Efficient Autoscaling in the Cloud Using Predictive Models for Workload Forecasting

By Nilabja Roy, Abhishek Kumar Dubey, Aniruddha S. Gokhale. IEEE International Conference on Cloud Computing, 2011

644 citations recorded by the source corpus.

Large-scale component-based enterprise applications that leverage Cloud resources expect Quality of Service(QoS) guarantees in accordance with service level agreements between the customer and service providers. In the context of Cloud computing, auto scaling mechanisms hold the promise of assuring QoS properties to the applications while simultaneously making efficient use of resources and keeping operational costs low for the service providers. Despite the perceived advantages of auto scaling, realizing the full potential of auto scaling is hard due to multiple challenges stemming from the need to precisely estimate resource usage in the face of significant variability in client workload patterns. This paper makes three contributions to overcome the general lack of effective techniques for workload forecasting and optimal resource allocation. First, it discusses the challenges involved in auto scaling in the cloud. Second, it develops a model-predictive algorithm for workload forecasting that is used for resource auto scaling. Finally, empirical results are provided that demonstrate that resources can be allocated and deal located by our algorithm in a way that satisfies both the application QoS while keeping operational costs low.

Subfields: Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/d5f14ec84179dac2c00f9e5abbd027ec4674fa2a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

Citations in the corpus

MArk: Exploiting Cloud Services for Cost-Effective, SLO-Aware Machine Learning Inference Serving (2019, methodology): “Existing works employ many well-established resource estimation methods, such as linear regression [27], autoregressive models [34, 61], and neural networks [19, 53, 57, 65].”
Workload Prediction Using ARIMA Model and Its Impact on Cloud Applications’ QoS (2015, methodology): “[13] apply the ARMA model for 450 IEEE TRANSACTIONS ON CLOUD COMPUTING, VOL.”
A Review of Auto-scaling Techniques for Elastic Applications in Cloud Environments (2014, methodology): “[94] combined an ARMA model for workload forecasting, with the look-ahead controller in order to optimize the resource allocation problem.”
Elasticity in Cloud Computing: State of the Art and Research Challenges (2018, methodology): “[109] follow Auto-Regression technique while [23], [35], [67] follow ARMA approach.”
Autopilot: workload autoscaling at Google (2020, methodology): “…to these simple statistics would be to use more advanced time series forecasting methods, such as autoregressive moving average (ARMA) (as in [28] that also uses a job performance model), neural networks (as in [18]), recurrent neural networks as in [9, 20] or a custom forecast as in [13]…”
Resource Central: Understanding and Predicting Workloads for Improved Resource Management in Large Cloud Platforms (2017, background): “These works predict resource demand, resource utilization, or job/task length for provisioning or scheduling purposes [4, 9, 12, 14, 23].”
A Survey on Cloud Computing Elasticity (2012, methodology): “CHALLENGES AND OPEN ISSUES Although many elasticity solutions has been developed by cloud providers and in academic researches, some existing issues have not been fully addressed. infrastructure automatic reactive replication cost GoGrid [10] infrastructure manual replication performance OnApp [35] ”
Pocket: Elastic Ephemeral Storage for Serverless Analytics (2018, background): “Elastic resource scaling: Various reactive [34], predictive [25, 50, 65, 30, 62, 72, 75] and hybrid [24, 41, 33, 60] approaches have been proposed to automatically scale resources based on demand [64, 61].”