Short-TermWind Power Prediction Based on Combinatorial Neural Networks

Wind power volatility not only limits the large-scale grid connection but also poses many challenges to safe grid operation.Accurate wind power prediction can mitigate the adverse effects of wind power volatility on wind power grid connections.For the characteristics of wind power antecedent data and precedent data jointly to determine the prediction accuracy of the prediction model,the short-term prediction of wind power based on a combined neural network is proposed.First,the Bi-directional Long Short Term Memory(BiLSTM)network prediction model is constructed,and the bi-directional nature of the BiLSTM network is used to deeply mine the wind power data information and find the correlation information within the data.Secondly,to avoid the limitation of a single prediction model when the wind power changes abruptly,the Wavelet Transform-Improved Adaptive Genetic Algorithm-Back Propagation(WT-IAGA-BP)neural network based on the combination of the WT-IAGA-BP neural network and BiLSTM network is constructed for the short-term prediction of wind power.Finally,comparing with LSTM,BiLSTM,WT-LSTM,WT-BiLSTM,WT-IAGA-BP,and WT-IAGA-BP&LSTM prediction models,it is verified that the wind power short-term prediction model based on the combination of WT-IAGA-BP neural network and BiLSTM network has higher prediction accuracy.

Gaussian Kernel Based SVR Model for Short-Term Photovoltaic MPP Power Prediction

Predicting the power obtained at the output of the photovoltaic(PV)system is fundamental for the optimum use of the PV system.However,it varies at different times of the day depending on intermittent and nonlinear environmen-tal conditions including solar irradiation,temperature and the wind speed,Short-term power prediction is vital in PV systems to reconcile generation and demand in terms of the cost and capacity of the reserve.In this study,a Gaussian kernel based Support Vector Regression(SVR)prediction model using multiple input variables is proposed for estimating the maximum power obtained from using per-turb observation method in the different irradiation and the different temperatures for a short-term in the DC-DC boost converter at the PV system.The performance of the kernel-based prediction model depends on the availability of a suitable ker-nel function that matches the learning objective,since an unsuitable kernel func-tion or hyper parameter tuning results in significantly poor performance.In this study for thefirst time in the literature both maximum power is obtained at max-imum power point and short-term maximum power estimation is made.While evaluating the performance of the suggested model,the PV power data simulated at variable irradiations and variable temperatures for one day in the PV system simulated in MATLAB were used.The maximum power obtained from the simu-lated system at maximum irradiance was 852.6 W.The accuracy and the perfor-mance evaluation of suggested forecasting model were identified utilizing the computing error statistics such as root mean square error(RMSE)and mean square error(MSE)values.MSE and RMSE rates which obtained were 4.5566*10-04 and 0.0213 using ANN model.MSE and RMSE rates which obtained were 13.0000*10-04 and 0.0362 using SWD-FFNN model.Using SVR model,1.1548*10-05 MSE and 0.0034 RMSE rates were obtained.In the short-term maximum power prediction,SVR gave higher prediction performance according to ANN and SWD-FFNN.

Rolling Generation Dispatch Based on Ultra-short-term Wind Power Forecast

The power systems economic and safety operation considering large-scale wind power penetration are now facing great challenges, which are based on reliable power supply and predictable load demands in the past. A rolling generation dispatch model based on ultra-short-term wind power forecast was proposed. In generation dispatch process, the model rolling correct not only the conventional units power output but also the power from wind farm, simultaneously. Second order Markov chain model was utilized to modify wind power prediction error state (WPPES) and update forecast results of wind power over the remaining dispatch periods. The prime-dual affine scaling interior point method was used to solve the proposed model that taken into account the constraints of multi-periods power balance, unit output adjustment, up spinning reserve and down spinning reserve.

Very Short-Term Generating Power Forecasting for Wind Power Generators Based on Time Series Analysis

In recent years, there has been introduction of alternative energy sources such as wind energy. However, wind speed is not constant and wind power output is proportional to the cube of the wind speed. In order to control the power output for wind power generators as accurately as possible, a method of wind speed estimation is required. In this paper, a technique considers that wind speed in the order of 1 - 30 seconds is investigated in confirming the validity of the Auto Regressive model (AR), Kalman Filter (KF) and Neural Network (NN) to forecast wind speed. This paper compares the simulation results of the forecast wind speed for the power output forecast of wind power generator by using AR, KF and NN.

