4 FM quick reads on data centers
1. Securing Co-location Data Centers
This is Casey Laughman, managing editor of Building Operating Management magazine. Today's tip is that co-location data centers offer unique security challenges.
Co-location data centers provide multiple customers with the ability to locate network, server and storage gear through a shared infrastructure, minimizing both capital and operational costs for users. With a number of tenants in a variety of space configurations, co-location data centers face a unique infrastructure security challenge. Because co-location data centers can be typically subdivided by cages or just by individual cabinets or IT racks, electronic access control is key.
Cages should be treated as rooms, with locks so that air conditioning is the only element shared. Tenants should gain access only to their own cage through an active card reader or similar equipment at the cage itself. For smaller clients that want just a cabinet or two, specify access control down to the cabinet level to provide individual access. This will allow security personnel to track who is in each space moment-to-moment. For example, if there are five clients in one area serving different racks, tracking who was where when something goes down will be streamlined.
Similarly, monitoring can be another function of the access control system in a co-lo data center. Personnel can monitor access to cages, cabinets and racks to determine who is in the building, which tenants have their doors open, closed, etc. By having a dedicated security IP network, the security team can maintain tight control over security communications and allow for 24/7/365 operation, which can be a great selling point to prospective tenants.
Data Center Infrastructure Management helps streamline operations
This is Casey Laughman, managing editor of Building Operating Management magazine. Today's tip is that data center infrastructure management helps streamline the management of data centers.
Asking five data center managers how to manage a data center from a technology perspective — software, remotely and integrated — would likely yield at least eight different answers. The same question posed to a data center's facilities department would generate equally disparate responses. Ask that same question of a data center IT manager and a data center facilities manager at the same time and watch the fireworks fly. Why? Data centers are not managed by one group or department. While there is a larger goal in meeting the overall objectives of the company, the various departments often act as autonomous collectives. Data centers, however, are not owned by departments but by companies, and managing one should be a joint corporate effort.
Today, data centers can be managed as a total enterprise using data center infrastructure management (DCIM), or a "middleware," a software/hardware component which can tie formerly or currently different systems into a congruent monitoring environment. These dissimilar systems are often "owned" by different responsible departments. However, these systems can be configured to report up one chain of event and alert management.
The benefits of a good DCIM/middleware solution include faster change control; better, more coordinated, change management; views into the electrical and HVAC systems in reference to information and communications technology; views into IT and facility asset management; space planning; and general building environmental monitoring. It is important for facility managers to keep in mind when selecting a DCIM or middleware solution that because DCIM and middleware integrates independent systems beyond facilities, there is no means to discuss DCIM without concepts of an integration with the facility's systems.
Should the IT department be looking into DCIM, they would naturally focus on typical network management systems providers for a solution. Likewise, should DCIM be facilities-driven, traditional manufacturers of building systems can provide DCIM predicated on those building systems. However, with the high costs associated with DCIM procurement, installation and operations, it will make sense to view DCIM at the enterprise level and find a solution that works for each.
UPS Systems, DC Power Can Solve Energy Issues
This is Casey Laughman, managing editor of Building Operating Management magazine. Today's tip is that energy-saving UPS systems and DC power can help solve energy issues in data centers.
New UPS systems and high-voltage power supply are the two major trends in infrastructure design and engineering to reduce power consumption. DC power is a rare solution in the United States today, but worth considering the potential benefits and risks to save energy.
Manufacturers have modified the designs of new UPS systems with an "energy-saver" operating mode, which increases their power efficiency by approximately 90 percent while operating at any load. Owners have been cautious to adopt this new operating mode until the new systems prove themselves, but more owners are willing to consider it today.
Operating a UPS in energy-saver mode has clear advantages over the conventional operating mode of older UPS systems, whose efficiency falls into the 30 to 40 percent range at low loads. Even as the load increases on an older unit, it never achieves a higher efficiency level than about 80 percent.
High-voltage power supply is an effective way to cut capital costs and power requirements, and it is an idea whose time has finally come. Running at higher voltages not only reduces the capital cost of wiring as the system uses fewer, smaller wires, but at higher voltages, the current is lower, so less energy is lost through the wire. One downside is the fact that high-voltage computer equipment is still a custom order even though it is more available.
Running a data center on DC power saves energy by reducing the energy losses associated with the number of power conversions typically required in a conventional data center. Energy is lost at each conversion, making this approach less efficient than a DC system, which efficiently converts AC to DC once at high voltage and then distributes it to the computer's power supply.
Seismic Risk Important Consideration in Data Center Design
This is Casey Laughman, managing editor of Building Operating Management magazine. Today's tip is that seismic risk needs to be a consideration for data centers.
Earthquakes in Colorado and along the Eastern seaboard are reminders that seismic risk isn't simply an issue for California. What's more, good seismic design means strengthening both structural and non-structural components, such as fire sprinklers, emergency power and emergency communications. Structural components have received the lion's share of the attention in the past, but in recent years, non-structural components have been the subject of increasing focus.
Seismic compliance of nonstructural components is a complicated matter. Buildings in areas of high seismic activity have stringent requirements for mechanical and electrical non-structural components. Most areas of the United States, however, are exempt from seismic compliance.
The code trigger for many seismic requirements in both structural and non-structural components is the building's "seismic design category." The seismic design category is based on a structure's occupancy category and the severity of expected ground motion at the site.
Data centers — unless they are considered as part of essential facilities and are located in one of the four major seismic activity zones — are generally not subject to the most stringent seismic compliance requirements.
But just because seismic compliance isn't required for most data centers doesn't mean it's a good idea to ignore it. A robust design that can withstand seismic events can keep a facility from losing time and money to a data center outage. If emergency power systems continue to operate, they also help data centers by allowing the preservation of computer data to reduce financial risk and ensure business continuity during the actual quake and its aftershocks.