Research on the IL-Bagging-DHKELM Short-Term Wind Power Prediction Algorithm Based on Error AP Clustering Analysis

With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.

A Wind Power Prediction Framework for Distributed Power Grids

To reduce carbon emissions,clean energy is being integrated into the power system.Wind power is connected to the grid in a distributed form,but its high variability poses a challenge to grid stability.This article combines wind turbine monitoring data with numerical weather prediction(NWP)data to create a suitable wind power prediction framework for distributed grids.First,high-precision NWP of the turbine range is achieved using weather research and forecasting models(WRF),and Kriging interpolation locates predicted meteorological data at the turbine site.Then,a preliminary predicted power series is obtained based on the fan’s wind speed-power conversion curve,and historical power is reconstructed using variational mode decomposition(VMD)filtering to form input variables in chronological order.Finally,input variables of a single turbine enter the temporal convolutional network(TCN)to complete initial feature extraction,and then integrate the outputs of all TCN layers using Long Short Term Memory Networks(LSTM)to obtain power prediction sequences for all turbine positions.The proposed method was tested on a wind farm connected to a distributed power grid,and the results showed it to be superior to existing typical methods.

Research on the Control Strategy of Micro Wind-Hydrogen Coupled System Based on Wind Power Prediction and Hydrogen Storage System Charging/Discharging Regulation

This paper addresses the micro wind-hydrogen coupled system,aiming to improve the power tracking capability of micro wind farms,the regulation capability of hydrogen storage systems,and to mitigate the volatility of wind power generation.A predictive control strategy for the micro wind-hydrogen coupled system is proposed based on the ultra-short-term wind power prediction,the hydrogen storage state division interval,and the daily scheduled output of wind power generation.The control strategy maximizes the power tracking capability,the regulation capability of the hydrogen storage system,and the fluctuation of the joint output of the wind-hydrogen coupled system as the objective functions,and adaptively optimizes the control coefficients of the hydrogen storage interval and the output parameters of the system by the combined sigmoid function and particle swarm algorithm(sigmoid-PSO).Compared with the real-time control strategy,the proposed predictive control strategy can significantly improve the output tracking capability of the wind-hydrogen coupling system,minimize the gap between the actual output and the predicted output,significantly enhance the regulation capability of the hydrogen storage system,and mitigate the power output fluctuation of the wind-hydrogen integrated system,which has a broad practical application prospect.

The Short-Term Prediction ofWind Power Based on the Convolutional Graph Attention Deep Neural Network

The fluctuation of wind power affects the operating safety and power consumption of the electric power grid and restricts the grid connection of wind power on a large scale.Therefore,wind power forecasting plays a key role in improving the safety and economic benefits of the power grid.This paper proposes a wind power predicting method based on a convolutional graph attention deep neural network with multi-wind farm data.Based on the graph attention network and attention mechanism,the method extracts spatial-temporal characteristics from the data of multiple wind farms.Then,combined with a deep neural network,a convolutional graph attention deep neural network model is constructed.Finally,the model is trained with the quantile regression loss function to achieve the wind power deterministic and probabilistic prediction based on multi-wind farm spatial-temporal data.A wind power dataset in the U.S.is taken as an example to demonstrate the efficacy of the proposed model.Compared with the selected baseline methods,the proposed model achieves the best prediction performance.The point prediction errors(i.e.,root mean square error(RMSE)and normalized mean absolute percentage error(NMAPE))are 0.304 MW and 1.177%,respectively.And the comprehensive performance of probabilistic prediction(i.e.,con-tinuously ranked probability score(CRPS))is 0.580.Thus,the significance of multi-wind farm data and spatial-temporal feature extraction module is self-evident.

