Harnessing solar power is essential for addressing the dual challenges of global warming and the depletion of traditional energy sources.However,the fluctuations and intermittency of photovoltaic(PV)power pose challen...Harnessing solar power is essential for addressing the dual challenges of global warming and the depletion of traditional energy sources.However,the fluctuations and intermittency of photovoltaic(PV)power pose challenges for its extensive incorporation into power grids.Thus,enhancing the precision of PV power prediction is particularly important.Although existing studies have made progress in short-term prediction,issues persist,particularly in the underutilization of temporal features and the neglect of correlations between satellite cloud images and PV power data.These factors hinder improvements in PV power prediction performance.To overcome these challenges,this paper proposes a novel PV power prediction method based on multi-stage temporal feature learning.First,the improved LSTMand SA-ConvLSTMare employed to extract the temporal feature of PV power and the spatial-temporal feature of satellite cloud images,respectively.Subsequently,a novel hybrid attention mechanism is proposed to identify the interplay between the two modalities,enhancing the capacity to focus on the most relevant features.Finally,theTransformermodel is applied to further capture the short-termtemporal patterns and long-term dependencies within multi-modal feature information.The paper also compares the proposed method with various competitive methods.The experimental results demonstrate that the proposed method outperforms the competitive methods in terms of accuracy and reliability in short-term PV power prediction.展开更多
Knowing the influence of the size of datasets for regression models can help in improving the accuracy of a solar power forecast and make the most out of renewable energy systems.This research explores the influence o...Knowing the influence of the size of datasets for regression models can help in improving the accuracy of a solar power forecast and make the most out of renewable energy systems.This research explores the influence of dataset size on the accuracy and reliability of regression models for solar power prediction,contributing to better forecasting methods.The study analyzes data from two solar panels,aSiMicro03036 and aSiTandem72-46,over 7,14,17,21,28,and 38 days,with each dataset comprising five independent and one dependent parameter,and split 80–20 for training and testing.Results indicate that Random Forest consistently outperforms other models,achieving the highest correlation coefficient of 0.9822 and the lowest Mean Absolute Error(MAE)of 2.0544 on the aSiTandem72-46 panel with 21 days of data.For the aSiMicro03036 panel,the best MAE of 4.2978 was reached using the k-Nearest Neighbor(k-NN)algorithm,which was set up as instance-based k-Nearest neighbors(IBk)in Weka after being trained on 17 days of data.Regression performance for most models(excluding IBk)stabilizes at 14 days or more.Compared to the 7-day dataset,increasing to 21 days reduced the MAE by around 20%and improved correlation coefficients by around 2.1%,highlighting the value of moderate dataset expansion.These findings suggest that datasets spanning 17 to 21 days,with 80%used for training,can significantly enhance the predictive accuracy of solar power generation models.展开更多
Photovoltaic(PV)power generation is undergoing significant growth and serves as a key driver of the global energy transition.However,its intermittent nature,which fluctuates with weather conditions,has raised concerns...Photovoltaic(PV)power generation is undergoing significant growth and serves as a key driver of the global energy transition.However,its intermittent nature,which fluctuates with weather conditions,has raised concerns about grid stability.Accurate PV power prediction has been demonstrated as crucial for power system operation and scheduling,enabling power slope control,fluctuation mitigation,grid stability enhancement,and reliable data support for secure grid operation.However,existing prediction models primarily target centralized PV plants,largely neglecting the spatiotemporal coupling dynamics and output uncertainties inherent to distributed PV systems.This study proposes a novel Spatio-Temporal Graph Neural Network(STGNN)architecture for distributed PV power generation prediction,designed to enhance distributed photovoltaic(PV)power generation forecasting accuracy and support regional grid scheduling.This approach models each PV power plant as a node in an undirected graph,with edges representing correlations between plants to capture spatial dependencies.The model comprises multiple Sparse Attention-based Adaptive Spatio-Temporal(SAAST)blocks.The SAAST blocks include sparse temporal attention,sparse spatial attention,an adaptive Graph Convolutional Network(GCN),and a temporal convolution network(TCN).These components eliminate weak temporal and spatial correlations,better represent dynamic spatial dependencies,and further enhance prediction accuracy.Finally,multi-dimensional comparative experiments between the STGNN and other models on the DKASC PV dataset demonstrate its superior performance in terms of accuracy and goodness-of-fit for distributed PV power generation prediction.展开更多
Short-term photovoltaic(PV)power forecasting plays a crucial role in enhancing the stability and reliability of power grid scheduling.To address the challenges posed by complex environmental variables and difficulties...Short-term photovoltaic(PV)power forecasting plays a crucial role in enhancing the stability and reliability of power grid scheduling.To address the challenges posed by complex environmental variables and difficulties in modeling temporal features in PV power prediction,a short-term PV power forecasting method based on an improved CNN-LSTM and cascade learning strategy is proposed.First,Pearson correlation coefficients and mutual information are used to select representative features,reducing the impact of redundant features onmodel performance.Then,the CNN-LSTM network is designed to extract local features using CNN and learn temporal dependencies through LSTM,thereby obtaining feature representations rich in temporal information.Subsequently,a multi-layer cascade structure is developed,progressively integrating prediction results from base learners such as LightGBM,XGBoost,Random Forest(RF),and Extreme Random Forest(ERF)to enhance model performance.Finally,an XGBoost-based meta-learner is utilized to integrate the outputs of the base learners and generate the final prediction results.The entire cascading process adopts a dynamic expansion strategy,where the decision to add new cascade layers is based on the R2 performance criterion.Experimental results demonstrate that the proposed model achieves high prediction accuracy and robustness under various weather conditions,showing significant improvements over traditional models and providing an effective solution for short-term PV power forecasting.展开更多
