Data Center
data center (American English) atau data centre (British English) adalah fasilitas yang digunakan untuk menampung sistem komputer dan komponen terkait, seperti telekomunikasi dan sistem penyimpanan. Ini umumnya mencakup redundan atau komponen dan infrastruktur cadangan untuk catu daya, koneksi komunikasi data, kontrol lingkungan (mis. AC, pencegah kebakaran) dan berbagai perangkat keamanan. Pusat data besar adalah operasi skala industri yang menggunakan listrik sebanyak kota kecil.
Sejarah
Data center berawal pada ruang komputer besar di tahun 1940-an, yang ditandai dengan ENIAC, salah satu contoh paling awal dari data center. Sistem komputer awal, rumit untuk dioperasikan dan dipelihara, membutuhkan lingkungan khusus untuk beroperasi. Banyak kabel diperlukan untuk menyambungkan semua komponen, dan metode untuk menampung dan mengaturnya telah dirancang seperti rak|19 inci standar untuk memasang peralatan, raised floor, dan cable tray (dipasang di atas kepala atau di bawah lantai yang ditinggikan). Satu mainframe membutuhkan banyak daya, dan harus didinginkan untuk menghindari panas berlebih. Keamanan menjadi penting – komputer mahal, dan sering digunakan untuk tujuan militer. Oleh karena itu, pedoman desain dasar untuk mengontrol akses ke ruang komputer telah dibuat.
Selama ledakan industri komputer mikro, dan khususnya selama tahun 1980-an, pengguna mulai menyebarkan komputer di mana-mana, dalam banyak kasus dengan sedikit atau tanpa peduli tentang persyaratan pengoperasian. Namun, karena teknologi informasi (TI) operasi mulai tumbuh dalam kompleksitas, organisasi semakin sadar akan kebutuhan untuk mengontrol sumber daya TI. Munculnya Unix dari awal 1970-an menyebabkan proliferasi selanjutnya dari sistem operasi Linux-kompatibel PC yang tersedia secara bebas selama tahun 1990-an. Ini disebut "server", sebagai timesharing sistem operasi seperti Unix sangat bergantung pada model klien-server untuk memfasilitasi berbagi sumber daya unik antara banyak pengguna. Ketersediaan peralatan jaringan yang murah, ditambah dengan standar baru untuk jaringan pengkabelan terstruktur, memungkinkan untuk menggunakan desain hierarkis yang menempatkan server di ruangan tertentu di dalam perusahaan. Penggunaan istilah "data center", sebagaimana diterapkan pada ruang komputer yang dirancang khusus, mulai mendapat pengakuan populer saat ini.
Ledakan pusat data terjadi selama dot-com bubble tahun 1997–2000. Perusahaan memerlukan konektivitas Internet yang cepat dan pengoperasian tanpa henti untuk menerapkan sistem dan membangun kehadiran di Internet. Memasang peralatan seperti itu tidak layak untuk banyak perusahaan kecil. Banyak perusahaan mulai membangun fasilitas yang sangat besar, yang disebut Internet data center (IDC), yang menyediakan klien komersial berbagai solusi untuk penerapan dan pengoperasian sistem. Teknologi dan praktik baru dirancang untuk menangani skala dan persyaratan operasional dari operasi skala besar tersebut. Praktik-praktik ini akhirnya bermigrasi ke pusat data pribadi, dan diadopsi sebagian besar karena hasil praktisnya. Pusat data untuk komputasi awan disebut cloud data center (CDC). Namun saat ini, pembagian istilah-istilah tersebut hampir menghilang dan diintegrasikan ke dalam istilah "data center".
Dengan peningkatan penggunaan cloud computing, organisasi bisnis dan pemerintah meneliti pusat data ke tingkat yang lebih tinggi di berbagai bidang seperti keamanan, ketersediaan, dampak lingkungan, dan kepatuhan terhadap standar. Dokumen standar dari grup profesional terakreditasi, seperti Telecommunications Industry Association, menetapkan persyaratan untuk desain pusat data. Metrik operasional terkenal untuk data-center availability dapat digunakan untuk mengevaluasi commercial impact gangguan. Pengembangan berlanjut dalam praktik operasional, dan juga dalam desain data center yang ramah lingkungan. Data center biasanya menghabiskan banyak biaya untuk membangun dan memelihara.
