The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary se...The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary services beyond consumers of electricity.However,EVs are gradually considered as nonnegligible loads due to their increasing penetration,which may result in negative effects such as voltage deviations,lines saturation,and power losses.Relationship and interaction among EVs,charging stations,and micro grid have to be considered in the next generation of smart grid.Therefore,the topic of smart charging has been the focus of many works where a wide range of control methods have been developed.As one of the bases of simulation,the EV charging behavior and characteristics have also become the focus of many studies.In this work,we review the charging behavior of EVs from the aspects of data,model,and control.We provide the links for most of the data sets reviewed in this work,based on which interested researchers can easily access these data for further investigation.展开更多
Electric Vehicles(EVs)have emerged as a cleaner,low-carbon,and environmentally friendly alternative to traditional internal combustion engine(ICE)vehicles.With the increasing adoption of EVs,they are expected to event...Electric Vehicles(EVs)have emerged as a cleaner,low-carbon,and environmentally friendly alternative to traditional internal combustion engine(ICE)vehicles.With the increasing adoption of EVs,they are expected to eventually replace ICE vehicles entirely.However,the rapid growth of EVs has significantly increased energy demand,posing challenges for power grids and infrastructure.This surge in energy demand has driven advancements in developing efficient charging infrastructure and energy management solutions to mitigate the risks of power outages and disruptions caused by the rising number of EVs on the road.To address these challenges,various deep learning(DL)models,such as Recurrent Neural Networks(RNNs)and Long Short-Term Memory(LSTM)networks,have been employed for predicting energy demand at EV charging stations(EVCS).However,these models face certain limitations.They often lack interpretability,treating all input steps equally without assigning greater importance to critical patterns that are more relevant for prediction.Additionally,these models process data sequentially,which makes them computationally slower and less efficient when dealing with large datasets.In the context of these limitations,this paper introduces a novel Attention-Augmented Long Short-Term Memory(AA-LSTM)model.The proposed model integrates an attention mechanism to focus on the most relevant time steps,thereby enhancing its ability to capture long-term dependencies and improve prediction accuracy.By combining the strengths of LSTM networks in handling sequential data with the interpretability and efficiency of the attention mechanism,the AA-LSTM model delivers superior performance.The attention mechanism selectively prioritizes critical parts of the input sequence,reducing the computational burden and making the model faster and more effective.The AA-LSTM model achieves impressive results,demonstrating a Mean Absolute Percentage Error(MAPE)of 3.90%and a Mean Squared Error(MSE)of 0.40,highlighting its accuracy and reliability.These results suggest that the AA-LSTM model is a highly promising solution for predicting energy demand at EVCS,offering improved performance and efficiency compared to contemporary approaches.展开更多
Accurate and reliable power system data are fundamental for critical operations such as gridmonitoring,fault diagnosis,and load forecasting,underpinned by increasing intelligentization and digitalization.However,data ...Accurate and reliable power system data are fundamental for critical operations such as gridmonitoring,fault diagnosis,and load forecasting,underpinned by increasing intelligentization and digitalization.However,data loss and anomalies frequently compromise data integrity in practical settings,significantly impacting system operational efficiency and security.Most existing data recovery methods require complete datasets for training,leading to substantial data and computational demands and limited generalization.To address these limitations,this study proposes a missing data imputation model based on an improved Generative Adversarial Network(BAC-GAN).Within the BAC-GAN framework,the generator utilizes Bidirectional Long Short-Term Memory(BiLSTM)networks and Multi-Head Attention mechanisms to capture temporal dependencies and complex relationships within power system data.The discriminator employs a Convolutional Neural Network(CNN)architecture to integrate local features with global structures,effectivelymitigating the generation of implausible imputations.Experimental results on two public datasets demonstrate that the BAC-GAN model achieves superior data recovery accuracy compared to five state-of-the-art and classical benchmarkmethods,with an average improvement of 17.7%in reconstruction accuracy.The proposedmethod significantly enhances the accuracy of grid fault diagnosis and provides reliable data support for the stable operation of smart grids,showing great potential for practical applications in power systems.展开更多
