Multivariate Time Series(MTS)forecasting is an essential problem in many fields.Accurate forecasting results can effectively help in making decisions.To date,many MTS forecasting methods have been proposed and widely ...Multivariate Time Series(MTS)forecasting is an essential problem in many fields.Accurate forecasting results can effectively help in making decisions.To date,many MTS forecasting methods have been proposed and widely applied.However,these methods assume that the predicted value of a single variable is affected by all other variables,ignoring the causal relationship among variables.To address the above issue,we propose a novel end-to-end deep learning model,termed graph neural network with neural Granger causality,namely CauGNN,in this paper.To characterize the causal information among variables,we introduce the neural Granger causality graph in our model.Each variable is regarded as a graph node,and each edge represents the casual relationship between variables.In addition,convolutional neural network filters with different perception scales are used for time series feature extraction,to generate the feature of each node.Finally,the graph neural network is adopted to tackle the forecasting problem of the graph structure generated by the MTS.Three benchmark datasets from the real world are used to evaluate the proposed CauGNN,and comprehensive experiments show that the proposed method achieves state-of-the-art results in the MTS forecasting task.展开更多
In today’s rapidly evolving internet landscape,prominent companies across various industries face increasingly complex business operations,leading to significant cluster-scale growth.However,this growth brings about ...In today’s rapidly evolving internet landscape,prominent companies across various industries face increasingly complex business operations,leading to significant cluster-scale growth.However,this growth brings about challenges in cluster management and the inefficient utilization of vast amounts of data due to its low value density.This paper,based on the large-scale cluster virtualization and monitoring system of the data center of the Bureau of Geophysical Prospecting(BGP),utilizes time series data of host resources from the monitoring system’s time series database to propose a multivariate multi-step time series forecasting model,MUL-CNN-BiGRU-Attention,for forecasting CPU load on virtual cluster hosts.The model undergoes extensive offline training using a large volume of time series data,followed by deployment using TensorFlow Serving.Recent small-batch data are employed for fine-tuning model parameters to better adapt to current data patterns.Comparative experiments are conducted between the proposed model and other baseline models,demonstrating notable improvements in Mean Absolute Error(MAE),Mean Squared Error(MSE),Root Mean Squared Error(RMSE),and R2 metrics by up to 35.2%,56.1%,32.5%,and 10.3%,respectively.Additionally,ablation experiments are designed to investigate the impact of different factors on the performance of the forecasting model,providing valuable insights for parameter optimization based on experimental results.展开更多
The use of computational intelligence has become commonplace for accurate wind speed and energy forecasting,however the energy-intensive processes involved in training and tuning stands as a critical issue for the sus...The use of computational intelligence has become commonplace for accurate wind speed and energy forecasting,however the energy-intensive processes involved in training and tuning stands as a critical issue for the sustainability of AI models.Quantum computing emerges as a key player in addressing this concern,offering a quantum advantage that could potentially accelerate computations or,more significantly,reduce energy consumption.It is a matter of debate if purely quantum machine learning models,as they currently stand,are capable of competing with the classical state of the art on relevant problems.We investigate the efficacy of quantum neural networks(QNNs)for wind speed nowcasting,comparing them to a baseline Multilayer Perceptron(MLP).Utilizing meteorological data from Bahia,Brazil,we develop a QNN tailored for up to six hours ahead wind speed prediction.Our analysis reveals that the QNN demonstrates competitive performance compared to MLP.We evaluate models using RMSE,Pearson’s R,and Factor of 2 metrics,emphasizing QNNs’promising generalization capabilities and robustness across various wind prediction scenarios.This study is a seminal work on the potential of QNNs in advancing renewable energy forecasting,advocating for further exploration of quantum machine learning in sustainable energy research.展开更多
基金supported in part by the National Natural Science Foundation of China (No.62002035)the Natural Science Foundation of Chongqing (No.cstc2020jcyj-bshX0034).