Persyaratan untuk modern data center
Operasi TI adalah aspek penting dari sebagian besar operasi organisasi di seluruh dunia. Salah satu perhatian utama adalah kelangsungan bisnis; perusahaan mengandalkan sistem informasi mereka untuk menjalankan operasi mereka. Jika suatu sistem menjadi tidak tersedia, operasi perusahaan dapat terganggu atau dihentikan sama sekali. Penyediaan infrastruktur yang andal untuk operasional TI diperlukan untuk meminimalkan kemungkinan gangguan. Keamanan informasi juga menjadi perhatian, dan untuk alasan ini pusat data harus menawarkan lingkungan yang aman yang meminimalkan kemungkinan pelanggaran keamanan. Oleh karena itu, data center harus menjaga standar tinggi untuk memastikan integritas dan fungsionalitas lingkungan komputer yang dihostingnya. Hal ini dicapai melalui redundansi pendinginan mekanis dan sistem daya (termasuk generator daya cadangan darurat) yang melayani data center bersama dengan kabel serat optik.
Telecommunications Infrastructure Standard for Data Center Telecommunications Industry Association menetapkan persyaratan minimum untuk infrastruktur telekomunikasi data center dan ruang komputer termasuk data center perusahaan penyewa tunggal dan pusat data hosting Internet multi-penyewa. Topologi yang diusulkan dalam dokumen ini dimaksudkan agar dapat diterapkan pada data center dengan ukuran berapa pun.
Telcordia GR-3160, NEBS Requirements for Telecommunications Data Center Equipment and Spaces, memberikan panduan untuk ruang data center dalam jaringan telekomunikasi, dan persyaratan lingkungan untuk peralatan yang ditujukan untuk pemasangan di ruang tersebut. Kriteria ini dikembangkan bersama oleh Telcordia dan perwakilan industri. Mereka dapat diterapkan ke ruang data center yang menampung pemrosesan data atau peralatan Teknologi Informasi (TI). Peralatan tersebut dapat digunakan untuk:
- Mengoperasikan dan mengelola jaringan telekomunikasi operator
- Menyediakan aplikasi berbasis data center langsung ke pelanggan operator
- Menyediakan aplikasi yang dihosting untuk pihak ketiga untuk memberikan layanan kepada pelanggan mereka
- Berikan kombinasi dari ini dan aplikasi data center serupa
Pengoperasian data center yang efektif memerlukan investasi yang seimbang baik dalam fasilitas maupun peralatan yang ada. Langkah pertama adalah menetapkan lingkungan fasilitas dasar yang sesuai untuk pemasangan peralatan. Standardisasi dan modularitas dapat menghasilkan penghematan dan efisiensi dalam desain dan konstruksi data center telekomunikasi.
Standarisasi berarti rekayasa bangunan dan peralatan terpadu. Modularitas memiliki manfaat skalabilitas dan pertumbuhan yang lebih mudah, bahkan ketika prakiraan perencanaan kurang optimal. Untuk alasan ini, data center telekomunikasi harus direncanakan dalam blok bangunan berulang dari peralatan, dan peralatan daya dan pendukung (pengkondisian) yang terkait jika dimungkinkan. Penggunaan sistem terpusat khusus memerlukan perkiraan kebutuhan masa depan yang lebih akurat untuk mencegah mahalnya pembangunan, atau mungkin lebih buruk — dalam pembangunan yang gagal memenuhi kebutuhan di masa depan.
Data center "lights-out", juga dikenal sebagai data center yang digelapkan atau gelap, adalah data center yang, idealnya, menghilangkan kebutuhan akan akses langsung oleh personel, kecuali dalam keadaan luar biasa. Karena kurangnya kebutuhan staf untuk masuk ke data center, maka bisa dioperasikan tanpa penerangan. Semua perangkat diakses dan dikelola oleh sistem jarak jauh, dengan program otomasi yang digunakan untuk melakukan operasi tanpa pengawasan. Selain penghematan energi, pengurangan biaya kepegawaian, dan kemampuan untuk menemukan lokasi lebih jauh dari pusat populasi, menerapkan data center tanpa lampu mengurangi ancaman serangan berbahaya terhadap infrastruktur.
Ada kecenderungan untuk memodernisasi data center untuk memanfaatkan kinerja dan efisiensi energi peningkatan peralatan dan kemampuan TI yang lebih baru, seperti cloud computing. Proses ini juga dikenal sebagai transformasi data center.
Organisasi sedang mengalami pertumbuhan TI yang cepat tetapi data center mereka menua. Perusahaan riset industri International Data Corporation (IDC) menetapkan usia rata-rata sebuah data center adalah sembilan tahun. Gartner, perusahaan riset lainnya, mengatakan data center yang berusia lebih dari tujuh tahun sudah usang. Pertumbuhan data (163 zettabytes pada tahun 2025) merupakan salah satu faktor yang mendorong perlunya modernisasi data center.
Pada bulan Mei 2011, organisasi riset pusat data Uptime Institute melaporkan bahwa 36 persen dari perusahaan besar yang disurvei diperkirakan akan kehabisan kapasitas TI dalam 18 bulan ke depan.
