Smart and Easy Ways to Save On Data Center Cooling
Data center cooling and airflow management are an integrated part of the infrastructure planning process. It’s important to help your data center operate efficiently and optimally. However, cooling and AFM is never set in stone. It’s an ever-evolving consideration where data center managers must always look for ways to keep up with save on data center Cooling work to keep up.
I recently wrote a post, here on the Upsite blog, discussing how even a few degrees upwards in your set data center temperature can help you save a lot of money. I touched on some great ways to actually accomplish these types of savings. For example:
- Reduce air mixing via hot/cold air separation through
- Optimize floor layout (CFD)
- Closely couple supply and returns for the IT load
- Provide higher voltage to racks, reduce step downs
- Use air side economizers & cooling towers
- Deploy virtualization
- Implement power save mode
- Upgrade technology
- Decommission servers
- Bill-back power to drive behavior
The big challenge is that IT departments often overcool data centers to ensure that their mission critical equipment will not fail due to overheating.
“Data center managers can save up to 4 percent in energy costs for every degree of upward change in the baseline temperature, known as a set point,” said David J. Cappuccio, Gartner Managing VP and Chief of research. “The higher set point means less frequent use of air conditioning, which saves the energy used to run cooling systems
In my experience, I’ve had the chance to work with both data center infrastructure teams as well as IT managers and leaders. Aside from optimizing your floor layout or improving air side economizers – there are some powerful ways to not only improve data center efficiency; but also impact the efficiency of your IT teams and your business. Let’s examine three points specifically:
- Virtualization. So much has happened in the world of virtual technologies. We’re able to carve up servers even more effectively, deliver powerful applications much more efficiently, and contain an entire desktop infrastructure within a virtualization ecosystem. If you’re running a legacy virtualization platform – it may be time for an upgrade. Leaders in the space – Citrix, VMware, Microsoft, and others – are changing the way we consolidate and deploy entries workloads. Virtualization gives you the fundamental ability to deploy more workloads and support more users while using less gear. If you’re not leveraging virtualization today, or have a small virtualization footprint, you need to be looking at this more closely. Furthermore, evaluating your environment to ensure everything is working properly is critical as well.
- Upgrading Technology. One of the hottest trends in the data center is the deployment of new types of converged and hyper-converged infrastructure systems. Removing legacy blades and standalone servers has paved the way for better, more economical, data center infrastructure components. New types of converged systems allow you to combine network, storage, compute, and virtualization all under one management and architectural plane. In fact, I’ve worked with data centers and various business who’ve been able to drastically reduce their data center footprint, while further improving their cooling and AFM infrastructure. Don’t let legacy gear slow you down.
- Decommissioning servers. Oftentimes, we get complacent with the technology tools that we use. Since it’s working, why change it? However, this is not the mentality we need to be leveraging moving forward. Legacy servers will prevent you from increasing your set point and can be problems when you try to design more optimal airflow architectures. We’ll often find at least a few legacy servers that aren’t really doing very much at all. So, why not shut them down? They’re running some small app, maybe some kind of service, or it has a big sticker that says “don’t turn me off!” I highly recommend you examine your data center environment, find servers which are old and challenging to manage, and create a roadmap to decommission those systems. This is an absolute must in today’s digital world.
Remember, there are great ways to improve data center efficiency and the way you manage your environmental variables. However, the methods defined above actually help your data center, IT function, and the overall business. With virtualization, IT and business have more agility to deploy what they need with less gear. Upgrading your technology helps you maintain a competitive edge. Finally, removing old servers is a great way to get rid of legacy gear that’s just eating up power and resources. Remember, just because “it works” doesn’t mean it’s bringing value to your data center or your business.
Leverage smart ways to optimize your cooling and AFM strategy; and you’ll end up positively impacting IT operations, your business, and your users.
Learn the importance of calculating your computer room’s CCF by downloading our free Cooling Capacity Factor white paper.
About the Author
Bill Kleyman, CTO, MTM Technologies Bill is an enthusiastic technologist with experience in data center design, management, and deployment. His architecture work includes large virtualization and cloud deployments as well as business network design and implementation. Bill enjoys writing, blogging, and educating colleagues around everything that is technology. During the day, Bill is the CTO at MTM Technologies, where he interacts with enterprise organizations and helps align IT strategies with direct business goals. Bill’s white papers, articles, video blogs, and podcasts have been published on InformationWeek, NetworkComputing, TechTarget, Wall Street Journal, ZDNet, Slashdot, and many others.