Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradi...Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.展开更多
China’s recently announced directive on tackling climate change,namely,to reach carbon peak by 2030 and to achieve carbon neutrality by 2060,has led to an unprecedented nationwide response among the academia and indu...China’s recently announced directive on tackling climate change,namely,to reach carbon peak by 2030 and to achieve carbon neutrality by 2060,has led to an unprecedented nationwide response among the academia and industry.Under such a directive,a rapid increase in the grid penetration rate of solar in the near future can be fully anticipated.Although solar radiation is an atmospheric process,its utilization,as to produce electricity,has hitherto been handled by engineers.In that,it is thought important to bridge the two fields,atmospheric sciences and solar engineering,for the common good of carbon neutrality.In thisüberreview,all major aspects pertaining to solar resource assessment and forecasting are discussed in brief.Given the size of the topic at hand,instead of presenting technical details,which would be overly lengthy and repetitive,the overarching goal of this review is to comprehensively compile a catalog of some recent,and some not so recent,review papers,so that the interested readers can explore the details on their own.展开更多
In the last two decades,renewable energy has been paid immeasurable attention to toward the attainment of electricity requirements for domestic,industrial,and agriculture sectors.Solar forecasting plays a vital role i...In the last two decades,renewable energy has been paid immeasurable attention to toward the attainment of electricity requirements for domestic,industrial,and agriculture sectors.Solar forecasting plays a vital role in smooth operation,scheduling,and balancing of electricity production by standalone PV plants as well as grid interconnected solar PV plants.Numerous models and techniques have been developed in short,mid and long-term solar forecasting.This paper analyzes some of the potential solar forecasting models based on various methodologies discussed in literature,by mainly focusing on investigating the influence of meteorological variables,time horizon,climatic zone,pre-processing techniques,air pollution,and sample size on the complexity and accuracy of the model.To make the paper reader-friendly,it presents all-important parameters and findings of the models revealed from different studies in a tabular mode having the year of publication,time resolution,input parameters,forecasted parameters,error metrics,and performance.The literature studied showed that ANN-based models outperform the others due to their nonlinear complex problem-solving capabilities.Their accuracy can be further improved by hybridization of the two models or by performing pre-processing on the input data.Besides,it also discusses the diverse key constituents that affect the accuracy of a model.It has been observed that the proper selection of training and testing period along with the correlated dependent variables also enhances the accuracy of the model.展开更多
The fundamental scientific and engineering knowledge concerning the solar power curve,which maps solar irradiance and other auxiliary meteorological variables to photovoltaic output power,has been gathered and put for...The fundamental scientific and engineering knowledge concerning the solar power curve,which maps solar irradiance and other auxiliary meteorological variables to photovoltaic output power,has been gathered and put forward in the preceding tutorial review.Despite the many pages of that review,it was incomplete in the sense that it did not elaborate on the applications of this very important tool of solar energy meteorology.Indeed,solar power curves are ubiquitously needed in a broad spectrum of solar forecasting and solar resource assessment tasks.Hence,this tutorial review should continue from where it left off and present examples concerning the usage of solar power curves.In a nutshell,this tutorial review,together with the preceding one,should elucidate how surface shortwave radiation data,be they ground-based,satelliteretrieved,or model-output,are bridged to various power system operations via solar power curves.展开更多
