The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks
Abstract
:1. Introduction
2. Related Works
3. Materials and Methods
3.1. The Dataset
- The open source Open-Meteo API was used to acquire weather forecasts, which were synchronized with power plant according to the time and geographical location. Open-Meteo serves as a publicly accessible repository of meteorological data [9], offering weather forecast records pertaining to several meteorological parameters, including wind speed, wind direction, air temperature, humidity, and atmospheric pressure, as well as multiple different weather models such as ICON, GEM Global, Meteo France, GSF Global, and the Best Match.
- The additional data set, synchronized with the weather forecasts, contains hourly measurements of the power generation from wind turbines located within a single wind farm located in Lithuania. The farm has six wind turbines with a capacity of 2.75 MW each.
3.2. Machine Learning Model for Power Generation Forecasting
- Number of Layers (NumLayers): This parameter was set as an integer within the range of one to five, determining the depth of the network by specifying the number of BiLSTM layers.
- Number of Hidden Units (NumHiddenUnits): The number of hidden units per layer was allowed to vary between 10 and 400, also as an integer, controlling the capacity of each layer to learn complex patterns in the data.
- Maximum Epochs (MaxEpochs): The training duration was set between 10 and 500 epochs, with the goal of finding an optimal stopping point that balances training time and model performance.
- Initial Learning Rate (InitialLearnRate): The initial learning rate was optimized over a logarithmic scale ranging from to , enabling the model to adjust its weights effectively during training.
- Mini-Batch Size (MiniBatchSize): The size of each mini-batch was varied between 8 and 228, which influences the gradient descent process and impacts training stability and speed.
- Dropout Rate (DropoutRate): This parameter, ranging from 0 to 0.6, was optimized to prevent overfitting by randomly dropping a fraction of units during training.
- Gradient Threshold (GradientThreshold): The gradient clipping threshold was varied between 1 and 10, ensuring that gradients do not explode during backpropagation, thus stabilizing the training process.
- L2 Regularization (L2Regularization): Applied to prevent overfitting, this parameter was optimized on a logarithmic scale between and to penalize large weights in the network.
- Gradient Clipping (ClipGradients): This categorical parameter determined whether gradient clipping was enabled (true) or disabled (false).
- Learning Rate Schedule (LearningRateSchedule): The learning rate schedule was set as a categorical variable, either piecewise or none, to assess whether a decaying learning rate schedule would improve convergence.
- Sequence Padding Value (SequencePaddingValue): Ranging from 0 to 1, this parameter defined the value used for padding sequences to a uniform length.
- Sequence Length (SequenceLength): This categorical parameter controlled whether sequences were padded to the longest or shortest length within each mini-batch.
3.3. The Proposed Technique
- are the predicted values;
- are the actual values;
- is the mean of the actual values.
4. Results and Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Global Wind Energy Council (GWEC). Global Wind Report 2023. 2023. Available online: https://gwec.net/globalwindreport2023 (accessed on 1 December 2023).
- Georgilakis, P.S. Technical challenges associated with the integration of wind power into power systems. Renew. Sustain. Energy Rev. 2008, 12, 852–863. [Google Scholar] [CrossRef]
- Tsai, W.C.; Hong, C.M.; Tu, C.S.; Lin, W.M.; Chen, C.H. A review of modern wind power generation forecasting technologies. Sustainability 2023, 15, 10757. [Google Scholar] [CrossRef]
- Wang, Z.; Wang, X.; Liu, W. Genetic least square estimation approach to wind power curve modelling and wind power prediction. Sci. Rep. 2023, 13, 9188. [Google Scholar] [CrossRef]
- Choudhary, A.; Jain, P.; Prajesh, A. Wind Power Forecasting Using Deep Learning Method: A Review. In Proceedings of the 2023 1st International Conference on Intelligent Computing and Research Trends (ICRT), Roorkee, India, 3–4 February 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 1–6. [Google Scholar]
- Mundotiya, P.; Mathuria, P.; Tiwari, H. Comprehensive Review on Uncertainty in Wind Power Forecasting-Models and Challenges. In Proceedings of the 2022 2nd International Conference on Innovative Sustainable Computational Technologies (CISCT), Dehradun, India, 23–24 December 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 1–6. [Google Scholar]
- Biswas, M.; Dhoom, T.; Barua, S. Weather Forecast Prediction: An Integrated Approach for Analyzing and Measuring Weather Data. Int. J. Comput. Appl. 2018, 182, 20–24. [Google Scholar] [CrossRef]
- Hennayake, K.; Dinalankara, D.; Mudunkotuwa, D. Machine Learning Based Weather Prediction Model for Short Term Weather Prediction in Sri Lanka. Int. J. Multidiscip. Stud. 2022, 9, 65. [Google Scholar] [CrossRef]
- Open-Meteo. Open-Meteo Documentation. Available online: https://open-meteo.com/en/docs (accessed on 1 December 2023).
