Regional photovoltaic(PV) power prediction plays an important role in power system planning and operation. To effectively improve the performance of prediction intervals(PIs) for very short-term regional PV outputs, a...Regional photovoltaic(PV) power prediction plays an important role in power system planning and operation. To effectively improve the performance of prediction intervals(PIs) for very short-term regional PV outputs, an efficient nonparametric probabilistic prediction method based on granulebased clustering(GC) and direct optimization programming(DOP) is proposed. First, GC is proposed to formulate and cluster the sample granules consisting of numerical weather prediction(NWP) and historical regional output data, for the enhanced hierarchical clustering performance. Then, to improve the accuracy of samples' utilization, an unbalanced extension is used to reconstruct the training samples consisting of power time series. After that, DOP is applied to quantify the output weights based on the optimal overall performance. Meanwhile, a balance coefficient is studied for the enhanced reliability of PIs. Finally, the proposed method is validated through multistep PIs based on the numerical comparison of real PV generation data.展开更多
To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger f...To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger flows.First,bus and metro data are processed and matched by association to construct the basis for public transport trip chain extraction.Second,a reasonable matching threshold method to discriminate the transfer relationship is used to extract the public transport trip chain,and the basic characteristics of the trip based on the trip chain are analyzed to obtain the metro-to-bus transfer passenger flow.Third,to address the problem of low accuracy of point prediction,the DeepAR model is proposed to conduct interval prediction,where the input is the interchange passenger flow,the output is the predicted median and interval of passenger flow,and the prediction scenarios are weekday,non-workday,and weekday morning and evening peaks.Fourth,to reduce the prediction error,a combined particle swarm optimization(PSO)-DeepAR model is constructed using the PSO to optimize the DeepAR model.Finally,data from the Beijing Xizhimen subway station are used for validation,and results show that the PSO-DeepAR model has high prediction accuracy,with a 90%confidence interval coverage of up to 93.6%.展开更多
Ensemble forecasting systems have become an important tool for estimating the uncertainties in initial conditions and model formulations and they are receiving increased attention from various applications.The Regiona...Ensemble forecasting systems have become an important tool for estimating the uncertainties in initial conditions and model formulations and they are receiving increased attention from various applications.The Regional Ensemble Prediction System(REPS),which has operated at the Beijing Meteorological Service(BMS)since 2017,allows for probabilistic forecasts.However,it still suffers from systematic deficiencies during the first couple of forecast hours.This paper presents an integrated probabilistic nowcasting ensemble prediction system(NEPS)that is constructed by applying a mixed dynamicintegrated method.It essentially combines the uncertainty information(i.e.,ensemble variance)provided by the REPS with the nowcasting method provided by the rapid-refresh deterministic nowcasting prediction system(NPS)that has operated at the Beijing Meteorological Service(BMS)since 2019.The NEPS provides hourly updated analyses and probabilistic forecasts in the nowcasting and short range(0-6 h)with a spatial grid spacing of 500 m.It covers the three meteorological parameters:temperature,wind,and precipitation.The outcome of an evaluation experiment over the deterministic and probabilistic forecasts indicates that the NEPS outperforms the REPS and NPS in terms of surface weather variables.Analysis of two cases demonstrates the superior reliability of the NEPS and suggests that the NEPS gives more details about the spatial intensity and distribution of the meteorological parameters.展开更多
Accurately predicting drought a few months in advance is important for drought mitigation and agricultural and water resources management,especially for a river basin like that of the Yellow River in North China.Howev...Accurately predicting drought a few months in advance is important for drought mitigation and agricultural and water resources management,especially for a river basin like that of the Yellow River in North China.However,summer drought predictability over the Yellow River basin is limited because of the low influence from ENSO and the large interannual variations of the East Asian summer monsoon.To explore the drought predictability from an ensemble prediction perspective,29-year seasonal hindcasts of soil moisture drought,taken directly from several North American multimodel ensemble(NMME)models with different ensemble sizes,were compared with those produced by combining bias-corrected NMME model predictions and variable infiltration capacity(VIC)land surface hydrological model simulations.It was found that the NMME/VIC approach reduced the root-mean-square error from the best NMME raw products by 48%for summer soil moisture drought prediction at the lead-1 season,and increased the correlation significantly.Within the NMME/VIC framework,the multimodel ensemble mean further reduced the error from the best single model by 6%.Compared with the NMME raw forecasts,NMME/VIC had a higher probabilistic drought forecasting skill in terms of a higher Brier skill score and better reliability and resolution of the ensemble.However,the performance of the multimodel grand ensemble was not necessarily better than any single model ensemble,suggesting the need to optimize the ensemble for a more skillful probabilistic drought forecast.展开更多
Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanageme...Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanagement costs, and better long-term performance, but are at the risk ofsevere short-term declines due to a lack of Risk Control tools. Although thereare some methods to use historical volatility for Risk Control, it is still difficultto adapt to the rapid switch of market styles. How to strengthen the RiskControl management of the portfolio while maintaining the original advantagesof smart beta has become a new issue of concern in the industry. Thispaper demonstrates the scientific validity of using a probability prediction forposition optimization through an optimization theory and proposes a novelnatural gradient boosting (NGBoost)-based portfolio optimization method,which predicts stock prices and their probability distributions based on non-Bayesian methods and maximizes the Sharpe ratio expectation of positionoptimization. This paper validates the effectiveness and practicality of themodel by using the Chinese stock market, and the experimental results showthat the proposed method in this paper can reduce the volatility by 0.08 andincrease the expected portfolio cumulative return (reaching a maximum of67.1%) compared with the mainstream methods in the industry.展开更多
To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before app...To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before applying the forecasting techniques, a support vector classifier was first used to classify the data, and then the filtering was used to create separate trend and volatility sequences. After forecasting, the Markov chain transition probability matrix was introduced to adjust the residual. Simulation results using surplus gas data from an iron and steel enterprise demonstrate that the constructed SVC-HP-ENN-LSSVM-MC prediction model prediction is accurate, and that the classification accuracy is high under different conditions. Based on this, the scheduling model was constructed for surplus gas operating, and it has been used to investigate the comprehensive measures for managing the operational probabilistic risk and optimize the economic benefit at various working conditions and implementations. It has extended the concepts of traditional surplus gas dispatching systems, and provides a method for enterprises to determine optimal schedules.展开更多
Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potenti...Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.展开更多
Turbine blisk is one of the typical components of gas turbine engines.The fatigue life of turbine blisk directly affects the reliability and safety of both turbine blisk and aeroengine whole-body.To monitor the perfor...Turbine blisk is one of the typical components of gas turbine engines.The fatigue life of turbine blisk directly affects the reliability and safety of both turbine blisk and aeroengine whole-body.To monitor the performance degradation of an aeroengine,an efficient deep learning-based modeling method called convolutional-deep neural network(C-DNN)method is proposed by absorbing the advantages of both convolutional neural network(CNN)and deep neural network(DNN),to perform the probabilistic low cycle fatigue(LCF)life prediction of turbine blisk regarding uncertain influencing parameters.In the C-DNN method,the CNN method is used to extract the useful features of LCF life data by adopting two convolutional layers,to ensure the precision of C-DNN modeling.The two close-connected layers in DNN are employed for the regression modeling of aeroengine turbine blisk LCF life,to keep the ac-curacy of LCF life prediction.Through the probabilistic analysis of turbine blisk and the com-parison of methods(ANN,CNN,DNN and C-DNN),it is revealed that the proposed C-DNN method is an effective mean for turbine blisk LCF life prediction and major factors affecting the LCF life were gained,and the method holds high efficiency and accuracy in regression modeling and simulations.This study provides a promising LCF life prediction method for complex structures,which contribute to monitor health status for aeroengines operation.展开更多
Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affect...Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affected by the lack of sample data.The peaks over threshold(POT)method and compound extreme value distribution(CEVD)theory are effective methods to expand samples,but they still rely on long-term sea state data.To construct a probabilistic model using shortterm sea state data instead of the traditional annual maximum series(AMS),the binomial-bivariate log-normal CEVD(BBLCED)model is established in this thesis.The model not only considers the frequency of the extreme sea state,but it also reflects the correlation between different sea state elements(wave height and wave period)and reduces the requirement for the length of the data series.The model is applied to the calculation of design wave elements in a certain area of the Yellow Sea.The results indicate that the BBLCED model has good stability and fitting effect,which is close to the probability prediction results obtained from the long-term data,and reasonably reflects the probability distribution characteristics of the extreme sea state.The model can provide a reliable basis for coastal engineering design under the condition of a lack of marine data.Hence,it is suitable for extreme value prediction and calculation in the field of disaster prevention and reduction.展开更多
Based on the precipitation and temperature data obtained from THORPEX （The Observing System Research and Predictability Experiment） Interactive Grand Global Ensemble （TIGGE）-China Meteorological Administration （...Based on the precipitation and temperature data obtained from THORPEX （The Observing System Research and Predictability Experiment） Interactive Grand Global Ensemble （TIGGE）-China Meteorological Administration （CMA） archiving center and the raingauge data, the three-layer variable infiltration capacity （VIC-3L） land surface model was employed to carry out probabilistic hydrological forecast experiments over the upper Huaihe River catchment from 20 July to 3 August 2008. The results show that the performance of the ensemble probabilistic prediction from each ensemble prediction system （EPS） is better than that of the deterministic prediction. Especially, the 72-h prediction has been improved obviously. The ensemble spread goes widely with increasing lead time and more observed discharge is bracketed in the 5th-99th quantile. The accuracy of river discharge prediction driven by the European Centre （EC）-EPS is higher than that driven by the CMA-EPS and the US National Centers for Environmental Prediction （NCEP）-EPS, and the grand-ensemble prediction is the best for hydrological prediction using the VIC model. With regard to Wangjiaba station, all predictions made with a single EPS are close to the observation between the 25th and 75th quantile. The onset of the flood ascending and the river discharge thresholds are predicted well, and so is the second rising limb. Nevertheless, the flood recession is not well predicted.展开更多
In order to lower the power consumption and improve the coefficient of resource utilization of current cloud computing systems, this paper proposes two resource pre-allocation algorithms based on the ＂shut down the r...In order to lower the power consumption and improve the coefficient of resource utilization of current cloud computing systems, this paper proposes two resource pre-allocation algorithms based on the ＂shut down the redundant, turn on the demanded＂ strategy here. Firstly, a green cloud computing model is presented, abstracting the task scheduling problem to the virtual machine deployment issue with the virtualization technology. Secondly, the future workloads of system need to be predicted： a cubic exponential smoothing algorithm based on the conservative control（CESCC） strategy is proposed, combining with the current state and resource distribution of system, in order to calculate the demand of resources for the next period of task requests. Then, a multi-objective constrained optimization model of power consumption and a low-energy resource allocation algorithm based on probabilistic matching（RA-PM） are proposed. In order to reduce the power consumption further, the resource allocation algorithm based on the improved simulated annealing（RA-ISA） is designed with the improved simulated annealing algorithm. Experimental results show that the prediction and conservative control strategy make resource pre-allocation catch up with demands, and improve the efficiency of real-time response and the stability of the system. Both RA-PM and RA-ISA can activate fewer hosts, achieve better load balance among the set of high applicable hosts, maximize the utilization of resources, and greatly reduce the power consumption of cloud computing systems.展开更多
Fractal and chaotic laws of engineering structures are discussed in this paper, it means that the intrinsic essences and laws on dynamic systems which are made from seismic dissipated energy intensity E d and int...Fractal and chaotic laws of engineering structures are discussed in this paper, it means that the intrinsic essences and laws on dynamic systems which are made from seismic dissipated energy intensity E d and intensity of seismic dissipated energy moment I e are analyzed. Based on the intrinsic characters of chaotic and fractal dynamic system of E d and I e, three kinds of approximate dynamic models are rebuilt one by one: index autoregressive model, threshold autoregressive model and local-approximate autoregressive model. The innate laws, essences and systematic error of evolutional behavior I e are explained over all, the short-term behavior predictability and long-term behavior probability of which are analyzed in the end. That may be valuable for earthquake-resistant theory and analysis method in practical engineering structures.展开更多
