Multi-unit Wind Power Prediction Based on Long Short-term Memory andParticle Swarm Optimization
[1]WU Zhenlong,MO Yipeng,WANG Ronghua,et al.Multi-unit Wind Power Prediction Based on Long Short-term Memory andParticle Swarm Optimization[J].Journal of Zhengzhou University (Engineering Science),2024,45(06):114-121.[doi:10.13705/j.issn.1671-6833.2024.06.005]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
45
Number of periods:
2024 06
Page number:
114-121
Column:
Public date:
2024-09-25
- Title:
- Multi-unit Wind Power Prediction Based on Long Short-term Memory andParticle Swarm Optimization
- Keywords:
- long short-term memory; wind power prediction; multi-unit; particle swarm optimization algorithm; feature selection
- CLC:
- TM614 TK81
- DOI:
- 10.13705/j.issn.1671-6833.2024.06.005
- Abstract:
- At present, the manual adjustment of hyper-parameter for current wind power prediction model was slowand unreliability. In order to achieve the prediction effect, the model used in wind power prediction needs to selectthe appropriate hyper-parameters for the model. Based on this, in this study, a multi-unit wind power predictionmodel was proposed based on long short-term memory ( LSTM) . Firstly, the Spearman correlation method was usedto quantitative analysis. Secondly, the principal component analysis ( PCA) was used to reduce the dimension ofthe input features as well as extract the key information. In addition, considering the difficulty of choosing parameters for LSTM, in this study, particle swarm optimization ( PSO) algorithm was used to optimize the number of hidden layer neurons in each layer of LSTM. For the problem of wind power prediction of multiple units, in this study,a single wind turbine was used to find the most excellent model in a single unit, and applied the prediction model tomulti-unit prediction. Experiments showed that compared with other models, the root mean square error of the proposed method was reduced by 11. 8%, and the mean absolute error was reduced by 5. 03%.
- References:
-
[1] ZHAO J, WANG J Z, GUO Z H, et al. Multi-step windspeed forecasting based on numerical simulations and anoptimized stochastic ensemble method[ J] . Applied Energy, 2019, 255: 113833.[2] NAIK J, DASH S, DASH P K, et al. Short term windpower forecasting using hybrid variational mode decomposition and multi-kernel regularized pseudo inverse neuralnetwork[ J] . Renewable Energy, 2018, 118: 180-212.[3] SHARIFIAN A, GHADI M J, GHAVIDEL S, et al. Anew method based on type-2 fuzzy neural network for accurate wind power forecasting under uncertain data [ J] .Renewable Energy, 2018, 120: 220-230.[4] ZHANG F, LI P C, GAO L, et al. Application of autoregressive dynamic adaptive ( ARDA) model in real-timewind power forecasting [ J ] . Renewable Energy, 2021,169: 129-143.[5] 张颖超, 成金杰, 邓华, 等. 基于相似日和特征提取的短期风电功率预测[ J] . 郑州大学学报(工学版) ,2020, 41(5) : 44-49.ZHANG Y C, CHENG J J, DENG H, et al. Short-termwind power prediction based on similar day and featureextraction [ J] . Journal of Zhengzhou University ( Engineering Science) , 2020, 41(5) : 44-49.[6] 朱俊丞, 杨之乐, 郭媛君, 等. 深度学习在电力负荷预测中的 应 用 综 述 [ J] . 郑 州大学学报 (工学版) ,2019, 40(5) : 13-22.ZHU J C, YANG Z L, GUO Y J, et al. Deep learningapplications in power system load forecasting: a survey[ J] . Journal of Zhengzhou University ( Engineering Science) , 2019, 40(5) : 13-22.[7] ZHANG J H, YAN J, INFIELD D, et al. Short-term forecasting and uncertainty analysis of wind turbine powerbased on long short-term memory network and Gaussianmixture model[J]. Applied Energy, 2019, 241: 229-244.[8] KISVARI A, LIN Z, LIU X L. Wind power forecasting:adata-driven method along with gated recurrent neural network[ J] . Renewable Energy, 2021, 163: 1895-1909.[9] ZHANG Y G, PAN G F, CHEN B, et al. Short-termwind speed prediction model based on GA-ANN improvedby VMD [ J ] . Renewable Energy, 2020, 156: 1373 -1388.