Probability density forecasting of wind power based on multi-core parallel quantile regression neural network

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.

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.

Recently, frequency regulation strategies have been widely adopted in the operation and control of doubly fed induction generator-based wind turbines (DFIG-WTs). Thus, wind power, which is becoming an increasingly important energy source, is expected to play a significant role in both power generation and frequency regulation in modern power systems. Under such circumstances, maintaining the reliability and frequency of power systems at a designated level may be more challenging due to inherent uncertainties in wind power generation. In this paper, the integrated assessment of the reliability and frequency deviation risks of power systems with a high penetration level of wind power is investigated. A multi-time scale analytical framework is proposed to calculate the integrated reliability and frequency deviation indices. The coupling between the reliability and frequency deviation is further addressed by developing a novel frequency-sensitive reliability model of the electric generator. Frequency deviations under supply/demand fluctuations and device failures are analyzed, and the power system frequency regulation process is modeled with the fuzzy adaptive virtual inertial response of DFIG-WTs and energy storage system (ESS). Furthermore, IEEE-RTS79 is used to verify the validity of the proposed model and solution method.

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.

Optimal planning for wind power capacity in an electric power system

Transmission switching, demand response and energy storage systems in an innovative integrated scheme for managing the uncertainty of wind power generation

Aiming at the wind power prediction problem, a wind power probability prediction method based on the quantile regression of a dilated causal convolutional neural network is proposed. With the developed model, the Adam stochastic gradient descent technique is utilized to solve the cavity parameters of the causal convolutional neural network under different quantile conditions and obtain the probability density distribution of wind power at various times within the following 200 hours. The presented method can obtain more useful information than conventional point and interval predictions. Moreover, a prediction of the future complete probability distribution of wind power can be realized. According to the actual data forecast of wind power in the PJM network in the United States, the proposed probability density prediction approach can not only obtain more accurate point prediction results, it also obtains the complete probability density curve prediction results for wind power. Compared with two other quantile regression methods, the developed technique can achieve a higher accuracy and smaller prediction interval range under the same confidence level.

This study deals with the voltage stability constrained optimal power flow (VSC‐OPF) problem considering the wind power generation uncertainty. The main feature of the proposed model is to handle the uncertainty of multiple wind farms (WFs) in a way that for a given worsening of total cost, maximum tolerable uncertainty of wind power generation is achieved for all WFs. This maximum uncertainty is determined in a way that a required loading margin (LM), is preserved. It is worth noting that LM is the most important measure of voltage stability which reflects the distance from the current operating point to the voltage collapse point. For this aim, information gap decision theory (IGDT) is utilised to handle the uncertainty of wind power generation. The proposed model is implemented on IEEE 39‐bus standard test system. In order to evaluate the effectiveness of the proposed VSC‐OPF model for uncertainty handling of multiple WFs, the results obtained by IGDT technique are compared with Monte Carlo simulations and scenario‐based approach. The simulation results imply that the uncertainty radius and the desired LM are inversely related, such that for a given tolerable increase of cost, the radius of uncertainty decreases by increasing the desired LM.

Due to the anti-peak shaving characteristics of wind power under the operation mode of “power determined by heat”, a large number of wind power is abandoned at night. In order to solve the problem, this paper proposes a method of coordinated operation of ground source heat pump (GSHP) and combined heat and power (CHP) units. Through indirectly reducing the generation power of CHP units, the accommodation space of wind power in power grid is improved. A two-stage robust optimal scheduling model of regional integrated heat-power system (RIHPS) considering the uncertainty of wind power generation and power load is established. And a distributed solution method based on Alternating Direction Method of Multipliers (ADMM) method and column-and-constraint generation (C&CG) algorithm is designed. Then, the Locational marginal pricing strategy with the goal of guiding users to participate in wind power accommodation is analyzed. The numerical simulation results show that the wind power accommodation capacity of the integrated system under the operation mode of “power determined by heat” can be improved through installing GSHP at CHP units and using price signal guidance.