Solar forecasting using ground-based sky image offers a promising approach to reduce uncertainty in photovoltaic(PV)power generation.However,existing methods often rely on deterministic predictions that lack diversity...Solar forecasting using ground-based sky image offers a promising approach to reduce uncertainty in photovoltaic(PV)power generation.However,existing methods often rely on deterministic predictions that lack diversity,making it difficult to capture the inherently stochastic nature of cloud movement.To address this limitation,we propose a new two-stage probabilistic forecasting framework.In the first stage,we introduce I-GPT,a multiscale physics-constrained generative model for stochastic sky image prediction.Given a sequence of past sky images,I-GPT uses a Transformer-based VQ-VAE.It also incorporates multi-scale physics-informed recurrent units(Multi-scale PhyCell)and dynamically weighted fuses physical and appearance features.This approach enables the generation of multiple plausible future sky images with realistic and coherent cloud motion.In the second stage,these predicted sky images are fed into an Image-to-Power U-Net(IP-U-Net)to produce 15-min-ahead probabilistic PV power forecasts.In experiments using our dataset,the proposed approach significantly outperforms deterministic,other stochastic,multimodal,and smart persistence baselines models,achieving a superior reliability–sharpness trade-off.It attains a Continuous Ranked Probability Score(CRPS)of 2.912 kW and a Winkler Score(WS)of 33.103 kW on the test set and CRPS of 2.073 kW and WS of 22.202 kW on the validation set.Translating to 35.9%and 42.78%improvement in predictive skill over the smart persistence model.Notably,our method excels during rapidly changing cloud-cover conditions.By enhancing both the accuracy and robustness of short-term PV forecasting,the framework provides tangible benefits for Virtual Power Plant(VPP)operation,supporting more reliable scheduling,grid stability,and risk-aware energy management.展开更多
Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation c...Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation can ensure the safety of photovoltaic grids and improve the utilization efficiency of the solar energy systems.In the study,a new decomposition-boosting model using artificial intelligence is proposed to realize the solar radiation multi-step prediction.The proposed model includes four parts:signal decomposition(EWT),neural network(NARX),Adaboost and ARIMA.Three real solar radiation datasets from Changde,China were used to validate the efficiency of the proposed model.To verify the robustness of the multi-step prediction model,this experiment compared nine models and made 1,3,and 5 steps ahead predictions for the time series.It is verified that the proposed model has the best performance among all models.展开更多
Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely h...Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.展开更多
Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challeng...Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.展开更多
Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weathe...Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.展开更多
Probabilistic forecasting provides insights in estimating the uncertainty of photovoltaic(PV)power forecasts.In this study,an innovative probabilistic ultra-short-term PV power forecasting framework that integrates na...Probabilistic forecasting provides insights in estimating the uncertainty of photovoltaic(PV)power forecasts.In this study,an innovative probabilistic ultra-short-term PV power forecasting framework that integrates natural gradient boosting(NGBoost)and deep neural networks is developed.Specifically,an attention-enhanced neural network combining convolutional neural networks(CNN)and bidirectional long short-term memory(BiLSTM)networks is employed for feature engineering to extract abstract features from time-series data.The extracted features are then fed into an optimized NGBoost model to yield probabilistic forecasts.In comparison to the benchmark models,i.e.,the recently reported quantile regression(QR)-based deep learning methods and NGBoost,the proposed model demonstrates an enhanced ability to capture variation patterns in PV power output,further improving the forecast skill score by approximately 15–60%in deterministic forecasting.In terms of probabilistic forecasting,the proposed model shows superior forecast reliability and sharpness compared to all benchmark methods.Its continuous ranked probability score(CRPS)ranges from 0.0710 kW to 0.0898 kW,achieving reductions of approximately 21–43%over QR-based models and 29–40%over NGBoost.Furthermore,within confidence intervals of 10–90%,the proposed model consistently maintains higher coverage probabilities along with narrower average forecast intervals,as evidenced by a lower Winkler score(WS)than the benchmark models.The findings of this study provide insightful references for probabilistic PV power forecasting research,contributing to efficient solar power management and dispatch.展开更多
