Dynamic resource allocation for shared data centers using online measurements

By Abhishek Chandra, W. Gong, Prashant J. Shenoy. International Workshop on Quality of Service, 2003

318 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/f31f2f8f080409d92627b4a1af964f43a9c2d331

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

On the use of hybrid reinforcement learning for autonomic resource allocation (2007, methodology): “To bootstrap our hybrid RL approach with reasonable initial policies we adopt some of the recently proposed modelbased approaches for online performance management and resource allocation [30–33].”
CloudScale: elastic resource scaling for multi-tenant cloud systems (2011, methodology): “[12] proposed workload prediction using auto-regression and histogram based methods.”
Utility functions in autonomic systems (2004, background): “Since goals provide only a binary classification into “desirable” and “undesirable” performance, some have considered softer measures, such as maximizing the probability of achieving goals [7, 16, 19] or minimizing the degree to which goals are not met [4].”
Workload characterization and prediction in the cloud: A multiple time series approach (2012, background): “Also related to this study are the works on capacity management and virtual server placement [23], [24], [25], [26], [27], [28], which typically employ some workload modeling and prediction techniques.”
Application Performance Management in Virtualized Server Environments (2006, background): “As the state of the VMs change (due to changes in utilization), it causes utilization to exceed thresholds in the pre-defined allocation, leading to possible SLA violations.”
Auto-scaling to minimize cost and meet application deadlines in cloud workflows (2011, background): “These projects attempt to achieve application performance goals through dynamic resource provisioning in virtualized environments.”
PRESS: PRedictive Elastic ReSource Scaling for cloud systems (2010, methodology): “[9] proposed two workload prediction algorithms: auto-regression and histogram based method.”
Resource Management in Clouds: Survey and Research Challenges (2015, background): “[42], who present a prediction algorithm that estimates the workload parameters of applications based on time series analysis of request arrivals (which are modeled as an AR(1) process [33]); Bennani and Menasce [24], who use multi-class queuing networks to model the workload of dedicated data cente”
A Review of Auto-scaling Techniques for Elastic Applications in Cloud Environments (2014, methodology): “The auto-regression method has also been used for resource or workload forecasting ([49, 50, 60, 71, 73, 94]).”
A Hybrid Reinforcement Learning Approach to Autonomic Resource Allocation (2006, methodology): “Following [16], [17], [18], [19], we reestimate the parameters of our models at the end of each allocation interval t, based on measurements of various state variables such as the mean arrival rate 2t, the mean response time Rt, the total number of servers allocated nt, and the number of customers M”
An artificial intelligence perspective on autonomic computing policies (2004, methodology): “Related work on using Goal policies for network and system optimization includes [12], [13], [14].”
Dynamic Placement of Virtual Machines for Managing SLA Violations (2007, methodology): “The authors of [5] employ prediction techniques and queuing theory results to allocate resources efficiently within a single server serving a web workload.”