Data loss or distortion causes adverse effects on the accuracy and stability of the thunderstorm point charge localization.To solve this problem,we propose a data complementary method based on the atmospheric electric...Data loss or distortion causes adverse effects on the accuracy and stability of the thunderstorm point charge localization.To solve this problem,we propose a data complementary method based on the atmospheric electric field apparatus array group.The electric field component measurement model of the atmospheric electric field apparatus is established,and the orientation parameters of the thunderstorm point charge are defined.Based on the mirror method,the thunderstorm point charge coordinates are obtained by using the potential distribution formulas.To test the validity of the basic algorithm,the electric field component measurement error and the localization accuracy are studied.Besides the azimuth angle and the elevation angle,the localization parameters also include the distance from the apparatus to the thunderstorm cloud.Based on a primary electric field apparatus,we establish the array group of apparatuses.Based on this,the data measured by each apparatus is complementarily processed to regain the thunderstorm point charge position.The results show that,compared with the radar map data,this method can accurately reflect the location of the thunderstorm point charge,and has a better localization effect.Additionally,several observation results during thunderstorm weather have been presented.展开更多
Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series da...Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series data, focusing on shorttime stocks prediction. This is an area that has been attracting a great deal of attention from researchers in the field. The main contribution of this paper is to provide an outline of the use of DM with time series data, using mainly examples related with short-term stocks prediction. This is important to a better understanding of the field. Some of the main trends and open issues will also be introduced.展开更多
A K-nearest neighbor （K-NN） based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways,...A K-nearest neighbor （K-NN） based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data （FCD） system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective.展开更多
This paper explores the movement of connected vehicles in Indiana for vehicles classified by the NHTSA Product Information Catalog Vehicle listing as being either electric (EV) or hybrid electric (HV). Analysis of tra...This paper explores the movement of connected vehicles in Indiana for vehicles classified by the NHTSA Product Information Catalog Vehicle listing as being either electric (EV) or hybrid electric (HV). Analysis of trajectories from July 12-18, 2021 for the state of Indiana observed nearly 33,300 trips and 267,000 vehicle miles travelled (VMT) for the combination of EV and HV. Approximately 53% of the VMT occurred in just 10 counties. For just EVs, there were 9814 unique trips and 64,700 Electric Vehicle Miles Traveled (EVMTs) in total. A further categorization of this revealed that 18% of these EVMTs were on Interstate roadways and 82% on non-interstate roads. <span style="font-family:Verdana;"> </span><span style="font-family:Verdana;">Proximity analysis of existing DC Fast charging stations in relation to interstate roadways revealed multiple charging deserts that would be most benefited by additional charging capacity. Eleven roadway sections among the 9 interstates were found to have a gap in available DC fast chargers of 50 miles or more. Although the connected vehicle data set analyzed did not include all EV’s the methodology presented in this paper provides a technique that can be scaled as additional EV connected vehicle data becomes available to agencies. Furthermore, it emphasizes the need for transportation agencies and automotive vendors to strengthen their data sharing partnerships to help accelerate </span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">adoption of EV and reduce consumer range anxiety with EV. Graphics are included that illustrate examples of counties that are both overserved and underserved by charging infrastructure.</span>展开更多
Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available f...Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available from real-world systems.To address this issue, Prof.展开更多