Improved AVOA based on LSSVM for wind power prediction

Improving the prediction accuracy of wind power is an effective means to reduce the impact of wind power on power grid.Therefore,we proposed an improved African vulture optimization algorithm(AVOA)to realize the prediction model of multi-objective optimization least squares support vector machine(LSSVM).Firstly,the original wind power time series was decomposed into a certain number of intrinsic modal components(IMFs)using variational modal decomposition(VMD).Secondly,random numbers in population initialization were replaced by Tent chaotic mapping,multi-objective LSSVM optimization was introduced by AVOA improved by elitist non-dominated sorting and crowding operator,and then each component was predicted.Finally,Tent multi-objective AVOA-LSSVM(TMOALSSVM)method was used to sum each component to obtain the final prediction result.The simulation results show that the improved AVOA based on Tent chaotic mapping,the improved non-dominated sorting algorithm with elite strategy,and the improved crowding operator are the optimal models for single-objective and multi-objective prediction.Among them,TMOALSSVM model has the smallest average error of stroke power values in four seasons,which are 0.0694,0.0545 and 0.0211,respectively.The average value of DS statistics in the four seasons is 0.9902,and the statistical value is the largest.The proposed model effectively predicts four seasons of wind power values on lateral and longitudinal precision,and faster and more accurately finds the optimal solution on the current solution space sets,which proves that the method has a certain scientific significance in the development of wind power prediction technology.

Short-Term Wind Power Prediction Using Fuzzy Clustering and Support Vector Regression

A sustainable production of electricity is essential for low carbon green growth in South Korea. The generation of wind power as renewable energy has been rapidly growing around the world. Undoubtedly, wind energy is unlimited in potential. However due to its own intermittency and volatility, there are difficulties in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. To cope with this, many works have been done for wind speed and power forecasting. In this paper, an SVR （support vector regression） using FCM （Fuzzy C-Means） is proposed for wind speed forecasting. This paper describes the design of an FCM based SVR to increase the prediction accuracy. Proposed model was compared with ordinary SVR model using balanced and unbalanced test data. Also, multi-step ahead forecasting result was compared. Kernel parameters in SVR are adaptively determined in order to improve forecasting accuracy. An illustrative example is given by using real-world wind farm dataset. According to the experimental results, it is shown that the proposed method provides better forecasts of wind power.

A Control Strategy for Smoothing Active Power Fluctuation of Wind Farm with Flywheel Energy Storage System Based on Improved Wind Power Prediction Algorithm

The fluctuation of active power output of wind farm has many negative impacts on large-scale wind power integration into power grid. In this paper, flywheel energy storage system (FESS) was connected to AC side of the doubly-fed induction generator (DFIG) wind farm to realize smooth control of wind power output. Based on improved wind power prediction algorithm and wind speed-power curve modeling, a new smooth control strategy with the FESS was proposed. The requirement of power system dispatch for wind power prediction and flywheel rotor speed limit were taken into consideration during the process. While smoothing the wind power fluctuation, FESS can track short-term planned output of wind farm. It was demonstrated by quantitative analysis of simulation results that the proposed control strategy can smooth the active power fluctuation of wind farm effectively and thereby improve power quality of the power grid.

Wind Power Prediction Based on Machine Learning and Deep Learning Models

Wind power is one of the sustainable ways to generate renewable energy.In recent years,some countries have set renewables to meet future energy needs,with the primary goal of reducing emissions and promoting sustainable growth,primarily the use of wind and solar power.To achieve the prediction of wind power generation,several deep and machine learning models are constructed in this article as base models.These regression models are Deep neural network(DNN),k-nearest neighbor(KNN)regressor,long short-term memory(LSTM),averaging model,random forest(RF)regressor,bagging regressor,and gradient boosting(GB)regressor.In addition,data cleaning and data preprocessing were performed to the data.The dataset used in this study includes 4 features and 50530 instances.To accurately predict the wind power values,we propose in this paper a new optimization technique based on stochastic fractal search and particle swarm optimization(SFSPSO)to optimize the parameters of LSTM network.Five evaluation criteria were utilized to estimate the efficiency of the regression models,namely,mean absolute error(MAE),Nash Sutcliffe Efficiency(NSE),mean square error(MSE),coefficient of determination(R2),root mean squared error(RMSE).The experimental results illustrated that the proposed optimization of LSTM using SFS-PSO model achieved the best results with R2 equals 99.99%in predicting the wind power values.

