Probabilistic Wind Power Forecasting Research Articles

Probabilistic wind power forecasting based on logarithmic transformation and boundary kernel

Abstracts Probabilistic wind power forecasting not only produces the expectation of wind power output, but also gives quantitative information on the associated uncertainty, which is essential for making better decisions about power system and market operations with the increasing penetration of wind power generation. This paper presents a novel kernel density estimator for probabilistic wind power forecasting, addressing two characteristics of wind power which have adverse impacts on the forecast accuracy, namely, the heavily skewed and double-bounded nature of wind power density. Logarithmic transformation is used to reduce the skewness of wind power density, which improves the effectiveness of the kernel density estimator in a transformed scale. Transformations partially relieve the boundary effect problem of the kernel density estimator caused by the double-bounded nature of wind power density. However, the case study shows that there are still some serious problems of density leakage after the transformation. In order to solve this problem in the transformed scale, a boundary kernel method is employed to eliminate the density leak at the bounds of wind power distribution. The improvement of the proposed method over the standard kernel density estimator is demonstrated by short-term probabilistic forecasting results based on the data from an actual wind farm. Then, a detailed comparison is carried out of the proposed method and some existing probabilistic forecasting methods.

Stochastic predictive control of battery energy storage for wind farm dispatching: Using probabilistic wind power forecasts

The limited dispatchability of wind energy poses a challenge to its increased penetration. One technically feasible solution to this challenge is to integrate a battery energy storage system (BESS) with a wind farm. This highlights the importance of a BESS control strategy. In view of this, a stochastic model predictive control scheme is proposed in this paper. Based on the forecasted wind power distributions, the proposed scheme ensures the optimal operation of BESS in the presence of practical system constraints, thus bringing the wind-battery combined power output to the desired dispatch levels. The salient feature of the proposed scheme is that it takes into account the non-Gaussian wind power uncertainties. In this scheme, a probabilistic wind power forecasting model is employed as the prediction model, which quantifies the non-Gaussian uncertainties in wind power forecasts. Using chance constraints, the quantified uncertainties are incorporated into the controller design, thus forming a chance constrained stochastic programming problem. Using warping function, this problem is recast as a convex quadratic optimization problem, which is tractable both theoretically and practically. This way, the proposed control scheme handles the non-Gaussian uncertainties in wind power forecasts. The simulation results on actual data demonstrate the effectiveness of the proposed scheme. The data used in the simulation are obtained in the real operation of a wind farm in China.

Very-Short-Term Probabilistic Wind Power Forecasts by Sparse Vector Autoregression

A spatio-temporal method for producing very-short-term parametric probabilistic wind power forecasts at a large number of locations is presented. Smart grids containing tens, or hundreds, of wind generators require skilled very-short-term forecasts to operate effectively and spatial information is highly desirable. In addition, probabilistic forecasts are widely regarded as necessary for optimal power system management as they quantify the uncertainty associated with point forecasts. Here, we work within a parametric framework based on the logit-normal distribution and forecast its parameters. The location parameter for multiple wind farms is modeled as a vector-valued spatio-temporal process and the scale parameter is tracked by modified exponential smoothing. A state-of-the-art technique for fitting sparse vector autoregressive models is employed to model the location parameter and demonstrates numerical advantages over conventional vector autoregressive models. The proposed method is tested on a dataset of 5 min mean wind power generation at 22 wind farms in Australia. Five-min ahead forecasts are produced and evaluated in terms of point, and probabilistic forecast skill scores and calibration. Conventional autoregressive and vector autoregressive models serve as benchmarks.

A novel application of an analog ensemble for short-term wind power forecasting

The efficient integration of wind in the energy market is limited by its natural variability and predictability. This limitation can be tackled by using the probabilistic predictions that provide accurate deterministic forecasts along with a quantification of their uncertainty. We propose as a novelty the application of an analog ensemble (AnEn) method to generate probabilistic wind power forecasts (WPF). The AnEn prediction of a given variable is constituted by a set of measurements of the past, concurrent to the past forecasts most similar to the current one. The AnEn performance for WPF is compared with three state-of-the-science methods for probabilistic predictions over a wind farm and a 505-day long period: a wind power prediction based on the ensemble wind forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF) Ensemble Prediction System (ECMWF-EPS), the Limited-area Ensemble Prediction System (LEPS) developed within the COnsortium for Small-scale MOdelling (COSMO-LEPS) and a quantile regression (QR) technique. The AnEn performs as well as ECMWF-EPS, COSMO-LEPS and QR for common events while it exhibits more skill for rare events. A comparison with the performances obtained with a deterministic forecasting method based on a Neural Network is also carried out showing the benefits of using AnEn.

