Adata center is abuilding, a dedicated space within a building, or a group of buildings[1] used to housecomputer systems and associated components, such astelecommunications andstorage systems.[2][3]
SinceIT operations are crucial forbusiness continuity, it generally includesredundant or backup components and infrastructure forpower supply,data communication connections, environmental controls (e.g.,air conditioning, fire suppression), and various security devices. A large data center is an industrial-scale operation using as much electricity as a medium town.[4] Estimated global data center electricity consumption in 2022 was 240–340 TWh, or roughly 1–1.3% of global electricity demand. This excludes energy used for cryptocurrency mining, which was estimated to be around 110 TWh in 2022, or another 0.4% of global electricity demand.[5] TheIEA projects that data center electric use could double between 2022 and 2026.[6] High demand for electricity from data centers, including bycryptomining andartificial intelligence, has also increased strain on local electric grids and increased electricity prices in some markets.
Data centers can vary widely in terms of size, power requirements, redundancy, and overall structure. Four common categories used to segment types of data centers are onsite data centers, colocation facilities,hyperscale data centers, and edge data centers.[7]
Data centers have their roots in the huge computer rooms of the 1940s, typified byENIAC, one of the earliest examples of a data center.[8][note 1] Early computer systems, complex to operate and maintain, required a special environment in which to operate. Many cables were necessary to connect all the components, and methods to accommodate and organize these were devised such as standardracks to mount equipment,raised floors, andcable trays (installed overhead or under the elevated floor). A singlemainframe required a great deal of power and had to be cooled to avoid overheating. Security became important – computers were expensive, and were often used formilitary purposes.[8][note 2] Basic design guidelines for controlling access to the computer room were therefore devised.
During the microcomputer industry boom of the 1980s, users started to deploy computers everywhere, in many cases with little or no care about operating requirements. However, asinformation technology (IT) operations started to grow in complexity, organizations grew aware of the need to control IT resources. The availability of inexpensivenetworking equipment, coupled with new standards for the networkstructured cabling, made it possible to use a hierarchical design that put the servers in a specific room inside the company. The use of the termdata center, as applied to specially designed computer rooms, started to gain popular recognition about this time.[8][note 3]
A boom of data centers came during thedot-com bubble of 1997–2000.[9][note 4]Companies needed fastInternet connectivity and non-stop operation to deploy systems and to establish a presence on the Internet. Installing such equipment was not viable for many smaller companies. Many companies started building very large facilities, calledinternet data centers (IDCs),[10] which provide enhanced capabilities, such as crossover backup: "If a Bell Atlantic line is cut, we can transfer them to ... to minimize the time of outage."[10]
The termcloud data centers (CDCs) has been used.[11] Increasingly, the division of these terms has almost disappeared and they are being integrated into the termdata center.[12]
The global data center market saw steady growth in the 2010s, with a notable acceleration in the latter half of the decade. According toGartner, worldwide data center infrastructure spending reached $200 billion in 2021, representing a 6% increase from 2020 despite the economic challenges posed by theCOVID-19 pandemic.[13]
The latter part of the 2010s and early 2020s saw a significant shift towardsAI andmachine learning applications, generating a global boom for more powerful and efficient data center infrastructure. As of March 2021, global data creation was projected to grow to more than 180 zettabytes by 2025, up from 64.2 zettabytes in 2020.[14]
The United States is currently the foremost leader in data center infrastructure, hosting 5,381 data centers as of March 2024, the highest number of any country worldwide.[15] According to global consultancy McKinsey & Co., U.S. market demand is expected to double to 35 gigawatts (GW) by 2030, up from 17 GW in 2022.[16] As of 2023, the U.S. accounts for roughly 40 percent of the global market.[16]
A study published by theElectric Power Research Institute (EPRI) in May 2024 estimates U.S. data center power consumption could range from 4.6% to 9.1% of the country’s generation by 2030.[17] As of 2023, about 80% of U.S. data center load was concentrated in 15 states, led by Virginia and Texas.[17]
Modernization and data center transformation enhances performance andenergy efficiency.[18]
Information security is also a concern, and for this reason, a data center has to offer a secure environment that minimizes the chances of a security breach. A data center must, therefore, keep high standards for assuring the integrity and functionality of its hosted computer environment.
Industry research companyInternational Data Corporation (IDC) puts the average age of a data center at nine years old.[18]Gartner, another research company, says data centers older than seven years are obsolete.[19] The growth in data (163 zettabytes by 2025[20]) is one factor driving the need for data centers to modernize.