Solar forecasting is of great importance for ensuring safe and stable operations of the power system with increased solar power integration,thus numerous models have been presented and reviewed to predict solar irradi...Solar forecasting is of great importance for ensuring safe and stable operations of the power system with increased solar power integration,thus numerous models have been presented and reviewed to predict solar irradiance and power forecasting in the past decade.Nevertheless,few studies take into account the temporal and spatial resolutions along with specific characteristics of the models.Therefore,this paper aims to demonstrate a comprehensive and systematic review to further solve these problems.First,five classifications and seven pre-processing methods of solar forecasting data are systematically reviewed,which are significant in improving forecasting accuracy.Then,various methods utilized in solar irradiance and power forecasting are thoroughly summarized and discussed,in which 128 algorithms are elaborated in tables in the light of input variables,temporal resolution,spatial resolution,forecast variables,metrics,and characteristics for a more fair and comprehensive comparison.Moreover,they are categorized into four groups,namely,statistical,physical,hybrid,and others with relevant application conditions and features.Meanwhile,six categories,along with 30 evaluation criteria,are summarized to clarify the major purposes/applicability of the different methods.The prominent merit of this study is that a total of seven perspectives and trends for further research in solar forecasting are identified,which aim to help readers more effectively utilize these approaches for future in-depth research.展开更多
Given the inherent fluctuation of photovoltaic(PV)generation,accurately forecasting solar power output and grid feed-in is crucial for optimizing grid operations.Data-driven methods facilitate efficient supply and dem...Given the inherent fluctuation of photovoltaic(PV)generation,accurately forecasting solar power output and grid feed-in is crucial for optimizing grid operations.Data-driven methods facilitate efficient supply and demand management in smart grids,but predicting solar power remains challenging due to weather dependence and data privacy restrictions.Traditional deep learning(DL)approaches require access to centralized training data,leading to security and privacy risks.To navigate these challenges,this study utilizes federated learning(FL)to forecast feed-in power for the low-voltage grid.We propose a bottom-up,privacy-preserving prediction method using differential privacy(DP)to enhance data privacy for energy analytics on the customer side.This study aims at proving the viability of an enhanced FL approach by employing three years of meter data from three residential PV systems installed in a southern city of Germany,incorporating irradiance weather data for accurate PV power generation predictions.For the experiments,the DL models long short-term memory(LSTM)and gated recurrent unit(GRU)are federated and integrated with DP.Consequently,federated LSTM and GRU models are compared with centralized and local baseline models using rolling 5-fold cross-validation to evaluate their respective performances.By leveraging advanced FL algorithms such as FedYogi and FedAdam,we propose a method that not only predicts sequential energy data with high accuracy,achieving an R^(2)of 97.68%,but also adheres to stringent privacy standards,offering a scalable solution for the challenges of smart grids analytics,thus clearly showing that the proposed approach is promising and worth being pursued further.展开更多
The integration of photovoltaic(PV)systems into power grids presents operational challenges due to the inherent variability in solar power generation.Accurate PV power forecasting can help address these issues by enha...The integration of photovoltaic(PV)systems into power grids presents operational challenges due to the inherent variability in solar power generation.Accurate PV power forecasting can help address these issues by enhancing grid reliability and energy management.This study introduces a novel hybrid deep learning approach that combines Wavelet Packet Decomposition(WPD)and Long Short-Term Memory(LSTM)networks to improve forecasting accuracy across multiple time horizons.The proposed model incorporates a dynamic weighting mechanism to optimally integrate the forecasts of decomposed subseries,effectively capturing both high-and low-frequency components of the power signal.Using real-world data from a solar parking site at the University of Twente,Netherlands,the proposed models are compared with standard LSTM,Linear Regression,and Persistence baselines across 15 min,1-hour,and day-ahead horizons.The WPD-LSTM model with weight optimization reduces nRMSE by up to 72.5%,52.9%,and 34.7%compared to Persistence,and by 68.6%,36.1%,and 7.5%compared to standalone LSTM,respectively.These results highlight the effectiveness of the hybrid approach in delivering more accurate and robust PV power forecasts.展开更多
