A Categorisation Wind Power Forecasting Methodologies, Highlighting Emerging Short-Term Forecasting Methods

A new multistage short-term wind power forecast model using decomposition and artificial intelligence methods

The fluctuation and uncertainty of wind power generation bring severe challenges to secure and economic operation of power systems. Because wind power forecasting error is unavoidable, probabilistic forecasting becomes critical to accurately quantifying the uncertainty involved in traditional point forecasts of wind power and to providing meaningful information to conduct risk management in power system operation. This paper proposes a novel direct quantile regression approach to efficiently generate nonparametric probabilistic forecasting of wind power generation combining extreme learning machine and quantile regression. Quantiles with different proportions can be directly produced via an innovatively formulated linear programming optimization model, without dependency on point forecasts. Multistep probabilistic forecasting of 10-min wind power is newly carried out based on real wind farm data from Bornholm Island in Denmark. The superiority of the proposed approach is verified through comparisons with other well-established benchmarks. The proposed approach forms a new artificial neural network-based nonparametric forecasting framework for wind power with high efficiency, reliability, and flexibility, which can be beneficial to various decision-making activities in power systems.

In a power system where there are many fast and/or large changes in generation or consumption, e.g. in a system with large amounts of wind power, it is more complicated to handle the frequency control efficiently. Minimizing regulation costs for the system operator in such a system requires the possibility to simulate the frequency control in the time range from minutes to a few hours. In this paper, it is shown how the frequency control during normal operation can be optimized using a multi‐area model, without exceeding frequency limits or transmission capacity. The model has also been expanded to include uncertainties in wind power forecasts, which may lead to an increase of the regulating costs. The optimization model is applied to numerical examples to show the impact of wind power on costs for regulating power and to show the value of better wind speed forecasts. No load forecast errors are taken into account. Copyright © 2007 John Wiley & Sons, Ltd.

In this study, wind power forecasting is performed for a Wind Power Plant (WPP) with an installed capacity of 135 MW in Turkey. The ruggedness index (RIX) of the terrain where WPP was installed is analyzed with Wind Atlas Analysis and Application Program (WAsP). According to the obtained RIX value, the terrain of WPP is found to be complex. Due to the complexity of the terrain, wind power forecasting becomes difficult. To deal with this problem, a forecasting method with fast, accurate, and high performance is needed. Therefore, Extreme Learning Machine (ELM) based method is proposed for wind power forecasting in this study. Electrical and meteorological measurements are obtained from WPP for the application of the proposed method. These measurements are provided with high quality measuring devices. Also, Global Positioning System (GPS) time synchronization is used to prevent lags between measurements. The wind speed, wind direction, and wind power data of 1-year period are obtained from WPP. These data are used to compare the proposed method with a classical Artificial Neural Network (ANN) based method in terms of two, three and four hours-ahead wind power forecast performances. In the forecast studies performed for all data related to 2, 3, and 4-hours ahead, Normalized Root Mean Square Error (NRMSE) values of ELM are obtained as 7.01, 10.12, and 12.06, respectively, while these values are found as 8.19, 12.18, and 13.09 for ANN. In addition, the values of Correlation Coefficients (R) of the proposed forecast method results regarding 2, 3, and 4-hours ahead are 0.96588, 0.93528, and 0.88984, respectively. The R values related to ANN are observed as 0.95421, 0.91373, and 0.87576, respectively. According to the obtained results, it is observed that ELM has better performance features than classic method under all forecast conditions and it is clearly seen that ELM has by far short training time than other one.

