Research on Wind-Photovoltaic Output Power Aggregation Method Considering Correlation

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

Most studies in wind integration ignore either the temporal or spatial correlation of the power data, which decreases the accuracy of the results. The objective of this paper is to model and verify the temporal correlation of wind power data using Copula and nonparametric kernel density estimation (KDE). A model for reconstructing wind power time series is proposed based on Copula theory. This model preserves the time correlation characteristics of the original wind power sequence as much as possible, which facilitates the subsequent research on the uncertainty of evolution over time. Then, based on the nonparametric KDE and maximum likelihood estimation algorithm, by selecting appropriate correlation coefficients, a time correlation model of Gaussian Copula is established and applied to the actual dataset of a wind farm in GEFCOM2014. Finally, the boxwhisker plot and the autocorrelation function are used to verify the uncertainty characteristics of the reconstructed sequence, and the accuracy of the fit is further proved by the root mean square error in both short-term and long-term case studies. From the comparison with original time series data, as well as the numerical results, the effectiveness of the proposed method is illustrated.

A new distributed decomposition–reconstruction–ensemble learning paradigm for short-term wind power prediction

The purpose of this paper is to synthesize sample paths of wind power from a wind farm in a certain location by considering the wind power variability in that location. In order to achieve this purpose, factors driving wind power variability are extracted from wind power time series through factor analysis. Then, wind farms with similar factor loadings are clustered through an agglomerative hierarchical cluster analysis. In those two processes, the number of factors and clusters are decided heuristically. The seasonal variation of wind farm clusters is also analyzed, and the relative variability among wind farms is plotted in a dendrogram of wind farm clusters. The factor loadings and statistical characteristics of wind power in the selected cluster are used to synthesize the future sample path of a wind farm in that cluster. Finally, the synthesized wind power is verified by testing whether the distribution of the minute by minute difference between wind power data follows the Laplace distribution.

This paper proposes a wind power probabilistic model (WPPM) using the reflection method and multi-kernel function kernel density estimation (KDE). With the increasing penetration of renewable energy sources (RESs) into power systems, several probabilistic approaches have been introduced to assess the impact of RESs on the power system. A probabilistic approach requires a wind power scenario (WPS), and the WPS is generated from the WPPM. Previously, WPPM was generated using a parametric density estimation, and it had limitations in reflecting the characteristics of wind power data (WPD) due to a boundary bias problem. The paper proposes a WPPM generated using the KDE, which is a non-parametric method. Additionally, the paper proposes a reflection method correcting for the boundary bias problem caused by the double-bounded characteristic of the WPD and the multi-kernel function KDE minimizing the effect of tied values. Six bandwidth selectors are used to calculate the bandwidth for the KDE, and one is selected by analyzing the correlation between the normalized WPD and the calculated bandwidth. The results were validated by generating WPPMs with WPDs in six regions of the Republic of Korea, and it was confirmed that the accuracy and goodness-of-fit are improved when the proposed method is used.

The intermittent and fluctuating of new energy bring significant uncertainty to the power system, which greatly increases the risk of safe and stable operation of the power system. Compared with classical point prediction, probabilistic prediction of wind power can effectively quantify the uncertainty of its output, provide more comprehensive prediction information, and provide more reliable data support for power system analysis and decision-making. In this paper, this paper proposes a wind power probability prediction method that combines kernel density estimation and copula, first the kernel density estimation method is used to estimate the marginal probability distribution of univariate variables, and proposing a thumb rule and grid search method to optimize the bandwidth h; then based on Copula theory to estimate the joint distribution of multiple variables; finally, based on the conditional probability formula, calculate the probability density and confidence interval of wind power conditions under specified predicted wind power and predicted wind speed. The actual data of a wind farm station in Inner Mongolia is taken as an example to calculate, the result shows that compared with the conventional kernel density estimation method, the interval coverage rate of the proposed method is closer to the preset confidence level, and the average width of the interval is also narrower.

Renewable energies, such as solar and wind power, have become promising sources of energy to address the increase in greenhouse gases caused by the use of fossil fuels and to resolve the current energy crisis. Integrating wind energy into a large-scale electric grid presents a significant challenge due to the high intermittency and nonlinear behavior of wind power. Accurate wind power forecasting is essential for safe and efficient integration into the grid system. Many prediction models have been developed to predict the uncertain and nonlinear time series of wind power, but most neglect the use of Bayesian optimization to optimize the hyperparameters while training deep learning algorithms. The efficiency of grid search strategies decreases as the number of hyperparameters increases, and computation time complexity becomes an issue. This paper presents a robust and optimized long-short term memory network for forecasting wind power generation in the day ahead in the context of Ethiopia’s renewable energy sector. The proposal uses Bayesian optimization to find the best hyperparameter combination in a reasonable computation time. The results indicate that tuning hyperparameters using this metaheuristic prior to building deep learning models significantly improves the predictive performances of the models. The proposed models were evaluated using MAE, RMSE, and MAPE metrics, and outperformed both the baseline models and the optimized gated recurrent unit architecture.