Focus onmodernization is not new: concern about obsolete equipment was decried in 2007,[21] and in 2011Uptime Institute was concerned about the age of the equipment therein.[note 5] By 2018 concern had shifted once again, this time to the age of the staff: "data center staff are aging faster than the equipment."[22]
TheTelecommunications Industry Association's Telecommunications Infrastructure Standard for Data Centers[23] specifies the minimum requirements for telecommunications infrastructure of data centers and computer rooms including single tenant enterprise data centers and multi-tenant Internet hosting data centers. The topology proposed in this document is intended to be applicable to any size data center.[24]
Telcordia GR-3160,NEBS Requirements for Telecommunications Data Center Equipment and Spaces,[25] provides guidelines for data center spaces within telecommunications networks, and environmental requirements for the equipment intended for installation in those spaces. These criteria were developed jointly by Telcordia and industry representatives. They may be applied to data center spaces housing data processing or Information Technology (IT) equipment. The equipment may be used to:
Data center transformation takes a step-by-step approach through integrated projects carried out over time. This differs from a traditional method of data center upgrades that takes a serial and siloed approach.[26] The typical projects within a data center transformation initiative include standardization/consolidation,virtualization,automation and security.
A raised floor standards guide named GR-2930 was developed byTelcordia Technologies, a subsidiary ofEricsson.[38]
Although the firstraised floor computer room was made byIBM in 1956,[39] and they've "been around since the 1960s",[40] it was the 1970s that made it more common for computer centers to thereby allow cool air to circulate more efficiently.[41][42]
The first purpose of the raised floor was to allow access for wiring.[39]
Thelights-out[43] data center, also known as a darkened or a dark data center, is a data center that, ideally, has all but eliminated the need for direct access by personnel, except under extraordinary circumstances. Because of the lack of need for staff to enter the data center, it can be operated without lighting. All of the devices are accessed and managed by remote systems, with automation programs used to perform unattended operations. In addition to the energy savings, reduction in staffing costs and the ability to locate the site further from population centers, implementing a lights-out data center reduces the threat of malicious attacks upon the infrastructure.[44][45]
Generally speaking, local authorities prefer noise levels at data centers to be "10 dB below the existing night-time background noise level at the nearest residence."[46]
OSHA regulations require monitoring of noise levels inside data centers if noise exceeds 85 decibels.[47] The average noise level in server areas of a data center may reach as high as 92-96 dB(A).[48]
Residents living near data centers have described the sound as "a high-pitched whirring noise 24/7", saying “It’s like being on atarmac with an airplane engine running constantly ... Except that the airplane keeps idling and never leaves.”[49][50][51][52]
External sources of noise include HVAC equipment and energy generators.[53][54]
The field ofdata center design has been growing for decades in various directions, including new construction big and small along with the creative re-use of existing facilities, like abandoned retail space, old salt mines and war-era bunkers.
Local building codes may govern the minimum ceiling heights and other parameters. Some of the considerations in the design of data centers are:
Various metrics exist for measuring the data-availability that results from data-center availability beyond 95% uptime, with the top of the scale counting how manynines can be placed after99%.[62]
Modularity and flexibility are key elements in allowing for a data center to grow and change over time. Data center modules are pre-engineered, standardized building blocks that can be easily configured and moved as needed.[63]
A modular data center may consist of data center equipment contained within shipping containers or similar portable containers.[64] Components of the data center can be prefabricated and standardized which facilitates moving if needed.[65]
Temperature and humidity are controlled via:
It is important that computers do not get humid or overheat, as high humidity can lead to dust clogging the fans, which leads to overheat, or can cause components to malfunction, ruining the board and running a fire hazard. Overheat can cause components, usually the silicon or copper of the wires or circuits to melt, causing connections to loosen, causing fire hazards.
Backup power consists of one or moreuninterruptible power supplies, battery banks, and/ordiesel /gas turbine generators.[68]
To preventsingle points of failure, all elements of the electrical systems, including backup systems, are typically givenredundant copies, and critical servers are connected to both theA-side andB-side power feeds. This arrangement is often made to achieveN+1 redundancy in the systems.Static transfer switches are sometimes used to ensure instantaneous switchover from one supply to the other in the event of a power failure.
