According to Gartner while 91 percent of
today's data is created and processed inside centralized data centers, by 2022
about 75 percent of data will need analysis and action at the edge.
A new report of 250 IT decision
makers, including IT director/IT manager/sys admins, data center managers,
application engineers, operations managers, and systems engineers reveals that
it's hard enough to collect data currently, and as things continue to move to
the edge and data becomes even more critical, it will only get more
difficult.
The report "The Modern Data Center: Supporting IoT Edge,
and Big Data-Generated Information," was a collaboration between Intel Data Center Manager and
Schneider Electric, and revealed that while edge computing
presents the ability to bring data processing and storage closer to the growing
number of connected devices, without the right tools, enterprises will struggle
to maintain control over their vast and complex data centers, making edge
computing strategies more difficult to adopt.
To learn more and dive into the findings, VMblog spoke with Jeff Klaus, General
Manager of Intel Data Center Management Solutions.
VMblog: Were you surprised that
almost half of the survey respondents said it's still a challenge to collect
data? Why is data collection so difficult for those managing data centers?
Managing power usage in any data center environment, whether
on-premises, a distributed data center architecture, or a regional or micro
data center facility serving the edge, can be complex.
Today, many data centers are maxed out in
power capacity and poor thermal design that make obtaining insights difficult.
So, I wasn't necessarily surprised when I saw that 40 percent of survey
respondents indicated that it's somewhat difficult to get data from the IT,
power, and cooling assets in their data center, and 7 percent of the
respondents indicated that it is very difficult to do so.
With 38 percent of respondents indicating
they are not using a DCIM tool, it's likely that the teams without the proper tools
to help gather critical data are hamstrung. Further, the cost and complexity for
these teams is going to continue rise as their decision-making process gets
delayed with a lack of insight into power and thermal monitoring, data center
health and energy efficiency, as well capacity planning.
VMblog: How is edge computing
impacting the data center?
Healthcare,
transportation, utilities, oil and gas, retail and agriculture are just a few
of the industries that will be transformed by smart systems and applications as
technology evolves from a state of connected things to IoT. But these types of
deployments require information processing closer to the source of the data.
Instead of incurring the cost and latency of sending this information to the
public cloud or an on-premise centralized data center, businesses are
incorporating edge computing within their infrastructures.
Of
the 87 percent of respondents that are collecting data from the IT, power, and
cooling assets in their data center, 64 percent are collecting data on the
edge. However, 54 percent of respondents are using one to three tools to
collect data from the edge and 32 percent are using four or more.
While edge computing presents the ability to bring
data processing and storage closer to the growing number of connected devices,
without the right tools enterprises will struggle to maintain control over
their vast and complex data centers, making edge computing strategies more
difficult to adopt. Furthermore,
with so many tools being used to collect data, the desire for a combined
solution at the edge to scale and automate is important.
VMblog: Can you make any
predictions for next year after gathering this insight?
In 2019 the edge use case I usually see is high bandwidth,
large volume applications. In fact, 50 percent of survey respondents indicated
that they are looking to address this exact use case when deploying an edge
solution. The next set of use cases after that are going to be moved up with 5G
enabling a network for machines to talk to machines, and machines to talk to
humans. We need the new networks to enable the amount of simultaneous
connections all the devices will require.
Also I think we'll see existing players and new entries
continue innovating edge stack infrastructure solutions, to handle the edge
applications demands. So not only will you have edge application, and data choices
to make, but also cloud infrastructure platforms that focus on various edge
blueprints and their applications to evaluate.
##
About Jeff Klaus
As General Manager of Intel® Data Center
Management Solutions, Jeff Klaus leads a global team that designs, builds,
sells and supports data center software products through an extensive
distribution network. Since joining Intel in 2000, Klaus built and maintains the
largest global distribution ecosystem of middleware solutions through Server
Hardware OEMs, Software Infrastructure Management Providers and Cloud Service
Providers.