Performance Comparison: Virtual Machines and Containers Running Artificial Intelligence Applications

Marquez, Jack; Castillo, Mario

doi:10.1007/978-3-030-68285-9_20

Cited by 2 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These efficiencies are manifested as performance improvements over VMs which are significant at scale, as shown in several recent studies that compared VMs to containers in various applications, including the classic cloud computing use cases of artificial intelligence [10], big data [11], edge computing [12], and databases [13].…”

Section: Virtualization and Containerizationmentioning

confidence: 99%

“…However, with the trend toward containerization in the infrastructure, a concurrent trend is being seen in the industry moving toward microservices-based system architectures [3]. These efficiencies are manifested as performance improvements over VMs wh significant at scale, as shown in several recent studies that compared VMs to contai various applications, including the classic cloud computing use cases of artificial gence [10], big data [11], edge computing [12], and databases [13].…”

Section: Microservices Architecturementioning

confidence: 99%

“…Thus, we define a complementary utility function, U C (t), which determines the improvement in overall expected cost if a redundant microservice container c is safely shut down and removed from the cloud (10).…”

Section: Proposed Spot Market Orchestration Algorithmmentioning

confidence: 99%

“…Equation ( 10) is similar to (9) in that it calculates the cost of failure before and after removing the container, but with the sign reversed on the spot price, representing the cost savings achieved by removing the superfluous container from the system. Thus, Algorithm 1 consists of three key steps: pruning of failed microservice containers (thereby enabling the effective redundancy of the task to be calculated), addition of redundant microservice containers using (9) until there is no further utility, and removal of surplus containers using (10) until there is no further utility, as the case may be.…”

Section: Proposed Spot Market Orchestration Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

Spot Market Cloud Orchestration Using Task-Based Redundancy and Dynamic Costing

O’Neill,

Soh

2023

Future Internet

View full text Add to dashboard Cite

Cloud computing has become ubiquitous in the enterprise environment as its on-demand model realizes technical and economic benefits for users. Cloud users demand a level of reliability, availability, and quality of service. Improvements to reliability generally come at the cost of additional replication. Existing approaches have focused on the replication of virtual environments as a method of improving the reliability of cloud services. As cloud systems move towards microservices-based architectures, a more granular approach to replication is now possible. In this paper, we propose a cloud orchestration approach that balances the potential cost of failure with the spot market running cost, optimizing the resource usage of the cloud system. We present the results of empirical testing we carried out using a simulator to compare the outcome of our proposed approach to a control algorithm based on a static reliability requirement. Our empirical testing showed an improvement of between 37% and 72% in total cost over the control, depending on the specific characteristics of the cloud models tested. We thus propose that in clouds where the cost of failure can be reasonably approximated, our approach may be used to optimize the cloud redundancy configuration to achieve a lower total cost.

show abstract