- Ye, H.; Yang, B.; Han, Y.; Li, Q.; Deng, J.; Tian, S. Wind Speed and Power Prediction Approaches: Classifications, Methodologies, and Comments. Front. Energy Res. 2022, 10, 901767. [Google Scholar] [CrossRef]
- Chen, X.; Zhang, X.; Dong, M.; Huang, L.; Guo, Y.; He, S. Deep learning-based prediction of wind power for multi-turbines in a wind farm. Front. Energy Res. 2021, 9, 723775. [Google Scholar] [CrossRef]
- El-Fouly, T.H.M.; El-Saadany, E.F.; Salama, M.M.A. One Day Ahead Prediction of Wind Speed and Direction. IEEE Trans. Energy Convers. 2008, 23, 191–201. [Google Scholar] [CrossRef]
- Lin, Z.; Liu, X. Wind power forecasting of an offshore wind turbine based on high-frequency SCADA data and deep learning neural network. Energy 2020, 201, 117693. [Google Scholar] [CrossRef]
- Kusiak, A.; Zheng, H.; Song, Z. On-line monitoring of power curves. Renew. Energy 2009, 34, 1487–1493. [Google Scholar] [CrossRef]
- Bouallègue, Z.B.; Clare, M.; Magnusson, L.; Gascon, E.; Maier-Gerber, M.; Janousek, M.; Rodwell, M.; Pinault, F.; Dramsch, J.; Lang, S.; et al. The rise of data-driven weather forecasting. Bull. Am. Meteorol. Soc. 2023, 105, E864–E883. [Google Scholar] [CrossRef]
- Adedipe, T.; Shafiee, M.; Zio, E. Bayesian Network Modelling for the Wind Energy Industry: An Overview. Reliab. Eng. Syst. Saf. 2020, 202, 107053. [Google Scholar] [CrossRef]
- Liu, L.; Liu, J.; Ye, Y.; Liu, H.; Chen, K.; Li, D.; Dong, X.; Sun, M. Ultra-short-term wind power forecasting based on deep Bayesian model with uncertainty. Renew. Energy 2023, 205, 598–607. [Google Scholar] [CrossRef]
- González-Sopeña, J.; Pakrashi, V.; Ghosh, B. An overview of performance evaluation metrics for short-term statistical wind power forecasting. Renew. Sustain. Energy Rev. 2021, 138, 110515. [Google Scholar] [CrossRef]
- Aggarwal, R.; Kumar, R. A Comprehensive Review of Numerical Weather Prediction Models. Int. J. Comput. Appl. 2013, 74, 44–48. [Google Scholar] [CrossRef]
- Chan, P. Advanced Applications of Numerical Weather Prediction Models—Case Studies. In Numerical Models in Geomechanics; InTech: Rijeka, Croatia, 2010. [Google Scholar] [CrossRef]
- Liu, Y.; Zhang, H.; Wu, C.; Shao, M.; Zhou, L.; Fu, W. A Short-Term Wind Speed Forecasting Framework Coupling a Maximum Information Coefficient, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, Shared Weight Gated Memory Network with Improved Northern Goshawk Optimization for Numerical Weather Prediction Correction. Sustainability 2024, 16, 6782. [Google Scholar] [CrossRef]
- Rashid, H.; Haider, W.; Batunlu, C. Forecasting of Wind Turbine Output Power Using Machine Learning. In Proceedings of the 2020 19th IEEE/ACIS International Conference on Computer and Information Science (ICIS), Deggendorf, Germany, 16–18 September 2020. [Google Scholar] [CrossRef]
- Ying, H.; Deng, C.; Xu, Z.; Huang, H.; Deng, W.; Yang, Q. Short-term prediction of wind power based on phase space reconstruction and BiLSTM. Energy Rep. 2023, 9, 474–482. [Google Scholar] [CrossRef]