In order to address the widespread data shortage problem in battery research,this paper proposes a generative adversarial network model that combines it with deep convolutional networks,the Wasserstein distance,and th...In order to address the widespread data shortage problem in battery research,this paper proposes a generative adversarial network model that combines it with deep convolutional networks,the Wasserstein distance,and the gradient penalty to achieve data augmentation.To lower the threshold for implementing the proposed method,transfer learning is further introduced.The W-DC-GAN-GP-TL framework is thereby formed.This framework is evaluated on 3 different publicly available datasets to judge the quality of generated data.Through visual comparisons and the examination of two visualization methods(probability density function(PDF)and principal component analysis(PCA)),it is demonstrated that the generated data is hard to distinguish from the real data.The application of generated data for training a battery state model using transfer learning is further evaluated.Specifically,Bi-GRU-based and Transformer-based methods are implemented on 2 separate datasets for estimating state of health(SOH)and state of charge(SOC),respectively.The results indicate that the proposed framework demonstrates satisfactory performance in different scenarios:for the data replacement scenario,where real data are removed and replaced with generated data,the state estimator accuracy decreases only slightly;for the data enhancement scenario,the estimator accuracy is further improved.The estimation accuracy of SOH and SOC is as low as 0.69%and 0.58%root mean square error(RMSE)after applying the proposed framework.This framework provides a reliable method for enriching battery measurement data.It is a generalized framework capable of generating a variety of time series data.展开更多
Although digital changes in power systems have added more ways to monitor and control them,these changes have also led to new cyber-attack risks,mainly from False Data Injection(FDI)attacks.If this happens,the sensors...Although digital changes in power systems have added more ways to monitor and control them,these changes have also led to new cyber-attack risks,mainly from False Data Injection(FDI)attacks.If this happens,the sensors and operations are compromised,which can lead to big problems,disruptions,failures and blackouts.In response to this challenge,this paper presents a reliable and innovative detection framework that leverages Bidirectional Long Short-Term Memory(Bi-LSTM)networks and employs explanatory methods from Artificial Intelligence(AI).Not only does the suggested architecture detect potential fraud with high accuracy,but it also makes its decisions transparent,enabling operators to take appropriate action.Themethod developed here utilizesmodel-free,interpretable tools to identify essential input elements,thereby making predictions more understandable and usable.Enhancing detection performance is made possible by correcting class imbalance using Synthetic Minority Over-sampling Technique(SMOTE)-based data balancing.Benchmark power system data confirms that the model functions correctly through detailed experiments.Experimental results showed that Bi-LSTM+Explainable AI(XAI)achieved an average accuracy of 94%,surpassing XGBoost(89%)and Bagging(84%),while ensuring explainability and a high level of robustness across various operating scenarios.By conducting an ablation study,we find that bidirectional recursive modeling and ReLU activation help improve generalization and model predictability.Additionally,examining model decisions through LIME enables us to identify which features are crucial for making smart grid operational decisions in real time.The research offers a practical and flexible approach for detecting FDI attacks,improving the security of cyber-physical systems,and facilitating the deployment of AI in energy infrastructure.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
A high integrated monolithic IC, with functions of clock recovery, data decision, and 1 ： 4 demultiplexer,is implemented in 0.25μm CMOS process for 2.5Gb/s fiber-optic communications. The recovered and frequency div...A high integrated monolithic IC, with functions of clock recovery, data decision, and 1 ： 4 demultiplexer,is implemented in 0.25μm CMOS process for 2.5Gb/s fiber-optic communications. The recovered and frequency divided 625MHz clock has a phase noise of -106.26dBc/Hz at 100kHz offset in response to a 2.5Gb/s PRBS input data （2^31-1）. The 2.5Gb/s PRBS data are demultiplexed to four 625Mb/s data. The 0.97mm× 0.97mm IC consumes 550mW under a single 3.3V power supply （not including output buffers）.展开更多
针对目前电池荷电状态(stage of charge,SOC)估计算法存在稳定性差、误差大等缺点,提出一种基于实车云端放电数据的自适应扩展卡尔曼滤波(adaptive extended Kalman filter,AEKF)与长短时记忆(long short term memory,LSTM)融合的算法,...针对目前电池荷电状态(stage of charge,SOC)估计算法存在稳定性差、误差大等缺点,提出一种基于实车云端放电数据的自适应扩展卡尔曼滤波(adaptive extended Kalman filter,AEKF)与长短时记忆(long short term memory,LSTM)融合的算法,预测小动力电动车的电池SOC。首先采用自适应遗忘因子最小二乘法(adaptive forgetting factor recursive least squares,AFFRLS)辨识电池的二阶RC等效电路模型参数。其次,将云端实时采集到的放电数据作为研究目标,通过AEKF-LSTM融合算法对小动力电动车的电池SOC进行预测实验,实验过程中AEKF-LSTM融合算法将当前时刻的端电压、电流、温度以及上一时刻电池的SOC作为输入,以更新的SOC作为输出训练估计模型。最后,将AEKF-LSTM融合算法和单一AEKF算法预测电池SOC的结果与实际SOC值进行比较,实验结果表明,AEKF-LSTM融合算法的均方根误差(root mean square error,RMSE)为0.0058 V,平均绝对误差(mean absolute error,MAE)为0.0041 V,比AEKF算法的RMSE减小0.0087 V,MAE减小0.1164 V,且AEKF-LSTM融合算法的RMSE和MAE均在0.6%以内,证明了该融合算法有较高的估计精度和较强的鲁棒性。展开更多
