Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models

This paper proposes a novel price forecasting method based on wavelet transform combined with ARIMA and GARCH models. By wavelet transform, the historical price series is decomposed and reconstructed into one approximation series and some detail series. Then each subseries can be separately predicted by a suitable time series model. The final forecast is obtained by composing the forecasted results of each subseries. This proposed method is examined on Spanish and PJM electricity markets and compared with some other forecasting methods.     

Short term wind speed forecasting for wind turbine applications using linear prediction method

In this paper a new method, based on linear prediction, is proposed for wind speed forecasting. The method utilizes the ‘linear prediction’ method in conjunction with ‘filtering’ of the wind speed waveform. The filtering eliminates the undesired parts of the frequency spectrum (i.e. smoothing) of the measured wind speed which is less effective in an application, for example, in a wind energy conversion system. The linear prediction method is intuitively explained with some easy to follow case studies to clarify the complex underlying mathematics. For verification purposes, the proposed method is compared with real wind speed data based on experimental results. The results show the effectiveness of the linear prediction method.     

A new strategy for wind speed forecasting using artificial intelligent methods

A new strategy in wind speed prediction based on fuzzy logic and artificial neural networks was proposed. The new strategy for fuzzy logic not only provides significantly less rule base but also has increased estimated wind speed accuracy when compared to traditional one. Meanwhile, applying the proposed approach to artificial neural network leads to less neuron numbers and less learning time process along with accurate wind speed prediction results. The experimental results demonstrate that the proposed method not only provides less computational time but also a better wind speed prediction performance.     

Regime‐switching models and multiple causal factors in forecasting wind speed

This study evaluates two types of models for wind speed forecasting. The first is models with multiple causal factors, such as offsite readings of wind speed and meteorological variables. These can be estimated using either regressions or neural networks. The second is state transition and the closely related class of regime‐switching transition models. These are attractive in that they can be used to predict outlying fluctuations or large ramp events. The regime‐switching model uses a persistence forecast during periods of high wind speed, and regressions for low and intermediate speeds. These techniques are tested on three databases. Two main criteria are used to evaluate the outcomes, the number of high and low states than can be predicted correctly and the mean absolute percent error of the forecast. Neural nets are found to predict the state transitions somewhat better than logistic regressions, although the regressions do not do badly. Three methods all achieve about the same degree of forecast accuracy: multivariate regressions, state transition and regime‐switching models. If the states could be predicted perfectly, the regime‐switching model would improve forecast accuracy by an additional 2.5 to 3 percentage points. Analysis of the density functions of wind speed and the forecasting models finds that the regime‐switching method more closely approximates the distribution of the actual data. Copyright © 2009 John Wiley & Sons, Ltd.     

测风数据间隔对风速预测精度影响的研究

风速预测对风电场控制和电网调度具有十分重要的意义。文章以不同时间间隔的测风数据为基础,采用时间序列法和人工神经网络法对风速进行预测,通过比较风速预测绝对平均误差,说明时间间隔较短时,采用BP神经网络预测精度较高;当时间间隔增大时,采用时间序列法预测精度较高;时间间隔过大,即风速数据太少时,两种预测方法误差都较大,须谨慎使用。该研究结果对风电机组控制系统的设计以及电网调度计划的制定具有参考价值。     

Modeling and forecasting the mean hourly wind speed time series using GMDH-based abductive networks

Wind speed forecasts are important for the operation and maintenance of wind farms and their profitable integration into power grids, as well as many important applications in shipping, aviation, and the environment. Modern machine learning techniques including neural networks have been used for this purpose, but it has proved hard to make significant improvements on the performance of the simple persistence model. As an alternative approach, we propose here the use of abductive networks, which offer the advantages of simplified and more automated model synthesis and transparent analytical input–output models. Various abductive models for predicting the mean hourly wind speed 1 h ahead have been developed using wind speed data at Dhahran, Saudi Arabia during the month of May over the years 1994–2005. The models were evaluated on the data for May 2006. Models described include a single generic model to forecast next-hour speed from the previous 24 hourly measurements and an hour index, which give an overall mean absolute error (MAE) of 0.85 m/s and a correlation coefficient of 0.83 between actual and predicted values. The model achieves an improvement of 8.2% reduction in MAE compared to hourly persistence. The above model was used iteratively to forecast the hourly wind speed 6 h and 24 h ahead at the end of a given day, with MAEs of 1.20 m/s and 1.42 m/s which are lower than forecasting errors based on day-to-day persistence by 14.6% and 13.7%. Relative improvements on persistence exceed those reported for several machine learning approaches reported in the literature.     