Options include:
Air flow management addresses the need to improve data centercomputer cooling efficiency by preventing the recirculation of hot air exhausted from IT equipment and reducing bypass airflow. There are several methods of separating hot and cold airstreams, such as hot/cold aisle containment and in-row cooling units.[70]
Cold aisle containment is done by exposing the rear of equipment racks, while the fronts of the servers are enclosed with doors and covers. This is similar to how large-scale food companies refrigerate and store their products.
Computer cabinets/Server farms are often organized for containment of hot/cold aisles. Proper air duct placement prevents the cold and hot air from mixing. Rows of cabinets are paired to face each other so that the cool and hot air intakes and exhausts don't mix air, which would severely reduce cooling efficiency.
Alternatively, a range of underfloor panels can create efficient cold air pathways directed to the raised-floor vented tiles. Either the cold aisle or the hot aisle can be contained.[71]
Another option is fitting cabinets with vertical exhaust ductchimneys.[72] Hot exhaust pipes/vents/ducts can direct the air into aPlenum space above aDropped ceiling and back to the cooling units or to outside vents. With this configuration, traditional hot/cold aisle configuration is not a requirement.[73]
Data centers featurefire protection systems, includingpassive andActive Design elements, as well as implementation offire prevention programs in operations.Smoke detectors are usually installed to provide early warning of a fire at its incipient stage.
Although the main room usually does not allowWet Pipe-based Systems due to the fragile nature ofCircuit-boards, there still exist systems that can be used in the rest of the facility or in cold/hot aisle air circulation systems that areclosed systems, such as:[74]
However, there also exist other means to put out fires, especially inSensitive areas, usually usingGaseous fire suppression, of whichHalon gas was the most popular, until the negative effects of producing and using it were discovered.[1]
Physical access is usually restricted. Layered security often starts with fencing,bollards andmantraps.[75]Video camera surveillance and permanentsecurity guards are almost always present if the data center is large or contains sensitive information. Fingerprint recognition mantraps are starting to be commonplace.
Logging access is required by some data protection regulations; some organizations tightly link this to access control systems. Multiple log entries can occur at the main entrance, entrances to internal rooms, and at equipment cabinets. Access control at cabinets can be integrated with intelligentpower distribution units, so that locks are networked through the same appliance.[76]
Energy use is a central issue for data centers. Power draw ranges from a few kW for a rack of servers in a closet to several tens of MW for large facilities. Some facilities have power densities more than 100 times that of a typical office building.[77] For higher power density facilities, electricity costs are a dominantoperating expense and account for over 10% of thetotal cost of ownership (TCO) of a data center.[78]
In 2020, data centers (excluding cryptocurrency mining) and data transmission each used about 1% of world electricity.[79] Although some of this electricity was low carbon, theIEA called for more "government and industry efforts on energy efficiency, renewables procurement and RD&D",[79] as some data centers still use electricity generated by fossil fuels.[80] They also said that lifecycle emissions should be considered, that is includingembodied emissions, such as in buildings.[79] Data centers are estimated to have been responsible for 0.5% of US greenhouse gas emissions in 2018.[81] Some Chinese companies, such asTencent, have pledged to be carbon neutral by 2030, while others such asAlibaba have been criticized byGreenpeace for not committing to become carbon neutral.[82] Google and Microsoft now each consume more power than some fairly big countries, surpassing the consumption of more than 100 countries.[83]
The most commonly used energy efficiency metric for data centers ispower usage effectiveness (PUE), calculated as the ratio of total power entering the data center divided by the power used by IT equipment.
PUE measures the percentage of power used by overhead devices (cooling, lighting, etc.). The average USA data center has a PUE of 2.0,[84] meaning two watts of total power (overhead + IT equipment) for every watt delivered to IT equipment. State-of-the-art data centers are estimated to have a PUE of roughly 1.2.[85]Google publishes quarterly efficiency metrics from its data centers in operation.[86] PUEs of as low as 1.01 have been achieved with two phase immersion cooling.[87]
TheU.S. Environmental Protection Agency has anEnergy Star rating for standalone or large data centers. To qualify for the ecolabel, a data center must be within the top quartile in energy efficiency of all reported facilities.[88] The Energy Efficiency Improvement Act of 2015 (United States) requires federal facilities — including data centers — to operate more efficiently. California'sTitle 24 (2014) of the California Code of Regulations mandates that every newly constructed data center must have some form of airflow containment in place to optimize energy efficiency.