Wind power generation is subjected to complex and variable meteorological conditions,resulting in intermittent and volatile power generation.Accurate wind power prediction plays a crucial role in enabling the power gr...Wind power generation is subjected to complex and variable meteorological conditions,resulting in intermittent and volatile power generation.Accurate wind power prediction plays a crucial role in enabling the power grid dispatching departments to rationally plan power transmission and energy storage operations.This enhances the efficiency of wind power integration into the grid.It allows grid operators to anticipate and mitigate the impact of wind power fluctuations,significantly improving the resilience of wind farms and the overall power grid.Furthermore,it assists wind farm operators in optimizing the management of power generation facilities and reducing maintenance costs.Despite these benefits,accurate wind power prediction especially in extreme scenarios remains a significant challenge.To address this issue,a novel wind power prediction model based on learning approach is proposed by integrating wavelet transform and Transformer.First,a conditional generative adversarial network(CGAN)generates dynamic extreme scenarios guided by physical constraints and expert rules to ensure realism and capture critical features of wind power fluctuations under extremeconditions.Next,thewavelet transformconvolutional layer is applied to enhance sensitivity to frequency domain characteristics,enabling effective feature extraction fromextreme scenarios for a deeper understanding of input data.The model then leverages the Transformer’s self-attention mechanism to capture global dependencies between features,strengthening its sequence modelling capabilities.Case analyses verify themodel’s superior performance in extreme scenario prediction by effectively capturing local fluctuation featureswhile maintaining a grasp of global trends.Compared to other models,it achieves R-squared(R^(2))as high as 0.95,and the mean absolute error(MAE)and rootmean square error(RMSE)are also significantly lower than those of othermodels,proving its high accuracy and effectiveness in managing complex wind power generation conditions.展开更多
The photovoltaic(PV)output process is inherently complex,often disrupted by a multitude of meteoro-logical factors,while conventional detection methods at PV power stations prove inadequate,compromising prediction acc...The photovoltaic(PV)output process is inherently complex,often disrupted by a multitude of meteoro-logical factors,while conventional detection methods at PV power stations prove inadequate,compromising prediction accuracy.To address this challenge,this paper introduces a power prediction method that leverages modal switching(MS),weight factor adjustment(WFA),and parallel long short-term memory(PALSTM).Initially,historical PV power station data is categorized into distinct modes based on global horizontal irradiance and converted solar angles.Correlation analysis is then employed to evaluate the impact of various meteorological factors on PV power,selecting those with strong correlations for each specific mode.Subsequently,the weights of meteorological parameters are optimized and adjusted,and a PALSTM neural network is constructed,with its parallel modal parameters refined through training.Depending on the prediction time and input data mode characteristics,the appropriate mode channel is selected to forecast PV power station generation.Ultimately,the feasibility of this method is validated through an illustrative analysis of measured data from an Australian PV power station.Comparative test results underscore the method’s advantages,particularly in scenarios where existing detection methods are lacking and meteorological factors frequently fluctuate,demonstrating its superior prediction accuracy and stability.展开更多
To enhance the accuracy of short-term photovoltaic power output prediction and address issues such as insufficient spatial resolution of meteorological forecast data and weak generalization ability of models,this pape...To enhance the accuracy of short-term photovoltaic power output prediction and address issues such as insufficient spatial resolution of meteorological forecast data and weak generalization ability of models,this paper proposes a prediction method that integrates spatial downscaling meteorological data with a convolutional neural network(CNN)-iTransformer-long short-term memory(LSTM)model.First,the rime-optimized random forest regression algorithm(RIME-RF)is employed to perform spatial downscaling on numerical weather prediction(NWP)data,thereby improving its local applicability.Second,a CNN-iTransformer-LSTM hybrid prediction model is constructed.This model utilizes a CNN as a spatial feature extractor to capture local patterns in meteorological data,employs an iTransformer to model the global dependencies among multiple variables,and leverages an LSTM to enhance the learning of short-term temporal dynamic features,thereby achieving efficient collaborative mining of multi-scale features.Finally,experiments are conducted using actual data from a photovoltaic power station in Hebei,China,during various seasons and weather conditions.The results show that the proposed model outperforms the comparison models in terms of the root mean square error(RMSE),mean absolute error(MAE),and R2,maintaining high prediction accuracy and stability even under complex weather conditions such as overcast and rainy days.The downscaling process further enhances the prediction performance,verifying the effectiveness and practicality of this method.展开更多
Photovoltaic(PV) power generation is characterized by randomness and intermittency due to weather changes.Consequently, large-scale PV power connections to the grid can threaten the stable operation of the power syste...Photovoltaic(PV) power generation is characterized by randomness and intermittency due to weather changes.Consequently, large-scale PV power connections to the grid can threaten the stable operation of the power system. An effective method to resolve this problem is to accurately predict PV power. In this study, an innovative short-term hybrid prediction model(i.e., HKSL) of PV power is established. The model combines K-means++, optimal similar day approach,and long short-term memory(LSTM) network. Historical power data and meteorological factors are utilized. This model searches for the best similar day based on the results of classifying weather types. Then, the data of similar day are inputted into the LSTM network to predict PV power. The validity of the hybrid model is verified based on the datasets from a PV power station in Shandong Province, China. Four evaluation indices, mean absolute error, root mean square error(RMSE),normalized RMSE, and mean absolute deviation, are employed to assess the performance of the HKSL model. The RMSE of the proposed model compared with those of Elman, LSTM, HSE(hybrid model combining similar day approach and Elman), HSL(hybrid model combining similar day approach and LSTM), and HKSE(hybrid model combining K-means++,similar day approach, and LSTM) decreases by 66.73%, 70.22%, 65.59%, 70.51%, and 18.40%, respectively. This proves the reliability and excellent performance of the proposed hybrid model in predicting power.展开更多