The rapid expansion of wind power gives rise to a number of challenges for power system operators and electricity market participants. The key operational challenge is to efficiently handle the uncertainty and variability of wind power when balancing supply and demand in ths system. In this report, we analyze how wind power forecasting can serve as an efficient tool toward this end. We discuss the current status of wind power forecasting in U.S. electricity markets and develop several methodologies and modeling tools for the use of wind power forecasting in operational decisions, from the perspectives of the system operator as well as the wind power producer. In particular, we focus on the use of probabilistic forecasts in operational decisions. Driven by increasing prices for fossil fuels and concerns about greenhouse gas (GHG) emissions, wind power, as a renewable and clean source of energy, is rapidly being introduced into the existing electricity supply portfolio in many parts of the world. The U.S. Department of Energy (DOE) has analyzed a scenario in which wind power meets 20% of the U.S. electricity demand by 2030, which means that the U.S. wind power capacity would have to reach more than 300 gigawatts (GW). The European Union is pursuing a target of 20/20/20, which aims to reduce greenhouse gas (GHG) emissions by 20%, increase the amount of renewable energy to 20% of the energy supply, and improve energy efficiency by 20% by 2020 as compared to 1990. Meanwhile, China is the leading country in terms of installed wind capacity, and had 45 GW of installed wind power capacity out of about 200 GW on a global level at the end of 2010. The rapid increase in the penetration of wind power into power systems introduces more variability and uncertainty in the electricity generation portfolio, and these factors are the key challenges when it comes to integrating wind power into the electric power grid. Wind power forecasting (WPF) is an important tool to help efficiently address this challenge, and significant efforts have been invested in developing more accurate wind power forecasts. In this report, we document our work on the use of wind power forecasting in operational decisions.

The wind power sector is experiencing rapid growth, which creates new challenges for its electricity grid integration. Accurate wind power forecasting (WPF) is crucial for trading, balancing, and dispatching wind energy. In this paper, we examine the use of aggregated turbine- and farm-level WPFs in the Nordic energy market. The turbine-level WPFs were retrieved from a previous study, while the farm-level WPFs were developed using the same methodology, incorporating inputs from three different numerical weather predictions (NWPs) and implementing both direct and indirect forecasting approaches. In the indirect WPF approach, we explore the impact of using wind direction as an input for the wind farm-level power performance model. The different WPFs are combined into one using weights related to up-to-date forecast errors. An automated and optimized machine-learning pipeline using data from a Norwegian wind farm is used to implement the proposed forecasting methods. The indirect approach, that uses the wind-downscaling model, improves the wind speed forecast accuracy compared to raw forecasts from the relevant NWPs. Additionally, we observed that the farm-level downscaling model exhibited lower error than those developed at the turbine level. The combined use of multiple NWP sources reduced forecasting errors by 8 %–30 % for direct and indirect WPFs, respectively. Direct and indirect forecasting methods present similar performance. Finally, the aggregated turbine-level improved WPF accuracy by 10 % and 15 % for RMSE and MAE, respectively, compared to farm-level WPF.

A new intelligent method based on combination of VMD and ELM for short term wind power forecasting

Unlike other traditional energy resources, wind power outputs depend on natural wind resources that vary over space and time. Accurate wind power forecasting can reduce the burden of balancing energy equilibrium in electrical power systems. In this paper, we propose the short-term probabilistic forecasting of wind energy resources using the enhanced ensemble method. The enhanced ensemble forecasting methods are grouped into two main categories: temporal ensemble and spatial ensemble forecasting. The temporal ensemble forecasting is implemented by autoregressive integrated moving average with explanatory variable model, polynomial regression with time-series data, and analog ensemble for a probabilistic approach. The spatial ensemble forecasting is implemented by geostatistical model and interpolation with geographical property data. In addition, the stochastic approach, analog ensemble is applied to reduce the uncertainty in wind power forecasting and use of Numerical Weather Prediction models for accurate wind power forecasting is considered. We conduct stochastic wind power forecasting using practical data of Jeju power system and evaluate the system reliability on wind power generation variations. As a result, the proposed model shows better performances than single models, while at the same time providing probabilistic forecasts. Based on these forecasts, the grid operators can identify critical operating time points to prepare for problems that can occur in the system due to wind power variations in advance.