Accurate regional wind power prediction plays an important role in the security and reliability of power systems.For the performance improvement of very short-term prediction intervals(PIs),a novel probabilistic predi...Accurate regional wind power prediction plays an important role in the security and reliability of power systems.For the performance improvement of very short-term prediction intervals(PIs),a novel probabilistic prediction method based on composite conditional nonlinear quantile regression(CCNQR)is proposed.First,the hierarchical clustering method based on weighted multivariate time series motifs(WMTSM)is studied to consider the static difference,dynamic difference,and meteorological difference of wind power time series.Then,the correlations are used as sample weights for the conditional linear programming(CLP)of CCNQR.To optimize the performance of PIs,a composite evaluation including the accuracy of PI coverage probability(PICP),the average width(AW),and the offsets of points outside PIs(OPOPI)is used to quantify the appropriate upper and lower bounds.Moreover,the adaptive boundary quantiles(ABQs)are quantified for the optimal performance of PIs.Finally,based on the real wind farm data,the superiority of the proposed method is verified by adequate comparisons with the conventional methods.展开更多
Based on summer precipitation hindcasts for 1991-2013 produced by the Beijing Climate Center Climate System Model （BCC_CSM）, the relationship between precipitation prediction error in northeastern China （NEC） and ...Based on summer precipitation hindcasts for 1991-2013 produced by the Beijing Climate Center Climate System Model （BCC_CSM）, the relationship between precipitation prediction error in northeastern China （NEC） and global sea surface temperature is analyzed, and dynamic-analogue prediction is carried out to improve the summer precipitation prediction skill of BCC_CSM, through taking care of model historical analogue prediction error in the real-time output. Seven correction schemes such as the systematic bias correction, pure statistical correction, dynamic-analogue correction, and so on, are designed and compared. Independent hindcast results show that the 5-yr average anomaly correlation coefficient （ACC） of summer precipitation is respectively improved from -0. 13/0.15 to 0.16/0.24 for 2009-13/1991-95 when using the equally weighted dynamic-analogue correction in the BCC_CSM prediction, which takes the arithmetical mean of the correction based on regional average error and that on grid point error. In addition, probabilistic prediction using the results from the multiple correction schemes is also performed and it leads to further improved 5-yr average prediction accuracy.展开更多
Wind power prediction interval(WPPI)models in the literature have predominantly been developed for and tested on specific case studies.However,wind behavior and characteristics can vary significantly across regions.Th...Wind power prediction interval(WPPI)models in the literature have predominantly been developed for and tested on specific case studies.However,wind behavior and characteristics can vary significantly across regions.Thus,a prediction model that performs well in one case might underperform in another.To address this shortcoming,this paper proposes an ensemble WPPI framework that integrates multiple WPPI models with distinct characteristics to improve robustness.Another important and often overlooked factor is the role of probabilistic wind power prediction(WPP)in quantifying wind power uncertainty,which should be handled by operating reserve.Operating reserve in WPPI frameworks enhances the efficacy of WPP.In this regard,the proposed framework employs a novel bi-layer optimization approach that takes both WPPI quality and reserve requirements into account.Comprehensive analysis with different real-world datasets and various benchmark models validates the quality of the obtained WPPIs while resulting in more optimal reserve requirements.展开更多
基金supported by the National Natural Science Foundation of China (No. 62073121)the National Key R&D Program of China “Technology and application of wind power/photovoltaic power prediction for promoting renewable energy consumption”(No. 2018YFB0904200)eponymous Complement S&T Program of State Grid Corporation of China (No. SGLNDKOOKJJS1800266)。
文摘Regional photovoltaic(PV) power prediction plays an important role in power system planning and operation. To effectively improve the performance of prediction intervals(PIs) for very short-term regional PV outputs, an efficient nonparametric probabilistic prediction method based on granulebased clustering(GC) and direct optimization programming(DOP) is proposed. First, GC is proposed to formulate and cluster the sample granules consisting of numerical weather prediction(NWP) and historical regional output data, for the enhanced hierarchical clustering performance. Then, to improve the accuracy of samples' utilization, an unbalanced extension is used to reconstruct the training samples consisting of power time series. After that, DOP is applied to quantify the output weights based on the optimal overall performance. Meanwhile, a balance coefficient is studied for the enhanced reliability of PIs. Finally, the proposed method is validated through multistep PIs based on the numerical comparison of real PV generation data.