Owing to the persisting hype in pushing toward global carbon neutrality,the study scope of atmospheric science is rapidly expanding.Among numerous trending topics,energy meteorology has been attracting the most attent...Owing to the persisting hype in pushing toward global carbon neutrality,the study scope of atmospheric science is rapidly expanding.Among numerous trending topics,energy meteorology has been attracting the most attention hitherto.One essential skill of solar energy meteorologists is solar power curve modeling,which seeks to map irradiance and auxiliary weather variables to solar power,by statistical and/or physical means.In this regard,this tutorial review aims to deliver a complete overview of those fundamental scientific and engineering principles pertaining to the solar power curve.Solar power curves can be modeled in two primary ways,one of regression and the other of model chain.Both classes of modeling approaches,alongside their hybridization and probabilistic extensions,which allow accuracy improvement and uncertainty quantification,are scrutinized and contrasted thoroughly in this review.展开更多
Improving the accuracy of solar power forecasting is crucial to ensure grid stability,optimize solar power plant operations,and enhance grid dispatch efficiency.Although hybrid neural network models can effectively ad...Improving the accuracy of solar power forecasting is crucial to ensure grid stability,optimize solar power plant operations,and enhance grid dispatch efficiency.Although hybrid neural network models can effectively address the complexities of environmental data and power prediction uncertainties,challenges such as labor-intensive parameter adjustments and complex optimization processes persist.Thus,this study proposed a novel approach for solar power prediction using a hybrid model(CNN-LSTM-attention)that combines a convolutional neural network(CNN),long short-term memory(LSTM),and attention mechanisms.The model incorporates Bayesian optimization to refine the parameters and enhance the prediction accuracy.To prepare high-quality training data,the solar power data were first preprocessed,including feature selection,data cleaning,imputation,and smoothing.The processed data were then used to train a hybrid model based on the CNN-LSTM-attention architecture,followed by hyperparameter optimization employing Bayesian methods.The experimental results indicated that within acceptable model training times,the CNN-LSTM-attention model outperformed the LSTM,GRU,CNN-LSTM,CNN-LSTM with autoencoders,and parallel CNN-LSTM attention models.Furthermore,following Bayesian optimization,the optimized model demonstrated significantly reduced prediction errors during periods of data volatility compared to the original model,as evidenced by MRE evaluations.This highlights the clear advantage of the optimized model in forecasting fluctuating data.展开更多
Accurate short-termphotovoltaic(PV)power prediction helps to improve the economic efficiency of power stations and is of great significance to the arrangement of grid scheduling plans.In order to improve the accuracy ...Accurate short-termphotovoltaic(PV)power prediction helps to improve the economic efficiency of power stations and is of great significance to the arrangement of grid scheduling plans.In order to improve the accuracy of PV power prediction further,this paper proposes a data cleaning method combining density clustering and support vector machine.It constructs a short-termPVpower predictionmodel based on particle swarmoptimization(PSO)optimized Long Short-Term Memory(LSTM)network.Firstly,the input features are determined using Pearson’s correlation coefficient.The feature information is clustered using density-based spatial clustering of applications withnoise(DBSCAN),and then,the data in each cluster is cleanedusing support vectormachines(SVM).Secondly,the PSO is used to optimize the hyperparameters of the LSTM network to obtain the optimal network structure.Finally,different power prediction models are established,and the PV power generation prediction results are obtained.The results show that the data methods used are effective and that the PSO-LSTM power prediction model based on DBSCAN-SVM data cleaning outperforms existing typical methods,especially under non-sunny days,and that the model effectively improves the accuracy of short-term PV power prediction.展开更多
The output of photovoltaic power stations is significantly affected by environmental factors,leading to intermittent and fluctuating power generation.With the increasing frequency of extreme weather events due to glob...The output of photovoltaic power stations is significantly affected by environmental factors,leading to intermittent and fluctuating power generation.With the increasing frequency of extreme weather events due to global warming,photovoltaic power stations may experience drastic reductions in power generation or even complete shutdowns during such conditions.The integration of these stations on a large scale into the power grid could potentially pose challenges to systemstability.To address this issue,in this study,we propose a network architecture based on VMDKELMfor predicting the power output of photovoltaic power plants during severe weather events.Initially,a grey relational analysis is conducted to identify key environmental factors influencing photovoltaic power generation.Subsequently,GMM clustering is utilized to classify meteorological data points based on their probabilities within different Gaussian distributions,enabling comprehensive meteorological clustering and extraction of significant extreme weather data.The data are decomposed using VMD to Fourier transform,followed by smoothing processing and signal reconstruction using KELM to forecast photovoltaic power output under major extreme weather conditions.The proposed prediction scheme is validated by establishing three prediction models,and the predicted photovoltaic output under four major extreme weather conditions is analyzed to assess the impact of severe weather on photovoltaic power station output.The experimental results show that the photovoltaic power output under conditions of dust storms,thunderstorms,solid hail precipitation,and snowstorms is reduced by 68.84%,42.70%,61.86%,and 49.92%,respectively,compared to that under clear day conditions.The photovoltaic power prediction accuracies,in descending order,are dust storms,solid hail precipitation,thunderstorms,and snowstorms.展开更多
The parameter estimation problem of Hammerstein finite impulse response models and its application on the wind curtailment prediction field were considered.By adopting the maximum likelihood principle,the maximum like...The parameter estimation problem of Hammerstein finite impulse response models and its application on the wind curtailment prediction field were considered.By adopting the maximum likelihood principle,the maximum likelihood estimate was obtained by minimizing the likelihood function.To reduce the impact of the unknown noise term,the maximum likelihood idea and the filtering theory were combined by changing the coupled nonlinear model into a parameter-independent model and to derive a filtering based maximum likelihood stochastic gradient algorithm for the Hammerstein system modeling on wind power curtailment prediction.The given simulation validates that the proposed algorithm can identify the wind power characteristic curve accurately and contributes to calculate the wind power curtailment prediction that shows its good practicability.展开更多