Wind power forecast plays an important role in wind farm operation and grid scheduling decisions. Prediction of power output from wind vector based on wind farm equivalent power curve is the final step of forecast, which has a lot of interaction with the grid dispatching, and it has a particularly prominent influence on the wind farm power output so as to cut down prediction accuracy. Focusing on the step of "wind-power transformation", a correction method of day-ahead wind power forecast including multiple factors such as wind-abandon coefficient is proposed in this paper. Firstly, it is proved that the wind power prediction error is affected by a variety of factors, such as the amplitude of predicted power, the volatility of forecast as well as the stability of recent wind power output. And a model is built to quantify them respectively. Then the wind-abandon coefficient is introduced to modeling the effect of wind power curtailment activities of grid dispatching to forecast accuracy. Finally, the evaluation model of wind power forecasting error is built by using the multiple linear regression method and corrects the predictive value. Case study basing on the actual operation data of a wind farm in northern China has shown that the proposed method is effective to improve the accuracy level of wind power forecast.

The uncertainty of wind power generation imposes significant challenges to optimal operation and control of electricity networks with increasing wind power penetration. To effectively address the uncertainties in wind power forecasts, probabilistic forecasts that can quantify the associated probabilities of prediction errors provide an alternative yet effective solution. This article proposes a hybrid artificial neural network approach to generate prediction intervals of wind power. An extreme learning machine is applied to conduct point prediction of wind power and estimate model uncertainties via a bootstrap technique. Subsequently, the maximum likelihood estimation method is employed to construct a distinct neural network to estimate the noise variance of forecasting results. The proposed approach has been tested on multi-step forecasting of high-resolution (10-min) wind power using actual wind power data from Denmark. The numerical results demonstrate that the proposed hybrid artificial neural network approach is effective and efficient for probabilistic forecasting of wind power and has high potential in practical applications.

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.

Wind power is undergoing a rapid development nationally as well as globally and in a number of countries covers an increasing part of the power supply. At the same time an ongoing liberalization of power markets is taking place and to an increasing extent the owners of wind power plants will themselves have to be responsible for trading the power at the spot market and financially handling the balancing. In the western part of Denmark (Jutland/Funen area), wind‐generated power from time to time covers almost 100% of total power consumption. Therefore some examples are chosen from this area to analyse in more detail how well large amounts of wind power in the short‐term are handled at the power spot market. It turns out that there is a tendency that more wind power in the system in the short run leads to relatively lower spot prices, while less wind power implies relatively higher spot prices, although, with the exception of December 2002, in general no strong relationship is found. A stronger relationship is found at the regulating market, where there is a fairly clear tendency that the more wind power produced, the higher is the need for down‐regulation, and, correspondingly, the less wind power produced, the higher is the need for up‐regulation. In general for the Jutland/Funen area the average cost of down‐regulation is calculated as 1·2 c€/kWh regulated for 2002, while the cost of up‐regulation amounts to 0·7 c€/kWh regulated. Copyright © 2003 John Wiley & Sons, Ltd.

Impact of large amounts of wind power on the operation of an electricity generation system: Belgian case study

Wind power impacts and electricity storage – A time scale perspective

Because wind has a high volatility and the respective energy produced cannot be stored on a large scale because of excessive costs, it is of utmost importance to be able to forecast wind power generation with the highest accuracy possible. The aim of this paper is to compare 1‐h‐ahead wind power forecasts performance using artificial intelligence‐based methods, such as artificial neural networks (ANNs), adaptive neural fuzzy inference system (ANFIS), and radial basis function network (RBFN). The latter was implemented using three different learning algorithms: stochastic gradient descent (SGD), hybrid, and orthogonal least squares (OLS). The application dataset is the injected wind power in the Portuguese power systems throughout the years 2010–2014. The network architecture optimization and the learning algorithms are presented. An initial data analysis showed data seasonality; therefore, the wind power forecasts were performed according to the seasons of the year. The results showed that ANFIS was the best performer method, and ANN and RBFN‐OLS also showed strong performances. RBFN‐Hybrid and RBFN‐SGD performed poorly. In general, all methods outperformed persistence.