Transformasi data center mengambil pendekatan langkah demi langkah melalui proyek terintegrasi yang dilakukan dari waktu ke waktu. Ini berbeda dari metode tradisional pemutakhiran data center yang menggunakan pendekatan serial dan silo. Proyek tipikal dalam inisiatif transformasi pusat data meliputi standardisasi/konsolidasi, virtualisasi, otomatisasi dan keamanan.
- Standardisasi/konsolidasi: Tujuan proyek ini adalah untuk mengurangi jumlah data center yang mungkin dimiliki organisasi besar. Proyek ini juga membantu mengurangi jumlah perangkat keras, platform perangkat lunak, alat, dan proses dalam data center. Organisasi mengganti peralatan data center yang sudah tua dengan yang lebih baru yang memberikan peningkatan kapasitas dan kinerja. Platform komputasi, jaringan, dan manajemen distandarisasi sehingga lebih mudah dikelola.
- Virtualisasi: Ada kecenderungan untuk menggunakan teknologi virtualisasi TI untuk mengganti atau menggabungkan beberapa peralatan data center, seperti server. Virtualisasi membantu menurunkan biaya modal dan operasional, serta mengurangi konsumsi energi. Teknologi virtualisasi juga digunakan untuk membuat desktop virtual, yang kemudian dapat dihosting di data center dan disewakan secara berlangganan. Data yang dikeluarkan oleh bank investasi Lazard Capital Markets melaporkan bahwa 48 persen operasi perusahaan akan divirtualisasikan pada tahun 2012. Gartner memandang virtualisasi sebagai katalis untuk modernisasi.
- Otomatisasi: Otomatisasi data center melibatkan tugas otomatisasi seperti penyediaan, konfigurasi, penambalan, manajemen rilis, dan kepatuhan. Karena perusahaan kekurangan pekerja TI yang terampil, otomatisasi tugas membuat operasi data center menjadi lebih efisien.
- Mengamankan: Di data center modern, keamanan data pada sistem virtual terintegrasi dengan keamanan infrastruktur fisik yang ada. Keamanan data center modern harus mempertimbangkan keamanan fisik, keamanan jaringan, dan keamanan data dan pengguna.
Carrier neutrality
Saat ini banyak pusat data dijalankan oleh Internet Service Provider(ISP) semata-mata untuk tujuan menghosting Server mereka sendiri dan pihak ketiga].
Namun secara tradisional data center dibangun hanya untuk penggunaan satu perusahaan besar, atau sebagai carrier hotel atau Network-neutral data center.
Fasilitas ini memungkinkan interkoneksi operator dan mitra, dan bertindak sebagai hub fiber regional yang melayani bisnis lokal selain menghosting konten Server.
Data center Level and Tier
Telecommunications Industry Association adalah asosiasi perdagangan yang diakreditasi oleh ANSI (American National Standards Institutea). Pada tahun 2005 menerbitkan ANSI/TIA-942,Telecommunications Infrastructure Standard for Data Centers, yang menetapkan empat tingkat pusat data secara menyeluruh dan terukur. TIA-942 diubah pada tahun 2008, 2010, 2014 dan 2017. TIA-942:Data Center Standards Overview menjelaskan persyaratan untuk infrastruktur data center. Yang paling sederhana adalah pusat data Level 1, yang pada dasarnya adalah ruang server, mengikuti panduan dasar untuk pemasangan sistem komputer. Level yang paling ketat adalah pusat data Level 4, yang dirancang untuk menampung sistem komputer yang paling kritis, dengan subsistem yang sepenuhnya redundan, kemampuan untuk terus beroperasi selama periode waktu yang tidak terbatas selama pemadaman listrik utama.
Uptime Institute, sebuah penelitian data center dan organisasi layanan profesional yang berbasis di Seattle, WA mendefinisikan apa yang sekarang disebut sebagai "Tiers" atau lebih tepatnya, "Tier Standard". Level Standar Tingkat Uptime menjelaskan ketersediaan pemrosesan data dari perangkat keras di suatu lokasi. Semakin tinggi level Tier, semakin besar ketersediaan yang diharapkan. Standar Tingkat Uptime Institute ditunjukkan di bawah ini.
Untuk revisi TIA-942 2014, organisasi TIA dan Uptime Institute sepakat bahwa TIA akan menghapus semua penggunaan kata "Tier" dari spesifikasi TIA-942 mereka yang dipublikasikan, dengan menggunakan terminologi tersebut hanya akan digunakan oleh Uptime Institute untuk mendeskripsikan sistemnya.
