Assessment of Deep Sequence Models for Characterization and Prediction of Cloud Workloads

Forecasting cloud workloads is necessary for allocating resources when an application request is received at a data center. The workload of a data center can be considered as a time sequence. Workload forecasting of a data center can be done using sequential models like Long Short Term Memory (LSTM) or Gated Recurrent Networks (GRN). The time sequence of workload across VMs is typically tracked at the granularity of groups of VM. In this paper, we use LSTM, GRU, and Encoder-decoder network for forecasting resource requirements and assess the performance of each model. We compare these models in grouped workload settings. We use the Azure workload dataset with approximately 2 × 105VMs and the Bitbrains dataset with 1250 VMs for validating the models.

[1]  Jitendra Kumar,et al.  Performance Assessment of Time Series Forecasting Models for Cloud Datacenter Networks’ Workload Prediction , 2020, Wireless Personal Communications.

[2]  Ricardo Bianchini,et al.  Resource Central: Understanding and Predicting Workloads for Improved Resource Management in Large Cloud Platforms , 2017, SOSP.

[3]  Bo Li,et al.  Workload Prediction for Cloud Cluster Using a Recurrent Neural Network , 2016, 2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI).

[4]  Alexandru Iosup,et al.  Statistical Characterization of Business-Critical Workloads Hosted in Cloud Datacenters , 2015, 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[7]  Sheng Di,et al.  Host load prediction in a Google compute cloud with a Bayesian model , 2012, 2012 International Conference for High Performance Computing, Networking, Storage and Analysis.

[8]  Xifeng Yan,et al.  Workload characterization and prediction in the cloud: A multiple time series approach , 2012, 2012 IEEE Network Operations and Management Symposium.

[9]  Jerome A. Rolia,et al.  Workload Analysis and Demand Prediction of Enterprise Data Center Applications , 2007, 2007 IEEE 10th International Symposium on Workload Characterization.

[10]  Michael J. Frank,et al.  Making Working Memory Work: A Computational Model of Learning in the Prefrontal Cortex and Basal Ganglia , 2006, Neural Computation.

[11]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[12]  Michael C. Mozer,et al.  Induction of Multiscale Temporal Structure , 1991, NIPS.

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..