基于非参数核密度估计的风电功率区间预测

由于风电的高度随机性和波动性,且风电功率的预测精度仍较低,因此传统的风电功率点预测不足以描绘风电的不确定性。在风电功率点预测值的基础上,采用非参数核密度估计方法计算风电功率预测误差的概率密度,并采用三次样条插值拟合预测误差的概率分布曲线,继而得出满足一定置信概率的风电功率预测区间。结果表明,采用风电功率区间预测能提供风电功率预测曲线和该曲线的变化范围,更有利于风电的不确定性建模。     

基于CGKELM的风功率预测研究

风功率预测在不同应用场景中发挥着越来越重要的作用,从时间尺度上可分为超短期、短期和中长期的风功率预测。基于短期风功率预测对训练时间和预测精度均有较高要求,提出了一种利用共轭梯度(cconjugate gradient,CG)法优化核极限学习机(kernel extreme learning machine,KELM)的方法,即利用共轭梯度核极限学习机(CGKELM)方法来预测风功率,在保证预测精度的前提下,进一步缩短KELM的训练时间。通过利用某风电场的实测数据进行仿真,以均方根误差和相对标准差作为评价指标,将仿真结果分别与反向传播(BP)神经网络、最小二乘支持向量机(LSSVM)和其他KELM方法得到的结果进行比较。研究结果表明：在短期风功率预测方面,CGKELM训练时间比其他方法短,且参数设置简单。该结果证明了CGKELM的有效性,对风电项目的投资决策具有一定的参考价值。     

基于ARMAX-GARCH模型的微电网风功率预测

目前风功率预测多为风功率期望的点预测,且以采样间隔较大的功率序列作为建模序列,这样会降低预测模型对风功率时序特征模拟的准确度和可信度。文中基于小采样间隔风功率序列,提出ARMAX-GARCH风功率预测模型。通过构造风功率新息序列,结合小时平均风功率序列,建立ARMAX点预测模型,采用BIC最小信息准则和相关性分析实现模型定阶和外生变量选择;采用GARCH模型模拟残差的波动特性实现区间预测。以海岛微电网实测风功率数据为例,进行提前1 h风功率预测。结果表明,与持续法、ARMA和RBF神经网络相比,该预测模型能显著提高风功率期望的点预测精度并具有较好的区间预测效果。     

基于QR-NFGLSTM与核密度估计的风电功率概率预测

为提高风电功率概率预测精度和缩短长短期记忆网络的训练时间,提出一种基于分位数回归结合新遗忘门长短期记忆(NFGLSTM)网络与核密度估计的风电功率概率预测方法.该方法对长短期记忆网络的结构改进,提出一种新的遗忘门结构,以缩短训练时间.基于分位数回归和NFGLSTM网络建立组合预测模型,得到风电功率点预测值和某一置信度下...     

基于风速误差校正和ALO-LSSVM的风电功率预测

风资源的随机波动性引起的相位滞后性问题,导致风电功率预测精度不高,尤其是风速变化较快时,滞后性引起的预测误差较大。考虑到风速波动与风功率变化密切相关,提出一种非参数核密度估计和数值天气预报(NWP)相结合的方法,并对预测风速误差进行校正,改善了预测风速的相位滞后性;然后将校正后的风速和风功率作为输入数据进行风电功率预测;采用蚁狮算法(ALO)优化最小二乘支持向量机(LSSVM)参数,从而建立基于风速误差校正和ALO-LSSVM组合的风电功率预测模型。算例结果表明,所提方法风功率预测精度更高。     

考虑风功率预测误差相关性的旋转备用容量优化

文章研究了风电场间风功率预测误差相关性对系统备用容量选取的影响。首先,对不同风电场的风功率预测误差及其相互间的关联特性进行了研究,建立联合概率分布模型;其次,建立了考虑其相关性的旋转备用容量优化模型,模型兼顾经济性与可靠性,以火电系统燃料成本与停电损失之和最小为目标,约束条件着重考虑了系统切负荷与弃风概率均小于设定的置信度;最后,算例验证了模型的有效性,可为系统旋转备用容量的优化制定提供参考。     