[10] FU W L, FANG P, WANG K, et al. Multi-step aheadshort-term wind speed forecasting approach coupling variational mode decomposition, improved beetle antennaesearch algorithm-based synchronous optimization and Volterra series model [ J] . Renewable Energy, 2021, 179:1122-1139.[11] NAIK J, DASH P K, DHAR S. A multi-objective windspeed and wind power prediction interval forecasting usingvariational modes decomposition based multi-kernel robustridge regression[J]. Renewable Energy, 2019, 136: 701-731.[12] LIU H, MI X W, LI Y F, et al. Smart wind speed deeplearning based multi-step forecasting model using singularspectrum analysis, convolutional gated recurrent unit network and support vector regression[ J] . Renewable Energy, 2019, 143: 842-854.[13] 李静茹, 姚方. 引入注意力机制的 CNN 和 LSTM 复合风电预测模型[ J] . 电气自动化, 2022, 44(6) : 4-6.LI J R, YAO F. Integrated CNN and LSTM wind powerprediction modelwith the introduction of attention mechanism[ J] . Electrical Automation, 2022, 44(6) : 4-6.[14] BENTSEN L Ø, WARAKAGODA N D, STENBRO R, etal. Spatio-temporal wind speed forecasting using graphnetworks and novel transformer architectures[ J] . AppliedEnergy, 2023, 333: 120565.[15] 黄秋娟. 基于注意力机制的风电功率预测[D] . 重庆:重庆大学, 2022.HUANG Q J. Wind power prediction based on attentionmechanism[D]. Chongqing: Chongqing University, 2022.[16] 吴珺玥, 赵二刚, 郭增良, 等. 基于 Spearman 系数和TCN 的光伏出力超短期多步预测 [ J] . 太阳能学报,2023, 44(9) : 180-186.WU J Y, ZHAO E G, GUO Z L, et al. Ultra-short-termphotovoltaic power multi-step prediction based onSpearman coefficient and TCN[ J] . Acta Energiae SolarisSinica, 2023, 44(9) : 180-186.[17] 余光正, 陆柳, 汤波, 等. 考虑转折性天气的海上风电功率超短期分段预测方法研究[ J] . 中国电机工程学报, 2022, 42(13) : 4859-4871.YU G Z, LU L, TANG B, et al. Research on ultra-shortterm subsection forecasting method of offshore wind powerconsidering transitional weather [ J] . Proceedings of theCSEE, 2022, 42(13) : 4859-4871.[18] 刘洋. 基于 NWP 数据优化下的风电场功率预测算法研究[D] . 太原: 太原科技大学, 2021.LIU Y. Wind farm power prediction algorithm based onNWP data optimization[ D] . Taiyuan: Taiyuan Universityof Science and Technology, 2021.[19] 王丽婕, 冬雷, 高爽. 基于多位置 NWP 与主成分分析的风电功率短期预测 [ J] . 电工技术学报, 2015, 30(5) : 79-84.WANG L J, DONG L, GAO S. Wind power short-termprediction based on principal component analysis of NWPof multiple locations [ J] . Transactions of China Electrotechnical Society, 2015, 30(5) : 79-84.[20] 赵晓阳. 基于神经网络的空气质量预测模型构建研究[D] . 包头: 内蒙古科技大学, 2020.ZHAO X Y. Research on construction of air quality forecast model based on neural network [ D] . Baotou: InnerMongolia University of Science & Technology, 2020.[21] 黄峰, 向 书 琛, 王 睿, 等. 一 种 基 于 VMD-PSO-SVM的短期风 电 功 率 预 测 算 法 [ J] . 湖 南 工 程 学 院 学 报(自然科学版) , 2022, 32(2) : 7-12.HUANG F, XIANG S C, WANG R, et al. A design ofPSO-SVM short-term wind power forecasting algorithmbased on VMD [ J]. Journal of Hunan Institute of Engineering (Natural Science Edition), 2022, 32(2): 7-12.[22] 刘洪波, 盖雪扬, 孙黎, 等. 计及数据降维和数据清洗的超短期风电功率预测[ J] . 东北电力大学学报,2023, 43(4) : 1-9.LIU H B, GAI X Y, SUN L, et al. Ultra-short-term windpower prediction considering data reduction and datacleaning[ J] . Journal of Northeast Electric Power University, 2023, 43(4) : 1-9.[23] 黄志祥, 周莉. 基于 VMD-LSTM 的短期电力负荷预测研究[ J] . 洛阳 理 工 学 院 学 报 ( 自 然 科 学 版) , 2022,32(3) : 76-80, 96.HUANG Z X, ZHOU L. Research on short term loadforecasting based on VMD-LSTM[ J] . Journal of LuoyangInstitute of Science and Technology (Natural Science Edition) , 2022, 32(3) : 76-80, 96.[24] QIAN Z, PEI Y, ZAREIPOUR H, et al. A review anddiscussion of decomposition-based hybrid models for windenergy forecasting applications [ J ] . Applied Energy,2019, 235: 939-953.[25] HOURAN M A, BUKHARI S M S, ZAFAR M H, et al.COA-CNN-LSTM: coati optimization algorithm-based hybrid deep learning model for PV / wind power forecastingin smart grid applications [ J ] . Applied Energy, 2023,349: 121638
- Similar References:
Memo
-
Last Update:
2024-09-29