Data Center Management – Solutions to Mitigate most Common Risks

June 28, 2012 By

Organizations today heavily depend on IT to support all their activities. This is why data centers have become a go-to facility for maintaining network and system functions. Customers too expect nothing but the best. This is why it is crucial to maintain a high performance service. Managing this infrastructure effectively is the key to enhanced operation rates. That is why data center managers should be able to track and assess the performance of individual sections of the data center effectively. Providing them with industry specific products should help them measure performance efficiently and mitigate potential risks. Let us look at these performance measurement products/tools and find out what they can do for the data center.

Availability of IT Equipment:

Downtime is data center manager’s worst nightmare. Generally customers expect system availability almost 100% of the time. Hence, IT personals need to access the reliability of the equipments of the data center so that that can reduce downtime considerably. The data obtained from assessing the equipments should also help them identify and alleviate issues.

Solution:

Technology has provided monitoring solutions which are based on the changing environmental factors and offers real time feedback about systems responding to factors like temperature, amperage draw, humidity, dew point, and physical security. These readings help the experts set thresholds for different atmospheric conditions. Additionally, this system also provides past information which can alert the personnel about the changing trends so that they are equipped with practices for that event.

Assessing Critical Services

Critical services means determining, classifying and rating the highest priority sites and facilities.  Systems like the four tiered classification system which is based on factors like useable capacity, fault tolerance, maintainability and sustainability helps in the evaluation .After undergoing the process, the administrators should be able to employ suitable managements and control systems for these critical sites which will help them mitigate potential vulnerabilities.

Solution:

Management solutions like KVM or service processor aggregation appliances offer the IT administrators access to servers, devices and even to equipments which are available locally and remotely. These provide BIOS – level access and offer assistance to reduce downtime by allowing instant access to all failed resources and data center management. These solutions also provide analysis and audit logging which helps the personnel gain valuable insight to the daily occurrence of the various operations in the data center.

Measuring the Data Center’s Energy Consumption

The rising rate of energy consumption is a cause of concern for most organizations. This has been a prime concern since companies are employing high density server racks which consume significant amount of energy. Experts are always looking for methods and practices to reduce the energy usage and making the data centers much more efficient. Proposition of implementing PUE and the DCE metrics should enable the data center managers estimate the efficiency of that data center. As Per Gris Grid which is consortium of IT companies, Power Usage Effectiveness (PUE) = Total Facility Power/ IT Equipment Power; Datacenter Efficiency (DCE) = IT Equipment Power/ Total Facility Power.  The PUE results are compared to different data centers to find out if the data center needs improvements to increase its efficiency.

Solution:

By using the results of PUE and DCE, administrators can evaluate the efficiency of their data center. Other than these, one can also use application specific data for evaluation. Performance rating tools like EPA energy star and Portfolio manager offers rating to the data center after comparing the results with other data centers. Switching to higher voltage power is also a practice which allows the IT equipment to operate much more efficiently. Regular audits of the facility including the racks and equipment will provide valuable insights like if the under the floor plan should be improved  or if some servers should be discarded. Using blanking panels and cable management accessories in the rack can also assist in reducing the energy usage of the data center making them energy efficient.

Data Center Talk updates its resources everyday. Visit us to know of the latest technology and standards from the data center world.

Please leave your views and comments on DCT Forum

Share on TwitterSubmit to StumbleUpon
Filed Under: Articles, Data Center Management, Data Center Power, Data Center Solutions Tagged With: , , ,

Reducing Data Center Cost Using Air Economizer – Intel

November 22, 2011 By

Electricity costs play a major role in the detail of the profit, loss or competence of a Data Center. Reducing them to a minimal amount is the key to an efficient and cost-effective site. Apart from the inevitable consumption of power by the server a major part of the electricity is consumed by the cooling systems. If an effectual way of achieving cooling is possible without the use of an air-conditioning system, the expenditure on cooling can be reduced considerably; here is where an Air-Economiser comes into play.

This approach to cooling has always been frowned upon by most in the industry mainly due to the feeble cooling power provided by prior prototypes of conceptually similar systems. The reliability of the servers can be questioned if proper cooling demands are not met; hence a good design towards 100 percent air cooling has never been successfully tested.