基于LSTM和非参数核密度估计的风电功率概率区间预测

高精度的风电功率点和区间预测可以为电网优化配置带来更多信息.提出采用长短期记忆(LSTM)网络实现风电功率的点预测,并基于该网络生成1组风电功率预测误差数据集,采用渐进积分均方误差准则的窗宽优化方法实现非参数核密度的估计,求出不同置信度下的风电功率波动区间.实验基于美国某风电场历史数据,通过与BP,Elman神经网络和...     

基于NACEMD-Elman神经网络的风功率组合预测

在电力系统中风电装机容量增长的背景下,高精度的超短期风功率预测是保证系统可靠运行的重要基础。为此,提出一种以复数据经验模态分解的噪声辅助信号分解法(NACEMD)和Elman神经网络为基础的超短期风功率组合预测方法。在风功率序列中添加白噪声,使用NACEMD将其按照不同波动尺度逐级分解,得到不同时频特性的分量,然后利用Elman神经网络对各分量建立预测模型,以各分量的不同时频特性为基准对预测结果进行叠加,得到风功率预测值。实例分析表明,提出的组合预测法既可进一步减轻现有方法中存在的模态混叠现象,具备较高的预测精度。研究成果可为风功率预测提供参考。     

基于总体平均经验模态分解与改进Elman神经 网络的风功率组合预测

风功率的短期预测对于电力系统的安全稳定运行具有重要意义。提出了一种基于总体平均经验模态分解（EEMD）和改进Elman神经网络的短期风功率组合预测方法。首先利用EEMD分解将风功率序列按不同波动尺度逐级分解,得到不同频率的分量以缓解风功率序列的非平稳性,然后对各分量分别建立改进的Elman神经网络预测模型进行预测,最后叠加各分量的预测结果得到最终预测数据。仿真结果表明,该方法不仅可以有效缓解风功率非平稳性对于预测精度的影响,还可以避免传统方法的模态混叠问题,具有较高的预测精度和适应性。     

基于SVM的风速风功率预测模型

风电是一种最方便、最成熟的可再生能源。风力发电具有波动性、间歇性和随机性,大容量的风力发电接入电网,对电力系统的安全、稳定运行带来影响。通过风速风功率预测,对风电场的出力进行短期预报,是解决这一问题的有效途径。常用的预测方法中,要么预测结果偏差太大,要么存在过学习、维数灾难和局部极值问题。支持向量机(SVM)应用于风速风功率预测,明显优于常用方法,得到相当可观的结果。     

An optimized autoregressive forecast error generator for wind and load uncertainty study

This paper presents a first‐order autoregressive algorithm used to generate real‐time (RT), hour‐ahead (HA) and day‐ahead (DA) wind and load forecast errors in time series. The modeled error time series preserve the characteristics of the historical forecast data sets. Four statistical characteristics are considered: the means, the standard deviations, the autocorrelations and the cross‐correlations. A stochastic optimization routine was used to find an optimal set of parameters that minimize the differences of the four characteristics between the generated error series and the targeted ones. The obtained parameters were then in due order of succession used to produce the RT, HA and DA forecasts. This method, although implemented as a first‐order regressive random forecast error generator, can be extended to higher orders. Simulation results have shown that the methodology produces random forecast error series that have statistics similar to those derived from real data sets. The wind and load forecast error generator can be used in wind integration studies to produce wind and load forecast in time series for stochastic planning processes. Our future studies will focus on reflecting the diurnal and seasonal differences of the wind and load statistics and on implementing them in the random forecast generator. Copyright © 2011 John Wiley & Sons, Ltd.     

