Accurate prediction of cloud resource utilization is critical.It helps improve service quality while avoiding resource waste and shortages.However,the time series of resource usage in cloud computing systems often exh...Accurate prediction of cloud resource utilization is critical.It helps improve service quality while avoiding resource waste and shortages.However,the time series of resource usage in cloud computing systems often exhibit multidimensionality,nonlinearity,and high volatility,making the high-precision prediction of resource utilization a complex and challenging task.At present,cloud computing resource prediction methods include traditional statistical models,hybrid approaches combining machine learning and classical models,and deep learning techniques.Traditional statistical methods struggle with nonlinear predictions,hybrid methods face challenges in feature extraction and long-term dependencies,and deep learning methods incur high computational costs.The above methods are insufficient to achieve high-precision resource prediction in cloud computing systems.Therefore,we propose a new time series prediction model,called SDVformer,which is based on the Informer model by integrating the Savitzky-Golay(SG)filters,a novel Discrete-Variation Self-Attention(DVSA)mechanism,and a type-aware mixture of experts(T-MOE)framework.The SG filter is designed to reduce noise and enhance the feature representation of input data.The DVSA mechanism is proposed to optimize the selection of critical features to reduce computational complexity.The T-MOE framework is designed to adjust the model structure based on different resource characteristics,thereby improving prediction accuracy and adaptability.Experimental results show that our proposed SDVformer significantly outperforms baseline models,including Recurrent Neural Network(RNN),Long Short-Term Memory(LSTM),and Informer in terms of prediction precision,on both the Alibaba public dataset and the dataset collected by Beijing Jiaotong University(BJTU).Particularly compared with the Informer model,the average Mean Squared Error(MSE)of SDVformer decreases by about 80%,fully demonstrating its advantages in complex time series prediction tasks in cloud computing systems.展开更多
The Electron Cyclotron Resonance(ECR)ion source is a critical device for producing highly charged ion beams in various applications.Analyzing the charge-state distribution of the ion beams is essential,but the manual ...The Electron Cyclotron Resonance(ECR)ion source is a critical device for producing highly charged ion beams in various applications.Analyzing the charge-state distribution of the ion beams is essential,but the manual analysis is labor-intensive and prone to inaccuracies due to impurity ions.An automatic spectrum recognition system based on intelligent algorithms was proposed for rapid and accurate chargestate analysis of ECR ion sources.The system employs an adaptive window-length Savitzky-Golay(SG)filtering algorithm,an improved automatic multiscale peak detection(AMPD)algorithm,and a greedy matching algorithm based on the relative distance to accurately match different peaks in the spectra with the corresponding charge-state ion species.Additionally,a user-friendly operator interface was developed for ease of use.Extensive testing on the online ECR ion source platform demonstrates that the system achieves high accuracy,with an average root mean square error of less than 0.1 A for identifying charge-state spectra of ECR ion sources.Moreover,the system minimizes the stand-ard deviation of the first-order derivative of the smoothed signal to 81.1846 A.These results indicate the capability of the designed system to identify ion beam spectra with mass numbers less than Xe,including Xe itself.The proposed automatic spectrum recognition system represents a significant advancement in ECR ion source analysis,offering a rapid and accurate approach for charge-state analysis while enhancing supply efficiency.The exceptional performance and successful imple-mentation of the proposed system on multiple ECR ion source platforms at IMPCAS highlight its potential for widespread adoption in ECR ion source research and applications.展开更多
文摘Accurate prediction of cloud resource utilization is critical.It helps improve service quality while avoiding resource waste and shortages.However,the time series of resource usage in cloud computing systems often exhibit multidimensionality,nonlinearity,and high volatility,making the high-precision prediction of resource utilization a complex and challenging task.At present,cloud computing resource prediction methods include traditional statistical models,hybrid approaches combining machine learning and classical models,and deep learning techniques.Traditional statistical methods struggle with nonlinear predictions,hybrid methods face challenges in feature extraction and long-term dependencies,and deep learning methods incur high computational costs.The above methods are insufficient to achieve high-precision resource prediction in cloud computing systems.Therefore,we propose a new time series prediction model,called SDVformer,which is based on the Informer model by integrating the Savitzky-Golay(SG)filters,a novel Discrete-Variation Self-Attention(DVSA)mechanism,and a type-aware mixture of experts(T-MOE)framework.The SG filter is designed to reduce noise and enhance the feature representation of input data.The DVSA mechanism is proposed to optimize the selection of critical features to reduce computational complexity.The T-MOE framework is designed to adjust the model structure based on different resource characteristics,thereby improving prediction accuracy and adaptability.Experimental results show that our proposed SDVformer significantly outperforms baseline models,including Recurrent Neural Network(RNN),Long Short-Term Memory(LSTM),and Informer in terms of prediction precision,on both the Alibaba public dataset and the dataset collected by Beijing Jiaotong University(BJTU).Particularly compared with the Informer model,the average Mean Squared Error(MSE)of SDVformer decreases by about 80%,fully demonstrating its advantages in complex time series prediction tasks in cloud computing systems.
文摘The Electron Cyclotron Resonance(ECR)ion source is a critical device for producing highly charged ion beams in various applications.Analyzing the charge-state distribution of the ion beams is essential,but the manual analysis is labor-intensive and prone to inaccuracies due to impurity ions.An automatic spectrum recognition system based on intelligent algorithms was proposed for rapid and accurate chargestate analysis of ECR ion sources.The system employs an adaptive window-length Savitzky-Golay(SG)filtering algorithm,an improved automatic multiscale peak detection(AMPD)algorithm,and a greedy matching algorithm based on the relative distance to accurately match different peaks in the spectra with the corresponding charge-state ion species.Additionally,a user-friendly operator interface was developed for ease of use.Extensive testing on the online ECR ion source platform demonstrates that the system achieves high accuracy,with an average root mean square error of less than 0.1 A for identifying charge-state spectra of ECR ion sources.Moreover,the system minimizes the stand-ard deviation of the first-order derivative of the smoothed signal to 81.1846 A.These results indicate the capability of the designed system to identify ion beam spectra with mass numbers less than Xe,including Xe itself.The proposed automatic spectrum recognition system represents a significant advancement in ECR ion source analysis,offering a rapid and accurate approach for charge-state analysis while enhancing supply efficiency.The exceptional performance and successful imple-mentation of the proposed system on multiple ECR ion source platforms at IMPCAS highlight its potential for widespread adoption in ECR ion source research and applications.