基于MRMR的ORELM的短期风速预测

由于风速具有间歇性、随机性及波动性等特点,导致大规模风电并网对电力系统的安全、稳定运行带来严重影响。文章提出一种基于最大相关最小冗余(Maximum Correlation Minimum Redundancy,MRMR)的离群鲁棒极限学习机(Outlier Robust Extreme Learning Machine,ORELM)的短期风速预测新方法。首先分析影响风速的属性特征,采用MRMR算法来衡量不同风速属性特征与风速的相关性,进而确定风速属性特征的输入维度;然后对极限学习机(Extreme Learning Machine,ELM)进行优化,构建ORELM风速预测模型。最后以美国某大型风电场实测数据为依据进行风速预测,仿真结果表明该方法具有较高的预测精度。     

Short-term forecasting of wind speed and related electrical power

Wind speed and the related electrical power of wind turbines are forecasted. The work is focused on the operation of power systems with integrated wind parks. Artificial neural networks models are proposed for forecasting average values of the following 10 min or 1 h. Input quantities for the prediction are wind speeds and their derivatives. Also, spatial correlation of wind speeds and its use for forecasting, are investigated. The methods are tested using data collected over seven years at six different sites on islands of the South and Central Aegean Sea in Greece.     

两种风速短临预报方法对比研究

利用BP神经网络法和最小二乘法,对不同地形条件下的4个测站的10 s量级和15 min量级平均风速进行短临预报实验。研究发现,最小二乘法预报误差小,满足预报误差小于35%的日数比较大。无论是10 s量级预报,还是15 min量级预报,对于风速较大的01号站和04号站,最小二乘法优于BP神经网络法;对于风速较小的02号站和03号站,两种预报方法的预报效果相近;在10 s量级和15 min量级的风速短临预报方面,算法复杂的BP神经网络法并无明显优势。因此,在选取预报方法前,应结合预报方法本身的特征,充分考虑预报方法对地形、地貌和气候特征以及预报时效的适应性,最好对几个备选方法进行预报效果比对。     

A new strategy for predicting short-term wind speed using soft computing models

Wind power prediction is a widely used tool for the large-scale integration of intermittent wind-powered generators into power systems. Given the cubic relationship between wind speed and wind power, accurate forecasting of wind speed is imperative for the estimation of future wind power generation output. This paper presents a performance analysis of short-term wind speed prediction techniques based on soft computing models (SCMs) formulated on a backpropagation neural network (BPNN), a radial basis function neural network (RBFNN), and an adaptive neuro-fuzzy inference system (ANFIS). The forecasting performance of the SCMs is augmented by a similar days (SD) method, which considers similar historical weather information corresponding to the forecasting day in order to determine similar wind speed days for processing. The test results demonstrate that all evaluated SCMs incur some level of performance improvement with the addition of SD pre-processing. As an example, the SD+ANFIS model can provide up to 48% improvement in forecasting accuracy when compared to the individual ANFIS model alone.     

Dynamic models of wind farms with fixed speed wind turbines

The increasing wind power penetration on power systems requires the development of adequate wind farms models for representing the dynamic behaviour of wind farms on power systems. The behaviour of a wind farm can be represented by a detailed model including the modelling of all wind turbines and the wind farm electrical network. But this detailed model presents a high order model if a wind farm with high number of wind turbines is modelled and therefore the simulation time is long. The development of equivalent wind farm models enables the model order and the computation time to be reduced when the impact of wind farms on power systems is studied. In this paper, equivalent models of wind farms with fixed speed wind turbines are proposed by aggregating wind turbines into an equivalent wind turbine that operates on an equivalent wind farm electrical network. Two equivalent wind turbines have been developed: one for aggregated wind turbines with similar winds, and another for aggregated wind turbines under any incoming wind, even with different incoming winds.The proposed equivalent models provide high accuracy for representing the dynamic response of wind farm on power system simulations with an important reduction of model order and simulation time compare to that of the complete wind farm modelled by the detailed model.     

Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm

Affected by various environment factors, wind speed presents characters of high fluctuations, autocorrelation and stochastic volatility; thereby it is hard to forecast with a single model. A hybrid model combining with input selected by deep quantitative analysis, Wavelet Transform (WT), Genetic Algorithm (GA) and Support Vector Machines (SVM) was proposed. WT was exploited to decompose the wind speed signal into two components, an approximation signal to maintain the major fluctuations and a detail signal to eliminate the stochastic volatility. SVM were built to model the approximation signal. Autocorrelation and partial correlation were applied to analyze the inner ARIMA Autoregressive Integrated Moving Average (ARIMA) relationship between the historical speeds thus to select the input of SVM from them, and Granger causality test was applied to select input from environment variables by checking the influence of temperature with different leading lengths. The parameters in SVM were fine-tuned by GA to ensure the generalization of SVM. A case study of a wind farm from North China demonstrates that this method outperforms the comparison models.     