Electric vehicles(EVs)are going to overrule the transportation sector due to their pollution-free technology and low running costs.However,charging the EVs causes significant power demand and stress on the power deliv...Electric vehicles(EVs)are going to overrule the transportation sector due to their pollution-free technology and low running costs.However,charging the EVs causes significant power demand and stress on the power delivery network.The challenge can be tackled well when charging and discharging scheduling are coordinated with intelligent EV routing.In this work,two-stage charging and discharging scheduling are proposed.In the first stage,a time scheduling algorithm is structured to identify EV charging/discharging slots at different hours,and at a later stage,the slots are optimally distributed among different charging stations.Routing of the EVs towards the EVCSs has been designed to enhance the useful participation of the EVs in the charging and discharging program.In this regard,a possible number of EVs in the test region has been forecasted with a regression model.The adequacy of the combined charging-discharging and location scheduling model is tested on a typical PV-enhanced 28-bus Indian distribution network.Three case studies containing three sub-cases in each have been performed incorporating the choice of the EV owners towards charging and discharging in different time slots in a day.The case studies have resulted in a peak-to-average ratio(PAR)of 1.151,0,1.165,0,1.196,8,1.165,0,1.180,9,1.196,8,1.196,8,1.196,8 and 1.196,8 for the 24-h demand pattern in Case-1a,Case-1b,Case-1c,Case-2a,Case-2b,Case-2c,Case-3a,Case-3b and Case-1c respectively in comparison to a PAR of 1.2 for the 24-h demand in base case.展开更多
Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar gen...Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar generation is determining clear-sky irradiance.Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors,but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content,which requires close proximity measurements,in time and space,to account for turbidity variability.Such measurements,though,are only available in near real-time at a limited,and decreasing,number of sites.This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data.The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance(or global irradiance driven)observations,despite an inherent dampening issue.The method is developed to operate in near real-time for solar forecasting applications.Validation examines the ability of the method to(1)reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions;and(2)provide input for clear-sky models in the form of persistence forecasts generated from daily mean values.展开更多
基金the Young Investigator Group“Artificial Intelligence for Probabilistic Weather Forecasting”funded by the Vector Stiftungfunding from the Federal Ministry of Education and Research(BMBF)and the Baden-Württemberg Ministry of Science as part of the Excellence Strategy of the German Federal and State Governments。
文摘Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.
文摘China’s recently announced directive on tackling climate change,namely,to reach carbon peak by 2030 and to achieve carbon neutrality by 2060,has led to an unprecedented nationwide response among the academia and industry.Under such a directive,a rapid increase in the grid penetration rate of solar in the near future can be fully anticipated.Although solar radiation is an atmospheric process,its utilization,as to produce electricity,has hitherto been handled by engineers.In that,it is thought important to bridge the two fields,atmospheric sciences and solar engineering,for the common good of carbon neutrality.In thisüberreview,all major aspects pertaining to solar resource assessment and forecasting are discussed in brief.Given the size of the topic at hand,instead of presenting technical details,which would be overly lengthy and repetitive,the overarching goal of this review is to comprehensively compile a catalog of some recent,and some not so recent,review papers,so that the interested readers can explore the details on their own.
文摘In the last two decades,renewable energy has been paid immeasurable attention to toward the attainment of electricity requirements for domestic,industrial,and agriculture sectors.Solar forecasting plays a vital role in smooth operation,scheduling,and balancing of electricity production by standalone PV plants as well as grid interconnected solar PV plants.Numerous models and techniques have been developed in short,mid and long-term solar forecasting.This paper analyzes some of the potential solar forecasting models based on various methodologies discussed in literature,by mainly focusing on investigating the influence of meteorological variables,time horizon,climatic zone,pre-processing techniques,air pollution,and sample size on the complexity and accuracy of the model.To make the paper reader-friendly,it presents all-important parameters and findings of the models revealed from different studies in a tabular mode having the year of publication,time resolution,input parameters,forecasted parameters,error metrics,and performance.The literature studied showed that ANN-based models outperform the others due to their nonlinear complex problem-solving capabilities.Their accuracy can be further improved by hybridization of the two models or by performing pre-processing on the input data.Besides,it also discusses the diverse key constituents that affect the accuracy of a model.It has been observed that the proper selection of training and testing period along with the correlated dependent variables also enhances the accuracy of the model.