A Hybrid Intelligent Model for Deterministic and Quantile Regression Approach for Probabilistic Wind Power Forecasting

With rapid increase in wind power penetration into the power grid, wind power forecasting is becoming increasingly important to power system operators and electricity market participants. The majority of the wind forecasting tools available in the literature provide deterministic prediction, but given the variability and uncertainty of wind, such predictions limit the use of the existing tools for decision-making under uncertain conditions. As a result, probabilistic forecasting, which provides information on uncertainty associated with wind power forecasting, is gaining increased attention. This paper presents a novel hybrid intelligent algorithm for deterministic wind power forecasting that utilizes a combination of wavelet transform (WT) and fuzzy ARTMAP (FA) network, which is optimized by using firefly (FF) optimization algorithm. In addition, support vector machine (SVM) classifier is used to minimize the wind power forecast error obtained from WT+FA+FF. The paper also presents a probabilistic wind power forecasting algorithm using quantile regression method. It uses the wind power forecast results obtained from the proposed hybrid deterministic WT+FA+FF+SVM model to evaluate the probabilistic forecasting performance. The performance of the proposed forecasting model is assessed utilizing wind power data from the Cedar Creek wind farm in Colorado.

Discussion of “Combined Nonparametric Prediction Intervals for Wind Power Generation”

In the above-named work, the lower upper bounds estimation (LUBE) method is proposed to construct combined nonparametric prediction intervals (PIs) of wind power generation, which is also used in [2]. We would like to commend the authors for their efforts in exploring probabilistic wind power forecasting, which is an important research area toward a renewable-energy-penetrated operation environment for power systems.

Probabilistic wind power forecasting with online model selection and warped gaussian process

Based on the online model selection and the warped Gaussian process (WGP), this paper presents an ensemble model for the probabilistic wind power forecasting. This model provides the non-Gaussian predictive distributions, which quantify the non-Gaussian uncertainties associated with wind power. In order to follow the time-varying characteristics of wind generation, multiple time dependent base forecasting models and an online model selection strategy are established, thus adaptively selecting the most probable base model for each prediction. WGP is employed as the base model, which handles the non-Gaussian uncertainties in wind power series. Furthermore, a regime switch strategy is designed to modify the input feature set dynamically, thereby enhancing the adaptiveness of the model. In an online learning framework, the base models should also be time adaptive. To achieve this, a recursive algorithm is introduced, thus permitting the online updating of WGP base models. The proposed model has been tested on the actual data collected from both single and aggregated wind farms.

Comparison of the economic impact of different wind power forecast systems for producers

Abstract. Deterministic forecasts of wind production for the next 72 h at a single wind farm or at the regional level are among the main end-users requirement. However, for an optimal management of wind power production and distribution it is important to provide, together with a deterministic prediction, a probabilistic one. A deterministic forecast consists of a single value for each time in the future for the variable to be predicted, while probabilistic forecasting informs on probabilities for potential future events. This means providing information about uncertainty (i.e. a forecast of the PDF of power) in addition to the commonly provided single-valued power prediction. A significant probabilistic application is related to the trading of energy in day-ahead electricity markets. It has been shown that, when trading future wind energy production, using probabilistic wind power predictions can lead to higher benefits than those obtained by using deterministic forecasts alone. In fact, by using probabilistic forecasting it is possible to solve economic model equations trying to optimize the revenue for the producer depending, for example, on the specific penalties for forecast errors valid in that market. In this work we have applied a probabilistic wind power forecast systems based on the "analog ensemble" method for bidding wind energy during the day-ahead market in the case of a wind farm located in Italy. The actual hourly income for the plant is computed considering the actual selling energy prices and penalties proportional to the unbalancing, defined as the difference between the day-ahead offered energy and the actual production. The economic benefit of using a probabilistic approach for the day-ahead energy bidding are evaluated, resulting in an increase of 23% of the annual income for a wind farm owner in the case of knowing "a priori" the future energy prices. The uncertainty on price forecasting partly reduces the economic benefit gained by using a probabilistic energy forecast system.

Review on probabilistic forecasting of wind power generation

The randomness and intermittence of wind resources is the biggest challenge in the integration of wind power into the power system. Accurate forecasting of wind power generation is an efficient tool to deal with such problem. Conventional wind power forecasting produces a value, or the conditional expectation of wind power output at a time point in the future. However, any prediction involves inherent uncertainty. In recent years, several probabilistic forecasting approaches have been reported in wind power forecasting studies. Compared to currently wide-used point forecasts, probabilistic forecasts could provide additional quantitative information on the uncertainty associated with wind power generation. For decision-makings in the uncertainty environment, probabilistic forecasts are optimal inputs. A review of state-of-the-art methods and new developments in wind power probabilistic forecasting is presented in this paper. Firstly, three different representations of wind power uncertainty are briefly introduced. Then, different forecasting methods are discussed. These methods are classified into three categories in terms of uncertainty representation, i.e. probabilistic forecasts (parametric and non-parametric), risk index forecasts and space-time scenario forecasts. Finally, requirements and the overall framework of the uncertainty forecasting evaluation are summarized. In addition, this article also describes current challenges and future developments associated with wind power probabilistic prediction.