Klasifikasi lain juga ada. Misalnya, German Datacenter Star Audit program menggunakan proses audit untuk mengesahkan lima tingkat "gratification" yang memengaruhi data center yang critical.
| Tier level | Persyaratan |
|---|---|
| I |
|
| II |
|
| III |
|
| IV |
|
Sementara salah satu sistem ketahanan data center industri diusulkan pada saat ketersediaan dinyatakan sebagai teori, dan sejumlah 'Nine' (angka sembilan) di sisi kanan titik desimal, secara umum disepakati bahwa pendekatan ini agak menipu. atau terlalu sederhana, sehingga vendor saat ini biasanya membahas ketersediaan secara mendetail yang sebenarnya dapat mereka pengaruhi, dan dalam istilah yang jauh lebih spesifik. Oleh karena itu, sistem leveling yang tersedia saat ini tidak lagi menentukan hasilnya dalam persentase waktu aktif.
Catatan: Uptime Institute juga mengklasifikasikan Tingkatan untuk masing-masing dari tiga fase pusat data, dokumen desainnya, fasilitas yang dibangun, dan keberlanjutan operasionalnya yang berkelanjutan.
Pertimbangan desain
Data center dapat menempati satu ruangan di gedung, satu lantai atau lebih, atau seluruh gedung. Sebagian besar peralatan seringkali berupa server yang dipasang di lemari rak 19 inci, yang biasanya ditempatkan dalam satu baris membentuk koridor (disebut lorong) di antaranya. Ini memungkinkan orang mengakses bagian depan dan belakang setiap kabinet. Ukuran server sangat berbeda dari server 1U hingga silo penyimpanan besar yang berdiri bebas yang menempati banyak ruang lantai. Beberapa peralatan seperti perangkat komputer mainframe dan penyimpanan seringkali sebesar rak itu sendiri, dan ditempatkan di sampingnya. Pusat data yang sangat besar dapat menggunakan shipping containers yang masing-masing dikemas dengan 1.000 server atau lebih; ketika perbaikan atau pemutakhiran diperlukan, seluruh wadah diganti (alih-alih memperbaiki server individual).
Kode bangunan lokal dapat mengatur ketinggian langit-langit minimum.
Design programming
Design programming, juga dikenal sebagai architectural programming, adalah proses penelitian dan pengambilan keputusan untuk mengidentifikasi ruang lingkup proyek desain. Selain arsitektur bangunan itu sendiri, ada tiga elemen untuk mendesain pemrograman untuk data center: facility topology design (space planning), engineering infrastructure design (sistem mekanis seperti pendinginan dan sistem kelistrikan termasuk daya) dan technology infrastructure design (cable plant). Masing-masing akan dipengaruhi oleh penilaian kinerja dan pemodelan untuk mengidentifikasi kesenjangan yang berkaitan dengan keinginan kinerja pemilik fasilitas dari waktu ke waktu.
Berbagai vendor yang menyediakan data center design service mendefinisikan langkah-langkah data center design sedikit berbeda, namun semuanya menangani aspek dasar yang sama seperti yang diberikan di bawah ini.
Kriteria pemodelan
Kriteria pemodelan digunakan untuk mengembangkan skenario masa depan untuk ruang, daya, pendinginan, dan biaya di data center. Tujuannya adalah untuk membuat rencana induk dengan parameter seperti jumlah, ukuran, lokasi, topologi, tata letak sistem lantai TI, serta teknologi dan konfigurasi daya dan pendinginan. Tujuan dari ini adalah untuk memungkinkan penggunaan yang efisien dari sistem mekanik dan listrik yang ada dan juga pertumbuhan di pusat data yang ada tanpa perlu membangun gedung baru dan lebih meningkatkan pasokan listrik yang masuk.
Rekomendasi desain
Rekomendasi/rencana desain umumnya mengikuti fase kriteria pemodelan. Infrastruktur teknologi optimal diidentifikasi dan kriteria perencanaan dikembangkan, seperti kapasitas daya kritis, kebutuhan daya data center keseluruhan menggunakan PUE (power utilization efficiency) yang disepakati, kapasitas pendinginan mekanis, kilowatt per kabinet, raised floor space, dan tingkat ketahanan untuk fasilitas.
Desain konseptual
Desain konseptual mewujudkan rekomendasi atau rencana desain dan harus mempertimbangkan skenario "what-if" untuk memastikan semua hasil operasional terpenuhi untuk membuktikan fasilitas di masa depan. Tata letak lantai konseptual harus didorong oleh persyaratan kinerja TI serta biaya siklus hidup yang terkait dengan permintaan TI, efisiensi energi, efisiensi biaya, dan ketersediaan. Pemeriksaan masa depan juga akan mencakup kemampuan ekspansi, yang seringkali disediakan di pusat data modern melalui desain modular. Ini memungkinkan ruang lantai yang lebih tinggi untuk dipasang di data center saat menggunakan pembangkit listrik utama yang ada di fasilitas tersebut.
Detailed design
Detailed design is undertaken once the appropriate conceptual design is determined, typically including a proof of concept. The detailed design phase should include the detailed architectural, structural, mechanical and electrical information and specification of the facility. At this stage development of facility schematics and construction documents as well as schematics and performance specification and specific detailing of all technology infrastructure, detailed IT infrastructure design and IT infrastructure documentation are produced.