The European Union also has a similar initiative: EU Code of Conduct for Data Centres.[89]
The focus of measuring and analyzing energy use goes beyond what is used by IT equipment; facility support hardware such as chillers and fans also use energy.[90]
In 2011, server racks in data centers were designed for more than 25 kW and the typical server was estimated to waste about 30% of the electricity it consumed. The energy demand for information storage systems is also rising. A high-availability data center is estimated to have a 1 megawatt (MW) demand and consume $20,000,000 in electricity over itslifetime, with cooling representing 35% to 45% of the data center'stotal cost of ownership. Calculations show that in two years, the cost of powering and cooling a server could be equal to the cost of purchasing the server hardware.[91] Research in 2018 has shown that a substantial amount of energy could still be conserved by optimizing IT refresh rates and increasing server utilization.[92]
In 2011,Facebook,Rackspace and others founded theOpen Compute Project (OCP) to develop and publish open standards for greener data center computing technologies. As part of the project, Facebook published the designs of its server, which it had built for its first dedicated data center in Prineville. Making servers taller left space for more effectiveheat sinks and enabled the use of fans that moved more air with less energy. By not buyingcommercial off-the-shelf servers, energy consumption due to unnecessary expansion slots on themotherboard and unneeded components, such as agraphics card, was also saved.[93] In 2016, Google joined the project and published the designs of its 48V DC shallow data center rack. This design had long been part ofGoogle data centers. By eliminating the multipletransformers usually deployed in data centers, Google had achieved a 30% increase in energy efficiency.[94] In 2017, sales for data center hardware built to OCP designs topped $1.2 billion and are expected to reach $6 billion by 2021.[93]
Power is the largest recurring cost to the user of a data center.[95] Cooling it at or below 70 °F (21 °C) wastes money and energy.[95] Furthermore, overcooling equipment in environments with a high relative humidity can expose equipment to a high amount of moisture that facilitates the growth of salt deposits on conductive filaments in the circuitry.[96]
Apower and cooling analysis, also referred to as a thermal assessment, measures the relative temperatures in specific areas as well as the capacity of the cooling systems to handle specific ambient temperatures.[97] A power and cooling analysis can help to identify hot spots, over-cooled areas that can handle greater power use density, the breakpoint of equipment loading, the effectiveness of a raised-floor strategy, and optimal equipment positioning (such as AC units) to balance temperatures across the data center. Power cooling density is a measure of how much square footage the center can cool at maximum capacity.[98] The cooling of data centers is the second largest power consumer after servers. The cooling energy varies from 10% of the total energy consumption in the most efficient data centers and goes up to 45% in standard air-cooled data centers.
An energy efficiency analysis measures the energy use of data center IT and facilities equipment. A typical energy efficiency analysis measures factors such as a data center's Power Use Effectiveness (PUE) against industry standards, identifies mechanical and electrical sources of inefficiency, and identifies air-management metrics.[99] However, the limitation of most current metrics and approaches is that they do not include IT in the analysis. Case studies have shown that by addressing energy efficiency holistically in a data center, major efficiencies can be achieved that are not possible otherwise.[100]
This type of analysis uses sophisticated tools and techniques to understand the unique thermal conditions present in each data center—predicting the temperature,airflow, and pressure behavior of a data center to assess performance and energy consumption, using numerical modeling.[101] By predicting the effects of these environmental conditions, CFD analysis of a data center can be used to predict the impact of high-density racks mixed with low-density racks[102] and the onward impact on cooling resources, poor infrastructure management practices, and AC failure or AC shutdown for scheduled maintenance.
Thermal zone mapping uses sensors and computer modeling to create a three-dimensional image of the hot and cool zones in a data center.[103]
This information can help to identify optimal positioning of data center equipment. For example, critical servers might be placed in a cool zone that is serviced by redundant AC units.
Data centers use a lot of power, consumed by two main usages: The power required to run the actual equipment and then the power required to cool the equipment. Power efficiency reduces the first category.
Cooling cost reduction through natural means includes location decisions: When the focus is avoiding good fiber connectivity, power grid connections, and people concentrations to manage the equipment, a data center can be miles away from the users. Mass data centers like Google or Facebook don't need to be near population centers. Arctic locations that can use outside air, which provides cooling, are becoming more popular.[104]
Renewable electricity sources are another plus. Thus countries with favorable conditions, such as Canada,[105] Finland,[106] Sweden,[107] Norway,[108] and Switzerland[109] are trying to attract cloud computing data centers.
