Three common mistakes in data center design and planning and how to avoid them

Designing and building a sustainable and efficient data center is a challenging process and full of potential pitfalls, especially if it cannot affect availability (uptime). In the data center design and planning, not only must the correct decision be made, but also the decision must be made in the correct order.

The adverse effects of poor design and planning include not only waste of time and energy and costly redesign work, but even worse, if the data center provider or the final data center facility is not competitive or cannot meet business needs , They may cause the company’s products or services to be delayed on the market. This may force companies to re-evaluate their outsourcing strategy, because more hosting services and cloud computing services must be found to meet business needs.
 
To help complete the design process successfully, the following analyzes and explains three common mistakes many companies make during the data center planning and design phase and how to avoid them:
 
Mistake 1: Improper setting of design standards and performance characteristics

Mistake 1: Improper setting of design standards and performance characteristics
 
Enterprises usually want the best performance, but unless they have a lot of resources from AWS or Microsoft, they may not need to build a Tier IV data center, in other words, don't overbuild. In the long run, it will eventually increase upfront costs, reduce energy efficiency, and the cost of maintaining and operating data center facilities will also be higher. In particular, stakeholders of non-technical projects may demand the best results without fully understanding the consequences such as cost and time to market. After making a lot of investment, it may be too late to realize the impact of these wrong decisions during the design or construction phase.
 
Industry vendors have developed some free tools for people to use in the early planning stages of data center projects. For example, data center trade-off tools can quickly compare and contrast various design alternatives very easily, so that even non-technical project participants can understand the trade-offs of various design decisions. These tools can save planners a lot of time and effort. data center


Reference design is another excellent free tool that can help companies complete the early planning phase faster and complete the detailed design phase with fewer errors. Its reference design library provides nearly a hundred high-level conceptual plans on how to build a data center. Each design covers electrical, mechanical, and IT space systems, with a specific set of performance characteristics.
 
Another mistake that companies tend to make is to pay too much attention to the details of technical specifications, and their speed and feedback may not be consistent with the company's business goals and risk status. For companies to pay attention to the overall situation, criticality (ie Tier level), efficiency, budget, capacity, power density, and future growth plans and other large-scale key project parameters are critical. These parameters drive almost all other aspects of data center design.
 
Planning failures, wasteful designs, and schedule delays can often be traced back to the absence of all input data collected by key stakeholders. The data center project manager needs to reach a consensus on these key project parameters.
 
In the early stages of this process, don't forget to collaborate with leaders from finance, IT, and business. Companies can hold seminars to discuss and agree on these trade-offs.


Mistake 2: Site selection before determining data center design standards
 
A common "put the cart before the horse" error is wasting time and effort to find the location of the data center before the data center design standards are determined. Problems may arise when deciding where to build or a specific geographic area without knowing the full scope of the data center.
 
When the geographical environment is selected prematurely, it may even affect the design requirements of the data center. For example, you may find that the availability, reliability, and cost associated with the power grid, water supply, and fiber optic cables are limited. Other site selection criteria include being close to emergency services such as fire stations, or close to major transportation facilities such as expressways.
 
The location of the data center should also take into account disaster prevention and preparedness-companies should be aware of the potential risks associated with flash floods, tornadoes, hurricanes, earthquakes, or other natural disasters.



On the other hand, building a new data center can also provide more opportunities to create a green, sustainable, and environmentally friendly facility. Therefore, the design criteria and site selection should also consider the opportunities for companies to obtain electricity from renewable energy sources (such as solar or wind energy) by themselves or through independent power producers (IPP). When energy and sustainability goals are important, utility suppliers, power purchase agreement terms, and renewable energy credits or carbon offsets are other key factors to consider.
 
Mistake 3: Planning the space before determining the design criteria
 
Some users rate data center standards based on the space required to accommodate their critical IT infrastructure, which may be very important. In a powerful computer room space, the ratio of IT equipment footprint to supporting equipment may be as high as 1:1. But this can cause major errors.
 
Mechanical equipment and electrical equipment take up a lot of space. In addition, many companies neglect the space required to accommodate office space, equipment yards, and temporary storage areas for IT equipment. Therefore, it is very important to determine the design standards before making a space plan. Without such a plan, it is impossible to plan the total space required to meet the overall demand.



It is important to create a detailed data center floor plan early in the design process. The floor plan should be considered as part of the preliminary specification process and should be determined before the detailed design begins.
 
Plan and design the data center correctly
 
The process of designing and building a data center is very complicated, and don’t make mistakes that might waste a lot of time and money. If the right problems are solved by the right people and in the right order, vague requirements can be transformed into detailed design plans that meet business needs. In the most important planning stage, companies need to establish key project parameters, develop system concepts, combine user preferences and constraints, and determine implementation requirements.

【Editor's Choice】