Wind Power Interval Prediction Research Articles

Analysis and evaluation of short-term wind power interval forecast error based on K-means clustering

The intermittency, volatility and randomness of wind power will inevitably affect the accuracy of wind power prediction. In order to improve the accuracy of wind power interval prediction and evaluation, a method of wind power interval prediction and evaluation based on K-means clustering is proposed. First, use K-means clustering to classify wind power prediction error data; second, combine the climate type to more accurately divide and process historical data, and apply multiple linear regression models to establish preliminary prediction models corresponding to each subset; Finally, according to the distribution characteristics of forecast errors, the results of wind power forecasting are analyzed and evaluated with interval coverage and interval average bandwidth as indicators. Comparing the K-means clustering algorithm with the BP neural network algorithm, the results show that the method proposed in this paper can better capture the characteristics of wind power error data, and can obtain more accurate wind power interval prediction and evaluation results.

A novel two‐stage interval prediction method based on minimal gated memory network for clustered wind power forecasting

AbstractAs the global demand for clean renewable energy has grown, the contribution of wind power in grid systems has significantly improved. Wind power predictions play an important role in the stable and safe operation of grid systems. Considering the shortcomings of traditional wind power point predictions, a novel two‐stage short‐term wind power interval prediction method is proposed in this study. In the proposed method, the minimal gated memory (MGM) network and improved interval width adaptive adjustment strategy, which is an approach that is designed to adjust the prediction interval (PI) labels, are combined for short‐term interval predictions of wind power. First, the point model for subsequence data based on the MGM network is proposed. Subsequently, the interval model is proposed to obtain the final PIs of wind power using the improved interval width adaptive adjustment strategy. Finally, with the purpose of verifying the prediction performance of the proposed model, two datasets and four representative benchmark models are implemented for comparative experiments. The superiority of the proposed model is demonstrated via experimental results, which show that the proposed model can obtain suitable wind power intervals with high confidence and quality.

Dynamic economic emission dispatch with wind power based on improved multi‐objective brain storm optimisation algorithm

Based on the non-parametric kernel density estimation technique, the probability distribution of wind power output and its forecast error are accurately modelled. The confidence interval and forecast error upper and lower bounds of wind power output are estimated to build a dynamic economic emission dispatch (DEED) model with wind power penetration. To effectively solve the DEED problem with multi-objective, high-dimensional, non-linear and strong constraints, based on the basic brainstorm optimisation (BSO) algorithm, three improvement mechanisms, namely random clustering centre, differential mutation operation and individual crossover operation are introduced to enhance the converging and diverging operation of BSO. Based on these improvements and external archive mechanism, an improved multi-objective BSO (IMOBSO) algorithm is proposed. Simulations on a classical test system with ten thermal units are performed, where two case studies are investigated carefully. The simulation results demonstrate that: (i) the proposed IMOBSO can optimise the cost and emission objectives simultaneously and have achieved better performance than other algorithms; (ii) the proposed DEED incorporating wind power model is reasonable and effective because it can achieve the optimal wind power output scheduling by adjusting the system's spinning reserve capacity and the confidence level of wind power prediction interval.

A new wind power interval prediction approach based on reservoir computing and a quality-driven loss function

Understanding the uncertainty of wind power forecasting is crucial for its practical application. This paper proposes a new forecasting approach to estimate the wind power prediction intervals (PIs) to quantify the prediction uncertainty. This approach integrates the reservoir computing methodology into a three-layer neural network architecture, and outputs the final PIs by minimizing a quality-driven loss function. The reservoir computing methodology can help study the nonlinear relationship implicit in data as well as accelerate computational time, while the quality-driven loss function is assumption-free and can help improve the forecasting capability of the proposed model. The proposed model is applied to real wind power data to test its effectiveness. Case studies show that for the data used in this paper, the proposed model can reduce the mean prediction interval width (MPIW) by up to 16.69%, reduce root mean square error (RMSE) by up to 7.36%, and save up to 5 times computation time compared to the benchmark models, these indicate that the proposed model has strong predictive capability.

