data centers in the age of the industrial internet

Data Centers in the age of the Industrial Internet

Industrial Internet

Industrial Internet – The Next Big Wave

• The Industrial Internet brings together the advances of two transformative revolutions:

the myriad machines, facilities, fleets and networks that arose from the Industrial Revolution, and the more recent powerful advances in computing, information and

communication systems brought to the fore by the Internet Revolution

• It is a wave of innovation that promises to change the way we do business and interact

with the world of industrial machines

Wave 1 Industrial Revolution

Machines and factories that

power economies of scale and scope

Wave 2 Internet

Revolution Computing

power and rise of distributed information

networks

Wave 3 Industrial Internet

Machine-based analytics: physics based,

deep domain expertise, automated,

predictive

Industrial Internet – What is it comprised of?

Three essential elements embody the essence of Industrial Internet:

• Intelligent Machines New ways of connecting the word’s myriad of machines, facilities, fleets and networks with advanced sensors, controls and software applications

• Advanced data analytics use physics-based analytics, predictive algorithms,

automation and deep domain expertise in material science, electrical engineering and other key disciplines required to understand how machines and larger systems operate

Using advanced data analytics can improve fuel efficiency, help identify machinery maintenance issues and make other operational improvements that could add up to trillions of dollars in savings

• People at work: connecting people, whether they be at work in industrial facilities, offices, hospitals or on the move, at any time to support more intelligent design, operations, maintenance as well as higher quality service and safety. Connecting and combining these elements offers new opportunities across firms and economies.

Industrial Internet – How does it work?

Data Collection – An essential element of the

Industrial Internet

Where does the data come from?

• The Industrial Internet starts with embedding sensors and other advanced

instrumentation in an array of machines from the simple to the highly complex

• This allows the collection and analysis of an enormous amount of data can be

used to improve machine performance, and inevitably the efficiency of the

systems and networks that link them

• An essential component of GE’s Intelligent Platforms business is Control and

Communication Systems that comprises advanced data collection and

advanced analytics

• The opportunity is huge considering the specific physical assets involved in

various parts of the industrial system.

How ‘BIG’ is this data?

• The industrial system is comprised of huge numbers of machines and critical

systems

• There are now millions of machines across the world ranging from simple electric

motors to highly advanced computed cosmography (CT scanners) used in the

delivery of health care

• All of these pieces of equipment are associated with information (temperature,

pressure, vibration and other key indicators) and are valuable to understanding

performance of the unit itself and in relation to other machines and systems

• Traditional statistical approaches use historical data gathering techniques where

often there is more separation between the data, the analysis, and decision making.

With advanced system monitoring, the ability to work with larger volumes of real-

time data has been expanding


Commercial Jet Aircraft

• There are approximately 21,500 commercial jet aircraft and 43,000 jet engines in

service around the world in 2011*

• Commercial jets are most commonly powered by a twin jet engine configuration.

These aircraft take approximately 3 departures per day, for a total of 23 million departures annually.

• Each jet engine contains many moving parts; however, there are three major pieces of

rotating equipment: a turbo fan, compressor, and turbine. Each of these components

will be instrumented and monitored separately. In total, there are approximately

129,000 major pieces of spinning equipment operating in the commercial fleet today

• While it is probably impossible to know precisely how many machines and devices,

fleets, and networks exist within the world’s ever expanding industrial system, it is possible to look at some specific segments to get a feel for the scale of the industrial

system


21,500 commercial

jet aircraft

43,000 jet engines

3 departures per day

23 million departures

annually

3 major pieces of

rotating

equipment in

each jet engine

Turbo fan Compressor

Turbine

Each of these

components will be instrumented and monitored

separately

129,000 major pieces of spinning equipment operating in the

commercial fleet today

How Would This Data Help?

• The Industrial Internet promises to have a range of benefits spanning machines,

facilities, fleets and industrial networks, which in turn influence the broader

economy

• Intelligent instrumentation enables individual machine optimization, which

leads to better performance, lower costs and higher reliability

• Intelligent decisioning will allow smart software to lock-in machine and system-

level benefits

• Further, the benefits of continued learning holds the key to the better design of

new products and services— leading to a virtuous cycle of increasingly better

products and services resulting in higher efficiencies and lower costs

How Would This Data Help?

Data Collection and Storage – Data Centers

Where does all this data sit?

• Data collection is the first step in the process of transforming recorded data into

information

• Most data centers now have to deal with the massively increasing volumes of

data collected from entities such as the industrial internet. For eg., data

collection at GE from jet engines in one year has been more than that collected in 96 years!

• By 2016, most new datacenters will be 40% smaller while supporting a 300%

increased workload

• Data centers facilities must be cost-effective, but flexible enough to enable

virtualization, cloud computing, mobility, social media and collaboration

applications.