Wind Speed Short-Term Prediction Based on Empirical Wavelet Transform, Recurrent Neural Network and Error Correction

Predicting wind speed accurately is essential to ensure the stability of the wind power system and improve the utilization rate of wind energy.However,owing to the stochastic and intermittent of wind speed,predicting wind speed accurately is difficult.A new hybrid deep learning model based on empirical wavelet transform,recurrent neural network and error correction for short-term wind speed prediction is proposed in this paper.The empirical wavelet transformation is applied to decompose the original wind speed series.The long short term memory network and the Elman neural network are adopted to predict low-frequency and high-frequency wind speed sub-layers respectively to balance the calculation efficiency and prediction accuracy.The error correction strategy based on deep long short term memory network is developed to modify the prediction errors.Four actual wind speed series are utilized to verify the effectiveness of the proposed model.The empirical results indicate that the method proposed in this paper has satisfactory performance in wind speed prediction.

A physical approach of the short-term wind power prediction based on CFD pre-calculated flow fields

A physical approach of the wind power prediction based on the CFD pre-calculated flow fields is proposed in this paper. The flow fields are obtained based on a steady CFD model with the discrete inflow wind conditions as the boundary conditions, and a database is established containing the important parameters including the inflow wind conditions, the flow fields and the corresponding wind power for each wind turbine. The power is predicted via the database by taking the Numerical Weather Prediction （NWP） wind as the input data. In order to evaluate the approach, the short-term wind power prediction for an actual wind farm is conducted as an example during the period of the year 2010. Compared with the measured power, the predicted results enjoy a high accuracy with the annual Root Mean Square Error （RMSE） of 15.2% and the annual MAE of 10.80%. A good performance is shown in predicting the wind power＇s changing trend. This approach is independent of the historical data and can be widely used for all kinds of wind farms including the newly-built wind farms. At the same time, it does not take much computation time while it captures the local air flows more precisely by the CFD model. So it is especially practical for engineering projects.

基于特征选择及ISSA-CNN-BiGRU的短期风功率预测

针对风电功率随机性大、平稳性低,以及直接输入预测模型往往难以取得较高精度等问题,提出了一种基于特征选择及改进麻雀搜索算法(ISSA)优化卷积神经网络-双向门控循环单元(CNN-BiGRU)的短期风电功率预测方法。首先,利用变分模态分解(VMD)将原始功率分解为一组包含不同信息的子分量,以降低原始功率序列的非平稳性,提升可预测性,同时通过观察中心频率方式确定模态分解数。其次,对每一分量采用随机森林(RF)特征重要度的方法进行特征选择,从风速、风向、温度、空气密度等气象特征因素中,选取对各个分量预测贡献度较高的影响因素组成输入特征向量。然后,建立各分量的CNN-BiGRU预测模型,针对神经网络算法参数难调、手动配置参数随机性大的问题,利用ISSA对模型超参数寻优,自适应搜寻最优参数组合。最后,叠加各分量的预测值,得到最终的预测结果。以中国内蒙古某风电场实际数据进行仿真实验,与多种单一及组合预测方法进行对比,结果表明,本文所提方法相比于其他方法具有更高的预测精度,其平均绝对百分比误差值达到2.644 0%;在其他4个数据集上进行的模型准确性及泛化性验证结果显示,模型平均绝对百分比误差值分别为4.385 3%、3.174 9%、1.576 1%和1.358 8%,均保持在5.000 0%以内,证明本文所提方法具有较好的预测精度及泛化能力。

基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测

为进一步提升短期风电功率的预测精度,提出了一种基于互补集合经验模态分解-样本熵(complementary ensemble empirical mode decomposition-sample entropy,CEEMD-SE)的卷积神经网络(convolutional neural network,CNN)和长短期记忆-门控循环单元(longshorttermmemory-gatedrecurrentunit,LSTM-GRU)的短期风电功率预测模型。首先,利用互补集合经验模态分解将原始风电功率序列分解为若干本征模态函数(intrinsic mode function,IMF)分量和一个残差(residual,RES)分量,利用样本熵算法将相近的分量进行重构;其次,搭建卷积神经网络和长短期记忆网络的并行网络结构,提取数据的局部特征和时序特征,并将特征融合后输入门控循环单元网络中进行学习预测;最后,通过算例进行验证,结果表明采用该模型后预测精度得到了有效提升,其均方根误差降低了15.06%、平均绝对误差降低了15.22%、决定系数提高了1.91%。

