Wind Farm Ultra-Short-Term Wind Speed Prediction Based on EEMDSE-ILSTM

doi:10.3778/j.issn.1002-8331.2007-0087

Abstract

Abstract:

The depletion of nonrenewable resources pushes forward the development of new energy. Wind power, as the main form of wind energy utilization, has been widely promoted. However, the non-linear, non-stationary and time-series characteristics of wind speed have adverse effects on the wind turbine generator itself and power system. Therefore, accurate wind speed prediction has become the key issue to be solved. In this paper, an EEMDSE-ILSTM wind speed prediction model is proposed based on the combination prediction method. In this model, Ensemble Empirical Mode Decomposition（EEMD） is used to decompose the wind speed data into several component data sets, and each component is filtered by sample entropy to simplify the data. Improved whale algorithm is combined with Long Short-Term Memory（LSTM） to generate appropriate model prediction parameters without supervision. The model predicts each decomposing data in turn and adds up the results to get the final prediction value. The simulation results show that the model has better prediction accuracy and generalization performance compared with other methods.

Key words: Ensemble Empirical Mode Decomposition（EEMD）, sample entropy, wind speed prediction, Improved Whale Optimization Algorithm（IWOA）, Long Short-Term Memory（LSTM）

摘要：

不可再生资源的枯竭推动着新能源的发展，风电作为目前风能利用的主要形式得到了大面积推广。但风速非线性、非平稳性、时序性的特点对风机本身和电力系统都会产生不利的影响，因此精准的风速预测已经成为亟待解决的关键课题。基于组合预测方法，提出了一种EEMDSE—ILSTM风速预测模型。该模型利用集合经验模态分解（Ensemble Empirical Mode Decomposition，EEMD）将风速数据分解为若干个分量数据集，并通过样本熵对各分量进行筛选以简化数据。将改进的鲸鱼算法与长短期记忆网络（Long Short-Term Memory，LSTM）结合，无监督生成合适的模型预测参数。在预测时依次对每个分量数据预测并将结果累加获得最终预测值。仿真结果表明，该模型与其他方法比较，显示出较好的预测精度和泛化性能。

关键词: 集合经验模态分解（EEMD）, 样本熵, 风速预测, 改进的鲸鱼优化算法（IWOA）, 长短期记忆网络（LSTM）

YI Lingzhi, WANG Shitong, YI Fang, DENG Dong, YI Zhimin, JIANG Peng. Wind Farm Ultra-Short-Term Wind Speed Prediction Based on EEMDSE-ILSTM[J]. Computer Engineering and Applications, 2021, 57(22): 288-294.

易灵芝，王仕通，易芳，邓栋，易志敏，姜鹏. 基于EEMDSE-ILSTM的风电场超短期风速预测[J]. 计算机工程与应用, 2021, 57(22): 288-294.