The development of high-performance liquid electrolytes is pivotal for advancing rechargeable lithium batteries,which are central to global electrification and renewable energy integration.Conventional electrolyte des...The development of high-performance liquid electrolytes is pivotal for advancing rechargeable lithium batteries,which are central to global electrification and renewable energy integration.Conventional electrolyte design,heavily reliant on empirical trial-and-error approaches,faces significant challenges in simultaneously optimizing a complex set of properties,including ionic conductivity,electrochemical stability window,thermal resilience,and most critically,compatibility with electrode interfaces.The efficiency of charge transfer processes and the stability of interphases formed on electrode surfaces,such as the solid electrolyte interphase(SEI)and cathode electrolyte interphase(CEI),are fundamentally governed by electrolyte composition.The nonlinear dependencies among these properties and the vast,unexplored chemical space render traditional methods inefficient.Emerging data-driven strategies represent a paradigm shift,leveraging artificial intelligence(AI)and machine learning(ML)to accelerate the discovery and rational design of next-generation electrolytes.This review comprehensively surveys recent progress in this rapidly evolving field.We begin by systematically outlining the fundamental properties of liquid electrolytes and establishing advanced descriptors for quantifying ion-solvent and ion-anion interactions.The core AI workflow encompassing data acquisition from diverse sources,feature engineering,and the application of various models from supervised learning to generative AI is critically examined.We then showcase the transformative applications of data-driven methodologies,including performance-targeted electrolyte formulation for extreme conditions,prediction of interfacial reaction pathways and SEI/CEI evolution mechanisms,and the development of novel AI algorithms and integrated computational platforms for end-to-end discovery.Despite promising advances,challenges remain,such as data scarcity and standardization,limited model generalizability,and the difficulty of multi-objective optimization balancing performance,safety,and sustainability.By synthesizing these developments and outlining a clear research trajectory,this review aims to provide novel perspectives and inspire continued innovation in the design of high-performance,safe,and sustainable electrolytes,ultimately enabling more reliable and powerful rechargeable lithium batteries for a clean energy future.展开更多
Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous...Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous.Considering the challenge mentioned,this article proposes a clustering-based machine learning(ML)framework to enhance the stability of EPS networks by suppressing LFOs through real-time tuning of key power system stabilizer(PSS)parameters.To validate the proposed strategy,two distinct EPS networks are selected:the single-machine infinite-bus(SMIB)with a single-stage PSS and the unified power flow controller(UPFC)coordinated SMIB with a double-stage PSS.To generate data under various loading conditions for both networks,an efficient but offline meta-heuristic algorithm,namely the grey wolf optimizer(GWO),is used,with the loading conditions as inputs and the key PSS parameters as outputs.The generated loading conditions are then clustered using the fuzzy k-means(FKM)clustering method.Finally,the group method of data handling(GMDH)and long short-term memory(LSTM)ML models are developed for clustered data to predict PSS key parameters in real time for any loading condition.A few well-known statistical performance indices(SPI)are considered for validation and robustness of the training and testing procedure of the developed FKM-GMDH and FKM-LSTM models based on the prediction of PSS parameters.The performance of the ML models is also evaluated using three stability indices(i.e.,minimum damping ratio,eigenvalues,and time-domain simulations)after optimally tuned PSS with real-time estimated parameters under changing operating conditions.Besides,the outputs of the offline(GWO-based)metaheuristic model,proposed real-time(FKM-GMDH and FKM-LSTM)machine learning models,and previously reported literature models are compared.According to the results,the proposed methodology outperforms the others in enhancing the stability of the selected EPS networks by damping out the observed unwanted LFOs under various loading conditions.展开更多
基金This work was supported in part by the National Key Research and Development Program of China(No.2016YFB0901900)the National Natural Science Foundation of China under grants(No.61673229)the 111 International Collaboration Project of China(No.BP2018006).