基金supported by the National Natural Science Foundation of China(project no.42375192)supported by the National Natural Science Foundation of China(project no.42030608)+3 种基金China Meteorological Administration Climate Change Special Program(CMA-CCSPproject no.QBZ202315)supported by the National Research,Development and Innovation Fund,project no.OTKA-FK 142702the János Bolyai Research Scholarship。
文摘The fundamental scientific and engineering knowledge concerning the solar power curve,which maps solar irradiance and other auxiliary meteorological variables to photovoltaic output power,has been gathered and put forward in the preceding tutorial review.Despite the many pages of that review,it was incomplete in the sense that it did not elaborate on the applications of this very important tool of solar energy meteorology.Indeed,solar power curves are ubiquitously needed in a broad spectrum of solar forecasting and solar resource assessment tasks.Hence,this tutorial review should continue from where it left off and present examples concerning the usage of solar power curves.In a nutshell,this tutorial review,together with the preceding one,should elucidate how surface shortwave radiation data,be they ground-based,satelliteretrieved,or model-output,are bridged to various power system operations via solar power curves.
基金supported by the“Regional Innovation Strategy(RIS)”through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(MOE)(2021RIS002)the Technology Development Program(RS-2025-02312851)funded by the Ministry of SMEs and Startups(MSS,Republic of Korea).
文摘Solar forecasting using ground-based sky image offers a promising approach to reduce uncertainty in photovoltaic(PV)power generation.However,existing methods often rely on deterministic predictions that lack diversity,making it difficult to capture the inherently stochastic nature of cloud movement.To address this limitation,we propose a new two-stage probabilistic forecasting framework.In the first stage,we introduce I-GPT,a multiscale physics-constrained generative model for stochastic sky image prediction.Given a sequence of past sky images,I-GPT uses a Transformer-based VQ-VAE.It also incorporates multi-scale physics-informed recurrent units(Multi-scale PhyCell)and dynamically weighted fuses physical and appearance features.This approach enables the generation of multiple plausible future sky images with realistic and coherent cloud motion.In the second stage,these predicted sky images are fed into an Image-to-Power U-Net(IP-U-Net)to produce 15-min-ahead probabilistic PV power forecasts.In experiments using our dataset,the proposed approach significantly outperforms deterministic,other stochastic,multimodal,and smart persistence baselines models,achieving a superior reliability–sharpness trade-off.It attains a Continuous Ranked Probability Score(CRPS)of 2.912 kW and a Winkler Score(WS)of 33.103 kW on the test set and CRPS of 2.073 kW and WS of 22.202 kW on the validation set.Translating to 35.9%and 42.78%improvement in predictive skill over the smart persistence model.Notably,our method excels during rapidly changing cloud-cover conditions.By enhancing both the accuracy and robustness of short-term PV forecasting,the framework provides tangible benefits for Virtual Power Plant(VPP)operation,supporting more reliable scheduling,grid stability,and risk-aware energy management.
基金Project(2020TJ-Q06)supported by Hunan Provincial Science&Technology Talent Support,ChinaProject(KQ1707017)supported by the Changsha Science&Technology,ChinaProject(2019CX005)supported by the Innovation Driven Project of the Central South University,China。
文摘Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation can ensure the safety of photovoltaic grids and improve the utilization efficiency of the solar energy systems.In the study,a new decomposition-boosting model using artificial intelligence is proposed to realize the solar radiation multi-step prediction.The proposed model includes four parts:signal decomposition(EWT),neural network(NARX),Adaboost and ARIMA.Three real solar radiation datasets from Changde,China were used to validate the efficiency of the proposed model.To verify the robustness of the multi-step prediction model,this experiment compared nine models and made 1,3,and 5 steps ahead predictions for the time series.It is verified that the proposed model has the best performance among all models.
文摘Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.
基金supported by the National Research Foundation of Korea (NRF)grant funded by the Korean government (MSIT) (No.2019M3F2A1073179).
文摘Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.
文摘Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.
基金supported by the National Key R&D Program of China(2021YFE0107400)Innovation Fund Denmark in relation to SEM4Cities(IFD 0143–0004).