基金The National Key Research and Development Program of China(No.2019YFB160-0200)the National Natural Science Foundation of China(No.71871011,71890972/71890970)。
文摘To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger flows.First,bus and metro data are processed and matched by association to construct the basis for public transport trip chain extraction.Second,a reasonable matching threshold method to discriminate the transfer relationship is used to extract the public transport trip chain,and the basic characteristics of the trip based on the trip chain are analyzed to obtain the metro-to-bus transfer passenger flow.Third,to address the problem of low accuracy of point prediction,the DeepAR model is proposed to conduct interval prediction,where the input is the interchange passenger flow,the output is the predicted median and interval of passenger flow,and the prediction scenarios are weekday,non-workday,and weekday morning and evening peaks.Fourth,to reduce the prediction error,a combined particle swarm optimization(PSO)-DeepAR model is constructed using the PSO to optimize the DeepAR model.Finally,data from the Beijing Xizhimen subway station are used for validation,and results show that the PSO-DeepAR model has high prediction accuracy,with a 90%confidence interval coverage of up to 93.6%.
基金supported by National Key Research and Development Program of China(Grant No.2018YFC1506804)the Beijing Natural Science Foundation(Grant No.8222051)the Key Innovation Team of China Meteorological Administration(CMA2022ZD04)。
文摘Ensemble forecasting systems have become an important tool for estimating the uncertainties in initial conditions and model formulations and they are receiving increased attention from various applications.The Regional Ensemble Prediction System(REPS),which has operated at the Beijing Meteorological Service(BMS)since 2017,allows for probabilistic forecasts.However,it still suffers from systematic deficiencies during the first couple of forecast hours.This paper presents an integrated probabilistic nowcasting ensemble prediction system(NEPS)that is constructed by applying a mixed dynamicintegrated method.It essentially combines the uncertainty information(i.e.,ensemble variance)provided by the REPS with the nowcasting method provided by the rapid-refresh deterministic nowcasting prediction system(NPS)that has operated at the Beijing Meteorological Service(BMS)since 2019.The NEPS provides hourly updated analyses and probabilistic forecasts in the nowcasting and short range(0-6 h)with a spatial grid spacing of 500 m.It covers the three meteorological parameters:temperature,wind,and precipitation.The outcome of an evaluation experiment over the deterministic and probabilistic forecasts indicates that the NEPS outperforms the REPS and NPS in terms of surface weather variables.Analysis of two cases demonstrates the superior reliability of the NEPS and suggests that the NEPS gives more details about the spatial intensity and distribution of the meteorological parameters.
基金supported by the China Special Fund for Meteorological Research in the Public Interest(Major projects)(Grant No.GYHY201506001)the National Natural Science Foundation of China(Grant No.91547103)
文摘Accurately predicting drought a few months in advance is important for drought mitigation and agricultural and water resources management,especially for a river basin like that of the Yellow River in North China.However,summer drought predictability over the Yellow River basin is limited because of the low influence from ENSO and the large interannual variations of the East Asian summer monsoon.To explore the drought predictability from an ensemble prediction perspective,29-year seasonal hindcasts of soil moisture drought,taken directly from several North American multimodel ensemble(NMME)models with different ensemble sizes,were compared with those produced by combining bias-corrected NMME model predictions and variable infiltration capacity(VIC)land surface hydrological model simulations.It was found that the NMME/VIC approach reduced the root-mean-square error from the best NMME raw products by 48%for summer soil moisture drought prediction at the lead-1 season,and increased the correlation significantly.Within the NMME/VIC framework,the multimodel ensemble mean further reduced the error from the best single model by 6%.Compared with the NMME raw forecasts,NMME/VIC had a higher probabilistic drought forecasting skill in terms of a higher Brier skill score and better reliability and resolution of the ensemble.However,the performance of the multimodel grand ensemble was not necessarily better than any single model ensemble,suggesting the need to optimize the ensemble for a more skillful probabilistic drought forecast.
基金supported by the National Natural Science Foundation of China[Grant Number 61902349].
