Abstract | ||
---|---|---|
Satisfying cloud customers’ requirements, i.e., respecting an agreed-on service level agreement (SLA), is not a trivial task in a multi-cloud context. This is mainly due to divergent SLA objectives among the involved cloud service providers and hence divergent reconfiguration strategies to enforce them. In this paper, we propose a hierarchical representation of multi-cloud SLAs: sub-SLAs associated with a system’s components deployed on distinct cloud service providers and global-SLA associated with the whole system. We also enrich these SLA representations with state machines reflecting reconfiguration strategies defined by cloud customers. Then, we propose an autonomous multi-cloud resource orchestrator based on the MAPE-K adaptation control loop to enforce them and to avoid SLA violations. Finally, in order to check the conformity of this enforcement with defined multi-cloud SLA, we propose an approach for multi-cloud SLA reporting inspired by conformance checking techniques. An implementation of the approach is presented in the paper and illustrates the approach feasibility.
|
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s11227-022-04363-0 | The Journal of Supercomputing |
Keywords | DocType | Volume |
SLA, Cloud resources, Multi-cloud, Autonomous computing, Reconfiguration strategy, State machine | Journal | 78 |
Issue | ISSN | Citations |
11 | 0920-8542 | 0 |
PageRank | References | Authors |
0.34 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeremy Mechouche | 1 | 0 | 0.34 |
Roua Touihri | 2 | 0 | 0.34 |
Mohamed Sellami | 3 | 126 | 19.13 |
Walid Gaaloul | 4 | 613 | 77.38 |