基于VMD-BiLSTM-WOA的短期风电功率预测

风力发电对于解决全球能源短缺问题有重要意义,准确预测风电功率有助于风电并网的合理调度和可靠的电网运行.文章提出了一种基于变分模态分解(Variational Mode Decomposition, VMD)、双向长短期记忆网络(Bidirectional Long Short-term Memory Network, BiLSTM)以及鲸鱼优化算法(Whale Optimization Algorithm, WOA)的混合深度学习模型,以用于短期风电功率预测.首先,VMD将原始风电功率分解为多个子模态,有效减少了序列的波动性;然后对每个子模态分别建立BiLSTM模型,使用WOA对BiLSTM中的参数进行优化,以提高混合模型的效率和预测性能;最后将各个子模型的结果叠加得到最终预测结果.在实验中通过建立不同的比较模型来说明改进策略的有效性和优越性,结果表明所提的混合模型在风电功率预测中具有较高的预测精度.

基于CNN-BiGRU-Attention的短期电力负荷预测

针对目前电力负荷数据随机性强,影响因素复杂,传统单一预测模型精度低的问题,结合卷积神经网络(Convolutional neural network,CNN)、双向门控循环单元(Bi-directional gated recurrent unit,BiGRU)以及注意力机制(Attention)在短期电力负荷预测上的不同优点,提出一种基于CNN-BiGRU-Attention的混合预测模型。该方法首先通过CNN对历史负荷和气象数据进行初步特征提取,然后利用BiGRU进一步挖掘特征数据间时序关联,再引入注意力机制,对BiGRU输出状态给与不同权重,强化关键特征,最后完成负荷预测。试验结果表明,该模型的平均绝对百分比误差(Mean absolute percentage error,MAPE)、均方根误差(Root mean square error,RMSE)、判定系数(R-square,R~2)分别为0.167%、0.057%、0.993,三项指标明显优于其他模型,具有更高的预测精度和稳定性,验证了模型在短期负荷预测中的优势。

基于CBAM-LSTM的风电集群功率短期预测方法

风电功率的精准预测对我国实现“碳达峰”、“碳中和”的目标具有重要意义。传统的风电功率预测方法往往忽视了时间序列数据中的长期依赖关系和空间相关性,导致预测结果不准确。为了解决这个问题,文中提出了了卷积块注意力机制(Convolutional Block Attention Module, CBAM)和长短时记忆网络(Long Short-Term Memory, LSTM)相结合的模型。首先,使用CBAM对风电功率时间序列数据特征和数值天气预报中蕴含的空间特性进行提取,该模块能够自适应地学习时间和空间上的重要特征;然后,将提取的特征输入到LSTM层结构中进行功率预测。为了验证所提方法的有效性,使用中国吉林省某风电场的数据集进行验证,实验结果表明,与其他功率预测方法相比,文中所提方法平均绝对误差(Mean Absolute Error, MAE)平均降低2.67%;决定系数(R-Square, R2)平均提高23%;均方根误差(Root Mean Square Error, RMSE)平均降低2.69%。

基于ikPCA-FABAS-KELM的短期风电功率预测

为了增强在短期风电功率预测领域中传统数据驱动机器学习模型的精度,提出基于ikPCA-FABAS-KELM的短期风电功率预测模型.首先,对主成分分析进行改进,提出可逆核主成分分析(ikPCA),在保证数据特征的同时,降低输入数据的复杂度,以提升模型运行速度;其次,引入萤火虫个体吸引策略对天牛须算法(BAS)进行改进,提出FABAS算法;最后,利用FABAS算法对核极限学习机(KELM)的正则化参数C和核参数γ进行寻优,降低人为因素对模型盲目训练的影响,提高模型预测精度.仿真结果显示,提出的预测模型有效提高了传统模型的预测精度.

