Probabilistic Wind Power Forecasting with Hybrid Artificial Neural Networks

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.

Multi-objective optimization dispatching of a micro-grid considering uncertainty in 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.

With the rising demand for environmental protection, wind energy has made considerable progress as a clean energy source. Due to the uncertainty of wind power generation, accurate forecasting of wind power is conducive to achieving stable grid-connected control of wind turbines. This paper proposes an ultra-short-term wind power forecasting model composed of variational modal decomposition (VMD) and long short-term memory (LSTM) networks. Obtain the recorded historical wind speed and historical power from the wind field data acquisition and monitoring control system (SCADA), and use VMD to decompose and reconstruct the historical wind speed of the wind field to form 5 training data sets. Using historical power, historical wind speed, and predicted wind speed as input, wind power forecasts for the next 4 hours (15 minutes apart) are made. In order to evaluate the prediction ability of the proposed model, two algorithms, LSTM and XGBoost, are used for prediction. Taking root mean square error (RMSE) and mean absolute error (MAE) as evaluation indicators, the results show that the prediction accuracy of wind power is significantly improved after VMD processing, and the performance of LSTM is better than XGBoost in the two evaluation indicators.

K-nearest neighbors and a kernel density estimator for GEFCom2014 probabilistic wind power forecasting

Accurate information regarding the uncertainty of short-term forecast for aggregate wind power is a key to efficient and cost effective integration of wind farms into power systems. This paper presents a methodology for producing wind power forecast scenarios. Using historical wind power time series data and the Kernel Density Estimator (KDE), probabilistic wind power forecast scenarios were generated according to a rolling process. The improvement achieved in the accuracy of forecasts through frequent updating of the forecasts taking into account the latest realized wind power was quantified. The forecast scenarios produced by the proposed method were used as inputs to a unit commitment and optimal dispatch model in order to investigate how the uncertainty in wind forecast affect the operation of power system and in particular gas-fired generators.

A review of state‐of‐the‐art short‐term wind power probabilistic forecasting models is the focus here. The improvement of the accuracy and efficiency of probabilistic forecasting models has been in the centre of attention of researchers in recent years, since the need to further comprehend and efficiently use the uncertainty of forecasts is increasing. Since the optimal operation and control of energy systems and electricity markets is one of the important aspects of performing wind power forecasts, this review focuses in short‐term probabilistic forecasting models, which could prove to be useful in the daily planning and operation of power systems. The short‐term concept of forecasts is analysed in detail, along with the case studies and examples proposed by the reviewed literature. The key advantages and disadvantages of the reviewed probabilistic forecasting methodologies are identified. Furthermore, different classifications of the reviewed works according to the data that are used to provide an accurate forecasting model are also provided. Future directions in the field of short‐term wind power probabilistic forecasting are also proposed.

This paper proposes a privacy-preserving framework that couples probabilistic wind power forecasting with decentralized anomaly detection in complex power networks. We first design an adaptive federated learning (FL) scheme to produce probabilistic forecasts for multiple geographically distributed wind farms while keeping their raw data local. In this scheme, an artificial neural network with quantile regression is trained collaboratively across sites to provide calibrated prediction intervals for wind power outputs. These forecasts are then embedded into an alternating direction method of multipliers (ADMM)-based load-side dispatch and anomaly detection model for decentralized power systems with plug-and-play industrial users. Each monitoring node uses local measurements and neighbor communication to solve a distributed economic dispatch problem, detect abnormal load behaviors, and maintain network consistency without a central coordinator. Experiments on the GEFCom 2014 wind power dataset show that the proposed FL-based probabilistic forecasting method outperforms persistence, local training, and standard FL in RMSE and MAE across multiple horizons. Simulations on IEEE 14-bus and 30-bus systems further verify fast convergence, accurate anomaly localization, and robust operation, indicating the effectiveness of the integrated forecasting–dispatch framework for smart industrial grids with high wind penetration.