The applicability of ultra-short-term wind power prediction(USTWPP)models is reviewed.The USTWPP method proposed extracts featrues from historical data of wind power time series(WPTS),and classifies every short WPTS into one of several different subsets well defined by stationary patterns.All the WPTS that cannot match any one of the stationary patterns are sorted into the subset of nonstationary pattern.Every above WPTS subset needs a USTWPP model specially optimized for it offline.For on-line application,the pattern of the last short WPTS is recognized,then the corresponding prediction model is called for USTWPP.The validity of the proposed method is verified by simulations.

A new intelligent method based on combination of VMD and ELM for short term 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.

Abstract: Home‐range estimators are commonly tested with simulated animal locational data in the laboratory before the estimators are used in practice. Although kernel density estimation (KDE) has performed well as a home‐range estimator for simulated data, several recent studies have reported its poor performance when used with data collected in the field. This difference may be because KDE and other home‐range estimators are generally tested with simulated point locations that follow known statistical distributions, such as bivariate normal mixtures, which may not represent well the space‐use patterns of all wildlife species. We used simulated animal locational data of 5 point pattern shapes that represent a range of wildlife utilization distributions to test 4 methods of home‐range estimation: 1) KDE with reference bandwidths, 2) KDE with least‐squares cross‐validation, 3) KDE with plug‐in bandwidths, and 4) minimum convex polygon (MCP). For the point patterns we simulated, MCP tended to produce more accurate area estimates than KDE methods. However, MCP estimates were markedly unstable, with bias varying widely with both sample size and point pattern shape. The KDE methods performed best for concave distributions, which are similar to bivariate normal mixtures, but still overestimated home ranges by about 40–50% even in the best cases. For convex, linear, perforated, and disjoint point patterns, KDE methods overestimated home‐range sizes by 50–300%, depending on sample size and method of bandwidth selection. These results indicate that KDE does not produce home‐range estimates that are as accurate as the literature suggests, and we recommend exploring other techniques of home‐range estimation.

Research on output distribution modeling of photovoltaic modules based on kernel density estimation method and its application in anomaly identification

Wind energy has become one of the fastest growing renewable sources during last few decades. Sudden changes in wind power output, called wind ramps, recently attracted great research interest in wind power forecasting community. Conventional ramp prediction methods derive future ramp estimates from power forecast series. We suggest to analyze real wind power series or other weather parameters, searching for specific patterns and dependencies indicating forthcoming wind ramp events.This paper presents a methodology for parametric analysis of time series preceding wind ramp events. The presented methodology is based on probabilistic data analysis. Sensitivity of the developed algorithm can be adjusted through the size of the time window defined before a ramp event. Power production and other weather data are standardized, averaged and then searched for specific patterns in the form of trend lines. The resulting methodology does not require the use of a numerical weather prediction (NWP) model; this is a significant simplification compared to most conventional methods. The proposed methodology is tested using power production and wind speed data collected between August 2011 and July 2012 at a wind farm located in a wind-rich region of southern Alberta, Canada.

This study evaluated a potential transition of India’s power sector to 100% wind and solar energy sources. Applying a macro-energy IDEEA (Indian Zero Carbon Energy Pathways) model to 32 regions and 114 locations of potential installation of wind energy and 60 locations of solar energy, we evaluated a 100% renewable power system in India as a concept. We considered 153 scenarios with varying sets of generating and balancing technologies to evaluate each intermittent energy source separately and their complementarity. Our analysis confirms the potential technical feasibility and long-term reliability of a 100% renewable system for India, even with solar and wind energy only. Such a dual energy source system can potentially deliver fivefold the annual demand of 2019. The robust, reliable supply can be achieved in the long term, as verified by 41 years of weather data. The required expansion of energy storage and the grid will depend on the wind and solar energy structure and the types of generating technologies. Solar energy mostly requires intraday balancing that can be achieved through storage or demand-side flexibility. Wind energy is more seasonal and spatially scattered, and benefits from the long-distance grid expansion for balancing. The complementarity of the two resources on a spatial scale reduces requirements for energy storage. The demand-side flexibility is the key in developing low-cost supply with minimum curtailments. This can be potentially achieved with the proposed two-level electricity market where electricity prices reflect variability of the supply. A modelled experiment with price signals demonstrates how balancing capacity depends on the price levels of guaranteed and flexible types of loads, and therefore, can be defined by the market.

The intermittency, uncontrollability, and variability of wind power affect the economical operation and reliable delivery of the power system. To ensure the smooth integration of wind power into the grid, an accurate wind power forecast is essential. In this paper, we propose a short-term wind power prediction model based on decomposition and reconstruction to improve the accuracy of wind power forecasts. This model has the following characteristics: (i) wind power time series are decomposition into multiple components through the application of a decomposition method that combines fully integrated empirical mode decomposition with adaptive noise algorithm; (ii) the components are clustered using K-means clustering based on dynamic time warping. According to the similarity of the complexity and lag of components, they are divided into three classes; (iii) three different prediction models, including seasonal autoregressive integrated moving average model (SARIMA), long short-term memory network (LSTM) and Bi-directional long short-term memory network (BiLSTM), predict three types of components respectively. Finally, to illustrate the capability of the model, we compare its performance with three typical models. The results demonstrate that the proposed method exceeds the baseline models in regard to prediction performance.