文摘The adoption and usage of electric vehicles(EVs)have emerged recently due to the increasing concerns on the greenhouse gas issues and energy revolution.As a part of the smart grid,EVs can provide valuable ancillary services beyond consumers of electricity.However,EVs are gradually considered as nonnegligible loads due to their increasing penetration,which may result in negative effects such as voltage deviations,lines saturation,and power losses.Relationship and interaction among EVs,charging stations,and micro grid have to be considered in the next generation of smart grid.Therefore,the topic of smart charging has been the focus of many works where a wide range of control methods have been developed.As one of the bases of simulation,the EV charging behavior and characteristics have also become the focus of many studies.In this work,we review the charging behavior of EVs from the aspects of data,model,and control.We provide the links for most of the data sets reviewed in this work,based on which interested researchers can easily access these data for further investigation.
基金supported by the SC&SS,Jawaharlal Nehru University,New Delhi,India.
文摘Electric Vehicles(EVs)have emerged as a cleaner,low-carbon,and environmentally friendly alternative to traditional internal combustion engine(ICE)vehicles.With the increasing adoption of EVs,they are expected to eventually replace ICE vehicles entirely.However,the rapid growth of EVs has significantly increased energy demand,posing challenges for power grids and infrastructure.This surge in energy demand has driven advancements in developing efficient charging infrastructure and energy management solutions to mitigate the risks of power outages and disruptions caused by the rising number of EVs on the road.To address these challenges,various deep learning(DL)models,such as Recurrent Neural Networks(RNNs)and Long Short-Term Memory(LSTM)networks,have been employed for predicting energy demand at EV charging stations(EVCS).However,these models face certain limitations.They often lack interpretability,treating all input steps equally without assigning greater importance to critical patterns that are more relevant for prediction.Additionally,these models process data sequentially,which makes them computationally slower and less efficient when dealing with large datasets.In the context of these limitations,this paper introduces a novel Attention-Augmented Long Short-Term Memory(AA-LSTM)model.The proposed model integrates an attention mechanism to focus on the most relevant time steps,thereby enhancing its ability to capture long-term dependencies and improve prediction accuracy.By combining the strengths of LSTM networks in handling sequential data with the interpretability and efficiency of the attention mechanism,the AA-LSTM model delivers superior performance.The attention mechanism selectively prioritizes critical parts of the input sequence,reducing the computational burden and making the model faster and more effective.The AA-LSTM model achieves impressive results,demonstrating a Mean Absolute Percentage Error(MAPE)of 3.90%and a Mean Squared Error(MSE)of 0.40,highlighting its accuracy and reliability.These results suggest that the AA-LSTM model is a highly promising solution for predicting energy demand at EVCS,offering improved performance and efficiency compared to contemporary approaches.
基金supported by the National Natural Science Foundation of China(No.51977113)the Science and Technology Project of State Grid Zhejiang Electric Power Co.,Ltd.(No.5211JX240001).
文摘Accurate and reliable power system data are fundamental for critical operations such as gridmonitoring,fault diagnosis,and load forecasting,underpinned by increasing intelligentization and digitalization.However,data loss and anomalies frequently compromise data integrity in practical settings,significantly impacting system operational efficiency and security.Most existing data recovery methods require complete datasets for training,leading to substantial data and computational demands and limited generalization.To address these limitations,this study proposes a missing data imputation model based on an improved Generative Adversarial Network(BAC-GAN).Within the BAC-GAN framework,the generator utilizes Bidirectional Long Short-Term Memory(BiLSTM)networks and Multi-Head Attention mechanisms to capture temporal dependencies and complex relationships within power system data.The discriminator employs a Convolutional Neural Network(CNN)architecture to integrate local features with global structures,effectivelymitigating the generation of implausible imputations.Experimental results on two public datasets demonstrate that the BAC-GAN model achieves superior data recovery accuracy compared to five state-of-the-art and classical benchmarkmethods,with an average improvement of 17.7%in reconstruction accuracy.The proposedmethod significantly enhances the accuracy of grid fault diagnosis and provides reliable data support for the stable operation of smart grids,showing great potential for practical applications in power systems.