Forecasting wind power quantiles using conditional kernel estimation

The efficient management of wind farms and electricity systems benefit greatly from accurate wind power quantile forecasts. For example, when a wind power producer offers power to the market for a future period, the optimal bid is a quantile of the wind power density. An approach based on conditional kernel density (CKD) estimation has previously been used to produce wind power density forecasts. The approach is appealing because: it makes no distributional assumption for wind power; it captures the uncertainty in forecasts of wind velocity; it imposes no assumption for the relationship between wind power and wind velocity; and it allows more weight to be put on more recent observations. In this paper, we adapt this approach. As we do not require an estimate of the entire wind power density, our new proposal is to optimise the CKD-based approach specifically towards estimation of the desired quantile, using the quantile regression objective function. Using data from three European wind farms, we obtained encouraging results for this new approach. We also achieved good results with a previously proposed method of constructing a wind power quantile as the sum of a point forecast and a forecast error quantile estimated using quantile regression.     

A control strategy for energy storage system based on wind power prediction error interval

由于风能的间歇性和随机性,风电功率预测的精度依然较低。随着大规模风电的集中接入,不确定性风电功率并网运行会加重电力系统的调控负担,同时会对日前调度计划安排带来不利影响。储能系统具有对功率和能量的时间迁移能力,被认为是平抑风电功率波动性、提高风电功率确定性的有效手段。本文从电力系统安全角度分析了制约风电上网规模的原因,使用基于时间序列的自回归模型预测风电功率,提出利用储能平抑风电功率预测误差区间的方法,对比考虑最大预测误差的传统调度方法,采用风电平均入网容量、风电发电量、电网空间利用率等评价指标评估所提出方法的有效性。     

基于Copula理论的风电功率条件预测误差短期概率分布估计

风电功率预测分析是降低风电不确定性对电力系统影响的重要手段。文章提出了基于Copula理论的风电功率预测不确定性研究方法,从风电功率实际值和预测值的相关性入手,采用Copula理论对风电功率实际值和预测值的相依关系进行分析,在某一预测值的条件下,计算风电功率实际值的条件概率分布,进而转移到误差的条件概率分析当中,之后再将误差的分布估计转换为风电功率预测的不确定性估计。以东北地区某风电场的实测数据和预测数据进行实例分析,通过评价指标验证了该方法的有效性。     

Lifetime and economic analyses of lithium‐ion batteries for balancing wind power forecast error

Wind power plant operators are often faced with extra charges when their power production does not match the forecasted power. Because the accuracy of wind power forecasts is limited, the use of energy storage systems is an attractive alternative even when large‐scale aggregation of wind power is considered. In this paper, the economic feasibility of lithium‐ion batteries for balancing the wind power forecast error is analysed. In order to perform a reliable assessment, an ageing model of lithium‐ion battery was developed considering both cycling and calendar life. The economic analysis considers two different energy management strategies for the storage systems and it is performed for the Danish market. Analyses have shown that the price of the Li‐ion BESS needs to decrease by 6.7 times in order to obtain a positive net present value considering the present prices on the Danish energy market. Moreover, it was found that for total elimination of the wind power forecast error, it is required to have a 25‐MWh Li‐ion battery energy storage system for the considered 2 MW WT. Copyright © 2015 John Wiley & Sons, Ltd.     

Assessing the suitability of wind speed probabilty distribution functions based on wind power density

Three functions have so far predominantly been used for fitting the measured wind speed probability distribution in a given location over a certain period of time, typically monthly or yearly. In the literature, it is common to fit these functions to compare which one fits the measured distribution best in a particular location. During this comparison process, parameters on which the suitability of the fit is judged are required. The parameters that are mostly used are the mean wind speed or the total wind energy output (primary parameters). It is, however, shown in the present study that one cannot judge the suitability of the functions based on the primary parameters alone. Additional parameters (secondary parameters) that complete the primary parameters are required to have a complete assessment of the fit, such as the discrepancy between the measured and fitted distributions, both for the wind speed and wind energy (that is the standard deviation of wind speed and wind energy distributions). Therefore, the secondary statistical parameters have to be known as well as the primary ones to make a judgement about the suitability of the distribution functions analysed. The primary and secondary parameters are calculated from the 12-month of measured hourly wind speed data and detailed analyses of wind speed distributions are undertaken in the present article.     