Short-TermWind Power Prediction Based on Combinatorial Neural Networks

Wind power volatility not only limits the large-scale grid connection but also poses many challenges to safe grid operation.Accurate wind power prediction can mitigate the adverse effects of wind power volatility on wind power grid connections.For the characteristics of wind power antecedent data and precedent data jointly to determine the prediction accuracy of the prediction model,the short-term prediction of wind power based on a combined neural network is proposed.First,the Bi-directional Long Short Term Memory(BiLSTM)network prediction model is constructed,and the bi-directional nature of the BiLSTM network is used to deeply mine the wind power data information and find the correlation information within the data.Secondly,to avoid the limitation of a single prediction model when the wind power changes abruptly,the Wavelet Transform-Improved Adaptive Genetic Algorithm-Back Propagation(WT-IAGA-BP)neural network based on the combination of the WT-IAGA-BP neural network and BiLSTM network is constructed for the short-term prediction of wind power.Finally,comparing with LSTM,BiLSTM,WT-LSTM,WT-BiLSTM,WT-IAGA-BP,and WT-IAGA-BP&LSTM prediction models,it is verified that the wind power short-term prediction model based on the combination of WT-IAGA-BP neural network and BiLSTM network has higher prediction accuracy.

Achievements and Prospects of Wind Power Prediction

Wind power prediction is crucial to the operation of the power system accommodating a large amount of wind power. From the perspective of power dispatch, this paper discusses the current situations of the technology, system building, prediction errors, the index for evaluating wind power prediction system and the main bodies responsible for the prediction. It delves into the existing problems such as incomplete basic data, poor prediction accuracy, short prediction time scale, as well as lacking of prediction in most wind farms. Suggestions on improvement are proposed including enhancing the construction of wind power prediction system on both the grid side and the wind farm side, speeding up the development of ultra-short term wind power prediction system, deepening the research on wind power prediction technology, strengthening the construction of technical standard system and carrying out cross-sector cooperation.

Research on Wind Power Prediction Modeling Based on Adaptive Feature Entropy Fuzzy Clustering

Wind farm power prediction is proposed based on adaptive feature weight entropy fuzzy clustering algorithm.According to the fuzzy clustering method,a large number of historical data of a wind farm in Inner Mongolia are analyzed and classified.Model of adaptive entropy weight for clustering is built.Wind power prediction model based on adaptive entropy fuzzy clustering feature weights is built.Simulation results show that the proposed method could distinguish the abnormal data and forecast more accurately and compute fastly.

Prediction of Wind Speed Using a Hybrid Regression-Optimization Approach

Predicting wind speed is a complex task that involves analyzing various meteorological factors such as temperature, humidity, atmospheric pressure, and topography. There are different approaches that can be used to predict wind speed, and a hybrid optimization approach is one of them. In this paper, the hybrid optimization approach combines a multiple linear regression approach with an optimization technique to achieve better results. In the context of wind speed prediction, this hybrid optimization approach can be used to improve the accuracy of existing prediction models. Here, a Grey Wolf Optimizer based Wind Speed Prediction (GWO-WSP) method is proposed. This approach is tested on the 2016, 2017, 2018, and 2019 Raw Data files from the Great Lakes Environmental Research Laboratories and the National Oceanic and Atmospheric Administration’s (GLERL-NOAA) Chicago Metadata Archive. The test results show that the implementation is successful and the approach yields accurate and feasible results. The computation time for execution of the algorithm is also superior compared to the existing methods in literature.

