By Healthcare Facilities Today

It's a conundrum. Healthcare is becoming more and more dependent on IT infrastructure to support everything from patient records to medical equipment. At the same time, the budgets to support robust data center facilities at hospitals are ever more constrained. In an ideal world, the answer would be to build new data center capacity as needed, but in addition to tight funds, crowded campus footprints make it tricky to find space for expanded data center facilities.

While avoiding a new data center is not possible indefinitely, it is possible for healthcare facility managers to stretch their existing data center infrastructure to support as much IT growth as possible. Here are ten steps from a Health Facilities Management article to consider to get the greatest IT bang for the FM buck when it comes to data centers: 

1. Figure out what you have. Inventory space, servers, network equipment and applications. Detail the existing cooling and power infrastructure capacities and current demand, down to the rack if possible.

2. Identify the necessary reliability factor. In healthcare this is usually Tier 3, as defined by the Uptime Institute. In this scheme, cooling systems need one backup, and power systems are fed by utility and emergency generators.

3. Use data center infrastructure management (DCIM) software to redistribute and optimize power use. This software gives real time insight into performance and demand, which can help identify peak load times. Facility managers can move some computing tasks to non-peak times, stretching out the capacity of the system.

4. Define what upper level of capacity is based on existing infrastructure and try to predict growth. Facility managers can use data center predictive modeling software to predict future loads. These use the DCIM data as a baseline and allow FMs the ability to speak to the full impact of proposed IT equipment by painting a clear picture of the current infrastructure capacity and how the IT equipment is consuming that capacity.

5.  Server virtualization. This cuts on square footage but increases cooling needs per rack.

6. Consider cloud computing for non-critical applications. (Check out this Building Operating Management article for information on expanding data centers to the cloud.)

7. Increase uninterruptible power supply (UPS) capacity incrementally and spread the IT load evenly over the UPS for greater efficiency.

8. Set a standard that all new IT equipment should be ASHRAE Class A4-rated, which tolerates inlet temperatures as high as 104 degrees. Consider installing Class A4 equipment in the return air path of Class A1 equipment, gaining energy efficiency by cooling two equipment areas with one system. However, this must be considered in the face of increased failure rate and noise.

9. Get the most out of allowable ASHRAE temperature and humidity levels. Even for Class A1 or A2 equipment, the allowed maximum for inlet starts at 89.6 degrees. The allowed humidity is 20 to 80 percent. "Raising temperature alone has limited effectiveness at expanding capacity because the distribution systems in the equipment are sized for rejecting a maximum amount of total heat, regardless of the specified temperature difference. Expanding the operating humidity range can significantly reduce cooling loads," says the article.

10. Capitalize on the expanded range to be able to use airside and waterside economizers. Also use the expanded range to be able to use outside air to cool water and air to the wet-bulb temperature, which can be 28 degrees F less than the dry-bulb temperature at peak. This is called adiabatic cooling.

Read the HFM article.