Accurate photovoltaic(PV)power prediction can effectively help the power sector to make rational energy planning and dispatching decisions,promote PV consumption,make full use of renewable energy and alleviate energy ...Accurate photovoltaic(PV)power prediction can effectively help the power sector to make rational energy planning and dispatching decisions,promote PV consumption,make full use of renewable energy and alleviate energy problems.To address this research objective,this paper proposes a prediction model based on kernel principal component analysis(KPCA),modified cuckoo search algorithm(MCS)and deep convolutional neural networks(DCNN).Firstly,KPCA is utilized to reduce the dimension of the feature,which aims to reduce the redundant input vectors.Then using MCS to optimize the parameters of DCNN.Finally,the photovoltaic power forecasting method of KPCA-MCS-DCNN is established.In order to verify the prediction performance of the proposed model,this paper selects a photovoltaic power station in China for example analysis.The results show that the new hybrid KPCA-MCS-DCNN model has higher prediction accuracy and better robustness.展开更多
With the increasing proportion of renewable energy in China’s energy structure,among which photovoltaic power generation is also developing rapidly.As the photovoltaic(PV)power output is highly unstable and subject t...With the increasing proportion of renewable energy in China’s energy structure,among which photovoltaic power generation is also developing rapidly.As the photovoltaic(PV)power output is highly unstable and subject to a variety of factors,it brings great challenges to the stable operation and dispatch of the power grid.Therefore,accurate short-term PV power prediction is of great significance to ensure the safe grid connection of PV energy.Currently,the short-term prediction of PV power has received extensive attention and research,but the accuracy and precision of the prediction have to be further improved.Therefore,this paper reviews the PV power prediction methods from five aspects:influencing factors,evaluation indexes,prediction status,difficulties and future trends.Then summarizes the current difficulties in prediction based on an in-depth analysis of the current research status of physical methods based on the classification ofmodel features,statistical methods,artificial intelligence methods,and combinedmethods of prediction.Finally,the development trend ofPVpower generation prediction technology and possible future research directions are envisioned.展开更多
For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the i...For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the input data of the model.Next,the dictionary learning techniques using the K-mean singular value decomposition(K-SVD)algorithm and the orthogonal matching pursuit(OMP)algorithm are used to obtain the corresponding sparse encoding based on all the input data,i.e.the initial dictionary.Then,to build the global prediction model,the sparse coding vectors are used as the input of the model of the kernel extreme learning machine(KELM).Finally,to verify the effectiveness of the combined K-SVD-OMP and KELM method,the proposed method is applied to a instance of the photovoltaic power prediction.Compared with KELM,SVM and ELM under the same conditions,experimental results show that different combined sparse representation methods achieve better prediction results,among which the combined K-SVD-OMP and KELM method shows better prediction results and modeling accuracy.展开更多
Due to the frequent changes of wind speed and wind direction,the accuracy of wind turbine(WT)power prediction using traditional data preprocessing method is low.This paper proposes a data preprocessing method which co...Due to the frequent changes of wind speed and wind direction,the accuracy of wind turbine(WT)power prediction using traditional data preprocessing method is low.This paper proposes a data preprocessing method which combines POT with DBSCAN(POT-DBSCAN)to improve the prediction efficiency of wind power prediction model.Firstly,according to the data of WT in the normal operation condition,the power prediction model ofWT is established based on the Particle Swarm Optimization(PSO)Arithmetic which is combined with the BP Neural Network(PSO-BP).Secondly,the wind-power data obtained from the supervisory control and data acquisition(SCADA)system is preprocessed by the POT-DBSCAN method.Then,the power prediction of the preprocessed data is carried out by PSO-BP model.Finally,the necessity of preprocessing is verified by the indexes.This case analysis shows that the prediction result of POT-DBSCAN preprocessing is better than that of the Quartile method.Therefore,the accuracy of data and prediction model can be improved by using this method.展开更多
This work proposed a LSTM(long short-term memory)model based on the double attention mechanism for power load prediction,to further improve the energy-saving potential and accurately control the distribution of power ...This work proposed a LSTM(long short-term memory)model based on the double attention mechanism for power load prediction,to further improve the energy-saving potential and accurately control the distribution of power load into each department of the hospital.Firstly,the key influencing factors of the power loads were screened based on the grey relational degree analysis.Secondly,in view of the characteristics of the power loads affected by various factors and time series changes,the feature attention mechanism and sequential attention mechanism were introduced on the basis of LSTM network.The former was used to analyze the relationship between the historical information and input variables autonomously to extract important features,and the latter was used to select the historical information at critical moments of LSTM network to improve the stability of long-term prediction effects.In the end,the experimental results from the power loads of Shanxi Eye Hospital show that the LSTM model based on the double attention mechanism has the higher forecasting accuracy and stability than the conventional LSTM,CNN-LSTM and attention-LSTM models.展开更多
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 com...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.展开更多
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...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.展开更多
基金supported by the Science and Technology Project of Jiangsu Coastal Power Infrastructure Intelligent Engineering Research Center“Photovoltaic Power Prediction System Driven by Deep Learning and Multi-Source Data Fusion”(F2024-5044).