Mechanical engineering infrastructure designs
Mechanical engineering infrastructure design addresses mechanical systems involved in maintaining the interior environment of a data center, such as heating, ventilation and air conditioning (HVAC); humidification and dehumidification equipment; pressurization; and so on.
This stage of the design process should be aimed at saving space and costs, while ensuring business and reliability objectives are met as well as achieving PUE and green requirements. Modern designs include modularizing and scaling IT loads, and making sure capital spending on the building construction is optimized.
Electrical engineering infrastructure design
Electrical Engineering infrastructure design is focused on designing electrical configurations that accommodate various reliability requirements and data center sizes. Aspects may include utility service planning; distribution, switching and bypass from power sources; uninterruptible power source (UPS) systems; and more.
These designs should dovetail to energy standards and best practices while also meeting business objectives. Electrical configurations should be optimized and operationally compatible with the data center user's capabilities. Modern electrical design is modular and scalable, and is available for low and medium voltage requirements as well as DC (direct current).
Technology infrastructure design
Technology infrastructure design addresses the telecommunications cabling systems that run throughout data centers. There are cabling systems for all data center environments, including horizontal cabling, voice, modem, and facsimile telecommunications services, premises switching equipment, computer and telecommunications management connections, keyboard/video/mouse connections and data communications. Wide area, local area, and storage area networks should link with other building signaling systems (e.g. fire, security, power, HVAC, EMS).
Availability expectations
The higher the availability needs of a data center, the higher the capital and operational costs of building and managing it. Business needs should dictate the level of availability required and should be evaluated based on characterization of the criticality of IT systems estimated cost analyses from modeled scenarios. In other words, how can an appropriate level of availability best be met by design criteria to avoid financial and operational risks as a result of downtime? If the estimated cost of downtime within a specified time unit exceeds the amortized capital costs and operational expenses, a higher level of availability should be factored into the data center design. If the cost of avoiding downtime greatly exceeds the cost of downtime itself, a lower level of availability should be factored into the design.
Site selection
Aspects such as proximity to available power grids, telecommunications infrastructure, networking services, transportation lines and emergency services can affect costs, risk, security and other factors to be taken into consideration for data center design. Whilst a wide array of location factors are taken into account (e.g. flight paths, neighbouring uses, geological risks) access to suitable available power is often the longest lead time item. Location affects data center design also because the climatic conditions dictate what cooling technologies should be deployed. In turn this impacts uptime and the costs associated with cooling. For example, the topology and the cost of managing a data center in a warm, humid climate will vary greatly from managing one in a cool, dry climate.
Modularity and flexibility
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.
A modular data center may consist of data center equipment contained within shipping containers or similar portable containers.But it can also be described as a design style in which components of the data center are prefabricated and standardized so that they can be constructed, moved or added to quickly as needs change.
Environmental control
The physical environment of a data center is rigorously controlled. Air conditioning is used to control the temperature and humidity in the data center. ASHRAE's "Thermal Guidelines for Data Processing Environments" recommends a temperature range of Template:Convert, a dew point range of Template:Convert, and ideal relative humidity of 60%, with an allowable range of 40% to 60% for data center environments. The temperature in a data center will naturally rise because the electrical power used heats the air. Unless the heat is removed, the ambient temperature will rise, resulting in electronic equipment malfunction. By controlling the air temperature, the server components at the board level are kept within the manufacturer's specified temperature/humidity range. Air conditioning systems help control humidity by cooling the return space air below the dew point. Too much humidity, and water may begin to condense on internal components. In case of a dry atmosphere, ancillary humidification systems may add water vapor if the humidity is too low, which can result in static electricity discharge problems which may damage components. Subterranean data centers may keep computer equipment cool while expending less energy than conventional designs.
Modern data centers try to use economizer cooling, where they use outside air to keep the data center cool. At least one data center (located in Upstate New York) will cool servers using outside air during the winter. They do not use chillers/air conditioners, which creates potential energy savings in the millions. Increasingly indirect air cooling is being deployed in data centers globally which has the advantage of more efficient cooling which lowers power consumption costs in the data center. Many newly constructed data centers are also using Indirect Evaporative Cooling (IDEC) units as well as other environmental features such as sea water to minimize the amount of energy needed to cool the space.
Telcordia NEBS: Raised Floor Generic Requirements for Network and Data Centers, GR-2930 presents generic engineering requirements for raised floors that fall within the strict NEBS guidelines.
There are many types of commercially available floors that offer a wide range of structural strength and loading capabilities, depending on component construction and the materials used. The general types of raised floors include stringer, stringerless, and structural platforms, all of which are discussed in detail in GR-2930 and summarized below.
