Webinar Takeaways: Power Capacity Planning Made Easy with AI and Machine Learning

The complexity of accurately planning and managing rack power capacity is a struggle for many modern data center managers. The traditional methods of capacity planning are unreliable and time-consuming, which led to many organizations turning to legacy Data Center Infrastructure Management (DCIM) software vendors that promised simplification but in reality provided nothing of the sort. In fact, according to 451 Research, capacity planning and power monitoring are the top two benefits data center managers want from their DCIM tool, but 25% of them deemed their product a failure and 10% ultimately abandoned their DCIM altogether.

In our recent webinar titled “Power Capacity Planning Made Easy with AI and Machine Learning,” Daniel Bizo, Principal Analyst, 451 Research, shared this insight and many more.

Accurately planning power capacity is easier said than done, but the repercussions of failing to do so are stranded rack power and space capacity and overspending on operating expenses. Fortunately, new automation capabilities in Sunbird’s second-generation DCIM solution now allow for fast, easy, and accurate power capacity planning.

In the webinar, you will also hear from successful Sunbird customers at Comcast, ProMedica, Simplot, and BJC Health as they share the obstacles they’ve had to overcome in power capacity planning and how Sunbird’s DCIM helps them reduce manual effort, inaccuracy, and risk.

Here are some key takeaways from the webinar:

Common Challenges of Data Center Power Capacity Management

The challenges many organizations run into in their attempts to plan and manage power capacity include:

• Expensive to build. It costs around $15,000 per cabinet to build the mission critical, redundant power chain to support the IT load. Any stranded capacity presents a substantial cost.
• Mission-critical uptime requirement. Data center managers must properly monitor and understand their power capacity and infrastructure health or risk costly downtime.
• Available capacity taken for granted. Overbuilding of data center capacity is widespread due to the expectation that the data center should be prepared for any unforeseen circumstance. This is a wasteful practice that leads to excessive stranded capacity which can come with significant costs.
• Lack of information and toolset. Data center managers need to make the most informed decisions when it comes to the efficient use of capacity. Having quick and easy access to highly accurate data is extremely valuable but requires the right tool.

Why the Traditional Capacity Planning Method Fails

Since a server device will never consume the amount of the nameplate rating—the maximum load the device should consume—data center managers follow the common practice of derating the nameplate value, usually to around 60% or 70%, when budgeting their power to determine how many servers can be deployed in a cabinet.

There are three ways this method fails data center managers:

• Manually intensive. It takes time and manual effort to calculate each server model’s derated value and then calculate each cabinet’s total budget value.
• Inaccurate. This approach is based on assumptions rather than data on how the devices are used and what the compute stress is in a specific environment.
• Costly. If the actual load is unknown and no live measurements are being made, there is a large potential for stranding capacity and overspending on capital expenditures to add new capacity.

A Better Way with Sunbird’s Auto Power Budget Feature

With recent advances in AI and machine learning technologies now available in Sunbird’s second-generation DCIM, the traditional method is no longer necessary. A complete solution of Sunbird’s DCIM software paired with intelligent rack PDUs brings automation to data center power capacity planning and management, making it fast, easy, and accurate.

Sunbird’s new Auto Power Budget feature unlocks precious rack capacity as each individual server make/model instance is assigned a unique power budget value that’s automatically set from real-time outlet-measured power readings from intelligent rack PDUs—your devices’ exact loads under your compute stress in your environment. This dramatically refines the traditional method of taking a percent of nameplate and improves the utilization of existing rack power and space.

Where the traditional derated budget method demands high effort and manual calculations, Auto Power Budget takes minimal effort and updates automatically. Where the traditional method provides low accuracy due to applying the same derating to all servers, Auto Power Budget provides high accuracy by using measured readings over long periods of time in its algorithms. And where the traditional approach presents high risk due to error-prone manual calculations and assumptions, Auto Power Budget’s built-in algorithms and validations intelligently manage risk.

Bringing It All Together

Data center managers must learn to better leverage their data to make smarter capacity planning decisions, or risk stranding capacity and overspending. Being able to automate this process is a key differentiator between a successful data center manager and one who struggles, and now with Sunbird’s Auto Power Budget feature, it’s never been easier.

Auto Power Budget takes the manual effort, inaccuracy, and risk out of data center power capacity planning, making it easy to deploy more compute power in existing racks. By automating power capacity planning, you will save time, reduce risk, eliminate stranded capacity, and save money.

Want to learn more about how second-generation DCIM software can help you make smarter, more informed data center capacity planning decisions with AI and machine learning? Watch the webinar, and then test drive Sunbird’s DCIM software today.