文摘Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanagement costs, and better long-term performance, but are at the risk ofsevere short-term declines due to a lack of Risk Control tools. Although thereare some methods to use historical volatility for Risk Control, it is still difficultto adapt to the rapid switch of market styles. How to strengthen the RiskControl management of the portfolio while maintaining the original advantagesof smart beta has become a new issue of concern in the industry. Thispaper demonstrates the scientific validity of using a probability prediction forposition optimization through an optimization theory and proposes a novelnatural gradient boosting (NGBoost)-based portfolio optimization method,which predicts stock prices and their probability distributions based on non-Bayesian methods and maximizes the Sharpe ratio expectation of positionoptimization. This paper validates the effectiveness and practicality of themodel by using the Chinese stock market, and the experimental results showthat the proposed method in this paper can reduce the volatility by 0.08 andincrease the expected portfolio cumulative return (reaching a maximum of67.1%) compared with the mainstream methods in the industry.
基金Project(51204082)supported by the National Natural Science Foundation of ChinaProject(KKSY201458118)supported by the Talent Cultivation Project of Kuning University of Science and Technology,China
文摘To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before applying the forecasting techniques, a support vector classifier was first used to classify the data, and then the filtering was used to create separate trend and volatility sequences. After forecasting, the Markov chain transition probability matrix was introduced to adjust the residual. Simulation results using surplus gas data from an iron and steel enterprise demonstrate that the constructed SVC-HP-ENN-LSSVM-MC prediction model prediction is accurate, and that the classification accuracy is high under different conditions. Based on this, the scheduling model was constructed for surplus gas operating, and it has been used to investigate the comprehensive measures for managing the operational probabilistic risk and optimize the economic benefit at various working conditions and implementations. It has extended the concepts of traditional surplus gas dispatching systems, and provides a method for enterprises to determine optimal schedules.
基金supported by the proactive SAFEty systems and tools for a constantly UPgrading road environment(SAFE-UP)projectfunding from the European Union’s Horizon 2020 Research and Innovation Program(861570)。
文摘Risk assessment is a crucial component of collision warning and avoidance systems for intelligent vehicles.Reachability-based formal approaches have been developed to ensure driving safety to accurately detect potential vehicle collisions.However,they suffer from over-conservatism,potentially resulting in false–positive risk events in complicated real-world applications.In this paper,we combine two reachability analysis techniques,a backward reachable set(BRS)and a stochastic forward reachable set(FRS),and propose an integrated probabilistic collision–detection framework for highway driving.Within this framework,we can first use a BRS to formally check whether a two-vehicle interaction is safe;otherwise,a prediction-based stochastic FRS is employed to estimate the collision probability at each future time step.Thus,the framework can not only identify non-risky events with guaranteed safety but also provide accurate collision risk estimation in safety-critical events.To construct the stochastic FRS,we develop a neural network-based acceleration model for surrounding vehicles and further incorporate a confidence-aware dynamic belief to improve the prediction accuracy.Extensive experiments were conducted to validate the performance of the acceleration prediction model based on naturalistic highway driving data.The efficiency and effectiveness of the framework with infused confidence beliefs were tested in both naturalistic and simulated highway scenarios.The proposed risk assessment framework is promising for real-world applications.
基金National Natural Science Foundation of China (Grant No.52375237)National Sci-ence and Technology Major Project (Grant J2022-IV-0012)+2 种基金Shanghai Belt and Road International Cooperation Project of China (Grant No.20110741700)China Postdoctoral Science Foundation (Grant No.2021M700783)Research Grants Council of the Hong Kong SAR of China (PolyU 15209520).
文摘Turbine blisk is one of the typical components of gas turbine engines.The fatigue life of turbine blisk directly affects the reliability and safety of both turbine blisk and aeroengine whole-body.To monitor the performance degradation of an aeroengine,an efficient deep learning-based modeling method called convolutional-deep neural network(C-DNN)method is proposed by absorbing the advantages of both convolutional neural network(CNN)and deep neural network(DNN),to perform the probabilistic low cycle fatigue(LCF)life prediction of turbine blisk regarding uncertain influencing parameters.In the C-DNN method,the CNN method is used to extract the useful features of LCF life data by adopting two convolutional layers,to ensure the precision of C-DNN modeling.The two close-connected layers in DNN are employed for the regression modeling of aeroengine turbine blisk LCF life,to keep the ac-curacy of LCF life prediction.Through the probabilistic analysis of turbine blisk and the com-parison of methods(ANN,CNN,DNN and C-DNN),it is revealed that the proposed C-DNN method is an effective mean for turbine blisk LCF life prediction and major factors affecting the LCF life were gained,and the method holds high efficiency and accuracy in regression modeling and simulations.This study provides a promising LCF life prediction method for complex structures,which contribute to monitor health status for aeroengines operation.