文摘Harnessing solar power is essential for addressing the dual challenges of global warming and the depletion of traditional energy sources.However,the fluctuations and intermittency of photovoltaic(PV)power pose challenges for its extensive incorporation into power grids.Thus,enhancing the precision of PV power prediction is particularly important.Although existing studies have made progress in short-term prediction,issues persist,particularly in the underutilization of temporal features and the neglect of correlations between satellite cloud images and PV power data.These factors hinder improvements in PV power prediction performance.To overcome these challenges,this paper proposes a novel PV power prediction method based on multi-stage temporal feature learning.First,the improved LSTMand SA-ConvLSTMare employed to extract the temporal feature of PV power and the spatial-temporal feature of satellite cloud images,respectively.Subsequently,a novel hybrid attention mechanism is proposed to identify the interplay between the two modalities,enhancing the capacity to focus on the most relevant features.Finally,theTransformermodel is applied to further capture the short-termtemporal patterns and long-term dependencies within multi-modal feature information.The paper also compares the proposed method with various competitive methods.The experimental results demonstrate that the proposed method outperforms the competitive methods in terms of accuracy and reliability in short-term PV power prediction.
文摘Knowing the influence of the size of datasets for regression models can help in improving the accuracy of a solar power forecast and make the most out of renewable energy systems.This research explores the influence of dataset size on the accuracy and reliability of regression models for solar power prediction,contributing to better forecasting methods.The study analyzes data from two solar panels,aSiMicro03036 and aSiTandem72-46,over 7,14,17,21,28,and 38 days,with each dataset comprising five independent and one dependent parameter,and split 80–20 for training and testing.Results indicate that Random Forest consistently outperforms other models,achieving the highest correlation coefficient of 0.9822 and the lowest Mean Absolute Error(MAE)of 2.0544 on the aSiTandem72-46 panel with 21 days of data.For the aSiMicro03036 panel,the best MAE of 4.2978 was reached using the k-Nearest Neighbor(k-NN)algorithm,which was set up as instance-based k-Nearest neighbors(IBk)in Weka after being trained on 17 days of data.Regression performance for most models(excluding IBk)stabilizes at 14 days or more.Compared to the 7-day dataset,increasing to 21 days reduced the MAE by around 20%and improved correlation coefficients by around 2.1%,highlighting the value of moderate dataset expansion.These findings suggest that datasets spanning 17 to 21 days,with 80%used for training,can significantly enhance the predictive accuracy of solar power generation models.
基金supported by the State Grid Corporation of China Headquarters Science and Technology Project“Research on Key Technologies for Power System Source-Load Forecasting and Regulation Capacity Assessment Oriented towards Major Weather Processes”(4000-202355381A-2-3-XG).
文摘Photovoltaic(PV)power generation is undergoing significant growth and serves as a key driver of the global energy transition.However,its intermittent nature,which fluctuates with weather conditions,has raised concerns about grid stability.Accurate PV power prediction has been demonstrated as crucial for power system operation and scheduling,enabling power slope control,fluctuation mitigation,grid stability enhancement,and reliable data support for secure grid operation.However,existing prediction models primarily target centralized PV plants,largely neglecting the spatiotemporal coupling dynamics and output uncertainties inherent to distributed PV systems.This study proposes a novel Spatio-Temporal Graph Neural Network(STGNN)architecture for distributed PV power generation prediction,designed to enhance distributed photovoltaic(PV)power generation forecasting accuracy and support regional grid scheduling.This approach models each PV power plant as a node in an undirected graph,with edges representing correlations between plants to capture spatial dependencies.The model comprises multiple Sparse Attention-based Adaptive Spatio-Temporal(SAAST)blocks.The SAAST blocks include sparse temporal attention,sparse spatial attention,an adaptive Graph Convolutional Network(GCN),and a temporal convolution network(TCN).These components eliminate weak temporal and spatial correlations,better represent dynamic spatial dependencies,and further enhance prediction accuracy.Finally,multi-dimensional comparative experiments between the STGNN and other models on the DKASC PV dataset demonstrate its superior performance in terms of accuracy and goodness-of-fit for distributed PV power generation prediction.
基金2023 Sustainable Development Science and Technology Innovation Action Plan Project of Chongming District Science and Technology Committee,Shanghai(CKST2023-01)Shanghai Science and Technology Commission Funded Project(19DZ2254800).
文摘Short-term photovoltaic(PV)power forecasting plays a crucial role in enhancing the stability and reliability of power grid scheduling.To address the challenges posed by complex environmental variables and difficulties in modeling temporal features in PV power prediction,a short-term PV power forecasting method based on an improved CNN-LSTM and cascade learning strategy is proposed.First,Pearson correlation coefficients and mutual information are used to select representative features,reducing the impact of redundant features onmodel performance.Then,the CNN-LSTM network is designed to extract local features using CNN and learn temporal dependencies through LSTM,thereby obtaining feature representations rich in temporal information.Subsequently,a multi-layer cascade structure is developed,progressively integrating prediction results from base learners such as LightGBM,XGBoost,Random Forest(RF),and Extreme Random Forest(ERF)to enhance model performance.Finally,an XGBoost-based meta-learner is utilized to integrate the outputs of the base learners and generate the final prediction results.The entire cascading process adopts a dynamic expansion strategy,where the decision to add new cascade layers is based on the R2 performance criterion.Experimental results demonstrate that the proposed model achieves high prediction accuracy and robustness under various weather conditions,showing significant improvements over traditional models and providing an effective solution for short-term PV power forecasting.