基金This work is supported by the National Key Research and Development Program of China(Grant No.2021YFE0105500)the National Natural Science Foundation of China(Grant No.61671248)+2 种基金the Key Research and Development Plan of Jiangsu Province,China(Grant No.BE2018719)Postgraduate Research and Practice Innovation Program of Jiangsu Province(Grant No.SJCX19_0309)the Advantage Discipline Information and Communication Engineering of Jiangsu Province,China.
文摘Data loss or distortion causes adverse effects on the accuracy and stability of the thunderstorm point charge localization.To solve this problem,we propose a data complementary method based on the atmospheric electric field apparatus array group.The electric field component measurement model of the atmospheric electric field apparatus is established,and the orientation parameters of the thunderstorm point charge are defined.Based on the mirror method,the thunderstorm point charge coordinates are obtained by using the potential distribution formulas.To test the validity of the basic algorithm,the electric field component measurement error and the localization accuracy are studied.Besides the azimuth angle and the elevation angle,the localization parameters also include the distance from the apparatus to the thunderstorm cloud.Based on a primary electric field apparatus,we establish the array group of apparatuses.Based on this,the data measured by each apparatus is complementarily processed to regain the thunderstorm point charge position.The results show that,compared with the radar map data,this method can accurately reflect the location of the thunderstorm point charge,and has a better localization effect.Additionally,several observation results during thunderstorm weather have been presented.
文摘Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series data, focusing on shorttime stocks prediction. This is an area that has been attracting a great deal of attention from researchers in the field. The main contribution of this paper is to provide an outline of the use of DM with time series data, using mainly examples related with short-term stocks prediction. This is important to a better understanding of the field. Some of the main trends and open issues will also be introduced.
基金The Project of Research on Technologyand Devices for Traffic Guidance (Vehicle Navigation)System of Beijing Municipal Commission of Science and Technology(No H030630340320)the Project of Research on theIntelligence Traffic Information Platform of Beijing Education Committee
文摘A K-nearest neighbor （K-NN） based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data （FCD） system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective.
文摘This paper explores the movement of connected vehicles in Indiana for vehicles classified by the NHTSA Product Information Catalog Vehicle listing as being either electric (EV) or hybrid electric (HV). Analysis of trajectories from July 12-18, 2021 for the state of Indiana observed nearly 33,300 trips and 267,000 vehicle miles travelled (VMT) for the combination of EV and HV. Approximately 53% of the VMT occurred in just 10 counties. For just EVs, there were 9814 unique trips and 64,700 Electric Vehicle Miles Traveled (EVMTs) in total. A further categorization of this revealed that 18% of these EVMTs were on Interstate roadways and 82% on non-interstate roads. <span style="font-family:Verdana;"> </span><span style="font-family:Verdana;">Proximity analysis of existing DC Fast charging stations in relation to interstate roadways revealed multiple charging deserts that would be most benefited by additional charging capacity. Eleven roadway sections among the 9 interstates were found to have a gap in available DC fast chargers of 50 miles or more. Although the connected vehicle data set analyzed did not include all EV’s the methodology presented in this paper provides a technique that can be scaled as additional EV connected vehicle data becomes available to agencies. Furthermore, it emphasizes the need for transportation agencies and automotive vendors to strengthen their data sharing partnerships to help accelerate </span><span style="font-family:Verdana;">the </span><span style="font-family:Verdana;">adoption of EV and reduce consumer range anxiety with EV. Graphics are included that illustrate examples of counties that are both overserved and underserved by charging infrastructure.</span>
基金supported by the grants from CASthe National Key R&D Program of Chinathe National Natural Science Foundation of China
文摘Making accurate forecast or prediction is a challenging task in the big data era, in particular for those datasets involving high-dimensional variables but short-term time series points,which are generally available from real-world systems.To address this issue, Prof.