Implementation of a Model Output Statistics based on meteorological variable screening for short‐term wind power forecast

A combination of physical and statistical treatments to post‐process numerical weather predictions (NWP) outputs is needed for successful short‐term wind power forecasts. One of the most promising and effective approaches for statistical treatment is the Model Output Statistics (MOS) technique. In this study, a MOS based on multiple linear regression is proposed: the model screens the most relevant NWP forecast variables and selects the best predictors to fit a regression equation that minimizes the forecast errors, utilizing wind farm power output measurements as input. The performance of the method is evaluated in two wind farms, located in different topographical areas and with different NWP grid spacing. Because of the high seasonal variability of NWP forecasts, it was considered appropriate to implement monthly stratified MOS. In both wind farms, the first predictors were always wind speeds (at different heights) or friction velocity. When friction velocity is the first predictor, the proposed MOS forecasts resulted to be highly dependent on the friction velocity–wind speed correlation. Negligible improvements were encountered when including more than two predictors in the regression equation. The proposed MOS performed well in both wind farms, and its forecasts compare positively with an actual operative model in use at Risø DTU and other MOS types, showing minimum BIAS and improving NWP power forecast of around 15% in terms of root mean square error. Further improvements could be obtained by the implementation of a more refined MOS stratification, e.g. fitting specific equations in different synoptic situations. Copyright © 2012 John Wiley & Sons, Ltd.     

Impacts of large amounts of wind power on design and operation of power systems,results of IEA collaboration

There are dozens of studies made and ongoing related to wind integration. However, the results are not easy to compare. IEA WIND R&D Task 25 on ‘Design and Operation of Power Systems with Large Amounts of Wind Power’ collects and shares information on wind generation impacts on power systems, with analyses and guidelines on methodologies. In the state‐of‐the‐art report (October, 2007), and the final report of the 3 years period (July, 2009) the most relevant wind power grid integration studies have been analysed especially regarding methodologies and input data. Several issues that impact on the amount of wind power that can be integrated have been identified. Large balancing areas and aggregation benefits of wide areas help in reducing the variability and forecast errors of wind power as well as help in pooling more cost effective balancing resources. System operation and functioning electricity markets at less than day‐ahead time scales help reduce forecast errors of wind power. Transmission is the key to aggregation benefits, electricity markets and larger balancing areas. Best practices in wind integration studies are described. There is also benefit when adding wind power to power systems: it reduces the total operating costs and emissions as wind replaces fossil fuels and this should be highlighted more in future studies. Copyright © 2010 John Wiley & Sons, Ltd.     

A comparison of methodologies for monthly wind energy estimation

Monthly wind energy estimations obtained by means of three different methodologies are evaluated. Hourly wind and wind power production data measured at five wind farms in the Northeast of Spain within the period spanning from June 1999 to June 2003 were employed for this purpose. One of the approaches is based on the combined contribution of the hourly wind speed frequency distribution and the corresponding power production. Several alternatives to represent the empirical wind power versus wind speed relationship are considered and their impacts on the error of monthly energy estimations assessed. Two more approaches derive monthly energy estimates directly from monthly wind values: one uses the theoretical power curve to obtain interpolated monthly wind power production values and the other consists in a simple linear regression between the observed wind speed and wind power monthly pairs, which serves as an approximation to the global power curve. The three methodologies reproduce reliably the total monthly wind energy. Results also reveal that linearity is a reasonable assumption for the relation between wind speed and power production at monthly timescales. This approach involves a simplification with respect to other standard procedures that require finer temporal resolution data. Copyright © 2009 John Wiley & Sons, Ltd.