Author(s)

LinYing Tang, JingXuan Liu^*

Affiliation(s)

School of Information Engineering, Hunan Automotive Engineering Vocational University, Zhuzhou 412001, Hunan, China.

Corresponding Author

JingXuan Liu

ABSTRACT

To address the challenge of decreased prediction accuracy caused by the significant uncertainty and volatility of renewable energy sources, this paper proposes a data-driven forecasting model that leverages an improved deep learning algorithm to enhance accuracy. First, data mining techniques are used to preprocess collected data, minimizing the impact of poor-quality data on forecasting outcomes. Then, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is applied to separate the data into high- and low-frequency components. A Gated Recurrent Unit (GRU) model is employed for predicting high-frequency data to capture short-term fluctuations, while a Kalman Filter (KF) model is used for low-frequency data to extract long-term trends. The final forecast is obtained by combining the high- and low-frequency predictions. Simulation results demonstrate that the proposed data preprocessing effectively removes poor-quality data, improving subsequent forecast accuracy. Additionally, the combined forecasting approach effectively captures both high-frequency fluctuations and low-frequency trends, meeting the accuracy requirements for renewable energy forecasting.

KEYWORDS

Deep Learning; Forecast; Load; Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

CITE THIS PAPER

LinYing Tang, JingXuan Liu. Renewable energy output forecasting based on deep learning. Eurasia Journal of Science and Technology. 2024, 6(5): 43-49. DOI: https://doi.org/10.61784/ejst3035.

REFERENCES

[1] Del Ser, J, Casillas-Perez, D, Cornejo-Bueno, L, et al. Randomization-based machine learning in renewable energy prediction problems: Critical literature review, new results and perspectives. Applied Soft Computing, 2022, 118(8): 108526. DOI:10.1016/j.asoc.2022.108526.

[2] van Wijk, J, Fischhendler, I, Rosen, G, et al. Penny wise or pound foolish? Compensation schemes and the attainment of community acceptance in renewable energy. Energy Research & Social Science, 2021, 81, 102260. DOI: https://doi.org/10.1016/j.erss.2021.102260.

[3] Chen, JJ, Qi, BX, Rong, ZK, et al. Multi-energy coordinated microgrid scheduling with integrated demand response for flexibility improvement. Energy, 2021, 217, 119387. DOI: https://doi.org/10.1016/j.energy.2020.119387.

[4] Willard, J, Jia, X, Xu, S, et al. Integrating scientific knowledge with machine learning for engineering and environmental systems. ACM Computing Surveys, 2022, 55(4): 1-37. DOI: https://doi.org/10.1145/3514228.

[5] Ahmed, R, Sreeram, V, Mishra, Y, et al. A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization. Renewable and Sustainable Energy Reviews, 2020, 124, 109792. DOI: https://doi.org/10.1016/j.rser.2020.109792.

[6] Bilal, B, Adjallah, KH, Sava, A, et al. (2023). Wind turbine output power prediction and optimization based on a novel adaptive neuro-fuzzy inference system with the moving window. Energy, 2023, 263, 126159. DOI: https://doi.org/10.1016/j.energy.2022.126159.

[7] Azad, A, Shateri, H. (2023). Design and optimization of an entirely hybrid renewable energy system (WT/PV/BW/HS/TES/EVPL) to supply electrical and thermal loads with considering uncertainties in generation and consumption. Applied Energy, 2023, 336, 120782. DOI: https://doi.org/10.1016/j.apenergy.2023.120782.

[8] Sadeghi, D, Amiri, N, Marzband, M, et al. Optimal sizing of hybrid renewable energy systems by considering power sharing and electric vehicles. International Journal of Energy Research, 2022, 46(6): 8288-8312. DOI: https://doi.org/10.1002/er.7729.

[9] Hu, Z, Gao, Y, Ji, S, et al. Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data. Applied Energy, 2024, 359, 122709. DOI: https://doi.org/10.1016/j.apenergy.2024.122709.

[10] Ji, C, Sun, W. A review on data-driven process monitoring methods: Characterization and mining of industrial data. Processes, 2022, 10(2): 335. DOI: https://doi.org/10.3390/pr10020335.

[11] Rahman, MM, Shakeri, M, Tiong, SK, et al. Prospective methodologies in hybrid renewable energy systems for energy prediction using artificial neural networks. Sustainability, 2021, 13(4): 2393. DOI: https://doi.org/10.3390/su13042393.

[12] Costa, VG, Pedreira, CE. Recent advances in decision trees: An updated survey. Artificial Intelligence Review, 2023, 56(5): 4765-4800. DOI: https://doi.org/10.1007/s10462-022-10275-5.

[13] Ikotun, AM, Ezugwu, AE, Abualigah, L, et al. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 2023, 622, 178-210. DOI: https://doi.org/10.1016/j.ins.2022.11.139.

[14] Ahmad, T, Madonski, R, Zhang, D, et al. Data-driven probabilistic machine learning in sustainable smart energy/smart energy systems: Key developments, challenges, and future research opportunities in the context of smart grid paradigm. Renewable and Sustainable Energy Reviews, 2022, 160, 112128. DOI: https://doi.org/10.1016/j.rser.2022.112128.

[15] Kordzadeh, N, Ghasemaghaei, M. Algorithmic bias: review, synthesis, and future research directions. European Journal of Information Systems, 2022, 31(3): 388-409. DOI: https://doi.org/10.1080/0960085X.2021.1927212.

[16] Lv, SX, Peng, L, Hu, H, et al. Effective machine learning model combination based on selective ensemble strategy for time series forecasting. Information Sciences, 2022, 612, 994-1023. DOI: https://doi.org/10.1016/j.ins.2022.09.002.

[17] Choudhary, K, DeCost, B, Chen, C, et al. Recent advances and applications of deep learning methods in materials science. npj Computational Materials, 2022, 8(1): 59. DOI: https://doi.org/10.1038/s41524-022-00734-6.

[18] Zhang, L, Wen, J, Li, Y, et al. A review of machine learning in building load prediction. Applied Energy, 2021, 285, 116452. DOI: https://doi.org/10.1016/j.apenergy.2021.116452.

[19] Sapoval, N, Aghazadeh, A, Nute, MG, et al. Current progress and open challenges for applying deep learning across the biosciences. Nature Communications, 2022, 13(1): 1728. DOI: https://doi.org/10.1038/s41467-022-29268-7.

[20] Yan, X, Wang, W, Xiao, M, et al. Survival prediction across diverse cancer types using neural networks. In Proceedings of the 2024 7th International Conference on Machine Vision and Applications, 2024, 134-138. DOI: https://doi.org/10.1145/3653946.3653966.

[21] Wu, Y, Dai, HN, Tang, H. Graph neural networks for anomaly detection in industrial Internet of Things. IEEE Internet of Things Journal, 2021, 9(12): 9214-9231. DOI: 10.1109/JIOT.2021.3094295.

[22] Shi, J, Teh, J. Load forecasting for regional integrated energy system based on complementary ensemble empirical mode decomposition and multi-model fusion. Applied Energy, 2024, 353, 122146. DOI: https://doi.org/10.1016/j.apenergy.2023.122146.