基于VMD-LILGWO-LSSVM短期风电功率预测

目的为了减小风电功率并入国家电网时产生的频率波动,提高风电功率预测精度,方法提出一种结合变分模态分解(VMD)、改进灰狼算法(LILGWO)和最小二乘支持向量机(LSSVM)的风电功率短期预测方法。首先通过VMD方法将风电功率序列分解重构成3个复杂程度性不同的模态分量,降低风电功率的波动性;其次使用LSSVM挖掘各分量的特征信息,对各分量分别进行预测,针对LSSVM模型中重要参数的选取对预测精度影响较大问题,引入LILGWO对参数进行寻优;最后将各分量预测结果叠加重构,得到最终预测风电功率。结果以宁夏回族自治区某地区风电站实际数据为例,对未来三天分别进行预测取平均值,本文方法的预测平均绝对误差(mean absolute error,MAE)为2.7068 kW,均方根误差(root mean square error,RMSE)为2.0211,拟合程度决定系数(R-Square,R^(2))为0.9769,与对比方法3~6相比,RMSE分别降低了40.93%,25.21%,14.7%,6.24%;MAE分别降低了42.34%,28.04%,16.97%,7.77%;R^(2)分别提升了4.21%,1.78%,0.82%,0.28%。预测时长方面,BP和LSSVM平均训练时间分别是10,138 s,虽然LSSVM预测时间较长但效果最好,采用PSO、GWO、LILGWO对LSSVM进行寻优后训练时间分别平均缩短了39,44,58 s。结论仿真验证了所提方法在短期风电功率预测方面的有效性。

基于BP-AHP风机状态评估的超短期风电功率动态预测研究

针对传统风电功率预测仅考虑气象因素,且无法计及风电机组真实出力状态导致预测精度较差问题,本文提出一种计及风机状态的超短期风电功率动态预测方法。首先,为能够精确评估风机状态,将BP(error back propagation, BP)算法引入层次分析法(analytic hierarchy process, AHP)的评估结构中,构建BP-AHP风机状态评估模型,实现单台风机状态评估;然后,综合考虑地形及机组排布等因素,将风电场所有风机的状态取均值作为风电场状态,利用皮尔逊相关系数衡量所评估状态与功率之间的相关性以验证评估模型合理性,并采用XGBoost构建计及风机状态的动态预测模型;最后,以陕西地区某风电场实测数据进行算例分析,验证了所提方法的可行性及有效性。

基于BIRCH聚类的L-Transformer分布式光伏短期发电功率预测

精准的分布式光伏短期发电功率预测有助于电力系统运行与功率就地平衡。该文提出一种基于BIRCH(balanced iterative reducing and clustering using hierarchies)相似日聚类的L-Transformer(LSTM-Transformer)模型进行短期光伏功率预测。首先使用BIRCH无监督聚类算法对历史数据聚类得到3种典型天气,根据聚类结果划分测试集对模型进行训练。为提高不同天气类型下的预测精度,采用双层架构的L-Transformer模型,首层通过长短期记忆网络(long short term memory,LSTM)的门控单元机制捕捉时间序列中的长期依赖关系;次层结合Transformer模型的自注意力机制聚焦于当前任务更关键的特征量,通过多注意力头与光伏数据特征量相结合生成向量,注意力头并行计算,从而高效、精确地预测短期光伏功率。实测数据验证结果表明L-Transformer模型对于不同天气类型功率预测泛化性优异、精确度高,气象数据波动大时鲁棒性强。

基于EMD-PSO-Bi LSTM组合模型的短期风电功率预测

风电功率预测对风电并网的稳定运行具有重要意义。为了解决风电功率预测中的精度和模型稳定性问题,引入了EMD-PSO-BiLSTM模型。通过经验模态分解技术将原始风电功率序列分解为一系列固有模态函数,以有效捕捉数据中的多尺度特征,并为每个模态序列建立了各自的预测模型。鉴于双向长短时记忆神经网络良好的泛化能力,建立了基于BiLSTM的各模态预测模型。进一步采用粒子群算法优化了BiLSTM参数,解决了模型非线性、高维、多模态等问题,获得了各模态分量的最优模型,并通过汇总各模态分量的结果得到了风电功率预测值。最后,以湖南省某风电场的实际运行数据为例,验证了EMD-PSO-BiLSTM模型可以有效提高风电功率短期预测精度。