The short-term interval prediction of wind power using the deep learning model with gradient descend optimization

The application of wind power interval prediction for power systems attempts to give more comprehensive support to dispatchers and operators of the grid. Lower upper bound estimation (LUBE) method is widely applied in interval prediction. However, the existing LUBE approaches are trained by meta-heuristic optimization, which is either time-consuming or show poor effect when the LUBE model is complex. In this paper, a deep interval prediction method is designed in the framework of LUBE and an efficient gradient descend (GD) training approach is proposed to train the LUBE model. In this method, the long short-term memory is selected as a representative to show the modelling approach. The architecture of the proposed model consists of three parts, namely the long short-term memory module, the fully connected layers and the rank ordered module. Two loss functions are specially designed for implementing the GD training method based on the root mean square back propagation algorithm. To verify the performance of the proposed model, conventional LUBE models, as well as popular statistic interval prediction models are compared in numerical experiments. The results show that the proposed approach performs best in terms of effectiveness and efficiency with average 45% promotion in quality of prediction interval and 66% reduction of time consumptions compared to traditional LUBE models.

Research on Short-Term Wind Power Forecasting by Data Mining on Historical Wind Resource

In order to enhance the accuracy of short-term wind power forecasting (WPF), a short-term wind power forecasting method based on historical wind resources by data mining has been designed. Firstly, the spoiled data resulting from wind turbine and meteorological monitoring equipment is eliminated, and the missing data is added by the Lomnaofski optimization model, which is based on the temporal-spatial correlation of meteorological data. Secondly, the wind characteristics are analyzed by the continuous time similarity clustering (CTSC) method, which is used to select similar samples. To improve the accuracy of deterministic prediction and prediction error, the radial basis function neural network (RBF) deterministic forecasting model was built, which can approximate nonlinear solutions. In addition, the wind power interval prediction method, combining fuzzy information granulation and an Elman neural network (FIG-Elman), is proposed to acquire forecasting intervals. The deterministic prediction of the RBF-CTSC model has high accuracy, which can accurately describe the randomness, fluctuation and nonlinear characteristics of wind speed. Additionally, the mean absolute error (MAE) and root mean square error (RMSE) are reduced by the new model. The interval prediction of FIG-Elman results show that the interval width decreased by 18.85%, and the coverage probability of interval increased by 10.94%.

A Reliability Assessment Approach for Electric Power Systems Considering Wind Power Uncertainty

The intermittence and uncertainty of wind power pose challenges to large-scale wind power grid integration. The study of wind power uncertainty is becoming increasingly important for power system planning and operation. This paper proposes a wind power probabilistic interval prediction model, and a novel reliability assessment approach is presented for electrical power systems. First, the unknown parameters estimation of the autoregressive integrated moving average (ARIMA) prediction model is based on the Markov chain Monte Carlo (MCMC)-based Bayesian estimation method to improve the quality of statistical inference. Then, a quantum genetic algorithm is used to segment the power to determine the best output for each power segment weight and calculate the probabilistic prediction interval of wind power. Finally, reliability assessment by the sequential Monte Carlo simulation is presented combining with the probabilistic prediction interval of wind power on IEEE-RTS79 reliability test system. The simulation results that proposed variation range of reliability assessment indices consider the uncertain scenario of wind power and has guiding significance for power generation scheduling. Compared with genetic algorithm and particle swarm optimization algorithm, it is proved that the proposed prediction interval model has better prediction interval coverage probability index and interval average bandwidth index.

Deep Learning Method Based on Gated Recurrent Unit and Variational Mode Decomposition for Short-Term Wind Power Interval Prediction.

Wind power interval prediction (WPIP) plays an increasingly important role in evaluations of the uncertainty of wind power and becomes necessary for managing and planning power systems. However, the intermittent and fluctuating characteristics of wind power mean that high-quality prediction intervals (PIs) production is a challenging problem. In this article, we propose a novel hybrid model for the WPIP based on the gated recurrent unit (GRU) neural networks and variational mode decomposition (VMD). In the hybrid model, VMD is employed to decompose complex wind power data into simplified modes. Basic GRU prediction models, comprising a GRU input layer, multiple fully connected layers, and a rank-ordered terminal layer, are then trained for each mode to produce PIs, which are combined to obtain final PIs. In addition, an adaptive optimization method based on constructed intervals (CIs) is proposed to build high-quality training labels for supervised learning with the hybrid model. Several numerical experiments were implemented to validate the effectiveness of the proposed method. The results indicate that the proposed method performs better than the traditional interval prediction models with much higher quality PIs, and it requires less training time.