The Air-Economizer:

Typically an air-conditioning unit would draw the hot air generated by the working servers, cool it down to the set temperature and recirculate the same. Outside air would be taken at regular intervals to maintain the balance of fresh air in the Data Center. A revision in this process modifies the air-conditioning unit into an air-economizer. Here, the hot air would be expelled to the outside of the Data Center and fresh, cooler air would be drawn in, continuously or at regular intervals based on the heat generated.

The Experiment:

Intel took up a challenge to defy the common assumptions in the industry about the air-cooling technique by conducting a Proof of Concept (PoC) test. The test aimed at cooling servers at 90 degrees Fahrenheit with 100 percent outside air. Potential annual savings by achieving this could be US$2.87 Million for a 10-megawatt (Mw) plant!

The PoC was run using about 900 production Blade servers divided equally by two compartments place side by side. One was provided with warehouse grade Direct Expansion (DX) unit to recirculate the hot air and provide cooling at all times; and the other an air-economizer. The PoC was run in a dry climate over a time period of 10 months.

This is What Happened:

  • The temperature of the air supply in the economizer compartment varied between 64 and a little beyond 92 degrees Fahrenheit. Cheaper air-conditioning units with reduced response rate used in the PoC may have caused this.
  • Humidity varied between 4 to way over 90 per cent.
  • The exterior and interior of the servers were covered with a layer of dust.
  • Total power consumed was 111.78 kilowatts (KW) as compared to 500 KW for air-conditioning in both compartments. This is a 74 percent decrease in energy consumption!
  • The server failure rate in the economizer compartment was 4.46 percent as compared to the 3.38 percent in the main Data Center. The failure in the DX cooling compartment was 2.26 percent which is lesser than that of the main Data Center itself.

The Savings:

If the site of the Data Center can be located in more temperate conditions, the economizer technique can be used for more than 90 percent of the year. If 90 percent of the year a reduced power plan can be achieved and there is 74 percent savings in this plan approximately 67 percent of the total power used annually can be saved; for a 10MW plant this figure would be about US$2.87 million! Capital can be saved on building new Data Centers with fewer air-conditioning units. Potentially about 76 million gallons of water can be saved by applying the air-economizer technique.

The Catch:

Server failures remain consistent with variations with humidity, temperature and inferior air quality; hence air-economizers are suited only for drier and more temperate climates. The availability of such locations can be scarce. As the location of a Data Center is crucial for business and stable networking setting up sites at these locations if too remote is pointless.

The Cherry!

Intel plans to test the economizer technique and check for hardware degradation by using server aging analysis, they also plan on setting up a 1MW demonstration Data Center to conduct further research on this. The cost-effectiveness of the entire setup promises financial gains as well as a greener approach to Data Center construction; clearly, this is technology of the future.

Reference: Intel IT white paper

 

You can also keep up to date with current trends and technology by visiting Data Centre Talk where we keep you informed on important changes as they occur.

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Cooling, Data Center Design, Data Center Power Tagged With: , , , , , , , , , , , , , , , , , , , , , , , , , ,

Data Center Monitoring

November 13, 2011 By

The monitoring systems of a data center facility provide visibility into the major environmental factors that can affect availability such as humidity, air pressure, temperature, leak detection and particle count. Branch circuit monitoring and some integrated current transformers (CTs) can pull the details of power consumption from smart plugs or PDUs which will in turn enable you to track efficiency of power down the server or rack. You can realize considerable savings of utility power if you understand the environmental factors that problems of airflow can cause as well as making intelligent adjustments depending on your actual data. In addition, some systems have the availability of graphical representation of real time in the environment of the data center including your Power Usage Effectiveness (PUE). Features of monitoring real time enable some systems of a data center to store as well as playback data of the historical environment thus allowing you to easily view, graphically, improvements or challenges of humidity, pressure and temperature for every zone in the data center. The Active Controls integration is one of the most exciting developments of monitoring. These controls use the data provided by the monitoring systems to manage dynamically set points of CRAH temperature and speed fans that are variable, hence providing substantial and immediate power savings.