文摘Extreme value analysis is an indispensable method to predict the probability of marine disasters and calculate the design conditions of marine engineering.The rationality of extreme value analysis can be easily affected by the lack of sample data.The peaks over threshold(POT)method and compound extreme value distribution(CEVD)theory are effective methods to expand samples,but they still rely on long-term sea state data.To construct a probabilistic model using shortterm sea state data instead of the traditional annual maximum series(AMS),the binomial-bivariate log-normal CEVD(BBLCED)model is established in this thesis.The model not only considers the frequency of the extreme sea state,but it also reflects the correlation between different sea state elements(wave height and wave period)and reduces the requirement for the length of the data series.The model is applied to the calculation of design wave elements in a certain area of the Yellow Sea.The results indicate that the BBLCED model has good stability and fitting effect,which is close to the probability prediction results obtained from the long-term data,and reasonably reflects the probability distribution characteristics of the extreme sea state.The model can provide a reliable basis for coastal engineering design under the condition of a lack of marine data.Hence,it is suitable for extreme value prediction and calculation in the field of disaster prevention and reduction.
基金Supported by the China Meteorological Administration Special Public Welfare Research Fund (GYHY201006037,GYHY200906007,and GYHY(QX)2007-6-1)Special Fund for Weather Forecasters of CMA in 2010 (CMATG2010Y23)Huaihe River Meteorology Open Research Fund (HRM200701)
文摘Based on the precipitation and temperature data obtained from THORPEX （The Observing System Research and Predictability Experiment） Interactive Grand Global Ensemble （TIGGE）-China Meteorological Administration （CMA） archiving center and the raingauge data, the three-layer variable infiltration capacity （VIC-3L） land surface model was employed to carry out probabilistic hydrological forecast experiments over the upper Huaihe River catchment from 20 July to 3 August 2008. The results show that the performance of the ensemble probabilistic prediction from each ensemble prediction system （EPS） is better than that of the deterministic prediction. Especially, the 72-h prediction has been improved obviously. The ensemble spread goes widely with increasing lead time and more observed discharge is bracketed in the 5th-99th quantile. The accuracy of river discharge prediction driven by the European Centre （EC）-EPS is higher than that driven by the CMA-EPS and the US National Centers for Environmental Prediction （NCEP）-EPS, and the grand-ensemble prediction is the best for hydrological prediction using the VIC model. With regard to Wangjiaba station, all predictions made with a single EPS are close to the observation between the 25th and 75th quantile. The onset of the flood ascending and the river discharge thresholds are predicted well, and so is the second rising limb. Nevertheless, the flood recession is not well predicted.
基金supported by the National Natural Science Foundation of China(6147219261202004)+1 种基金the Special Fund for Fast Sharing of Science Paper in Net Era by CSTD(2013116)the Natural Science Fund of Higher Education of Jiangsu Province(14KJB520014)
文摘In order to lower the power consumption and improve the coefficient of resource utilization of current cloud computing systems, this paper proposes two resource pre-allocation algorithms based on the ＂shut down the redundant, turn on the demanded＂ strategy here. Firstly, a green cloud computing model is presented, abstracting the task scheduling problem to the virtual machine deployment issue with the virtualization technology. Secondly, the future workloads of system need to be predicted： a cubic exponential smoothing algorithm based on the conservative control（CESCC） strategy is proposed, combining with the current state and resource distribution of system, in order to calculate the demand of resources for the next period of task requests. Then, a multi-objective constrained optimization model of power consumption and a low-energy resource allocation algorithm based on probabilistic matching（RA-PM） are proposed. In order to reduce the power consumption further, the resource allocation algorithm based on the improved simulated annealing（RA-ISA） is designed with the improved simulated annealing algorithm. Experimental results show that the prediction and conservative control strategy make resource pre-allocation catch up with demands, and improve the efficiency of real-time response and the stability of the system. Both RA-PM and RA-ISA can activate fewer hosts, achieve better load balance among the set of high applicable hosts, maximize the utilization of resources, and greatly reduce the power consumption of cloud computing systems.