基金funded by the Science and Technology Project of State Grid Corporation of China under Grant No.5108-202218280A-2-299-XG.
文摘Wind power generation is subjected to complex and variable meteorological conditions,resulting in intermittent and volatile power generation.Accurate wind power prediction plays a crucial role in enabling the power grid dispatching departments to rationally plan power transmission and energy storage operations.This enhances the efficiency of wind power integration into the grid.It allows grid operators to anticipate and mitigate the impact of wind power fluctuations,significantly improving the resilience of wind farms and the overall power grid.Furthermore,it assists wind farm operators in optimizing the management of power generation facilities and reducing maintenance costs.Despite these benefits,accurate wind power prediction especially in extreme scenarios remains a significant challenge.To address this issue,a novel wind power prediction model based on learning approach is proposed by integrating wavelet transform and Transformer.First,a conditional generative adversarial network(CGAN)generates dynamic extreme scenarios guided by physical constraints and expert rules to ensure realism and capture critical features of wind power fluctuations under extremeconditions.Next,thewavelet transformconvolutional layer is applied to enhance sensitivity to frequency domain characteristics,enabling effective feature extraction fromextreme scenarios for a deeper understanding of input data.The model then leverages the Transformer’s self-attention mechanism to capture global dependencies between features,strengthening its sequence modelling capabilities.Case analyses verify themodel’s superior performance in extreme scenario prediction by effectively capturing local fluctuation featureswhile maintaining a grasp of global trends.Compared to other models,it achieves R-squared(R^(2))as high as 0.95,and the mean absolute error(MAE)and rootmean square error(RMSE)are also significantly lower than those of othermodels,proving its high accuracy and effectiveness in managing complex wind power generation conditions.
基金This work was supported in part by the Natural Science Foundation of Henan Province,and the specific grant number is 232300420301the initial of author is P.L.,the URL to the sponsors’websites is https://kjt.henan.gov.cn/(accessed on 09 February 2025)And this work was also supported in part by the Fundamental Research Funds for the Universities of Henan Province,and the specific grant number is NSFRF220425,the initial of author is P.L.,the URL to sponsors websites is http://app.hnkjt.gov.cn/web/index.do(accessed on 09 February 2025).
文摘The photovoltaic(PV)output process is inherently complex,often disrupted by a multitude of meteoro-logical factors,while conventional detection methods at PV power stations prove inadequate,compromising prediction accuracy.To address this challenge,this paper introduces a power prediction method that leverages modal switching(MS),weight factor adjustment(WFA),and parallel long short-term memory(PALSTM).Initially,historical PV power station data is categorized into distinct modes based on global horizontal irradiance and converted solar angles.Correlation analysis is then employed to evaluate the impact of various meteorological factors on PV power,selecting those with strong correlations for each specific mode.Subsequently,the weights of meteorological parameters are optimized and adjusted,and a PALSTM neural network is constructed,with its parallel modal parameters refined through training.Depending on the prediction time and input data mode characteristics,the appropriate mode channel is selected to forecast PV power station generation.Ultimately,the feasibility of this method is validated through an illustrative analysis of measured data from an Australian PV power station.Comparative test results underscore the method’s advantages,particularly in scenarios where existing detection methods are lacking and meteorological factors frequently fluctuate,demonstrating its superior prediction accuracy and stability.
文摘To enhance the accuracy of short-term photovoltaic power output prediction and address issues such as insufficient spatial resolution of meteorological forecast data and weak generalization ability of models,this paper proposes a prediction method that integrates spatial downscaling meteorological data with a convolutional neural network(CNN)-iTransformer-long short-term memory(LSTM)model.First,the rime-optimized random forest regression algorithm(RIME-RF)is employed to perform spatial downscaling on numerical weather prediction(NWP)data,thereby improving its local applicability.Second,a CNN-iTransformer-LSTM hybrid prediction model is constructed.This model utilizes a CNN as a spatial feature extractor to capture local patterns in meteorological data,employs an iTransformer to model the global dependencies among multiple variables,and leverages an LSTM to enhance the learning of short-term temporal dynamic features,thereby achieving efficient collaborative mining of multi-scale features.Finally,experiments are conducted using actual data from a photovoltaic power station in Hebei,China,during various seasons and weather conditions.The results show that the proposed model outperforms the comparison models in terms of the root mean square error(RMSE),mean absolute error(MAE),and R2,maintaining high prediction accuracy and stability even under complex weather conditions such as overcast and rainy days.The downscaling process further enhances the prediction performance,verifying the effectiveness and practicality of this method.
基金supported by the No. 4 National Project in 2022 of the Ministry of Emergency Response (2022YJBG04)the International Clean Energy Talent Program (201904100014)。
文摘Photovoltaic(PV) power generation is characterized by randomness and intermittency due to weather changes.Consequently, large-scale PV power connections to the grid can threaten the stable operation of the power system. An effective method to resolve this problem is to accurately predict PV power. In this study, an innovative short-term hybrid prediction model(i.e., HKSL) of PV power is established. The model combines K-means++, optimal similar day approach,and long short-term memory(LSTM) network. Historical power data and meteorological factors are utilized. This model searches for the best similar day based on the results of classifying weather types. Then, the data of similar day are inputted into the LSTM network to predict PV power. The validity of the hybrid model is verified based on the datasets from a PV power station in Shandong Province, China. Four evaluation indices, mean absolute error, root mean square error(RMSE),normalized RMSE, and mean absolute deviation, are employed to assess the performance of the HKSL model. The RMSE of the proposed model compared with those of Elman, LSTM, HSE(hybrid model combining similar day approach and Elman), HSL(hybrid model combining similar day approach and LSTM), and HKSE(hybrid model combining K-means++,similar day approach, and LSTM) decreases by 66.73%, 70.22%, 65.59%, 70.51%, and 18.40%, respectively. This proves the reliability and excellent performance of the proposed hybrid model in predicting power.