Ensynch’s NOC

Monitoring of a data center, the sensors of humidity and temperatures, airflow, power meters and efficiency measurements can help alert you to potential dangers while assisting you to reduce the cost of operation. The fundamental mission of the data center use is that it should remain online at all costs, but today, even though availability is still principal, fiscal metrics and costs receive more scrutiny than before. This is because the usage of energy across data centers in the US has reached into the billions. Similarly, an enterprise of e-commerce or a financial firm’s down time can within minutes reach millions. These grave financial consequences require data center managers to be equally proactive in safeguarding both up-time and in addressing inefficiency. In order for them to mange this they need intuitive and impaction tools that go past Excel sheets and simple Visio documents. The data center monitoring tools they choose should provide the data center with the operational intelligence and visibility to continually optimize their facility.

The Power of Visualization

The two main subsets of a data center cooling system are the temperature and airflow. Even so, it has proven very tough to monitor each of these two subsets in a production environment. Representing a snapshot of conditions of operation is the CFD or Computational Fluid Dynamics even though it is valuable for validation of design. When there is a change in these conditions, you require a new model that normally comes with heavy consulting charges. Thermal mapping is a less expensive but flexible alternative to the Computational Fluid Dynamics. The thermal maps offer color coded visibility of real time in the operating environment of a data center, while temperature maps offer temperature profiles that are color coded all through the facility and identify areas of over-cooling or hotspots. Thermal mapping also has humidity maps that monitor and color code profiles of humidity through the facility and pressure maps that compare the differential of pressure between plenums of air delivery and raised spaces of the floor. Unlike the Computational Fluid Dynamics which requires model input, thermal mapping establishes in real time this imagery through the end-to-end solution of hardware and software. The users will immediately see the fruits of their labor as they make improvements.

Branch circuit monitoring evades guess work from equipment provisioning, power usage and capacity planning. Users are able to understand available capacity and circuit loading, drill down to each circuit’s consumption and can even implement protocols and procedures of billing based on the actual usage of circuit power. The power of visibility of the branch circuit should not be underestimated. Alarms can be set around thresholds of power to help users immediately receive notification if there is any danger of tripping in one of the circuits. In addition, the element of color coding offers a clear safety path for installing fresh equipment.

IT and Facility Convergence

There is clear and excellent documentation of the IT and Facility divide in large organizations. Nevertheless, the line is blurring between these two departments in small companies or middle-sized enterprises. Take for example a university or a regional hospital; the physical data may be owned by an IT team of network engineers or system administrators while the staff of the facility works with the infrastructure of the larger campus. To make sure of reliability, the facility’s personnel should not concern themselves only with their comfort zone professions but they also need visibility into the physical infrastructure that provides support to HVAC, UPS, the data center generators. The operations of the data center could be compromised if the chiller of the campus suddenly went offline.

Thermal mapping not only allows real time monitoring solutions to enable professionals to understand the environment of the data center, but they can also pull information about real time from products of supporting infrastructure, and conveniently bring them into a single plane of glass. In other words, the professionals in a data center can have electrical and mechanical diagrams that are ‘one-line’ displayed on the screen.

 In situations where isolated infrastructure reports to a BMS, these systems of monitoring can utilize devices of gateway communication Bacnet and Modbus to pull points of data into the interface of the software. In the event that metering of the remote infrastructure does not occur, in most cases communication cards are installed to facilitate the integration of the system.

There are numerous options of instrumentation given the unique layout and lists of a data center. Some of the likely points of measurements and likely measurements include Rack Cooling Index (RCI), Recirculation airflow percentage and Bypass airflow percentage, Thermal Maps, Humidity, Hot Aisle Temperature and Cold Aisle Temperature. Data center control and monitoring is a crucial element in maintaining utmost availability of your critical operations.

You can also keep up to date with current trends and technology by visiting Data Center Talk where we keep you informed on important changes as they occur.

Share on TwitterSubmit to StumbleUpon
Filed Under: Data Center Management Tagged With: , , , , , , , , , , , , , ,