CEEMDAN-WPE-CLSA超短期风电功率预测方法研究

提出了一种结合自适应噪声完全集合经验模态分解、加权排列熵、卷积神经网络、长短期记忆网络和自注意力机制的超短期风电功率预测方法。首先,利用自适应噪声完全集合经验模态分解将原始风电功率时间序列自适应分解为一系列的模态分量,降低原始序列的非线性和波动性;其次,根据加权排列熵计算各模态分量间的相似性并对相似的分量进行重组,以修正自适应噪声完全集合经验模态分解的过度分解问题,使得修正后的模态分量更具规律性;最后,将重组后的分量输入卷积长短期记忆网络进行时序建模,并利用自注意力机制对卷积长短期记忆网络的神经元权重进行重新分配,提高了卷积长短期记忆网络对输入特征不确定性的适应能力。在此基础上,明确了自注意力机制和自适应噪声完全集合经验模态分解、加权排列熵在风电功率预测中的作用机制,以及风电功率信号包含的重要物理信息,证明了自适应噪声完全集合经验模态分解、加权排列熵以及自注意力机制在风电功率信号模态分解和长短期记忆网络隐层输出权重分配中的有效性。

基于ICEEMDAN-PSO-LSTM的短期风速预测

提出一种改进自适应噪声完备集合经验模态分解与粒子群优化长短时记忆神经网络模型的短期风速预测方法。采用ICEEMDAN算法对日风速数据进行分解并计算相应边际谱,以谱相关性为依据对历史数据进行筛选;运用PSO算法优化LSTM神经网络参数,对输入数据进行ICEEMDAN分解,将所获得的多个模态分量分别用PSO-LSTM进行预测,并通过将各分量预测值叠加的方法得到风速预测结果。使用所提方法对国内某风电场风速进行预测,通过比较分析验证所提方法的有效性。

基于SSA-VMD-INGO-RF的短期风电功率预测

为解决风电功率输出的不确定性、弱化电网波动以及电网的提质增效等问题,提出一种基于变分模态分解(VMD)、Piecewise混沌映射、北方苍鹰优化(NGO)算法和随机森林(RF)的组合模型。该模型采用麻雀搜索算法(SSA)对VMD核心参数(K值和惩罚系数α)进行寻优,通过SSA-VMD将原始功率序列分解为多个有限带宽的特征模态分量,以降低原始数据的复杂度和非平稳性对预测精度的影响;然后,构建模态分量并在改进的北方苍鹰算法优化随机森林中进行预测;最后,将各分量预测结果叠加,得到最终预测值。以内蒙古某风电场的实测数据为研究对象,将所提组合模型与另外6种模型进行比较。结果表明,所设计模型预测结果平均绝对百分比误差(MAPE)为1.734%,均方根误差为0.068 MW,R^(2)为0.992,证明了该模型的有效性。

基于KCR-Informer的长期风电功率预测研究

准确的长期风电功率预测对电网系统稳定运行至关重要,传统预测方法在处理长序列预测时效果并不理想,近期研究表明Informer模型在长序列预测领域取得良好效果。然而,该模型在捕捉数据的局部特征以及处理网络层数堆叠问题上还有待改进。文章提出一种基于卡尔曼滤波器-卷积神经网络-残差网络-Informer(Kalman filter-convolutional neural network-residual network-informer,KCR-Informer)模型的长期风电功率预测方法,首先分析气象数据对风电功率的影响,使用卡尔曼滤波器对风电气象数据进行数据平滑处理,以减轻噪声对数据的影响,然后基于Informer模型建立风电功率预测模型,根据气象数据以及历史功率数据进行长期功率预测;在此基础上,引入卷积神经网络和残差连接模块,使模型能够更好的捕捉到局部特征,同时加快模型收敛,解决模型网络退化问题。算例的结果表明,与长短期记忆网络(long short-term memory,LSTM)算法、Transformer算法、Informer算法相比,文章方法在不同预测步长下的平均绝对误差(mean absolute error,MAE)降低5.7%~30%,均方误差(mean square error,MSE)降低8.3%~35%,长期风功率预测的精度得到提升,验证了模型的有效性。