A wind power short-term forecasting method based on discrete wavelet transform and long short-term memory networks (DWT_LSTM) is proposed. The LSTM network is designed to effectively exhibit the dynamic behavior of the wind power time series. The discrete wavelet transform is introduced to decompose the non-stationary wind power time series into several components which have more stationarity and are easier to predict. Each component is dug by an independent LSTM. The forecasting results of the wind power are obtained by synthesizing the prediction values of all components. The prediction accuracy has been improved by the proposed method, which is validated by the MAE (mean absolute error), MAPE (mean absolute percentage error), and RMSE (root mean square error) of experimental results of three wind farms as the benchmarks. Wind power forecasting based on the proposed method provides an alternative way to improve the security and stability of the electric power network with the high penetration of wind power.

https://www.mdpi.com/2076-3417/9/6/1108/pdf

Wind Power Short-Term Prediction Based on LSTM and Discrete Wavelet Transform

Short-term wind speed prediction based on LMD and improved FA optimized combined kernel function LSSVM

An improved residual-based convolutional neural network for very short-term wind power forecasting

A novel convolutional neural network framework based solar irradiance prediction method

AbstractIn earlier work with Gabor Lugosi, we introduced a method to select a smoothing factor for kernel density estimation such that, forall densities in all dimensions, theL1 error of the corresponding kernel estimate is not larger than 3+∈ times the error of the estimate with the optimal smoothing factor plus a constant times\n$$\\sqrt {\\log n/n}$$\n, wheren is the sample size, and the constant only depends on the complexity of the kernel used in the estimate. The result is nonasymptotic, that is, the bound is valid for eachn. The estimate uses ideas from the minimum distance estimation work of Yatracos. We present a practical implementation of this estimate, report on some comparative results, and highlight some key properties of the new method.

Universal smoothing factor selection in density estimation: theory and practice - Discussion

Decomposition methods are widely applied as a prestage of wind power prediction (WPP) to reduce the prediction errors caused by the nonstationarity and nonlinearity of wind power time series (TS); however, they cannot address the issues posed by the chaotic behavior of wind power TS. This paper, therefore, proposes a novel decomposition approach to take the chaotic nature of wind power TS into account and to improve WPP accuracy. In this decomposition approach, as a primary step, the wind power TS is separated into several components with different time-frequency characteristics (scales) by means of ensemble empirical mode decomposition. Chaotic TS analysis is then applied to determine which components are chaotic, and then singular spectrum analysis (SSA) is applied thereto. This multi-scale SSA (MSSSA) can maintain the general trend of chaotic components, which become smoother by eliminating extremely rapid changes with low amplitudes, and thus several steps ahead WPP with higher accuracy can be realized. Following the proposed decomposition, a novel short-term WPP method comprised of localized direct and iterative prediction is proposed to perform multi-step prediction for the chaotic and nonchaotic components of MSSSA, respectively. The proposed framework is finally validated using historical data related to overall wind power generation for Alberta (Canada), the Sotavento wind farm (Spain), and Centennial wind farm in Saskatchewan (Canada).

Novel Multi-Step Short-Term Wind Power Prediction Framework Based on Chaotic Time Series Analysis and Singular Spectrum Analysis

The inherent uncertainty in predicting wind power generation makes the operation and control of power systems very challenging. Probabilistic measurement of wind power uncertainty in the form of a reliable and sharp interval is of utmost importance, but construction of such high-quality prediction intervals (PIs) is difficult because wind power time series are nonstationary. In this paper, a framework based on the concept of bandwidth selection for a new and flexible kernel density estimator is proposed. Unlike previous related works, the proposed framework uses neither a cost function-based optimization problem nor point prediction results; rather, a diffusion-based kernel density estimator (DiE) is utilized to achieve high-quality PIs for nonstationary wind power time series. Moreover, to adaptively capture the uncertainties of both the prediction model and wind power time series in different seasons, the DiE is equipped with a fuzzy inference system and a tri-level adaptation function. The proposed framework is also founded based on a parallel computing procedure to promote the computational efficiency for practical applications in power systems. Simulation results demonstrate the efficiency of the proposed framework compared to well-known conventional benchmarks using real wind power datasets from Canada and Spain.

A Fuzzy Adaptive Probabilistic Wind Power Prediction Framework Using Diffusion Kernel Density Estimators

This paper presents lessons learned to date during the coronavirus disease 2019 (COVID-19) pandemic from the viewpoint of Saskatchewan power system operations A load estimation approach is developed to identify how the closures affecting businesses, schools, and other non-critical businesses due to COVID-19 changed the electricity consumption Furthermore, the impacts of COVID-19 containment measures and re-opening phases on load uncertainty are examined Changes in CO2 emissions resulting from an increased proportion of renewable energy generation and the change in load pattern are discussed In addition, the influence of COVID-19 on the balancing authority's power control performance is investigated Analyses conducted here are based on data from SaskPower Corporation, which is the principal electric utility in Saskatchewan, Canada Some recommendations for future power system operation and planning are developed

Comprehensive assessment of COVID-19 impact on Saskatchewan power system operations

The empirical mode decomposition (EMD) method and its variants have been extensively employed in the load and renewable forecasting literature. Using this multiresolution decomposition, time series (TS) related to the historical load and renewable generation are decomposed into several intrinsic mode functions (IMFs), which are less non-stationary and non-linear. As such, the prediction of the components can theoretically be carried out with notably higher precision. The EMD method is prone to several issues, including modal aliasing and boundary effect problems, but the TS decomposition-based load and renewable generation forecasting literature primarily focuses on comparing the performance of different decomposition approaches from the forecast accuracy standpoint; as a result, these problems have rarely been scrutinized. Underestimating these issues can lead to poor performance of the forecast model in real-time applications. This paper examines these issues and their importance in the model development stage. Using real-world data, EMD-based models are presented, and the impact of the boundary effect is illustrated.

G. C. D. Price

Papers

Novel Multi-Step Short-Term Wind Power Prediction Framework Based on Chaotic Time Series Analysis and Singular Spectrum Analysis

A Fuzzy Adaptive Probabilistic Wind Power Prediction Framework Using Diffusion Kernel Density Estimators

Comprehensive assessment of COVID-19 impact on Saskatchewan power system operations

Analysis of Empirical Mode Decomposition-based Load and Renewable Time Series Forecasting

Analysis of Empirical Mode Decomposition-based Load and Renewable Time Series Forecasting