Managing Data Centers – Key Challenges

Key Challenges involved in managing data centers include:

Standalone subsystems

• Visibility into baseline infrastructure eg. paralleling switchgear, standby power generation,

alternative energy sources, automatic transfer switches, UPS systems and chillers which may not

easily integrate with each other, due to disparate systems, so failures have to be managed locally

• Identifying trends, uncovering root causes and implementing strategies for improvement cannot

happen due to difficulty to collect, correlate and analyze data from these systems

Inability to scale solution

• Scalability is a challenge with standalone . Adding redundancy eliminates single points of failure

and increases reliability, but also increases complexity and systemic risk, threatening reliability

altogether

• If a data center needs to scale its technology infrastructure, extensive reprogramming and

reconfiguration is often required, which also increases costs and time to solution

Managing Data Centers – Key Challenges

Proprietary technologies

• Systems that leverage proprietary technologies generally face a higher likelihood of failure

when these systems are interfaced with components from other manufacturers or software

from third-party suppliers

Integration of advanced hardware and software technologies can deliver insight through

information for the highest level of efficiency, reliability, and uptime — enabling a

sustainable competitive advantage

Data Center Strategy and Key Components

Key Components of a Holistic Data Center Strategy

• As downtime costs continue to rise, forward-looking strategies must address

various infrastructure challenges and encompass both hardware and software

solutions that are scalable, open, and tightly integrated—working together as a

comprehensive system

• Integrating existing infrastructures with high availability control and advanced software capabilities such as monitoring or alarming can significantly increase

operational performance by reducing human error, improving system availability

and performance, and reducing energy consumption

• Following are five key components that are critical to helping data centers shift toward long-term maintainability, efficiency, and reliability for facility optimization


1. High availability control

Availability control is at the core of data center performance and helps data centers ensure data

protection, continuous operations, and recovery, in the event of an outage

A high availability solution that synchronizes systems at the beginning and end of each logic

scan execution can keep all variable data the same—providing fast, full system synchronization

and bumpless switchover for maximized reliability

Why high availability control?

Reliability:

Insure consistent critical control system availability Control system malfunctions must not

impact uptime

Performance:

Quick response to catastrophic failures Concurrent maintainability

Precision:

No loss of data during system failover Eliminate single point of failure


2. Advanced data collection

• Continuous operation and performance improvements of all data center systems are

only as good as the runtime data collected for analysis and action from all the

infrastructure systems

• A key challenge for many data centers today is the difficulty of integrating many disparate

hardware and software systems and standalone products into a common data collection and management strategy

3. Advanced analytics

• With the data collected, advanced analytics can then help extract knowledge from the data, which is critical to driving corrective action for maximized performance and reliability

• Advanced analytics can provide data centers with critical context to otherwise static historical and real-time data, increasing data integrity and enabling better decision making for improved facility management and performance


4. Critical alarm response

• Leveraging next-generation alarm response management software can help data

centers reduce costs and risk by ensuring the correct response to the small subset of

critical alarms—increasing system availability and reducing liability exposure and costs

• Alarm response management software can help operators make better decisions by

providing information and guidance with the exact responses needed to address critical alarms. It also helps track performance and allows managers to review results and

improve response instructions.


Why advanced data collection, analytics and critical alarm response?

Reliability: Measure and analyze system performance

metrics Energy optimization Leverage redundancy depth to detect and

repair failures while maintaining continuous system operation

Insight: Quick response to catastrophic failures

Concurrent maintainability

Precision: Data collection to assess downtime events

Eliminate human error


5. Integration of all systems

• As improving efficiency of power supply systems is a key goal, it is only through an integrated,

holistic approach that data centers can gain real-time views across systems and global comparative analytics for complete facility risk assessment

• The selected technology for managing power supply systems and infrastructure should be open

and flexible for seamless integration with a data center’s current systems as well as its future technologies because integration enables critical understanding into the overall state of the facility


Total System Integration

•Power Generation

•Electrical

Distribution

•Cooling:

IT & Facility

•IT

Infrastructure

•Facilities

Infrastructure

•Power Quality

• Facility Management Integration, Data Acquisition, Analysis, Visualization, Optimize & Control

‐ Conventional ‐ Alternatives ‐ Back-up

‐ UPS ‐ Monitoring &

Optimization

‐ Switchgear ‐ Intelligent

Control ‐ ATS

‐ HVAC ‐ Automation ‐ Drives

‐ Security ‐ Lamps ‐ Lighting Control

‐ Racks ‐ Servers ‐ Software

• High Availability Control

– Real-time views across systems – Global comparative views & analysis – Prioritized / dollarized analysis for improvement

decision making – Advanced Control Strategies

GE Data Center – An Example

GE Data Center

• 11% energy savings

• 20% water savings

• 50% chemicals

reduction

Challenges

• 30,000 feet2 raised floor, 3,800 servers, 2/5MVA UPS

• Reducing water & electrical consumption

• Improving maintainability • Cooling • Disparate & overlapping hardware & software

systems for redundancy & reliability

Operational Results

• Complete facility visualization

• Insight into prioritized actions through

actionable data

• Automatic PUE & EPA compliance data

collection

• Multiple maintenance contracts eliminated

• High Availability control of data center

cooling system

Conclusion

• Data centers need to capitalize on the real opportunity available to maximize their

system reliability for continuous operations by moving toward an integrated and

holistic technology approach

• High availability redundant control, combined with a set of critical software

capabilities, allows data center users to precisely monitor and control all critical systems; understand cross-functional synergies, constraints, and performance

and cost metrics; and immediately respond to critical events with corrective action

• By implementing the right mix of enabling technologies that provide critical

capabilities, data centers can position themselves to attain the highest level of reliability, availability, and operational efficiency—optimizing the management of

their facility for a sustainable competitive advantage

Connect with us on /GEIndia

/GEIndia

@GEIndia

data centers in the age of the industrial internet

Technology