Dynamic Scheduling of Operating Reserves in Co-Optimized Electricity Markets With Wind Power

We propose a probabilistic methodology to estimate a demand curve for operating reserves, where the curve represents the amount that a system operator is willing to pay for these services. The demand curve is quantified by the cost of unserved energy and the expected loss of load, accounting for uncertainty from generator contingencies, load forecasting errors, and wind power forecasting errors. The methodology addresses two key challenges in electricity market design: integrating wind power more efficiently and improving scarcity pricing. In a case study, we apply the proposed operating reserve strategies in a two-settlement electricity market with centralized unit commitment and economic dispatch and co-optimization of energy and reserves. We compare the proposed probabilistic approach to traditional operating reserve rules. We use the Illinois power system to illustrate the efficiency of the proposed reserve market modeling approach when it is combined with probabilistic wind power forecasting.

Probabilistic wind power forecasts with an inverse power curve transformation and censored regression

ABSTRACTForecasting wind power is an important part of a successful integration of wind power into the power grid. Forecasts with lead times longer than 6 h are generally made by using statistical methods to post‐process forecasts from numerical weather prediction systems. Two major problems that complicate this approach are the non‐linear relationship between wind speed and power production and the limited range of power production between zero and nominal power of the turbine. In practice, these problems are often tackled by using non‐linear non‐parametric regression models. However, such an approach ignores valuable and readily available information: the power curve of the turbine's manufacturer. Much of the non‐linearity can be directly accounted for by transforming the observed power production into wind speed via the inverse power curve so that simpler linear regression models can be used. Furthermore, the fact that the transformed power production has a limited range can be taken care of by employing censored regression models.In this study, we evaluate quantile forecasts from a range of methods: (i) using parametric and non‐parametric models, (ii) with and without the proposed inverse power curve transformation and (iii) with and without censoring. The results show that with our inverse (power‐to‐wind) transformation, simpler linear regression models with censoring perform equally or better than non‐linear models with or without the frequently used wind‐to‐power transformation. © 2013 The Authors. Wind Energy published by John Wiley & Sons Ltd.

PROBABILISTIC WIND POWER FORECASTING USING A SINGLE FORECAST

This paper develops a new approach for producing probabilistic wind power forecasts using a single forecast. The Singular Spectrum Analysis technique is used as the forecasting technique. Given the confidence interval calculated for the single forecast, a large number of random forecasts were generated through the Monte Carlo method. The purpose of generating probabilistic wind power forecasts is to use the results in a stochastic programming unit commitment problem. Therefore, probabilistic forecasts are reduced to a small number of representative forecast scenarios by applying a scenario reduction algorithm. The stability of the scenario reduction algorithm is also evaluated. The results indicate that the insignificant changes of operational cost of the stochastic programming problem reflect a deletion of unimportant forecast scenarios

Sparse online warped Gaussian process for wind power probabilistic forecasting

Wind generation has experienced rapid growth around the world in the past decade. This highlights the importance of the short-term wind power forecasting. This paper focuses on the probabilistic short-term wind power forecasting. An online sparse Bayesian model is established. The key features of the proposed model are its non-Gaussian predictive distributions and its time-adaptiveness. This model based on the warped Gaussian process (WGP), which handles the non-Gaussian uncertainties in wind power series by automatically transforming it to a latent series. The transformed series is well-modeled by a Gaussian process (GP), then the non-Gaussian uncertainty associated with the wind power can be predicted in a standard GP framework. Wind generation is a process whose characteristics change with time, so a wind power forecasting model should exhibit adaptive features. To address this, we introduce an online learning algorithm to WGP, thus permitting WGP to track the time-varying characteristic of wind generation. Moreover, since the high computational costs of WGP hinder its practical application on large-scale problems such as wind power forecast, the proposed model also employs a sparsification method to reduce its computational costs, thus enhancing its practical applicability. The simulation on actual data validates the effectiveness of the proposed model. The data used in the simulation are obtained in the real operation of a wind farm in China.

Demand Dispatch and Probabilistic Wind Power Forecasting in Unit Commitment and Economic Dispatch: A Case Study of Illinois

In this paper, we analyze how demand dispatch combined with the use of probabilistic wind power forecasting can help accommodate large shares of wind power in electricity market operations. We model the operation of day-ahead and real-time electricity markets, which the system operator clears by centralized unit commitment and economic dispatch. We use probabilistic wind power forecasting to estimate dynamic operating reserve requirements, based on the level of uncertainty in the forecast. At the same time, we represent price responsive demand as a dispatchable resource, which adds flexibility in the system operation. In a case study of the power system in Illinois, we find that both demand dispatch and probabilistic wind power forecasting can contribute to efficient operation of electricity markets with large shares of wind power.