基于特征选择的RELM风速短期预测

准确的风速预测是风电场功率预测的基础,对大规模风电并网具有重要的价值。文章提出一种基于信息增益(IG)的正则化极限学习机(RELM)短期风速预测方法。首先采用信息增益对32维风速属性序列进行特征选择,并对其进行加权;然后将正则化系数引入极限学习机(ELM)网络,构建RELM风速预测模型;最后结合美国风能技术中心的实测数据进行仿真,与传统ELM网络、BP神经网络相比,该方法具有较高的准确性和预测精度。     

基于k-means聚类的SVR短期风速预测

准确的风速预测是风力发电功率预测的重要基础。为了进一步提高风速预测精度,文章提出一种基于k-means聚类的支持向量回归机(SVR)的短期风速组合预测新方法。首先分析影响风速变化的因素,计算不同风速属性相对于风速序列的皮尔逊相关系数(PCC)值,并对其进行加权;然后采用k-means聚类方法对风速样本进行聚类;再利用SVR针对每组样本建模;最后结合实际风电场进行仿真,结果表明,该方法具有较高的准确性和可行性。     

On comparing three artificial neural networks for wind speed forecasting

Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. In this paper, we present a comprehensive comparison study on the application of different artificial neural networks in 1-h-ahead wind speed forecasting. Three types of typical neural networks, namely, adaptive linear element, back propagation, and radial basis function, are investigated. The wind data used are the hourly mean wind speed collected at two observation sites in North Dakota. The performance is evaluated based on three metrics, namely, mean absolute error, root mean square error, and mean absolute percentage error. The results show that even for the same wind dataset, no single neural network model outperforms others universally in terms of all evaluation metrics. Moreover, the selection of the type of neural networks for best performance is also dependent upon the data sources. Among the optimal models obtained, the relative difference in terms of one particular evaluation metric can be as much as 20%. This indicates the need of generating a single robust and reliable forecast by applying a post-processing method.     

Very short-term wind speed forecasting with Bayesian structural break model

This paper examines a new time series method for very short-term wind speed forecasting. The time series forecasting model is based on Bayesian theory and structural break modeling, which could incorporate domain knowledge about wind speed as a prior. Besides this Bayesian structural break model predicts wind speed as a set of possible values, which is different from classical time series model's single-value prediction This set of predicted values could be used for various applications, such as wind turbine predictive control, wind power scheduling. The proposed model is tested with actual wind speed data collected from utility-scale wind turbines.     

A new formulation for rotor equivalent wind speed for wind resource assessment and wind power forecasting

The spurt of growth in the wind energy industry has led to the development of many new technologies to study this energy resource and improve the efficiency of wind turbines. One of the key factors in wind farm characterization is the prediction of power output of the wind farm that is a strong function of the turbulence in the wind speed and direction. A new formulation for calculating the expected power from a wind turbine in the presence of wind shear, turbulence, directional shear and direction fluctuations is presented. It is observed that wind shear, directional shear and direction fluctuations reduce the power producing capability, while turbulent intensity increases it. However, there is a complicated superposition of these effects that alters the characteristics of the power estimate that indicates the need for the new formulation. Data from two field experiments is used to estimate the wind power using the new formulation, and results are compared to previous formulations. Comparison of the estimates of available power from the new formulation is not compared to actual power outputs and will be a subject of future work. © 2015 The Authors. Wind Energy published by John Wiley & Sons, Ltd.     

Improved week-ahead predictions of wind speed using simple linear models with wavelet decomposition

Simple linear methods are widely used for time series modelling and prediction and in particular for the forecast of wind speed variations. Linear prediction models are popular for their simplicity and computational efficiency, but their prediction accuracy generally deteriorates beyond a few time steps. In this paper we demonstrate that the prediction accuracy of simple auto-regressive (AR) models can be significantly improved, by as much as 60.15% for day-ahead predictions and up to 18.25% for week-ahead predictions, when combined with suitable time series decomposition. The comparison with new reference forecast model (NRFM) also shows similar accuracy gain of week ahead predictions. The combined model is capable of forecasting wind speed up to 7 days ahead with an average root mean square error less than 3 m/s. We also compare the performance of AR and f-ARIMA models in wind speed prediction and observe that the f-ARIMA model is no better than the AR model when used in combination with time series decomposition.     

Short‐term forecasting of surface layer wind speed using a continuous random cascade model

This paper describes a statistical method for short‐term forecasting (1–12 h ahead) of surface layer wind speed using only recent observations, relying on the notion of continuous cascades. Inspired by recent empirical findings that suggest the existence of some cascading process in the mesoscale range, we consider that wind speed can be described by a seasonal component and a fluctuating part represented by a ‘multifractal noise’ associated with a random cascade. Performances of our model are tested on hourly wind speed series gathered at various locations in Corsica (France) and the Netherlands. The obtained results show that a better modeling of the noise term based on cascade process enhances the forecast; furthermore, there is a systematic improvement in the prediction as compared with reference models. Copyright © 2011 John Wiley & Sons, Ltd.     

基于优化聚类的组合风速短期预测

准确的风功率预测对电力系统安全、稳定运行具有重要意义,而风速预测是风功率预测的关键。文章提出一种基于优化模糊C均值(Optimal Fuzzy C means,OFCM)聚类的组合风速短期预测方法。首先,采用模拟退火遗传算法优化模糊C均值聚类算法的初始聚类中心;其次,基于优化模糊C均值聚类算法将初始风速属性样本数据进行分组;再根据不同风速样本组,运用极限学习机(Extremely Learning Machine,ELM)构建组合风速预测模型;最后,通过风速实测值与预测值的对比,验证了该方法的可行性。