文摘Probabilistic forecasting provides insights in estimating the uncertainty of photovoltaic(PV)power forecasts.In this study,an innovative probabilistic ultra-short-term PV power forecasting framework that integrates natural gradient boosting(NGBoost)and deep neural networks is developed.Specifically,an attention-enhanced neural network combining convolutional neural networks(CNN)and bidirectional long short-term memory(BiLSTM)networks is employed for feature engineering to extract abstract features from time-series data.The extracted features are then fed into an optimized NGBoost model to yield probabilistic forecasts.In comparison to the benchmark models,i.e.,the recently reported quantile regression(QR)-based deep learning methods and NGBoost,the proposed model demonstrates an enhanced ability to capture variation patterns in PV power output,further improving the forecast skill score by approximately 15–60%in deterministic forecasting.In terms of probabilistic forecasting,the proposed model shows superior forecast reliability and sharpness compared to all benchmark methods.Its continuous ranked probability score(CRPS)ranges from 0.0710 kW to 0.0898 kW,achieving reductions of approximately 21–43%over QR-based models and 29–40%over NGBoost.Furthermore,within confidence intervals of 10–90%,the proposed model consistently maintains higher coverage probabilities along with narrower average forecast intervals,as evidenced by a lower Winkler score(WS)than the benchmark models.The findings of this study provide insightful references for probabilistic PV power forecasting research,contributing to efficient solar power management and dispatch.
基金supported by National Natural Science Foundation of China(61963020,52037003)Key Science and Technology Project of Yunnan Province(202002AF080001)Science and Technology Project of State Grid Corporation of China(Research on Demand Strategies of Multi-source Interconnected Distribution Network and Diversified Power Consumption in Energy Internet).
文摘Solar forecasting is of great importance for ensuring safe and stable operations of the power system with increased solar power integration,thus numerous models have been presented and reviewed to predict solar irradiance and power forecasting in the past decade.Nevertheless,few studies take into account the temporal and spatial resolutions along with specific characteristics of the models.Therefore,this paper aims to demonstrate a comprehensive and systematic review to further solve these problems.First,five classifications and seven pre-processing methods of solar forecasting data are systematically reviewed,which are significant in improving forecasting accuracy.Then,various methods utilized in solar irradiance and power forecasting are thoroughly summarized and discussed,in which 128 algorithms are elaborated in tables in the light of input variables,temporal resolution,spatial resolution,forecast variables,metrics,and characteristics for a more fair and comprehensive comparison.Moreover,they are categorized into four groups,namely,statistical,physical,hybrid,and others with relevant application conditions and features.Meanwhile,six categories,along with 30 evaluation criteria,are summarized to clarify the major purposes/applicability of the different methods.The prominent merit of this study is that a total of seven perspectives and trends for further research in solar forecasting are identified,which aim to help readers more effectively utilize these approaches for future in-depth research.
基金supported by the project InterBDL(Project funding indicator 01MV23025A)and Project OrPHEus(Project No.608930)The data preparation process was further supported by David Gögelein,a research associate of the Technical University of Applied Sciences at Ulm.
文摘Given the inherent fluctuation of photovoltaic(PV)generation,accurately forecasting solar power output and grid feed-in is crucial for optimizing grid operations.Data-driven methods facilitate efficient supply and demand management in smart grids,but predicting solar power remains challenging due to weather dependence and data privacy restrictions.Traditional deep learning(DL)approaches require access to centralized training data,leading to security and privacy risks.To navigate these challenges,this study utilizes federated learning(FL)to forecast feed-in power for the low-voltage grid.We propose a bottom-up,privacy-preserving prediction method using differential privacy(DP)to enhance data privacy for energy analytics on the customer side.This study aims at proving the viability of an enhanced FL approach by employing three years of meter data from three residential PV systems installed in a southern city of Germany,incorporating irradiance weather data for accurate PV power generation predictions.For the experiments,the DL models long short-term memory(LSTM)and gated recurrent unit(GRU)are federated and integrated with DP.Consequently,federated LSTM and GRU models are compared with centralized and local baseline models using rolling 5-fold cross-validation to evaluate their respective performances.By leveraging advanced FL algorithms such as FedYogi and FedAdam,we propose a method that not only predicts sequential energy data with high accuracy,achieving an R^(2)of 97.68%,but also adheres to stringent privacy standards,offering a scalable solution for the challenges of smart grids analytics,thus clearly showing that the proposed approach is promising and worth being pursued further.