基金funded by the Bavarian State Ministry of Science,Research and Art(Grant number:H.2-F1116.WE/52/2)。
文摘In order to address the widespread data shortage problem in battery research,this paper proposes a generative adversarial network model that combines it with deep convolutional networks,the Wasserstein distance,and the gradient penalty to achieve data augmentation.To lower the threshold for implementing the proposed method,transfer learning is further introduced.The W-DC-GAN-GP-TL framework is thereby formed.This framework is evaluated on 3 different publicly available datasets to judge the quality of generated data.Through visual comparisons and the examination of two visualization methods(probability density function(PDF)and principal component analysis(PCA)),it is demonstrated that the generated data is hard to distinguish from the real data.The application of generated data for training a battery state model using transfer learning is further evaluated.Specifically,Bi-GRU-based and Transformer-based methods are implemented on 2 separate datasets for estimating state of health(SOH)and state of charge(SOC),respectively.The results indicate that the proposed framework demonstrates satisfactory performance in different scenarios:for the data replacement scenario,where real data are removed and replaced with generated data,the state estimator accuracy decreases only slightly;for the data enhancement scenario,the estimator accuracy is further improved.The estimation accuracy of SOH and SOC is as low as 0.69%and 0.58%root mean square error(RMSE)after applying the proposed framework.This framework provides a reliable method for enriching battery measurement data.It is a generalized framework capable of generating a variety of time series data.
基金the Deanship of Scientific Research and Libraries in Princess Nourah bint Abdulrahman University for funding this research work through the Research Group project,Grant No.(RG-1445-0064).
文摘Although digital changes in power systems have added more ways to monitor and control them,these changes have also led to new cyber-attack risks,mainly from False Data Injection(FDI)attacks.If this happens,the sensors and operations are compromised,which can lead to big problems,disruptions,failures and blackouts.In response to this challenge,this paper presents a reliable and innovative detection framework that leverages Bidirectional Long Short-Term Memory(Bi-LSTM)networks and employs explanatory methods from Artificial Intelligence(AI).Not only does the suggested architecture detect potential fraud with high accuracy,but it also makes its decisions transparent,enabling operators to take appropriate action.Themethod developed here utilizesmodel-free,interpretable tools to identify essential input elements,thereby making predictions more understandable and usable.Enhancing detection performance is made possible by correcting class imbalance using Synthetic Minority Over-sampling Technique(SMOTE)-based data balancing.Benchmark power system data confirms that the model functions correctly through detailed experiments.Experimental results showed that Bi-LSTM+Explainable AI(XAI)achieved an average accuracy of 94%,surpassing XGBoost(89%)and Bagging(84%),while ensuring explainability and a high level of robustness across various operating scenarios.By conducting an ablation study,we find that bidirectional recursive modeling and ReLU activation help improve generalization and model predictability.Additionally,examining model decisions through LIME enables us to identify which features are crucial for making smart grid operational decisions in real time.The research offers a practical and flexible approach for detecting FDI attacks,improving the security of cyber-physical systems,and facilitating the deployment of AI in energy infrastructure.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
文摘A high integrated monolithic IC, with functions of clock recovery, data decision, and 1 ： 4 demultiplexer,is implemented in 0.25μm CMOS process for 2.5Gb/s fiber-optic communications. The recovered and frequency divided 625MHz clock has a phase noise of -106.26dBc/Hz at 100kHz offset in response to a 2.5Gb/s PRBS input data （2^31-1）. The 2.5Gb/s PRBS data are demultiplexed to four 625Mb/s data. The 0.97mm× 0.97mm IC consumes 550mW under a single 3.3V power supply （not including output buffers）.
文摘针对目前电池荷电状态(stage of charge,SOC)估计算法存在稳定性差、误差大等缺点,提出一种基于实车云端放电数据的自适应扩展卡尔曼滤波(adaptive extended Kalman filter,AEKF)与长短时记忆(long short term memory,LSTM)融合的算法,预测小动力电动车的电池SOC。首先采用自适应遗忘因子最小二乘法(adaptive forgetting factor recursive least squares,AFFRLS)辨识电池的二阶RC等效电路模型参数。其次,将云端实时采集到的放电数据作为研究目标,通过AEKF-LSTM融合算法对小动力电动车的电池SOC进行预测实验,实验过程中AEKF-LSTM融合算法将当前时刻的端电压、电流、温度以及上一时刻电池的SOC作为输入,以更新的SOC作为输出训练估计模型。最后,将AEKF-LSTM融合算法和单一AEKF算法预测电池SOC的结果与实际SOC值进行比较,实验结果表明,AEKF-LSTM融合算法的均方根误差(root mean square error,RMSE)为0.0058 V,平均绝对误差(mean absolute error,MAE)为0.0041 V,比AEKF算法的RMSE减小0.0087 V,MAE减小0.1164 V,且AEKF-LSTM融合算法的RMSE和MAE均在0.6%以内,证明了该融合算法有较高的估计精度和较强的鲁棒性。
基金support from the National Natural Science Foundation of China(No.52402052)The Hong Kong Polytechnic University(U-CDCA)+1 种基金Natural Science Foundation of Guangdong(No.2025A1515011149)Innovation and Technology Fund(ITS-322-23FP).