An Inter Type-2 FCR Algorithm Based T–S Fuzzy Model for Short-Term Wind Power Interval Prediction

Due to the intermittent and random nature of wind energy, wind power interval prediction (WPIP) is important to weaken the uncertainty and support the planning and scheduling of the power system. To improve the quality of WPIP, a novel fuzzy interval prediction model (FIPM) based on the lower upper bound estimation method is proposed in this paper. In the frame of the FIPM, a novel inter type-2 (IT-2) fuzzy model is designed to construct the lower and upper bounds of the prediction interval (PI), in which an IT-2 fuzzy c-regression algorithm is used to partition the data space and identify the fuzzy model. The gravitational search algorithm is employed to optimize the FIPM by minimizing coverage width-based criterion to reach a tradeoff between the interval width and coverage probability. In order to verify the effectiveness of the proposed method, existing interval prediction approaches are adopted in comparative experiments with 17 datasets extracted from five wind fields. The experimental results show that the proposed IT-2 FIPM achieves significant performance with huge promotion in the quality of the PI compared to the traditional forecasting models.

Prediction interval of wind power using parameter optimized Beta distribution based LSTM model

Prediction interval of wind power (PIWP) is crucial to assessing the economic and safe operation of the wind turbine and providing support for analysis of the stability of power systems. The hybrid model (Beta-PSO-LSTM) of long short-term memory (LSTM) neural network and Beta distribution function based particle swarm optimization (PSO) is put forward for prediction interval of wind power. In order to enhance the performance of the Beta-PSO-LSTM for PIWP in training process, wind power series are divided into different power intervals, and then the Beta-PSO-LSTM is used to estimate each power interval of the original wind power series. Furthermore, based on the analysis of the interval forecasting error information in wind power training data set, Beta distribution model is proposed to get better PIWP, and PSO is used to optimize the parameters of the model. Finally, the proposed Beta-PSO-LSTM model is compared with the Beta distribution optimized by PSO based the BP neural network (Beta-PSO-BP), the normal distribution based LSTM neural network (Norm-LSTM), Beta distribution based LSTM neural network (Beta-LSTM), and Beta distribution optimized by iterative method based LSTM neural network (Beta-IM-LSTM) for PIWP. The simulation results show that the PIWP obtained by the Beta-PSO-LSTM model has higher reliability and narrower interval bandwidth, which can provide decision support for the safe and stable operation of power systems.

Very Short-Term Wind Power Prediction Interval Framework via Bi-Level Optimization and Novel Convex Cost Function

Substantial challenges in power systems operation and control as a result of the intermittent and stochastic nature of wind power generation can be significantly alleviated by proficient very short-term wind power prediction interval (WPPI) models. In WPPI models, minimization of cost functions is conducted to train prediction engines and consequently tune their parameters. The prevalent cost functions of prediction engines in WPPI models are mainly non-differentiable and non-convex, and therefore the training process becomes problematic. To transcend such a crucial barrier, this paper addresses a new very short-term WPPI framework based on a bi-level formulation and benefiting from a differentiable and convex cost function. The prediction engine is trained by classical global optimization of the cost function in the lower-level problem, while hyperparameters that control the quality of the WPPIs are injected thereto from the upper-level problem. The hyperparameters can be tuned such that the most useful WPPIs are constructed from the lower-level problem depending on the power system operator's preferences. Lessening the need to heuristically tune a large number of prediction engine parameters is the foremost contribution of this work to the WPPI literature. The superior performance of the proposed WPPI is verified in the multistep ahead prediction of real wind power generation data in comparison to well-tailored benchmark models.

Improved Chicken Swarm Algorithms Based on Chaos Theory and Its Application in Wind Power Interval Prediction

Probabilistic interval prediction can be used to quantitatively analyse the uncertainty of wind energy. In this paper, a wind power interval prediction model based on chaotic chicken swarm optimization and extreme learning machine (CCSO-ELM) is proposed. Traditional optimization has limitations of low population diversity and a tendency to easily fall into local minima. To address these limitations, chaos theory is adopted in the chicken swarm optimization (CSO), which improves its performance and efficiency. In addition, the traditional cost function does not reflect the deviation degree of off-interval points; hence, an evaluation index considering the relative deviation of off-interval points is proposed in this paper. Finally, the new cost function is taken as the fitness function, the output layer weight of ELM is optimized using CCSO, and the lower upper bound estimation (LUBE) is adopted to output the prediction interval directly. The simulation result shows that the proposed method can effectively reduce the average bandwidth, improve the quality of interval prediction, and guarantee the interval coverage.