文摘Multivariate Time Series(MTS)forecasting is an essential problem in many fields.Accurate forecasting results can effectively help in making decisions.To date,many MTS forecasting methods have been proposed and widely applied.However,these methods assume that the predicted value of a single variable is affected by all other variables,ignoring the causal relationship among variables.To address the above issue,we propose a novel end-to-end deep learning model,termed graph neural network with neural Granger causality,namely CauGNN,in this paper.To characterize the causal information among variables,we introduce the neural Granger causality graph in our model.Each variable is regarded as a graph node,and each edge represents the casual relationship between variables.In addition,convolutional neural network filters with different perception scales are used for time series feature extraction,to generate the feature of each node.Finally,the graph neural network is adopted to tackle the forecasting problem of the graph structure generated by the MTS.Three benchmark datasets from the real world are used to evaluate the proposed CauGNN,and comprehensive experiments show that the proposed method achieves state-of-the-art results in the MTS forecasting task.
文摘In today’s rapidly evolving internet landscape,prominent companies across various industries face increasingly complex business operations,leading to significant cluster-scale growth.However,this growth brings about challenges in cluster management and the inefficient utilization of vast amounts of data due to its low value density.This paper,based on the large-scale cluster virtualization and monitoring system of the data center of the Bureau of Geophysical Prospecting(BGP),utilizes time series data of host resources from the monitoring system’s time series database to propose a multivariate multi-step time series forecasting model,MUL-CNN-BiGRU-Attention,for forecasting CPU load on virtual cluster hosts.The model undergoes extensive offline training using a large volume of time series data,followed by deployment using TensorFlow Serving.Recent small-batch data are employed for fine-tuning model parameters to better adapt to current data patterns.Comparative experiments are conducted between the proposed model and other baseline models,demonstrating notable improvements in Mean Absolute Error(MAE),Mean Squared Error(MSE),Root Mean Squared Error(RMSE),and R2 metrics by up to 35.2%,56.1%,32.5%,and 10.3%,respectively.Additionally,ablation experiments are designed to investigate the impact of different factors on the performance of the forecasting model,providing valuable insights for parameter optimization based on experimental results.
基金partially funded by the project“Master’s and PhD in Quantum Technologies-QIN-FCRH-2025-5-1-1”in supported by QuIIN-Quantum Industrial Innovation,EMBRAPII CIMATEC Com-petence Center in Quantum Technologiesfinancial resources from the PPI IoT/Manufatura 4.0 of the MCTI grant number 053/2023,signed with EMBRAPII+1 种基金National Council for Scientific and Technological Development(CNPq,Brazil),for partially funding this work.Erick G.Sperandio Nascimento is a CNPq techno-logical development fellow(Proc.308963/2022-9)the Surrey Institute for People-Centred AI at the University of Surrey(UK)for their institutional support.
文摘The use of computational intelligence has become commonplace for accurate wind speed and energy forecasting,however the energy-intensive processes involved in training and tuning stands as a critical issue for the sustainability of AI models.Quantum computing emerges as a key player in addressing this concern,offering a quantum advantage that could potentially accelerate computations or,more significantly,reduce energy consumption.It is a matter of debate if purely quantum machine learning models,as they currently stand,are capable of competing with the classical state of the art on relevant problems.We investigate the efficacy of quantum neural networks(QNNs)for wind speed nowcasting,comparing them to a baseline Multilayer Perceptron(MLP).Utilizing meteorological data from Bahia,Brazil,we develop a QNN tailored for up to six hours ahead wind speed prediction.Our analysis reveals that the QNN demonstrates competitive performance compared to MLP.We evaluate models using RMSE,Pearson’s R,and Factor of 2 metrics,emphasizing QNNs’promising generalization capabilities and robustness across various wind prediction scenarios.This study is a seminal work on the potential of QNNs in advancing renewable energy forecasting,advocating for further exploration of quantum machine learning in sustainable energy research.