文摘The development of high-performance liquid electrolytes is pivotal for advancing rechargeable lithium batteries,which are central to global electrification and renewable energy integration.Conventional electrolyte design,heavily reliant on empirical trial-and-error approaches,faces significant challenges in simultaneously optimizing a complex set of properties,including ionic conductivity,electrochemical stability window,thermal resilience,and most critically,compatibility with electrode interfaces.The efficiency of charge transfer processes and the stability of interphases formed on electrode surfaces,such as the solid electrolyte interphase(SEI)and cathode electrolyte interphase(CEI),are fundamentally governed by electrolyte composition.The nonlinear dependencies among these properties and the vast,unexplored chemical space render traditional methods inefficient.Emerging data-driven strategies represent a paradigm shift,leveraging artificial intelligence(AI)and machine learning(ML)to accelerate the discovery and rational design of next-generation electrolytes.This review comprehensively surveys recent progress in this rapidly evolving field.We begin by systematically outlining the fundamental properties of liquid electrolytes and establishing advanced descriptors for quantifying ion-solvent and ion-anion interactions.The core AI workflow encompassing data acquisition from diverse sources,feature engineering,and the application of various models from supervised learning to generative AI is critically examined.We then showcase the transformative applications of data-driven methodologies,including performance-targeted electrolyte formulation for extreme conditions,prediction of interfacial reaction pathways and SEI/CEI evolution mechanisms,and the development of novel AI algorithms and integrated computational platforms for end-to-end discovery.Despite promising advances,challenges remain,such as data scarcity and standardization,limited model generalizability,and the difficulty of multi-objective optimization balancing performance,safety,and sustainability.By synthesizing these developments and outlining a clear research trajectory,this review aims to provide novel perspectives and inspire continued innovation in the design of high-performance,safe,and sustainable electrolytes,ultimately enabling more reliable and powerful rechargeable lithium batteries for a clean energy future.
基金supported by the Deanship of Research at the King Fahd University of Petroleum&Minerals,Dhahran,31261,Saudi Arabia,under Project No.EC241001.
文摘Various factors,including weak tie-lines into the electric power system(EPS)networks,can lead to low-frequency oscillations(LFOs),which are considered an instant,non-threatening situation,but slow-acting and poisonous.Considering the challenge mentioned,this article proposes a clustering-based machine learning(ML)framework to enhance the stability of EPS networks by suppressing LFOs through real-time tuning of key power system stabilizer(PSS)parameters.To validate the proposed strategy,two distinct EPS networks are selected:the single-machine infinite-bus(SMIB)with a single-stage PSS and the unified power flow controller(UPFC)coordinated SMIB with a double-stage PSS.To generate data under various loading conditions for both networks,an efficient but offline meta-heuristic algorithm,namely the grey wolf optimizer(GWO),is used,with the loading conditions as inputs and the key PSS parameters as outputs.The generated loading conditions are then clustered using the fuzzy k-means(FKM)clustering method.Finally,the group method of data handling(GMDH)and long short-term memory(LSTM)ML models are developed for clustered data to predict PSS key parameters in real time for any loading condition.A few well-known statistical performance indices(SPI)are considered for validation and robustness of the training and testing procedure of the developed FKM-GMDH and FKM-LSTM models based on the prediction of PSS parameters.The performance of the ML models is also evaluated using three stability indices(i.e.,minimum damping ratio,eigenvalues,and time-domain simulations)after optimally tuned PSS with real-time estimated parameters under changing operating conditions.Besides,the outputs of the offline(GWO-based)metaheuristic model,proposed real-time(FKM-GMDH and FKM-LSTM)machine learning models,and previously reported literature models are compared.According to the results,the proposed methodology outperforms the others in enhancing the stability of the selected EPS networks by damping out the observed unwanted LFOs under various loading conditions.