References

[1] 孙丽玲，胡兰青.双馈风力发电机的调频策略及机组定子故障下的弱电网稳定性研究[J].电网技术，2018，42（2）：509-516.
SUN L L，HU L Q.Frequency regulation strategy of DFIG-based wind power generating unit and stability research of weak grids considering DFIG stator fault[J].Power System Technology，2018，42（2）：509-516.
[2] 唐振浩，孟庆煜，曹生现，等.基于小波深度置信网络的风电爬坡预测方法[J].太阳能学报，2019，40（11）：3213-3220.
TANG Z H，MENG Q Y，CAO S X，et al.Wind power ramp prediction algorithm cased on wavelet deep belief network[J].Acta Energiae Solaris Sinica，2019，40（11）：3213-3220.
[3] 王勃，汪步惟，杨明，等.风电爬坡事件的非精确条件概率预测[J].山东大学学报（工学版），2020，50（1）：82-94.
WANG B，WANG B W，YANG M，et al.Imprecise conditional probability prediction of wind power ramp events[J].Journal of Shandong University（Engineering Science），2020，50（1）：82-94.
[4] 李冰，张妍，刘石.基于LSTM的短期风速预测研究[J].计算机仿真，2018，35（11）：456-461.
LI B，ZHANG Y，LIU S.Wind speed short term prediction study based on LSTM[J].Computer Simulation，2018，35（11）：456-461.
[5] 杨锡运，孙翰墨.基于时间序列模型的风电场风速预测研究[J].动力工程学报，2011，31（3）：203-208.
YANG X Y，SUN H M.Wind speed prediction in wind farms based on time series model[J].Journal of Chinese Society of Power Engineering，2011，31（3）：203-208.
[6] AASIM，SINGH S，MOHAPATRA A.Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting[J].Renewable Energy，2019，136：758-768.
[7] 赵征，汪向硕，乔锦涛.基于VMD和改进ARIMA模型的超短期风速预测[J].华北电力大学学报，2019，46（1）：54-59.
ZHAO Z，WANG X S，QIAO J T.Ultra-short-term wind speed prediction based on VMD and improved ARIMA model[J].Journal of North China Electric Power University，2019，46（1）：54-59.
[8] SHIVANI，SANDHU K S.A comparative study of ARIMA and RNN for short term wind speed forecasting[C]//2019 10th International Conference on Computing，Communication and Networking Technologies，2019.
[9] JAMIL M，ZEESHAN M.A comparative analysis of ANN and chaotic approach-based wind speed prediction in India[J].Neural Computing and Applications，2019，31：6807-6819.
[10] 张妍，韩璞，王东风，等.基于变分模态分解和LSSVM的风电场短期风速预测[J].太阳能学报，2018，39（1）：194-202.
ZHANG Y，HAN P，WANG D F，et al.Short-term prediction of wind speed for wind farm based on variational mode decomposition and LSSVM model[J].Acta Energiae Solaris Sinica，2018，39（1）：194-202.
[11] 潘超，秦本双，何瑶，等.基于优化FCM聚类的RELM风速预[J].电网技术，2018，42（3）：842-848.
PAN C，QIN B S，HE Y，et al.Wind speed forecasting of regularized ELM based on optimized FCM clustering[J].Power System Technology，2018，42（3）：842-848.
[12] 刘云鹏，许自强，董王英，等.基于经验模态分解和长短期记忆神经网络的变压器油中溶解气体浓度预测方[J].中国电机工程学报，2019，39（13）：3998-4008.
LIU Y P，XU Z Q，DONG W Y，et al.Concentration prediction of dissolved gases in transformer oil based on empirical mode decomposition and long short-term memory neural networks[J].Proceedings of the CSEE，2019，39（13）：3998-4008.
[13] 陈亮，刘宏立，郑倩，等.基于EEMD-SVD-PE的轨道波磨趋势项提取[J].哈尔滨工业大学学报，2019，51（5）：171-177.
CHEN L，LIU H L，ZHENG Q，et al.An EEMD-SVD-PE approach to extract the trend of track irregularity[J].Journal of Harbin Institute of Technology，2019，51（5）：171-177.
[14] LI X Y，DAI K L，WANG Z P，et al.Lithium-ion batteries fault diagnostic for electric vehicles using sample entropy analysis method[J].Journal of Energy Storage，2020，27：101121.
[15] HOCHREITER S，SCHMIDHUBER J A.LSTM can solve hard long time lag problems[C]//9th International Conference on Neural Information Processing Systems，1996：473-479.
[16] MIRJALILI S，LEWIS A.The whale optimization algorithm[J].Advances in Engineering Software，2016，95：51-67.
[17] 王静，李维德.基于CEEMD和GWO的超短期风速预测[J].电力系统保护与控制，2018，46（9）：69-74.
WANG J，LI W D.Ultra-short-term forecasting of wind speed based on CEEMD and GWO[J].Power System Protection and Control，2018，46（9）：69-74.