- Stringered raised floors - This type of raised floor generally consists of a vertical array of steel pedestal assemblies (each assembly is made up of a steel base plate, tubular upright, and a head) uniformly spaced on two-foot centers and mechanically fastened to the concrete floor. The steel pedestal head has a stud that is inserted into the pedestal upright and the overall height is adjustable with a leveling nut on the welded stud of the pedestal head.
- Stringerless raised floors - One non-earthquake type of raised floor generally consists of an array of pedestals that provide the necessary height for routing cables and also serve to support each corner of the floor panels. With this type of floor, there may or may not be provisioning to mechanically fasten the floor panels to the pedestals. This stringerless type of system (having no mechanical attachments between the pedestal heads) provides maximum accessibility to the space under the floor. However, stringerless floors are significantly weaker than stringered raised floors in supporting lateral loads and are not recommended.
- Structural platforms - One type of structural platform consists of members constructed of steel angles or channels that are welded or bolted together to form an integrated platform for supporting equipment. This design permits equipment to be fastened directly to the platform without the need for toggle bars or supplemental bracing. Structural platforms may or may not contain panels or stringers.
Data centers typically have raised flooring made up of Template:Convert removable square tiles. The trend is towards Template:Convert void to cater for better and uniform air distribution. These provide a plenum for air to circulate below the floor, as part of the air conditioning system, as well as providing space for power cabling.
Metal whiskers
Raised floors and other metal structures such as cable trays and ventilation ducts have caused many problems with zinc whiskers in the past, and likely are still present in many data centers. This happens when microscopic metallic filaments form on metals such as zinc or tin that protect many metal structures and electronic components from corrosion. Maintenance on a raised floor or installing of cable etc. can dislodge the whiskers, which enter the airflow and may short circuit server components or power supplies, sometimes through a high current metal vapor plasma arc. This phenomenon is not unique to data centers, and has also caused catastrophic failures of satellites and military hardware.
Electrical power
Backup power consists of one or more uninterruptible power supplies, battery banks, and/or diesel / gas turbine generators.
To prevent single points of failure, all elements of the electrical systems, including backup systems, are typically fully duplicated, and critical servers are connected to both the "A-side" and "B-side" power feeds. This arrangement is often made to achieve N+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.
Low-voltage cable routing
Data cabling is typically routed through overhead cable trays in modern data centers. But someTemplate:Who are still recommending under raised floor cabling for security reasons and to consider the addition of cooling systems above the racks in case this enhancement is necessary. Smaller/less expensive data centers without raised flooring may use anti-static tiles for a flooring surface. Computer cabinets are often organized into a hot aisle arrangement to maximize airflow efficiency.
Fire protection
Data centers feature fire protection systems, including passive and Active Design elements, as well as implementation of fire prevention programs in operations. Smoke detectors are usually installed to provide early warning of a fire at its incipient stage. This allows investigation, interruption of power, and manual fire suppression using hand held fire extinguishers before the fire grows to a large size. An active fire protection system, such as a fire sprinkler system or a clean agent fire suppression gaseous system, is often provided to control a full scale fire if it develops. High sensitivity smoke detectors, such as aspirating smoke detectors, activating clean agent fire suppression gaseous systems activate earlier than fire sprinklers.
- Sprinklers = structure protection and building life safety.
- Clean agents = business continuity and asset protection.
- No water = no collateral damage or clean up.
Passive fire protection elements include the installation of fire walls around the data center, so a fire can be restricted to a portion of the facility for a limited time in the event of the failure of the active fire protection systems. Fire wall penetrations into the server room, such as cable penetrations, coolant line penetrations and air ducts, must be provided with fire rated penetration assemblies, such as fire stopping.
Security
Physical security also plays a large role with data centers. Physical access to the site is usually restricted to selected personnel, with controls including a layered security system often starting with fencing, bollards and mantraps. Video camera surveillance and permanent security guards are almost always present if the data center is large or contains sensitive information on any of the systems within. The use of finger print recognition mantraps is starting to be commonplace.
Documenting access is required by some data protection regulations. To do so, some organizations use access control systems that provide a logging report of accesses. Logging can occur at the main entrance, at the entrances to mechanical rooms and white spaces, as well as in at the equipment cabinets. Modern access control at the cabinet allows for integration with intelligent power distribution units so that the locks can be powered and networked through the same appliance.
Energy use
Energy use is a central issue for data centers. Power draw for data centers 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. For higher power density facilities, electricity costs are a dominant operating expense and account for over 10% of the total cost of ownership (TCO) of a data center. By 2012 the cost of power for the data center is expected to exceed the cost of the original capital investment.
According to a Greenpeace study, in 2012, data centers represented 21% of the electricity consumed by the IT sector, which was about 382 billion kWh a year. U.S. data centers use more than 90 billion kWh of electricity a year. Global data centers used roughly 416 TWh in 2016, nearly 40% more than the entire United Kingdom.