文摘Fractal and chaotic laws of engineering structures are discussed in this paper, it means that the intrinsic essences and laws on dynamic systems which are made from seismic dissipated energy intensity E d and intensity of seismic dissipated energy moment I e are analyzed. Based on the intrinsic characters of chaotic and fractal dynamic system of E d and I e, three kinds of approximate dynamic models are rebuilt one by one: index autoregressive model, threshold autoregressive model and local-approximate autoregressive model. The innate laws, essences and systematic error of evolutional behavior I e are explained over all, the short-term behavior predictability and long-term behavior probability of which are analyzed in the end. That may be valuable for earthquake-resistant theory and analysis method in practical engineering structures.
基金This work was supported by the National Key R&D Program of China“Technology and Application of Wind Power/Photovoltaic Power Prediction for Promoting Renewable Energy Consumption”(No.2018YFB0904200)Complement S&T Program of State Grid Corporation of China(No.SGLNDKOOKJJS1800266).
文摘Accurate regional wind power prediction plays an important role in the security and reliability of power systems.For the performance improvement of very short-term prediction intervals(PIs),a novel probabilistic prediction method based on composite conditional nonlinear quantile regression(CCNQR)is proposed.First,the hierarchical clustering method based on weighted multivariate time series motifs(WMTSM)is studied to consider the static difference,dynamic difference,and meteorological difference of wind power time series.Then,the correlations are used as sample weights for the conditional linear programming(CLP)of CCNQR.To optimize the performance of PIs,a composite evaluation including the accuracy of PI coverage probability(PICP),the average width(AW),and the offsets of points outside PIs(OPOPI)is used to quantify the appropriate upper and lower bounds.Moreover,the adaptive boundary quantiles(ABQs)are quantified for the optimal performance of PIs.Finally,based on the real wind farm data,the superiority of the proposed method is verified by adequate comparisons with the conventional methods.
基金Supported by the Science and Technology Research Project of Liaoning Provincial Meteorological Bureau(201502)Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)+1 种基金Liaoning Province Agricultural Research and Industrialization Project(2015103038)China Meteorological Administration Special Public Welfare Research(GYHY201306021)
文摘Based on summer precipitation hindcasts for 1991-2013 produced by the Beijing Climate Center Climate System Model （BCC_CSM）, the relationship between precipitation prediction error in northeastern China （NEC） and global sea surface temperature is analyzed, and dynamic-analogue prediction is carried out to improve the summer precipitation prediction skill of BCC_CSM, through taking care of model historical analogue prediction error in the real-time output. Seven correction schemes such as the systematic bias correction, pure statistical correction, dynamic-analogue correction, and so on, are designed and compared. Independent hindcast results show that the 5-yr average anomaly correlation coefficient （ACC） of summer precipitation is respectively improved from -0. 13/0.15 to 0.16/0.24 for 2009-13/1991-95 when using the equally weighted dynamic-analogue correction in the BCC_CSM prediction, which takes the arithmetical mean of the correction based on regional average error and that on grid point error. In addition, probabilistic prediction using the results from the multiple correction schemes is also performed and it leads to further improved 5-yr average prediction accuracy.
基金supported in part by the Natural Sciences and Engineering Research Council(NSERC)of Canada and the Saskatchewan Power Corporation(SaskPower).
文摘Wind power prediction interval(WPPI)models in the literature have predominantly been developed for and tested on specific case studies.However,wind behavior and characteristics can vary significantly across regions.Thus,a prediction model that performs well in one case might underperform in another.To address this shortcoming,this paper proposes an ensemble WPPI framework that integrates multiple WPPI models with distinct characteristics to improve robustness.Another important and often overlooked factor is the role of probabilistic wind power prediction(WPP)in quantifying wind power uncertainty,which should be handled by operating reserve.Operating reserve in WPPI frameworks enhances the efficacy of WPP.In this regard,the proposed framework employs a novel bi-layer optimization approach that takes both WPPI quality and reserve requirements into account.Comprehensive analysis with different real-world datasets and various benchmark models validates the quality of the obtained WPPIs while resulting in more optimal reserve requirements.