To address the environmental concern and improve the economic efficiency, the wind power is rapidly integrated into smart grids. However, the inherent uncertainty of wind energy raises operational challenges. To ensure the cost-efficient, reliable and robust operation, it is critically important to find the optimal decision that can correctly and rigorously hedge against all sources of uncertainty. In this paper, we propose data-driven stochastic unit commitment (SUC) to guide the power grids scheduling. Specifically, given the finite historical data, the posterior predictive distribution is developed to quantify the wind power prediction uncertainty accounting for both inherent stochastic uncertainty of wind power generation and input model estimation error. For complex power grid systems, a finite number of scenarios is used to estimate the expected cost in the planning horizon. To further control the impact of finite sampling error induced by using the sample average approximation (SAA), we propose a parallel computing based optimization solution methodology, which can quickly find the reliable optimal unit commitment decision hedging against various sources of uncertainty. The empirical study over six-bus and 118-bus systems demonstrates that our approach can provide more cost-efficient and robust performance than the existing deterministic and stochastic unit commitment approaches.

Aiming at the difficulty of wind power prediction due to the volatility and uncertainty of wind power generation, this paper proposes a hybrid model based on Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM), and optimises the model hyper-parameters using Bayesian Optimization Algorithm (BO) in order to improve the prediction accuracy. Firstly, the input features that are highly correlated with wind power are screened using the Pearson Coefficient method (PCC). Then, CNN is used to extract features from the screened data. Next, the features extracted by CNN are further processed using BiLSTM to capture the long-term dependence and bi-directional information of the time series data. Finally, the hyperparameters of the model are adjusted by BO to obtain the best prediction performance. The experimental results show that the proposed BO-CNN-BiLSTM model reduces the RMSE by 35.3%, the MAE by 46.7%, and the R2 improves by 1.5% compared with the BiLSTM model.

Impact of large-scale wind power penetration on incentive of individual investors, a supply function equilibrium approach

Wind power has been valued by countries for its renewability and cleanness and has become most of the focus of energy development in all countries. However, due to the uncertainty and volatility of wind power generation, making the grid-connected wind power system presents some serious challenges. Improving the accuracy of wind power prediction has become the focus of current research. Therefore, this paper proposes a combined short-term wind power prediction model based on T-LSTNet_markov to improve prediction accuracy. First, perform data cleaning and data preprocessing operations on the original data. Second, forecast using T-LSTNet model in original wind power data. Finally, calculate the error between the forecast value and the actual value. The k-means++ method and Weighted Markov process are used to correct errors and to get the result of the final prediction. The data that are collected from a wind farm in Inner Mongolia Autonomous Region, China, are selected as a case study to demonstrate the effectiveness of the proposed combined models. The empirical results show that the prediction accuracy is further improved after correcting errors.

The adequacy assessment of generation system including wind farm is a complicated process due to the inherent uncertainty of wind power generation. To evaluate the reliability benefit of the integration of wind power properly, it is critical to model the stochastic characteristics of wind power generation accurately. Considering that wind power output highly depends on wind speed, several methods to simulate wind speed have been studied. However, some statistical indices that obtained from the wind speeds simulated by the existing methods and the historical wind data do not match exactly. In this paper, a novel model, where time-sequential transition matrices of wind speed are established based on historical hourly data, is proposed to simulate the wind speed series. The proposed model is compared with probability sampling, time series analysis in terms of several statistical indices, and it is observed that the proposed method has an advantage over other methods. Through the wind integrated IEEE-RTS test system, the ability of different wind speed models to reflect the macroscopic statistical properties of actual wind speed data is compared. Besides, the impact of different wind speed models on the adequacy assessment of generation system is analyzed.

In this paper, a new formula for AC unit commitment problem with safety constraints is proposed, which can express the uncertainty of wind power with bounded interval. The proposed SCUC model can flexibly adjust the width of the interval by selecting an appropriate confidence level, so as to achieve a good compromise between security and economy. In addition, the proposed SCUC model is equivalent to a two-stage stochastic programming problem in one expected case, while the second stage represents the corrective operation in two extreme cases. In order to deal with the large-scale and integer mixed nonlinear characteristics of the model, a new calculation strategy based on generalized Benders Decomposition is developed to solve this problem and obtain robust commitment plan to withstand the worst-case realization of uncertain wind energy. The proposed SCUC model is illustrated by IEEE 9 bus and 118 bus test system, and its advantages over the existing random programming technology are verified. The simulation results show that the proposed method is applicable to UC problem with uncertainty of wind power generation.