Applying gated recurrent units pproaches for workload prediction

Guo, Yanghu; Yao, Wenbin

doi:10.1109/noms.2018.8406290

Cited by 15 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9(b) to (f), the TSA for workload compression is effective under proper settings of top hidden units, which is able to provide an effective feature representation that can greatly reduce the computational complexity of our proposed method for cloud workload prediction. Based on the Google datasets and the preprocessed results of workload compression by using the TSA, we evaluate the proposed L-PAW and other recent RNN-based methods for workload prediction, including recurrent neural network (RNN) [22], long short-term memory (LSTM) [27], gated recurrent unit (GRU) [30], and echo state networks (ESN) [28]. We compare both the prediction accuracy and learning efficiency among these methods, measured by MSE and the average training time, respectively.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Towards Accurate Prediction for High-Dimensional and Highly-Variable Cloud Workloads with Deep Learning

Chen

Min

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

134

View full text Add to dashboard Cite

Resource provisioning for cloud computing necessitates the adaptive and accurate prediction of cloud workloads. However, the existing methods cannot effectively predict the high-dimensional and highly-variable cloud workloads. This results in resource wasting and inability to satisfy service level agreements (SLAs). Since recurrent neural network (RNN) is naturally suitable for sequential data analysis, it has been recently used to tackle the problem of workload prediction. However, RNN often performs poorly on learning longterm memory dependencies, and thus cannot make the accurate prediction of workloads. To address these important challenges, we propose a deep Learning based Prediction Algorithm for cloud Workloads (L-PAW). First, a top-sparse auto-encoder (TSA) is designed to effectively extract the essential representations of workloads from the original high-dimensional workload data. Next, we integrate TSA and gated recurrent unit (GRU) block into RNN to achieve the adaptive and accurate prediction for highly-variable workloads. Using realworld workload traces from Google and Alibaba cloud data centers and the DUX-based cluster, extensive experiments are conducted to demonstrate the effectiveness and adaptability of the L-PAW for different types of workloads with various prediction lengths. Moreover, the performance results show that the L-PAW achieves superior prediction accuracy compared to the classic RNN-based and other workload prediction methods for high-dimensional and highly-variable real-world cloud workloads.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Compared with LSTM, GRU is able to converge more easily with fewer settings of parameters [12]. But there is little research work [30] using GRU-based approaches with the consideration of training efficiency of neural networks for workload prediction in the cloud environment.…”

Section: Rnn-based Approaches For Workload Predictionmentioning

confidence: 99%

Towards Accurate Prediction for High-Dimensional and Highly-Variable Cloud Workloads with Deep Learning

Chen

Min

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

134

View full text Add to dashboard Cite

show abstract

“…Guo et al [26] designed and proposed an improved LSTM-based model N-LSTM to solve the problem of virtual machine workload forecasting, and it could make forecast at irregular time intervals. Guo and Yao [27] proposed a method for workload prediction based on GRU [13]. The model can learn temporal patterns and longterm dependencies of large sequences of arbitrary length, and the model training time is shorter than that of LSTM.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…GRU [27]: The basic gate recurrent unit (GRU) [13] network is a recurrent neural network using GRU cell as the calculation unit. The historical data will be input to the multilayer GRU network, and the last output value of the last layer will be taken as the forecast value.…”

Section: B Experimental Setting 1) Baseline Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An Accurate Ensemble Forecasting Approach for Highly Dynamic Cloud Workload With VMD and R-Transformer

Zhou

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

To efficiently manage the cloud resources, improve the quality of service, and avoid the violations of Service-Level Agreement (SLA) agreements, it is very important to make accurate forecast for cloud workload. Prior works concerning cloud workload forecasting are mainly designed based on Recurrent Neural Networks (RNN). However, when it comes to a highly-dynamic cloud workload scenario where resource utilization changes faster and more frequently, these RNN-based methods are not effective in obtaining the linear and non-linear relationships and cannot give accurate forecast, because classic RNN has the problem of vanishing gradient. To address this issue, we propose an Ensemble Forecasting Approach (EFA) for highly-dynamic cloud workload by applying Variational Mode Decomposition (VMD) and R-Transformer. Specifically, to decrease the non-stationarity and high randomness of highly-dynamic cloud workload sequences, we decompose the workload into multiple Intrinsic Mode Functions (IMFs) by VMD. The IMFs are then imported into our ensemble forecasting module based on R-Transformer and Autoregressive model, in order to capture long-term dependencies and local non-linear relationship of workload sequences. The effectiveness and adaptability of proposed EFA is verified on real-world workload from Google and Alibaba cluster traces. Moreover, the performance evaluation results show that the EFA performs higher forecasting accuracy than prior related works over various forecasting time lengths for highly-dynamic cloud workload. INDEX TERMS Workload forecasting, Cloud computing, Deep learning, Variational mode decomposition.

show abstract

Predicting Instances Demand and Occupancy Toward Efficient VMs Rightsizing and Resources Allocation Strategies: Amazon Case Study

Ikhlasse

Duthil

Courboulay

et al. 2022

Service Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future

View full text Add to dashboard Cite

Applying gated recurrent units pproaches for workload prediction

Cited by 15 publications

References 13 publications

Towards Accurate Prediction for High-Dimensional and Highly-Variable Cloud Workloads with Deep Learning

Towards Accurate Prediction for High-Dimensional and Highly-Variable Cloud Workloads with Deep Learning

An Accurate Ensemble Forecasting Approach for Highly Dynamic Cloud Workload With VMD and R-Transformer

Predicting Instances Demand and Occupancy Toward Efficient VMs Rightsizing and Resources Allocation Strategies: Amazon Case Study

Contact Info

Product

Resources

About