Welcome to Francis Academic Press

Academic Journal of Environment & Earth Science, 2022, 4(3); doi: 10.25236/AJEE.2022.040301.

Research on Wind Speed Prediction Model Based on WOA-LSTM


Haoqian Wu, Zhaozhengyang Li

Corresponding Author:
Haoqian Wu

Automated Institute, Chongqing University of Posts and Telecommunications, Chongqing, China


To tackle the issues of haphazardness of LSTM model boundaries and slow model intermingling speed, work on the exactness of wind speed forecast model, and better work on the security and economy of wind power age frameworks, this paper proposes an improved LSTM based on the Whale Optimization Algorithm (WOA), and conducts simulation analysis based on the US meteorological data. The exploration results show that:1) Through persistent preparation to track down reasonable hyperparameters and confirm them, it is observed that the attributes of the WOA calculation can successfully track down the worldwide ideal answer for upgrade the boundaries of the LSTM model; 2) Compared with the traditional LSTM neural network prediction model, the WOA-LSTM reduces the root mean square error (RMSE) and mean absolute error (MAE) by 0.43035 and 0.23115, respectively, and improves the goodness of fit (R^2) by 0.03763. It shows that the model has better accuracy and stability for wind speed prediction.


Whale Algorithm; Long and Short-term Neural Memory Network; Wavelet Noise Reduction; Wind Speed Prediction

Cite This Paper

Haoqian Wu, Zhaozhengyang Li. Research on Wind Speed Prediction Model Based on WOA-LSTM. Academic Journal of Environment & Earth Science (2022) Vol. 4 Issue 3: 1-6. https://doi.org/10.25236/AJEE.2022.040301.


[1] Yang X Y, Sun H M. Research on wind speed prediction of wind farm based on time series model [J]. Chinese Journal of Power Engineering, 2011, 31(03): 203-208.

[2] Han S, Yang Y P, Liu Y Q. Application of three methods in wind speed prediction [J]. Journal of North China Electric Power University (Natural Science Edition), 2008(03): 57-61.

[3] Gu Y, Tang W, Qu R Q. Short-term wind speed prediction of wind farms based on BP neural network group structure [J]. Rural Electrification, 2013(01): 50-52.

[4] Zhou X J, Chen X Q, Xie L, Jiang C L. Mixed model for short-term wind speed prediction based on EMD [J]. Journal of Liaoning University of Petroleum and Chemical Technology, 2021, 41(06): 79-86.

[5] N Neeraj, Mathew J, Agarwal M, et al. Long short-term memory-singular spectrum analysis-based model for electric load forecasting[J]. Electrical Engineering, 2020(1): 1-16. 

[6] Hochreiter S and Schmidhuber J. Long short-term memory. [J]. Neural computation, 1997, 9(8): 1735-80.

[7] Wang Y Y, An W Z, Qiao T T, Zhu C L, Yang X G, Zhu H S. Temperature prediction and early warning method of underwater electronic module based on LSTM [J]. China Offshore Oil and Gas, 2022, 34(01): 161-167.

[8] Li L, Ni F S, Jiang S, Yao M H. Prediction model of dredging pipeline flow velocity based on LSTM [J]. Automation and Instrumentation, 2022,37(02):86-90.

[9] Seyedali Mirjalili and Andrew Lewis. The Whale Optimization Algorithm [J]. Advances in Engineering Software, 2016, 95: 51-67.

[10] Al-falahi M, Jayasinghe S, Enshaei H. A Review on RecentSize Optimization Methodologies for Standalone Solarand Wind Hybrid Renewable Energy System [J]. EnergyConversion Management, 2017, 143: 252-274.

[11] Mikolov T, M Karafiát, Burget L, et al. Recurrent NeuralNetwork based Language Model [C]// Interspeech, Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September. DBLP, 2015.

[12] Rampasek L, Goldenberg A. Tensor Flow: Biology’s Gatewayto Deep Learning [J]. Cell Systems, 2016, 2(1): 12-14.

[13] Wan J J, Shan H T. Reliability evaluation of distribution network based on WOA optimization of LSTM neural network [J]. Intelligent Computer and Application, 2021, 11(10): 107-112+117.