Title
A Framework for Amazon EC2 Bidding Strategy under SLA Constraints
Abstract
With the recent introduction of Spot Instances in the Amazon Elastic Compute Cloud (EC2), users can bid for resources and, thus, control the balance of reliability versus monetary costs. Mechanisms and tools that deal with the cost-reliability tradeoffs under this scheme are of great value for users seeking to reduce their costs while maintaining high reliability. In this paper, we propose a set of bidding strategies under several service-level agreement (SLA) constraints. In particular, we aim to minimize the monetary cost and volatility of resource provisioning. Essentially, to derive an optimal bidding strategy, we formulate this problem as a Constrained Markov Decision Process (CMDP). Based on this model, we are able to obtain an optimal randomized bidding strategy through linear programming. Using real Instance price traces and workload models, we compare several adaptive checkpointing schemes in terms of monetary costs and job completion time. We evaluate our model and demonstrate how users should bid optimally on Spot Instances to reach different objectives with desired levels of confidence.
Year
DOI
Venue
2014
10.1109/TPDS.2013.15
IEEE Trans. Parallel Distrib. Syst.
Keywords
Field
DocType
sla constraints,cost-reliability tradeoffs,contracts,spot instances,workload model,ec2,tendering,service-level agreement,checkpointing,adaptive checkpointing schemes,monetary cost minimization,cloud computing,amazon ec2 bidding strategy,optimal randomized bidding strategy,linear programming,optimal bidding strategy,randomized bidding strategy,monetary cost,amazon elastic compute cloud,job completion time,workload models,high reliability,constrained markov decision process,bidding strategy,resource provisioning volatility,electronic commerce,cmdp,instance price traces,markov processes,cost reduction,resource management
Markov process,Computer science,Markov decision process,Provisioning,Linear programming,Procurement,Bidding,Cost reduction,Distributed computing,Cloud computing
Journal
Volume
Issue
ISSN
25
1
1045-9219
Citations 
PageRank 
References 
16
0.65
12
Authors
4
Name
Order
Citations
PageRank
Tang Shaojie12224157.73
Jing Yuan223711.92
Cheng Wang328527.81
Xiang-Yang Li46855435.18