A multi-objective wind speed and wind power prediction interval forecasting using variational modes decomposition based Multi-kernel robust ridge regression

This paper presents a new hybrid multi-objective wind speed and wind power prediction interval forecasting (PIs) model which is the combination of variational mode decomposition (VMD), Multi-kernel robust ridge regression (MKRR) and a multi-objective Chaotic water cycle algorithm (MOCWCA). VMD is applied to decompose the main time series signals into appropriate number of modes that avoids the mutual effects present in between the modes. The VMD based MKRR method is applied to estimate the wind speed and wind power prediction intervals at a prediction interval nominal confidence levels (PINC) of 95%, 90%,85% and 80%, respectively. Further to improve the performance of the proposed prediction model MOCWCA is introduced for the optimization of the prediction models parameters in such a way that multiple objectives are satisfied to produce Pareto-optimal solutions. The wind speed and power data samples for prediction interval forecasting are collected at 30 min and 1 hour time intervals from the Sotavento wind farm located in Spain.

A Naive Bayesian Wind Power Interval Prediction Approach Based on Rough Set Attribute Reduction and Weight Optimization

Intermittency and uncertainty pose great challenges to the large-scale integration of wind power, so research on the probabilistic interval forecasting of wind power is becoming more and more important for power system planning and operation. In this paper, a Naive Bayesian wind power prediction interval model, combining rough set (RS) theory and particle swarm optimization (PSO), is proposed to further improve wind power prediction performance. First, in the designed prediction interval model, the input variables are identified based on attribute significance using rough set theory. Next, the Naive Bayesian Classifier (NBC) is established to obtain the prediction power class. Finally, the upper and lower output weights of NBC are optimized segmentally by PSO, and are used to calculate the upper and lower bounds of the optimal prediction intervals. The superiority of the proposed approach is demonstrated by comparison with a Naive Bayesian model with fixed output weight, and a rough set-Naive Bayesian model with fixed output weight. It is shown that the proposed rough set-Naive Bayesian-particle swarm optimization method has higher coverage of the probabilistic prediction intervals and a narrower average bandwidth under different confidence levels.

Wind Power Interval Prediction Based on Improved PSO and BP Neural Network

As is known to all that the output of wind power generation has a character of randomness and volatility because of the influence of natural environment conditions. At present, the research of wind power prediction mainly focuses on point forecasting, which can hardly describe its uncertainty, leading to the fact that its application in practice is low. In this paper, a wind power range prediction model based on the multiple output property of BP neural network is built, and the optimization criterion considering the information of predicted intervals is proposed. Then, improved Particle Swarm Optimization (PSO) algorithm is used to optimize the model. The simulation results of a practical example show that the proposed wind power range prediction model can effectively forecast the output power interval, and provide power grid dispatcher with decision.

Wind power prediction interval estimation method using wavelet-transform neuro-fuzzy network

Wind power point forecasting is the primary method to deal with its uncertainty. However, in many applications, the probabilistic interval of wind power is more useful than traditional point forecasting. Methods to determine the probabilistic interval of wind power point forecasting value is very essential to power system operations. Based on the bootstrap method, this paper proposed a wavelet transform combined with a neuro-fuzzy network model to estimate the prediction interval of wind power. In the model, to account for the ramp event of wind power series, a wavelet-based ramp event was used and the moving block bootstrap method, which considers the dependence of wind power series, was used to construct sampling datasets. Then, the bootstrapped datasets were estimated by a neuro-fuzzy network inference system. A case study provided a 90% confidence level of prediction intervals, which was constructed to examine the effectiveness of the model.

An optimized short-term wind power interval prediction method considering NWP accuracy

In recent years, the accuracy of the wind power prediction has been urgently studied and improved to satisfy the requirements of power system operation. In this paper, the relevance vector machine (RVM)-based models are established to predict the wind power and its interval for a given confidence level. An NWP improvement module is presented considering the characteristic of NWP error. Moreover, two parameter optimization algorithms are applied to further improve the prediction model and to compare each performance. To take three wind farms in China as examples, the performance of two RVM-based models optimized, respectively, by genetic algorithm (GA) and particle swarm optimization (PSO) are compared with predictions based on a genetic algorithm–artificial neural network (GA–ANN) and support vector machine. Results show that the proposed models have better prediction accuracy with GA–RVM model and more efficient calculation with PSO–RVM.