Performance Management of Cloud Populations via Cloud Probing

Zhanikeev, Marat

doi:10.2197/ipsjjip.24.99

“…For example, Virtual Network Embedding (VNE) problem in virtual networking (including clouds) is created as a means of distributing the process of optimization of service-specific topology and allowing for a certain level of coordination across services . Similarly, the method called Cloud Probing is a full-fledged DiY approach to topology optimization of cloud services (Zhanikeev, 2016). Incidentally, the latter method provides one of the two datasets for trace-based analysis further in this paper.…”

Section: Related Researchmentioning

confidence: 99%

“…• Cloud Measurement Project in (WISC), from this point on referred to as the WISC dataset; • The paper on the Cloud Probing method (Zhanikeev, 2016) whose trace will be referred to as the CloudProbing dataset.…”

Section: Analysis Setup: Models and Tracesmentioning

confidence: 99%

“…The CloudProbing dataset (Zhanikeev, 2016) also comes from a measurement project run on Amazon EC2 cloud. However, the measurement target was connections between regions, i.e.…”

Section: Analysis Setup: Models and Tracesmentioning

confidence: 99%

“…DC-DC connections. The paper in (Zhanikeev, 2016) argues that services can measure the network between its own locations and optimize its own performance by migrating to locations which provide a more optimal service overall.…”

Section: Analysis Setup: Models and Tracesmentioning

confidence: 99%

“…Part of the adjustment is to measure end-to-end network performance and use it to optimize the topology of the global distribution network. This topic is discussed in the measurement study in (Zhanikeev, 2016) and a recent paper on CDN service accountability in (Coileain, 2015). It is also revisited in the next section when reviewing the related literature.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fog Caching and a Trace-Based Analysis of its Offload Effect

Zhanikeev

¹

2017

International Journal of Information Technologies and Systems Approach

Self Cite

0

View full text Add to dashboard Cite

Many years of research on Content Delivery Networks (CDNs) offers a number of effective methods for caching of content replicas or forwarding requests. However, recently CDNs have aggressively started migrating to clouds. Clouds present a new kind of distribution environment as each location can support multiple caching options varying in the level of persistence of stored content. A subclass of clouds located at network edge is referred to as fog clouds. Fog clouds help by allowing CDNs to offload popular content to network edge, closer to end users. However, due to the fact that fog clouds are extremely heterogeneous and vary wildly in network and caching performance, traditional caching technology is no longer applicable. This paper proposes a multi-level caching technology specific to fog clouds. To deal with the heterogeneity problem and, at the same time, avoid centralized control, this paper proposes a function that allows CDN services to discover local caching facilities dynamically, at runtime. Using a combination of synthetic models and real measurement dataset, this paper analyzes efficiency of offload both at the local level of individual fog locations and at the global level of the entire CDN infrastructure. Local analysis shows that the new method can reduce inter-cloud traffic by between 16 and 18 times while retaining less than 30% of total content in a local cache. Global analysis further shows that, based on existing measurement datasets, centralized optimization is preferred to distributed coordination among services.

show abstract

Modeling Components for Cut-Through Performance Analysis of Network Switches

Zhanikeev

¹

2020

2020 16th International Conference on Network and Service Management (CNSM)

0

View full text Add to dashboard Cite

Fog Caching and a Trace-Based Analysis of Its Offload Effect

Zhanikeev

¹

Fog Computing

0

View full text Add to dashboard Cite

Many years of research on Content Delivery Networks (CDNs) offers a number of effective methods for caching of content replicas or forwarding requests. However, recently CDNs have aggressively started migrating to clouds. Clouds present a new kind of distribution environment as each location can support multiple caching options varying in the level of persistence of stored content. A subclass of clouds located at network edge is referred to as fog clouds. Fog clouds help by allowing CDNs to offload popular content to network edge, closer to end users. However, due to the fact that fog clouds are extremely heterogeneous and vary wildly in network and caching performance, traditional caching technology is no longer applicable. This paper proposes a multi-level caching technology specific to fog clouds. To deal with the heterogeneity problem and, at the same time, avoid centralized control, this paper proposes a function that allows CDN services to discover local caching facilities dynamically, at runtime. Using a combination of synthetic models and real measurement dataset, this paper analyzes efficiency of offload both at the local level of individual fog locations and at the global level of the entire CDN infrastructure. Local analysis shows that the new method can reduce inter-cloud traffic by between 16 and 18 times while retaining less than 30% of total content in a local cache. Global analysis further shows that, based on existing measurement datasets, centralized optimization is preferred to distributed coordination among services.

show abstract

Performance Management of Cloud Populations via Cloud Probing

Cited by 3 publications

References 18 publications

Fog Caching and a Trace-Based Analysis of its Offload Effect

Fog Caching and a Trace-Based Analysis of its Offload Effect

Modeling Components for Cut-Through Performance Analysis of Network Switches

Fog Caching and a Trace-Based Analysis of Its Offload Effect

Contact Info

Product

Resources

About