Greenhouse gas emissions
In 2007 the entire information and communication technologies or ICT sector was estimated to be responsible for roughly 2% of global carbon emissions with data centers accounting for 14% of the ICT footprint. for 2007. Given a business as usual scenario greenhouse gas emissions from data centers is projected to more than double from 2007 levels by 2020.
Siting is one of the factors that affect the energy consumption and environmental effects of a datacenter. In areas where climate favors cooling and lots of renewable electricity is available the environmental effects will be more moderate. Thus countries with favorable conditions, such as: Canada, Finland, Sweden, Norway and Switzerland, are trying to attract cloud computing data centers.
In an 18-month investigation by scholars at Rice University's Baker Institute for Public Policy in Houston and the Institute for Sustainable and Applied Infodynamics in Singapore, data center-related emissions will more than triple by 2020.
Energy efficiency
The most commonly used metric to determine the energy efficiency of a data center is power usage effectiveness, or PUE. This simple ratio is the total power entering the data center divided by the power used by the IT equipment.
- <math> \mathrm{PUE} = {\mbox{Total Facility Power} \over \mbox{IT Equipment Power}} </math>
Total facility power consists of power used by IT equipment plus any overhead power consumed by anything that is not considered a computing or data communication device (i.e. cooling, lighting, etc.). An ideal PUE is 1.0 for the hypothetical situation of zero overhead power. The average data center in the US has a PUE of 2.0,<ref name="energystar1"/> meaning that the facility uses two watts of total power (overhead + IT equipment) for every watt delivered to IT equipment. State-of-the-art data center energy efficiency is estimated to be roughly 1.2. Some large data center operators like Microsoft and Yahoo! have published projections of PUE for facilities in development; Google publishes quarterly actual efficiency performance from data centers in operation.
The U.S. Environmental Protection Agency has an Energy Star rating for standalone or large data centers. To qualify for the ecolabel, a data center must be within the top quartile of energy efficiency of all reported facilities. The United States passed the Energy Efficiency Improvement Act of 2015, which requires federal facilities — including data centers — to operate more efficiently. In 2014, California enacted title 24 of the California Code of Regulations, which mandates that every newly constructed data center must have some form of airflow containment in place, as a measure to optimize energy efficiency.
European Union also has a similar initiative: EU Code of Conduct for Data Centres
Energy use analysis
Often, the first step toward curbing energy use in a data center is to understand how energy is being used in the data center. Multiple types of analysis exist to measure data center energy use. Aspects measured include not just energy used by IT equipment itself, but also by the data center facility equipment, such as chillers and fans.
Power and cooling analysis
Power is the largest recurring cost to the user of a data center. A power 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. 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. 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.
Energy efficiency analysis
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. 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.
Computational fluid dynamics (CFD) analysis
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. By predicting the effects of these environmental conditions, CFD analysis in the data center can be used to predict the impact of high-density racks mixed with low-density racks and the onward impact on cooling resources, poor infrastructure management practices and AC failure or AC shutdown for scheduled maintenance.
Thermal zone mapping
Thermal zone mapping uses sensors and computer modeling to create a three-dimensional image of the hot and cool zones in a data center.
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.
Green data centers
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. The first category is addressed by designing computers and storage systems that are increasingly power-efficient. To bring down cooling costs data center designers try to use natural ways to cool the equipment. Many data centers are located near good fiber connectivity, power grid connections and also people-concentrations to manage the equipment, but there are also circumstances where the data center can be miles away from the users and don't need a lot of local management. Examples of this are the 'mass' data centers like Google or Facebook: these DC's are built around many standardized servers and storage-arrays and the actual users of the systems are located all around the world. After the initial build of a data center staff numbers required to keep it running are often relatively low: especially data centers that provide mass-storage or computing power which don't need to be near population centers.Data centers in arctic locations where outside air provides all cooling are getting more popular as cooling and electricity are the two main variable cost components.
Energy reuse
The practice of cooling data centers is a topic of discussion. 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. 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 which captures all heat in water. Different liquid technologies are categorised 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). This combination of technologies allows the creation of a thermal cascade as part of temperature chaining scenarios to create high temperature water outputs from the data center.
Network infrastructure
Communications in data centers today are most often based on networks running the IP protocol suite. Data centers contain a set of routers and switches that transport traffic between the servers and to the outside world which are connected according to the data center network architecture. Redundancy of the Internet connection is often provided by using two or more upstream service providers (see Multihoming).
Some of the servers at the data center are used for running the basic Internet and intranet services needed by internal users in the organization, e.g., e-mail servers, proxy servers, and DNS servers.
Network security elements are also usually deployed: firewalls, VPN gateways, intrusion detection systems, etc. 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.