With the increasing penetration of wind power, the inherent intermittency and fluctuation of wind power generation bring severe challenges to the secure operations of power systems. Hybrid wind-storage systems equip a wind farm with multiple energy storage devices and are capable of smoothing wind power fluctuations effectively. This paper proposes a novel probabilistic forecasting based adaptive power smoothing framework for hybrid wind-storage systems. To begin with, probabilistic wind power forecasting is combined with multivariate copula function to generate the temporally correlated wind power scenario set. Then, an adaptive variational mode decomposition technique is proposed to decompose the wind power scenarios into various mode components, which are used to calculate the target grid-connected wind power and the target charging/discharging power of different energy storage devices. With these target power allocations, a stochastic rolling optimization model is established to obtain the schedule plan for hybrid wind-storage systems for the purpose of smoothing power fluctuations and enhancing system operational economy. The effectiveness of the proposed adaptive power smoothing framework and the feasibility of utilizing hybrid energy storage system to smooth wind power fluctuations are verified by case studies based on actual data from a Danish wind farm.

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.

Probabilistic wind power forecasting is an important input in the decision-making process in future electric power grids with large penetrations of renewable generation. Traditional probabilistic wind power forecasting models are trained offline and are then used to make predictions online. However, this strategy cannot make full use of the most recent information during the prediction process. In addition, ensemble learning is recognized as an effective approach for further improving forecasting performance by combining multiple forecasting models. This paper studies an online ensemble approach for probabilistic wind power forecasting by taking full advantage of the most recent information and leveraging the strengths of multiple forecasting models. The online ensemble approach is first formulated as an online convex optimization problem. On this basis, a quantile passive-aggressive regression model is proposed to solve the online convex optimization problem. Case studies and comparisons with other online learning methods are conducted on an open wind power data set from Belgium. Results show that the proposed method outperforms competing methods in terms of pinball loss and Winkler score with high reliability.

In this paper, the model of strategic wind power offering in the day-ahead (DA) market is proposed considering the uncertainties of wind power production, and price forecasting of DA and real-time (RT) market. The wind power deviation in the RT market is settled with the two-price mechanism based on the deviation direction and the relation between the locational marginal prices (LMPs) of DA and RT. Instead of using the point forecasting for the DA and RT LMPs, the uncertainties of LMP forecasting are modeled. In addition, the correlation between the forecasting errors of DA and RT LMP are directly modeled instead of generating the correlated scenarios. Finally, the optimal offered quantity of wind power in the DA market is derived using the probability theory based on the probabilistic wind power forecasting. The case study using the price data of actual DA and RT from Midcontinent Independent System Operator (MISO) validates the effectiveness of the proposed model. It shows that the correlation of the forecasting errors of DA and RT LMP has a significant impact on the wind power quantity offered by DA and revenue results.

On-line quantile regression in the RKHS (Reproducing Kernel Hilbert Space) for operational probabilistic forecasting of wind power

In recent years, a large number of wind power has been applied in the micro-grid (MG). Influenced by randomness characteristics of wind speed, the uncertainty in the power output of wind turbines imposes some safety and stability problems on the optimal energy management in MG. To address this problem, an expert energy management system (EEMS) considering wind power probability is developed in this study for optimal dispatching of a typical grid-connected MG. The EEMS composes of wind power probabilistic forecasting module, multi-objective optimization module and energy storage system (ESS) module. In the wind power forecasting module, wind power probabilistic forecasting based on complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and Gaussian process regression (GPR) is proposed in this study. To improve the forecasting results, CEEMDAN, an effective signal processing method, is employed to decompose the wind power data, then, the decomposed subseries are utilized as the inputs of GPR for probabilistic forecasting. A two-step solution methodology combining an efficient and effective improved multi-objective bat algorithm (IMOBA) with fuzzy set theory (FST) is put forward to solve the optimal dispatching problems. In the first step, IMOBA is developed to optimize the energy dispatching of EEMS by minimizing both economic cost and pollutant emissions simultaneously, and obtain a well-distributed set of Pareto optimal front (POF), then, FST is employed to identify the best compromise solutions from POF. Six operational scenarios of a typical grid-connected MG based one-POF-one-day and one-POF-one-hour dispatching schemes are constructed to investigate the effectiveness of the proposed strategy and provide more flexibility for decision makers. The results illustrate that EEMS can effectively schedule power generation and energy storage by considering economic cost and pollutant emission objectives simultaneously.

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.