基金supported by the National Natural Science Foundation of China(project no.42375192),and the China Meteorological Administration Climate Change Special Program(CMA-CCSPproject no.QBZ202315)+2 种基金supported by the National Natural Science Foundation of China(project no.42030608)supported by the National Research,Development and Innovation Fund,project no.OTKA-FK 142702by the Hungarian Academy of Sciences through the Sustainable Development and Technologies National Programme(FFT NP FTA)and the János Bolyai Research Scholarship.
文摘Owing to the persisting hype in pushing toward global carbon neutrality,the study scope of atmospheric science is rapidly expanding.Among numerous trending topics,energy meteorology has been attracting the most attention hitherto.One essential skill of solar energy meteorologists is solar power curve modeling,which seeks to map irradiance and auxiliary weather variables to solar power,by statistical and/or physical means.In this regard,this tutorial review aims to deliver a complete overview of those fundamental scientific and engineering principles pertaining to the solar power curve.Solar power curves can be modeled in two primary ways,one of regression and the other of model chain.Both classes of modeling approaches,alongside their hybridization and probabilistic extensions,which allow accuracy improvement and uncertainty quantification,are scrutinized and contrasted thoroughly in this review.
基金supported by the State Grid Science&Technology Project(5400-202224153A-1-1-ZN).
文摘Improving the accuracy of solar power forecasting is crucial to ensure grid stability,optimize solar power plant operations,and enhance grid dispatch efficiency.Although hybrid neural network models can effectively address the complexities of environmental data and power prediction uncertainties,challenges such as labor-intensive parameter adjustments and complex optimization processes persist.Thus,this study proposed a novel approach for solar power prediction using a hybrid model(CNN-LSTM-attention)that combines a convolutional neural network(CNN),long short-term memory(LSTM),and attention mechanisms.The model incorporates Bayesian optimization to refine the parameters and enhance the prediction accuracy.To prepare high-quality training data,the solar power data were first preprocessed,including feature selection,data cleaning,imputation,and smoothing.The processed data were then used to train a hybrid model based on the CNN-LSTM-attention architecture,followed by hyperparameter optimization employing Bayesian methods.The experimental results indicated that within acceptable model training times,the CNN-LSTM-attention model outperformed the LSTM,GRU,CNN-LSTM,CNN-LSTM with autoencoders,and parallel CNN-LSTM attention models.Furthermore,following Bayesian optimization,the optimized model demonstrated significantly reduced prediction errors during periods of data volatility compared to the original model,as evidenced by MRE evaluations.This highlights the clear advantage of the optimized model in forecasting fluctuating data.
基金supported in part by the Inner Mongolia Autonomous Region Science and Technology Project Fund(2021GG0336)Inner Mongolia Natural Science Fund(2023ZD20).
文摘Accurate short-termphotovoltaic(PV)power prediction helps to improve the economic efficiency of power stations and is of great significance to the arrangement of grid scheduling plans.In order to improve the accuracy of PV power prediction further,this paper proposes a data cleaning method combining density clustering and support vector machine.It constructs a short-termPVpower predictionmodel based on particle swarmoptimization(PSO)optimized Long Short-Term Memory(LSTM)network.Firstly,the input features are determined using Pearson’s correlation coefficient.The feature information is clustered using density-based spatial clustering of applications withnoise(DBSCAN),and then,the data in each cluster is cleanedusing support vectormachines(SVM).Secondly,the PSO is used to optimize the hyperparameters of the LSTM network to obtain the optimal network structure.Finally,different power prediction models are established,and the PV power generation prediction results are obtained.The results show that the data methods used are effective and that the PSO-LSTM power prediction model based on DBSCAN-SVM data cleaning outperforms existing typical methods,especially under non-sunny days,and that the model effectively improves the accuracy of short-term PV power prediction.
基金funded by the Open Fund of National Key Laboratory of Renewable Energy Grid Integration(China Electric Power Research Institute)(No.NYB51202301624).
文摘The output of photovoltaic power stations is significantly affected by environmental factors,leading to intermittent and fluctuating power generation.With the increasing frequency of extreme weather events due to global warming,photovoltaic power stations may experience drastic reductions in power generation or even complete shutdowns during such conditions.The integration of these stations on a large scale into the power grid could potentially pose challenges to systemstability.To address this issue,in this study,we propose a network architecture based on VMDKELMfor predicting the power output of photovoltaic power plants during severe weather events.Initially,a grey relational analysis is conducted to identify key environmental factors influencing photovoltaic power generation.Subsequently,GMM clustering is utilized to classify meteorological data points based on their probabilities within different Gaussian distributions,enabling comprehensive meteorological clustering and extraction of significant extreme weather data.The data are decomposed using VMD to Fourier transform,followed by smoothing processing and signal reconstruction using KELM to forecast photovoltaic power output under major extreme weather conditions.The proposed prediction scheme is validated by establishing three prediction models,and the predicted photovoltaic output under four major extreme weather conditions is analyzed to assess the impact of severe weather on photovoltaic power station output.The experimental results show that the photovoltaic power output under conditions of dust storms,thunderstorms,solid hail precipitation,and snowstorms is reduced by 68.84%,42.70%,61.86%,and 49.92%,respectively,compared to that under clear day conditions.The photovoltaic power prediction accuracies,in descending order,are dust storms,solid hail precipitation,thunderstorms,and snowstorms.