Data center infrastructure management
Data center infrastructure management (DCIM) is the integration of information technology (IT) and facility management disciplines to centralize monitoring, management and intelligent capacity planning of a data center's critical systems. Achieved through the implementation of specialized software, hardware and sensors, DCIM enables common, real-time monitoring and management platform for all interdependent systems across IT and facility infrastructures.
Depending on the type of implementation, DCIM products can help data center managers identify and eliminate sources of risk to increase availability of critical IT systems. DCIM products also can be used to identify interdependencies between facility and IT infrastructures to alert the facility manager to gaps in system redundancy, and provide dynamic, holistic benchmarks on power consumption and efficiency to measure the effectiveness of "green IT" initiatives.
It's important to measure and understand data center efficiency metrics. A lot of the discussion in this area has focused on energy issues, but other metrics beyond the PUE can give a more detailed picture of the data center operations. Server, storage, and staff utilization metrics can contribute to a more complete view of an enterprise data center. In many cases, disc capacity goes unused and in many instances the organizations run their servers at 20% utilization or less. More effective automation tools can also improve the number of servers or virtual machines that a single admin can handle.
DCIM providers are increasingly linking with computational fluid dynamics providers to predict complex airflow patterns in the data center. The CFD component is necessary to quantify the impact of planned future changes on cooling resilience, capacity and efficiency.
Managing the capacity of a data center
Several parameters may limit the capacity of a data center. For long term usage, the main limitations will be available area, then available power. In the first stage of its life cycle, a data center will see its occupied space growing more rapidly than consumed energy. With constant densification of new IT technologies, the need in energy is going to become dominant, equaling then overcoming the need in area (second then third phase of cycle). The development and multiplication of connected objects, the needs in storage and data treatment lead to the necessity of data centers to grow more and more rapidly. It is therefore important to define a data center strategy before being cornered. The decision, conception and building cycle lasts several years. Therefore, it is imperative to initiate this strategic consideration when the data center reaches about 50% of its power capacity. Maximum occupation of a data center needs to be stabilized around 85%, be it in power or occupied area. Resources thus managed will allow a rotation zone for managing hardware replacement and will allow temporary cohabitation of old and new generations. In the case where this limit would be overcrossed durably, it would not be possible to proceed to material replacements, which would invariably lead to smothering the information system. The data center is a resource in its own right of the information system, with its own constraints of time and management (life span of 25 years), it therefore needs to be taken into consideration in the framework of the SI midterm planning (between 3 and 5 years).
Applications
The main purpose of a data center is running the IT systems applications that handle the core business and operational data of the organization. Such systems may be proprietary and developed internally by the organization, or bought from enterprise software vendors. Such common applications are ERP and CRM systems.
A data center may be concerned with just operations architecture or it may provide other services as well.
Often these applications will be composed of multiple hosts, each running a single component. Common components of such applications are databases, file servers, application servers, middleware, and various others.
Data centers are also used for off site backups. Companies may subscribe to backup services provided by a data center. This is often used in conjunction with backup tapes. Backups can be taken off servers locally on to tapes. However, tapes stored on site pose a security threat and are also susceptible to fire and flooding. Larger companies may also send their backups off site for added security. This can be done by backing up to a data center. Encrypted backups can be sent over the Internet to another data center where they can be stored securely.
For quick deployment or disaster recovery, several large hardware vendors have developed mobile/modular solutions that can be installed and made operational in very short time. Companies such as
- Cisco Systems,
- Sun Microsystems (Sun Modular Datacenter),
- Bull (mobull),
- IBM (Portable Modular Data Center),
- Schneider-Electric (Portable Modular Data Center),
- HP (Performance Optimized Datacenter),
- ZTE Corporation,
- FiberHome Technologies Group (FitMDC Modular Data Center Solution),
- Huawei (Container Data Center Solution),
- Google (Google Modular Data Center) have developed systems that could be used for this purpose.
- BASELAYER has a patent on the software defined modular data center.
US wholesale and retail colocation providers
According to data provided in the third quarter of 2013 by Synergy Research Group, "the scale of the wholesale colocation market in the United States is very significant relative to the retail market, with Q3 wholesale revenues reaching almost $700 million. Digital Realty Trust is the wholesale market leader, followed at a distance by DuPont Fabros." Synergy Research also described the US colocation market as the most mature and well-developed in the world, based on revenue and the continued adoption of cloud infrastructure services.
- Estimates from Synergy Research Group's Q3 2013 data.
| Rank | Company name | US market share |
|---|---|---|
| 1 | Various providers | 34% |
| 2 | Equinix | 18% |
| 3 | CenturyLink-Savvis | 8% |
| 4 | SunGard | 5% |
| 5 | AT&T | 5% |
| 6 | Verizon | 5% |
| 7 | Telx | 4% |
| 8 | CyrusOne | 4% |
| 9 | Level 3 Communications | 3% |
| 10 | Internap | 2% |