Short-Term Wind Power Prediction Based on WVMD and Spatio-Temporal Dual-Stream Network

As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power prediction is essential for algorithms like scheduling and optimization control.Based on the spatio-temporal features of Numerical Weather Prediction(NWP)data,it proposes the WVMD_DSN(Whale Optimization Algorithm,Variational Mode Decomposition,Dual Stream Network)model.The model first applies Pearson correlation coefficient(PCC)to choose some NWP features with strong correlation to wind power to form the feature set.Then,it decomposes the feature set using Variational Mode Decomposition(VMD)to eliminate the nonstationarity and obtains Intrinsic Mode Functions(IMFs).Here Whale Optimization Algorithm(WOA)is applied to optimise the key parameters of VMD,namely the number of mode components K and penalty factor a.Finally,incorporating attention mechanism(AM),Squeeze-Excitation Network(SENet),and Bidirectional Gated Recurrent Unit(BiGRU),it constructs the dual-stream network(DSN)for short-term wind power prediction.Comparative experiments demonstrate that the WVMD_DSN model outperforms existing baseline algorithms and exhibits good generalization performance.The relevant code is available at https://github.com/ruanyuyuan/Wind-power-forecast.git(accessed on 20 August 2024).

Distributed Model Predictive Load Frequency Control of Multi-area Power System with DFIGs

Reliable load frequency control LFC is crucial to the operation and design of modern electric power systems. Considering the LFC problem of a four-Area interconnected power system with wind turbines, this paper presents a distributed model predictive control DMPC based on coordination scheme. The proposed algorithm solves a series of local optimization problems to minimize a performance objective for each control area. The generation rate constraints GRCs, load disturbance changes, and the wind speed constraints are considered. Furthermore, the DMPC algorithm may reduce the impact of the randomness and intermittence of wind turbine effectively. A performance comparison between the proposed controller with and without the participation of the wind turbines is carried out. Analysis and simulation results show possible improvements on closed-loop performance, and computational burden with the physical constraints. © 2014 Chinese Association of Automation.

A Long-Range Generalized Predictive Control Algorithm for a DFIG Based Wind Energy System

This paper presents a new Long-range generalized predictive controller in the synchronous reference frame for a wind energy system doubly-fed induction generator based. This controller uses the state space equations that consider the rotor current and voltage as state and control variables, to execute the predictive control action. Therefore, the model of the plant must be transformed into two discrete transference functions, by means of an auto-regressive moving average model, in order to attain a discrete and decoupled controller, which makes it possible to treat it as two independent single-input single-output systems instead of a magnetic coupled multiple-input multiple-output system. For achieving that, a direct power control strategy is used, based on the past and future rotor currents and voltages estimation. The algorithm evaluates the rotor current predictors for a defined prediction horizon and computes the new rotor voltages that must be injected to controlling the stator active and reactive powers. To evaluate the controller performance, some simulations were made using Matlab/Simulink. Experimental tests were carried out with a small-scale prototype assuming normal operating conditions with constant and variable wind speed profiles. Finally, some conclusions respect to the dynamic performance of this new controller are summarized.

Wind Farm Coordinated Control for Power Optimization

以降低风电场尾流损失、优化风场出力为目标,设计基于Laguerre函数非线性预测控制（nonlinear modelpredictive control,NLMPC）方案的风场集群控制器。该控制器应用风场动态尾流模型,通过NLMPC统一调整风场内各机组转速以提升风场功率。在控制器设计中,使用有效风速预测误差校正对预测模型失配及超短期风速预测误差进行补偿,引入Laguerre函数降低滚动时域优化计算负担并分析了控制器对风速预测误差的鲁棒性能。仿真研究表明,集群控制器能够在不同风速条件下提升风场功率、降低优化计算负担,且对风速预测模型失配与风场自然风速预测误差具有鲁棒性。