基金China Postdoctoral Science Foundation Funded Project(2016M591765)Jiangsu Postdoctoral Science Foundation Funded Project(1601252C)Fundamental Research Funds for the Central Universities(JUSRP115A30)
文摘The parameter estimation problem of Hammerstein finite impulse response models and its application on the wind curtailment prediction field were considered.By adopting the maximum likelihood principle,the maximum likelihood estimate was obtained by minimizing the likelihood function.To reduce the impact of the unknown noise term,the maximum likelihood idea and the filtering theory were combined by changing the coupled nonlinear model into a parameter-independent model and to derive a filtering based maximum likelihood stochastic gradient algorithm for the Hammerstein system modeling on wind power curtailment prediction.The given simulation validates that the proposed algorithm can identify the wind power characteristic curve accurately and contributes to calculate the wind power curtailment prediction that shows its good practicability.
文摘Accurate photovoltaic(PV)power prediction can effectively help the power sector to make rational energy planning and dispatching decisions,promote PV consumption,make full use of renewable energy and alleviate energy problems.To address this research objective,this paper proposes a prediction model based on kernel principal component analysis(KPCA),modified cuckoo search algorithm(MCS)and deep convolutional neural networks(DCNN).Firstly,KPCA is utilized to reduce the dimension of the feature,which aims to reduce the redundant input vectors.Then using MCS to optimize the parameters of DCNN.Finally,the photovoltaic power forecasting method of KPCA-MCS-DCNN is established.In order to verify the prediction performance of the proposed model,this paper selects a photovoltaic power station in China for example analysis.The results show that the new hybrid KPCA-MCS-DCNN model has higher prediction accuracy and better robustness.
基金supported in part by the Inner Mongolia Autonomous Region Science and Technology Project Fund(2021GG0336)Inner Mongolia Natural Science Fund(2023ZD20).
文摘With the increasing proportion of renewable energy in China’s energy structure,among which photovoltaic power generation is also developing rapidly.As the photovoltaic(PV)power output is highly unstable and subject to a variety of factors,it brings great challenges to the stable operation and dispatch of the power grid.Therefore,accurate short-term PV power prediction is of great significance to ensure the safe grid connection of PV energy.Currently,the short-term prediction of PV power has received extensive attention and research,but the accuracy and precision of the prediction have to be further improved.Therefore,this paper reviews the PV power prediction methods from five aspects:influencing factors,evaluation indexes,prediction status,difficulties and future trends.Then summarizes the current difficulties in prediction based on an in-depth analysis of the current research status of physical methods based on the classification ofmodel features,statistical methods,artificial intelligence methods,and combinedmethods of prediction.Finally,the development trend ofPVpower generation prediction technology and possible future research directions are envisioned.
基金National Natural Science Foundation of China(No.51467008)。
文摘For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the input data of the model.Next,the dictionary learning techniques using the K-mean singular value decomposition(K-SVD)algorithm and the orthogonal matching pursuit(OMP)algorithm are used to obtain the corresponding sparse encoding based on all the input data,i.e.the initial dictionary.Then,to build the global prediction model,the sparse coding vectors are used as the input of the model of the kernel extreme learning machine(KELM).Finally,to verify the effectiveness of the combined K-SVD-OMP and KELM method,the proposed method is applied to a instance of the photovoltaic power prediction.Compared with KELM,SVM and ELM under the same conditions,experimental results show that different combined sparse representation methods achieve better prediction results,among which the combined K-SVD-OMP and KELM method shows better prediction results and modeling accuracy.
基金National Natural Science Foundation of China(Nos.51875199 and 51905165)Hunan Natural Science Fund Project(2019JJ50186)the Ke7y Research and Development Program of Hunan Province(No.2018GK2073).
文摘Due to the frequent changes of wind speed and wind direction,the accuracy of wind turbine(WT)power prediction using traditional data preprocessing method is low.This paper proposes a data preprocessing method which combines POT with DBSCAN(POT-DBSCAN)to improve the prediction efficiency of wind power prediction model.Firstly,according to the data of WT in the normal operation condition,the power prediction model ofWT is established based on the Particle Swarm Optimization(PSO)Arithmetic which is combined with the BP Neural Network(PSO-BP).Secondly,the wind-power data obtained from the supervisory control and data acquisition(SCADA)system is preprocessed by the POT-DBSCAN method.Then,the power prediction of the preprocessed data is carried out by PSO-BP model.Finally,the necessity of preprocessing is verified by the indexes.This case analysis shows that the prediction result of POT-DBSCAN preprocessing is better than that of the Quartile method.Therefore,the accuracy of data and prediction model can be improved by using this method.
基金Supported by the Shaanxi Provincial Education Department 2022 Key Research Program Project(22JS022)the National Natural Science Foundation of China(51808428)
文摘This work proposed a LSTM(long short-term memory)model based on the double attention mechanism for power load prediction,to further improve the energy-saving potential and accurately control the distribution of power load into each department of the hospital.Firstly,the key influencing factors of the power loads were screened based on the grey relational degree analysis.Secondly,in view of the characteristics of the power loads affected by various factors and time series changes,the feature attention mechanism and sequential attention mechanism were introduced on the basis of LSTM network.The former was used to analyze the relationship between the historical information and input variables autonomously to extract important features,and the latter was used to select the historical information at critical moments of LSTM network to improve the stability of long-term prediction effects.In the end,the experimental results from the power loads of Shanxi Eye Hospital show that the LSTM model based on the double attention mechanism has the higher forecasting accuracy and stability than the conventional LSTM,CNN-LSTM and attention-LSTM models.
基金funded by National Key Research and Development Program of China (2021YFB2601400)。
文摘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.
文摘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.