- Liu, W.; Liu, Q.; Li, Y. Ultra-short-term photovoltaic power prediction based on modal reconstruction and BiLSTM-CNN-Attention model. Earth Sci. Inform. 2024, 17, 2711–2725. [Google Scholar] [CrossRef]
- Jankauskas, M.; Serackis, A.; Pomornacki, R.; Hyunh, V.K.; Šapurov, M.; Baškys, A. Short-term Wind Energy Forecasting with Advanced Recurrent Neural Network Models: A Comparative Study. In Proceedings of the 2023 IEEE 10th Jubilee Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE), Vilnius, Lithuania, 27–29 April 2023; pp. 1–5. [Google Scholar] [CrossRef]
- Liu, Y.; He, J.; Wang, Y.; Liu, Z.; He, L.; Wang, Y. Short-Term Wind Power Prediction Based on CEEMDAN-SE and Bidirectional LSTM Neural Network with Markov Chain. Energies 2023, 16, 5476. [Google Scholar] [CrossRef]
- Chai, Z. BiLSTM Short-term Wind Power Prediction Based on Attention Mechanism. In Proceedings of the 2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China, 26–28 May 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 1341–1346. [Google Scholar]
- Wang, L.; Dernoncourt, F.; Bui, T. Bayesian Optimization for Selecting Efficient Machine Learning Models. arXiv 2020, arXiv:2008.00386. [Google Scholar]
- Wang, J.; Li, X.; Li, J.; Sun, Q.; Wang, H. NGCU: A New RNN Model for Time-Series Data Prediction. Big Data Res. 2022, 27, 100296. [Google Scholar] [CrossRef]
- Lagos, A.; Caicedo, J.E.; Coria, G.; Quete, A.R.; Martínez, M.; Suvire, G.; Riquelme, J. State-of-the-Art Using Bibliometric Analysis of Wind-Speed and -Power Forecasting Methods Applied in Power Systems. Energies 2022, 15, 6545. [Google Scholar] [CrossRef]
Model | RMSE | MAE | R² | NMAE |
---|---|---|---|---|
Best Match | 1.7604 | 1.258 | 0.85478 | 0.21643 |
ICON | 1.7565 | 1.2549 | 0.85543 | 0.21591 |
GEM Global | 2.0086 | 1.4447 | 0.81094 | 0.24857 |
Meteo France | 1.952 | 1.3909 | 0.82146 | 0.2393 |
Gsf Global | 2.0242 | 1.4621 | 0.80801 | 0.25155 |
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
Jankauskas, M.; Serackis, A.; Paulauskas, N.; Pomarnacki, R.; Hyunh, V.K. The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks. Electronics 2024, 13, 3472. https://doi.org/10.3390/electronics13173472
Jankauskas M, Serackis A, Paulauskas N, Pomarnacki R, Hyunh VK. The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks. Electronics. 2024; 13(17):3472. https://doi.org/10.3390/electronics13173472
Chicago/Turabian StyleJankauskas, Mindaugas, Artūras Serackis, Nerijus Paulauskas, Raimondas Pomarnacki, and Van Khang Hyunh. 2024. "The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks" Electronics 13, no. 17: 3472. https://doi.org/10.3390/electronics13173472
APA StyleJankauskas, M., Serackis, A., Paulauskas, N., Pomarnacki, R., & Hyunh, V. K. (2024). The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks. Electronics, 13(17), 3472. https://doi.org/10.3390/electronics13173472