Database Reference
In-Depth Information
content provider can also move from one cloud provider to another. However, achieving a
hybrid model is very challenging due to various CCDN ownership issues and QoS issues.
3.9 CCDN Monitoring
The CCDNs can deliver end-to-end QoS monitoring by tracking the overall service
availability and pinpoint issues. Clouds can also provide additional tools for monitoring
speci
c content e.g. video quality monitoring. However, developing a CCDN moni-
toring framework is always a challenge.
3.10 CCDN QoS
With the notion of virtually unlimited resources offered by the cloud, quality for service
plays a key role in CCDNs to maintain a balance between service delivery quality and
cost. De
s to enforce QoS and guarantee service quality is very
important and is also challenging. Further, the notion of hybrid clouds further complicate
CCDN QoS challenges due to the involvement of multiple cloud providers with varying
SLAs. CCDNs must accommodate highly transient, unpredictable users behaviour (arrival
patterns, service time distributions, I/O system behaviours, user pro
ning appropriate SLA
'
le, network usage,
etc.) and activities (streaming, searching, editing, and downloading).
3.11 CCDN Demand Prediction
It is critical that CCDNs are able to predict the demands and behaviours of hosted
applications, so that it can manage the cloud resources optimally. Concrete prediction or
forecasting models must be built before the demands and behaviours of CDN applications
can be predicted accurately. The hard challenge is to accurately identify and continuously
learn the most important behaviours and accurately compute statistical prediction func-
tions based on the observed demands and behaviours such as request arrival pattern,
service time distributions, I/O system behaviours, user pro
le, and network usage.
3.12 CCDN Cloud Selection
The diversity of offering by Cloud providers make cloud section to host CDN com-
ponents a complex task. A practical question to be addressed is: how well does a cloud
provider perform compared to the other providers? For example, how does a CDN
application engineer compare the cost/performance features of CPU, storage, and net-
work resources offered by Amazon EC2, Microsoft Azure, GoGrid, FelxiScale, Terre-
Mark, and RackSpace. For instance, a low-end CPU resource of Microsoft Azure is
30 % more expensive than the comparable Amazon EC2 CPU resource, but it can
process CDN application workload twice as quickly. Similarly, a CDN application
engineer may choose one provider for storage intensive applications and another for
computation intensive CDN applications. Hence, there is need to develop novel decision
making framework that can analyse existing cloud providers to help CDN service
engineers in making optimal selection decisions.
Search WWH ::
Custom Search