Probabilistic Wind Power Forecasting Using Radial Basis Function Neural Networks

A novel methodology for probabilistic wind power forecasting is described. The method is based on artificial intelligence and concentrates on the uncertainty information about the future wind power production predicting a set of quantiles with predefined nominal probabilities. The proposed model uses the point predictions of an existing state-of-the-art wind power forecasting model and forecasts the prediction uncertainties due to the inaccuracies of the numerical weather predictions (NWP), the weather stability and the deterministic forecasting model. The performance of the proposed model is evaluated on two wind farms that are located in areas with different weather conditions.

Wind Power Trading Under Uncertainty in LMP Markets

This paper presents a new model for optimal trading of wind power in day-ahead (DA) electricity markets under uncertainty in wind power and prices. The model considers settlement mechanisms in markets with locational marginal prices (LMPs), where wind power is not necessarily penalized from deviations between DA schedule and real-time (RT) dispatch. We use kernel density estimation to produce a probabilistic wind power forecast, whereas uncertainties in DA and RT prices are assumed to be Gaussian. Utility theory and conditional value at risk (CVAR) are used to represent the risk preferences of the wind power producers. The model is tested on real-world data from a large-scale wind farm in the United States. Optimal DA bids are derived under different assumptions for risk preferences and deviation penalty schemes. The results show that in the absence of a deviation penalty, the optimal bidding strategy is largely driven by price expectations. A deviation penalty brings the bid closer to the expected wind power forecast. Furthermore, the results illustrate that the proposed model can effectively control the trade-off between risk and return for wind power producers operating in volatile electricity markets.

Very-Short-Term Probabilistic Forecasting of Wind Power With Generalized Logit–Normal Distributions

SummaryVery-short-term probabilistic forecasts, which are essential for an optimal management of wind generation, ought to account for the non-linear and double-bounded nature of that stochastic process. They take here the form of discrete–continuous mixtures of generalized logit–normal distributions and probability masses at the bounds. Both auto-regressive and conditional parametric auto-regressive models are considered for the dynamics of their location and scale parameters. Estimation is performed in a recursive least squares framework with exponential forgetting. The superiority of this proposal over classical assumptions about the shape of predictive densities, e.g. normal and beta, is demonstrated on the basis of 10-min-ahead point and probabilistic forecasting at the Horns Rev wind farm in Denmark.

Time-adaptive quantile-copula for wind power probabilistic forecasting

This paper presents a novel time-adaptive quantile-copula estimator for kernel density forecast and a discussion of how to select the adequate kernels for modeling the different variables of the problem. Results are presented for different case-studies and compared with splines quantile regression (QR). The datasets used are from NREL’s Eastern Wind Integration and Transmission Study, and from a real wind farm located in the Midwest region of the United States. The new probabilistic prediction model is elegant and simple and yet displays advantages over the traditional QR approach. Especially notable is the quality of the results achieved with the time-adaptive version, namely when evaluated in terms of prediction calibration, which is a characteristic that is advantageous for both system operators and wind power producers.

Setting the Operating Reserve Using Probabilistic Wind Power Forecasts

In power systems with a large integration of wind power, setting the adequate operating reserve levels is one of the main concerns of system operators (SO). The integration of large shares of wind generation in power systems led to the development of new forecasting methodologies, including probabilistic forecasting tools, but management tools able to use those forecasts to help making operational decisions are still needed. In this paper, a risk evaluation perspective is used, showing that it is possible to describe the consequences of each possible reserve level through a set of risk indices useful for decision making. The new reserve management tool (RMT) described in the paper is intended to support the SO in defining the operating reserve needs for the daily and intraday markets. Decision strategies like setting an acceptable risk level or finding a compromise between economic issues and the risk of loss of load are explored. An illustrative example based on the Portuguese power system demonstrates the usefulness and efficiency of the tool.

A comparison of a few statistical models for making quantile wind power forecasts

AbstractDuring the last few years, probabilistic wind power forecasts have received increasing attention because of their assumed value in decision‐making processes. In the current article, three statistical methods are described and several models based on these are compared. The statistical methods are local quantile regression, a local Gaussian model and the Nadaraya–Watson estimator for conditional cumulative distribution functions. The focus is on quantile forecasts, since these often provide the required type of information to make optimal economic decisions and are ideal for visualizing uncertainty. The statistical methods are applied to data from a wind farm in Norway and results are compared using appropriate measures for assessment of quantile forecasts and in terms of a simple model for economic value. Copyright © 2005 John Wiley & Sons, Ltd.