168, pp. 558–572, may 2019, doi: 10.1016/J.ENERGY.2018.11.128.

S. Han, Y. Liu, J. Li, “Wind power combination prediction based on the maximum information entropy principle,” 2012. [Online]. Available: https://ieeexplore.ieee.org/document/6321153.

M. I. A. A. Khalaf, J. Q. Gan, “Deep classifier structures with autoencoder for higher-level feature extraction,” IJCCI 2018 - Proceedings of the 10th International Joint Conference on Computational Intelligence, pp. 31–38, 2018, doi: 10.5220/0006883000310038.

C. Fu, G.-Q. Li, K.-P. Lin, and H.-J. Zhang, “Short-Term Wind Power Prediction Based on Improved Chicken Algorithm Optimization Support Vector Machine,” Sustainability, vol. 11, pp. 512, May 2019, doi: 10.3390/SU11020512.

Y. Wu, M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, M. Krikun, Y. Cao, Q. Gao, K. Macherey, et al., “Google’s neural machine translation system: Bridging the gap between human and machine translation,” arXiv preprint arXiv:1609.08144, 2016.

A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, pp. 9, 2019.

J. Shah, D. Vaidya, and M. Shah, “A comprehensive review on multiple hybrid deep learning approaches for stock prediction,” Intelligent Systems with Applications, vol. 16, 2022, https://doi.org/10.1016/j.iswa.2022.200111.

R. K. Behera, S. Das, S. K. Rath, S. Misra, R. Damasevicius, “Comparative study of real time machine learning models for stock prediction through streaming data.,” The Journal of Universal Computer Science, vol. 26, no. 9, pp. 1128–1147, 2020.

A. M. AlRassas, M. A. Al-qaness, A. A. Ewees, S. Ren, M. Abd Elaziz, R. Damaševičius, T. Krilavičius, “Optimized anfis model using aquila optimizer for oil production forecasting,” Processes, vol. 9, no. 7, p. 1194, 2021.

B. Y. El-Habil, S. S. Abu-Naser, “Global climate prediction using deep learning,” Journal of Theoretical and Applied Information Technology, vol. 100, no. 24, 2022.

J. Oruh, S. Viriri, A. Adegun, “Long short-term memory recurrent neural network for automatic speech recognition,” IEEE Access, vol. 10, pp. 30069– 30079, 2022.

D. Chen, J. Wen, C. Lv, “A spatio-temporal attention graph convolutional networks for sea surface temperature prediction,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 8, pp. 64–72, 2023, doi: https://doi.org/10.9781/ijimai.2023.02.011.

M. Martínez-Comesaña, J. Martínez-Torres, P. Eguía- Oller, J. López-Gómez, “Use of optimised lstm neural networks pre-trained with synthetic data to estimate pv generation,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 8, pp. 1–10, 2023, doi: https://doi.org/10.9781/ijimai.2023.11.002.

M. Roy, S. Majumder, A. Halder, U. Biswas, “Ecg-net: A deep lstm autoencoder for detecting anomalous ecg,” Engineering Applications of Artificial Intelligence, vol. 124, 2023.

M. Bojarski, D. Del Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L. D. Jackel, M. Monfort, U. Muller, J. Zhang, et al., “End to end learning for self-driving cars,” arXiv preprint arXiv:1604.07316, 2016.

F. J. Ordóñez, D. Roggen, “Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition,” Sensors, vol. 16, no. 1, pp. 115, 2016.

H. N. Akouemo, R. J. Povinelli, “Data improving in time series using ARX and ANN models,” IEEE Transactions on Power Systems, vol. 32, no. 5, pp. 3352– 3359, 2017.

F. Harlé, F. Chatelain, C. Gouy-Pailler, S. Achard, “Bayesian model for multiple change-points detection in multivariate time series,” IEEE Transactions on Signal Processing, vol. 64, no. 16, pp. 4351–4362, 2016.

O. Alghushairy, R. Alsini, T. Soule, X. Ma, “A review of local outlier factor algorithms for outlier detection in big data streams,” Big Data and Cognitive Computing, vol. 5, no. 1, 2020.

M. Galphade, V. Nikam, B. Banerjee, A. Kiwelekar, “Intelligent multiperiod wind power forecast model using statistical and machine learning model,” Bulletin of Electrical Engineering and Informatics, vol. 11, pp. 1186–1193, may 2022, doi: 10.11591/EEI.V11I3.3756.

T. Carpenito, J. Manjourides, “MISL: Multiple imputation by super learning,” Statistical methods in medical research, vol. 31, no. 10, pp. 1904–1915, 2022.