Singapore lifted a three-year ban on new data centers in April 2022. A major data center hub for the Asia-Pacific region,[110] Singapore lifted its moratorium on new data center projects in 2022, granting 4 new projects, but rejecting more than 16 data center applications from over 20 new data centers applications received. Singapore's new data centers shall meet very strict green technology criteria including "Water Usage Effectiveness (WUE) of 2.0/MWh, Power Usage Effectiveness (PUE) of less than 1.3, and have a "Platinum certification under Singapore's BCA-IMDA Green Mark for New Data Centre" criteria that clearly addressed decarbonization and use of hydrogen cells or solar panels.[111][112][113][114]
Direct current data centers are data centers that producedirect current on site withsolar panels and store the electricity on site in abattery storage power station. Computers run on direct current and the need forinverting theACpower from the grid would be eliminated. The data center site could still use AC power as a grid-as-a-backup solution. DC data centers could be 10% moreefficient and use lessfloor space for inverting components.[115][116]
It is very difficult to reuse the heat which comes from air-cooled data centers. For this reason, data center infrastructures are more often equipped with heat pumps.[117]
An alternative to heat pumps is the adoption of liquid cooling throughout a data center. Different liquid cooling techniques are mixed and matched to allow for a fully liquid-cooled infrastructure that captures all heat with water. Different liquid technologies are categorized in 3 main groups, indirect liquid cooling (water-cooled racks), direct liquid cooling (direct-to-chip cooling) and total liquid cooling (complete immersion in liquid, seeserver immersion cooling). This combination of technologies allows the creation of athermal cascade as part oftemperature chaining scenarios to create high-temperature water outputs from the data center.[citation needed]
Cryptomining and theartificial intelligence boom of the 2020s has also led to increased demand for electricity,[118][119] that theIEA expects could double global overall data center demand for electricity between 2022 and 2026.[6] The US could see its share of the electricity market going to data centers increase from 4% to 6% over those four years.[6]Bitcoin used up 2% of US electricity in 2023.[120] This has led to increased electricity prices in some regions,[121] particularly in regions with lots of data centers likeSanta Clara, California[122] andupstate New York.[123] Data centers have also generated concerns inNorthern Virginia about whether residents will have to foot the bill for future power lines.[120] It has also made it harder to develop housing in London.[124] A Bank of America Institute report in July 2024 found that the increase in demand for electricity due in part to AI has been pushing electricity prices higher and is a significant contributor to electricityinflation.[125][126][127]
Dynamic infrastructure[128] provides the ability to intelligently, automatically and securely move workloads within a data center[129] anytime, anywhere, for migrations,provisioning,[130] to enhance performance, or buildingco-location facilities. It also facilitates performing routine maintenance on either physical or virtual systems all while minimizing interruption. A related concept is Composable Infrastructure, which allows for the dynamic reconfiguration of the available resources to suit needs, only when needed.[131]
Side benefits include
Communications in data centers today are most often based onnetworks running theInternet protocol suite. Data centers contain a set ofrouters andswitches that transport traffic between the servers and to the outside world[133] which are connected according to thedata center network architecture.Redundancy of the internet connection is often provided by using two or more upstream service providers (seeMultihoming).
Some of the servers at the data center are used for running the basic internet andintranet services needed by internal users in the organization, e.g., e-mail servers,proxy servers, andDNS servers.
Network security elements are also usually deployed:firewalls,VPNgateways,intrusion detection systems, and so on. Also common are monitoring systems for the network and some of the applications. Additional off-site monitoring systems are also typical, in case of a failure of communications inside the data center.
Non-mutually exclusive options fordata backup are:
Onsite is traditional,[134] and one of its major advantages is immediate availability.
Data backup techniques include having anencrypted copy of the data offsite. Methods used for transporting data are:[135]
For quick deployment orIT disaster recovery, several large hardware vendors have developed mobile/modular solutions that can be installed and made operational in a very short amount of time.
Micro data centers (MDCs) are access-level data centers which are smaller in size than traditional data centers but provide the same features.[138] They are typically located near the data source to reduce communication delays, as their small size allows several MDCs to be spread out over a wide area.[139][140] MDCs are well suited to user-facing, front end applications.[141] They are commonly used inedge computing and other areas where low latency data processing is needed.[142]
data center .. a giant .. facility .. 15 of these buildings, and six more .. under construction
'Friends don't let friends build data centers,' said Charles Phillips, chief executive officer of Infor, a business software maker