文摘The integration of photovoltaic(PV)systems into power grids presents operational challenges due to the inherent variability in solar power generation.Accurate PV power forecasting can help address these issues by enhancing grid reliability and energy management.This study introduces a novel hybrid deep learning approach that combines Wavelet Packet Decomposition(WPD)and Long Short-Term Memory(LSTM)networks to improve forecasting accuracy across multiple time horizons.The proposed model incorporates a dynamic weighting mechanism to optimally integrate the forecasts of decomposed subseries,effectively capturing both high-and low-frequency components of the power signal.Using real-world data from a solar parking site at the University of Twente,Netherlands,the proposed models are compared with standard LSTM,Linear Regression,and Persistence baselines across 15 min,1-hour,and day-ahead horizons.The WPD-LSTM model with weight optimization reduces nRMSE by up to 72.5%,52.9%,and 34.7%compared to Persistence,and by 68.6%,36.1%,and 7.5%compared to standalone LSTM,respectively.These results highlight the effectiveness of the hybrid approach in delivering more accurate and robust PV power forecasts.
文摘Electric vehicles(EVs)are going to overrule the transportation sector due to their pollution-free technology and low running costs.However,charging the EVs causes significant power demand and stress on the power delivery network.The challenge can be tackled well when charging and discharging scheduling are coordinated with intelligent EV routing.In this work,two-stage charging and discharging scheduling are proposed.In the first stage,a time scheduling algorithm is structured to identify EV charging/discharging slots at different hours,and at a later stage,the slots are optimally distributed among different charging stations.Routing of the EVs towards the EVCSs has been designed to enhance the useful participation of the EVs in the charging and discharging program.In this regard,a possible number of EVs in the test region has been forecasted with a regression model.The adequacy of the combined charging-discharging and location scheduling model is tested on a typical PV-enhanced 28-bus Indian distribution network.Three case studies containing three sub-cases in each have been performed incorporating the choice of the EV owners towards charging and discharging in different time slots in a day.The case studies have resulted in a peak-to-average ratio(PAR)of 1.151,0,1.165,0,1.196,8,1.165,0,1.180,9,1.196,8,1.196,8,1.196,8 and 1.196,8 for the 24-h demand pattern in Case-1a,Case-1b,Case-1c,Case-2a,Case-2b,Case-2c,Case-3a,Case-3b and Case-1c respectively in comparison to a PAR of 1.2 for the 24-h demand in base case.
基金This work was funded by the Office of Naval Research(ONR),United States under the Asia Pacific Research Initiative for Sustainable Energy Systems(APRISES)project,Grant Award Number N00014-16-1-2116by the U.S.Department of Energy,United States under the U.S.-India collAborative for smart diStribution System wIth STorage(UI-ASSIST)project,Award Number DE-IA0000025.
文摘Photovoltaic technologies provide significant capacity to electric grids,however,resource variability and production uncertainty complicate power balancing and reserve management.A crucial step in predicting solar generation is determining clear-sky irradiance.Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors,but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content,which requires close proximity measurements,in time and space,to account for turbidity variability.Such measurements,though,are only available in near real-time at a limited,and decreasing,number of sites.This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data.The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance(or global irradiance driven)observations,despite an inherent dampening issue.The method is developed to operate in near real-time for solar forecasting applications.Validation examines the ability of the method to(1)reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions;and(2)provide input for clear-sky models in the form of persistence forecasts generated from daily mean values.