Special report on relationship between wind farms and power grids

The installed capacity of a large scale wind power plant will be up to a number of hundreds MW, and the wind power is transmitted to load centers through long distance transmission lines with 220 kV, 500 kV, or 750 kV. Therefore, it is necessary not only considering the power transmission line between a wind power plant and the first connection node of the power network, but also the power network among the group of those wind power plants in a wind power base, the integration network from the base to the existed grids, as well as the distribution and consumption of the wind power generation by loads. Meanwhile, the impact of wind power stochastic fluctuation on power systems must be studied. In recent years, wind power prediction technology has been studied by the utilities and wind power plants. As a matter of fact, some European countries have used this prediction technology as a tool in national power dispatch centers and wind power companies.

PI-MPC Frequency Control of Power System in the Presence of DFIG Wind Turbines

For the recent expansion of renewable energy applications, Wind Energy System (WES) is receiving much interest all over the world. However, area load change and abnormal conditions lead to mismatches in frequency and scheduled power interchanges between areas. These mismatches have to be corrected by the LFC system. This paper, therefore, proposes a new robust frequency control technique involving the combination of conventional Proportional-Integral (PI) and Model Predictive Control (MPC) controllers in the presence of wind turbines (WT). The PI-MPC technique has been designed such that the effect of the uncertainty due to governor and turbine parameters variation and load disturbance is reduced. A frequency response dynamic model of a single-area power system with an aggregated generator unit is introduced, and physical constraints of the governors and turbines are considered. The proposed technique is tested on the single-area power system, for enhancement of the network frequency quality. The validity of the proposed method is evaluated by computer simulation analyses using Matlab Simulink. The results show that, with the proposed PI-MPC combination technique, the overall closed loop system performance demonstrated robustness regardless of the presence of uncertainties due to variations of the parameters of governors and turbines, and loads disturbances. A performance comparison between the proposed control scheme, the classical PI control scheme and the MPC is carried out confirming the superiority of the proposed technique in presence of doubly fed induction generator (DFIG) WT.

Wind Power Potential in Interior Alaska from a Micrometeorological Perspective

The wind power potential in Interior Alaska is evaluated from a micrometeorological perspective. Based on the local balance equation of momentum and the equation of continuity we derive the local balance equation of kinetic energy for macroscopic and turbulent systems, and in a further step, Bernoulli’s equation and integral equations that customarily serve as the key equations in momentum theory and blade-element analysis, where the Lanchester-Betz-Joukowsky limit, Glauert’s optimum actuator disk, and the results of the blade-element analysis by Okulov and Sorensen are exemplarily illustrated. The wind power potential at three different sites in Interior Alaska (Delta Junction, Eva Creek, and Poker Flat) is assessed by considering the results of wind field predictions for the winter period from October 1, 2008, to April 1, 2009 provided by the Weather Research and Forecasting (WRF) model to avoid time-consuming and expensive tall-tower observations in Interior Alaska which is characterized by a relatively low degree of infrastructure outside of the city of Fairbanks. To predict the average power output we use the Weibull distributions derived from the predicted wind fields for these three different sites and the power curves of five different propeller-type wind turbines with rated powers ranging from 2 MW to 2.5 MW. These power curves are represented by general logistic functions. The predicted power capacity for the Eva Creek site is compared with that of the Eva Creek wind farm established in 2012. The results of our predictions for the winter period 2008/2009 are nearly 20 percent lower than those of the Eva Creek wind farm for the period from January to September 2013.

Bootstrapped Multi-Model Neural-Network Super-Ensembles for Wind Speed and Power Forecasting

The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a multi-ANN model super-ensemble for application to multi-step-ahead forecasting of wind speed and of the associated power generated from a wind turbine. A statistical combination of the individual forecasts from the various ANNs of the super-ensemble is used to construct the best deterministic forecast, as well as the prediction uncertainty interval associated with this forecast. The bootstrapped neural-network methodology is validated using measured wind speed and power data acquired from a wind turbine in an operational wind farm located in northern China.