Data Center with warranty
To accommodate the equipment, we use several data centers and decided to create a series of materials about the life support system of one of them.
DataPro on Aviamotornaya Street is one of the most reliable data centers in Russia that has received Uptime Design and Facility certification. Today we will talk a little about the project and consider as closely as possible the technical implementation and features of the power supply system.
The data center at Aviamotornaya 69 is the second data center built by DataPro, which specializes in providing services to commercial data centers.
International certification of Uptime Design and Facility means that the data center is designed and built in accordance with all applicable standards for the Tier III reliability category. The next level in 2016 will be Uptime Operations certification, confirming that all the procedures and procedures implemented in the data center comply with the requirements. The maximum downtime for a data center of this level is 1.6 hours per year.
In 2015, DataPro Data Center on Aviamotor was awarded the best project of the year. In September, the first in Russia presentation of awards of professional awards in the field of data center construction took place. The competition program was attended by 19 data centers applying for prizes in five nominations. The international jury recognized DataPro's data center as the most ambitious and innovative and awarded DataPro the main Russian Data Center Awards 2015 award .
For most tasks, this is the only option in which you do not need to look for any compromises.
Certificates of the international institute Uptime Institute cannot be purchased. All the technologies and solutions used are certified; this guarantees maximum resiliency of the data center to ensure the business continuity of customers. All this leads to guaranteed availability of resources and is an insurance against unexpected situations.
In the end, the cost of placing equipment in the data center of this level may be somewhat higher. What does the user pay for?
The cost is caused not just by the way, the user pays not for the “status”, but for confidence in the availability of resources, confirmed by professionals.
In the following materials we will describe in detail all the life support systems of this data center. And today we will briefly review the main elements of the infrastructure and talk in detail about the power supply.
The average size of the machine room in the DataPro data center is 180 square meters. m, it is designed for about 100 racks or can be divided into several enclosures. There are eight such halls now. The building provides space for technical personnel, equipment storage, loading and unloading, catering. Clients can not only rent a rack, but also create a backup office, where the client’s critical personnel will continue to work in the event of an emergency.
Eight Schneider Electric Ecobreeze units are currently used for cooling server rooms and auxiliary technological premises of the data center. The temperature regime in the halls is maintained at + 25 ° C at a humidity of 40–60%. The use of this modular cooling system in combination with other engineering solutions made it possible to achieve a high PUE rate, the total average annual value of which does not exceed 1.3. In the next article we will tell about Ecobreeze in more detail.
A fiber optic link is connected to the data center via two independent routes, connecting it with all the largest telecommunications centers in Moscow and traffic exchange points. The technology platform policy is neutral with respect to telecom operators, so there are more than 10 telecom operators on the site (Garstelecom, Mastertel, RETN, Macomnet, MTS, Beeline, Orange Business Services, etc.).
Considerable attention is paid to security: security is responsible for the security of the data center itself and the surrounding area. The security system includes more than 350 network cameras. The data center also provides advanced methods for preventing ignition: a super early Vesda smoke detection system and an automatic gas fire extinguishing system based on freon-227.
Power supply - the basis of reliable data center operation. It should be uninterrupted, for which uninterruptible power supplies (UPS) are traditionally used, and guaranteed, for which diesel generator sets (DGS) are used, supporting the work of the data center during a prolonged power outage.
The DataPro data center has two independent inputs of 10 kV from the Mosenergo substation, and the cables are laid in different collectors, provide the necessary electrical power to the facility. Power is supplied to consumers through a group of step-down transformers. These dry transformers are constantly in operation in the presence of power from the city substation.
Now the allowed and connected data center power is 6 MW. Another 8 MW of power is in the process of registration. The power supply of the data center is actually reserved under the 2N scheme. For example, even at a 100% load in the event of an accident of a power supply panel, transformer, DRUPS, the entire turbine hall will be powered from the second input / shield. It is assumed that customers use equipment with redundant power supplies or rack-mount ATS.
Here are the main components of the data center power supply system. On the right - transformers, on the left diesel rotor UPS (DRUPS).
For powering the data center dry transformers rated at 1600 kVA each are used. They convert 10 kV at the input to 0.4 kV at the output.
Part of the data center power system circuitry.
Traditionally, in the event of the disappearance of the city network voltage, the UPS batteries must maintain the power supply of the equipment until the diesel generator set is fully started, which can provide the entire data center with electricity. This process usually takes from 20-30 seconds to 2 minutes, on which the power of the UPS and the capacity of the batteries are calculated.
The DataPro data center uses a different, more economical approach for its scale. The main components of the DataPro data center infrastructure were power supply solutions for diesel rotary UPSs manufactured by Hitec Power Protection (currently four units) and Euro-Diesel (two cars). A service contract with two different vendors allows you to optimize prices and compare services.
In essence, a diesel rotary or dynamic UPS (DRUPS) of these manufacturers is a diesel engine assembled coaxially on one shaft, an electromagnetic clutch, a synchronous electric machine and a dynamic flywheel. A decoupling choke connects the mains voltage input to the “clean” voltage output of the UPS system. It provides a high degree of isolation between the input and output, blocking the passage of harmonics and transients.
If there is an external power supply, the UPS synchronous electric machine operates in the electric motor mode, rotating the rotor of the flywheel. When the parameters of the network outside the set limits, it goes into generator mode, maintaining a continuous sinusoidal voltage on the load. The source of energy during the transition process is the flywheel, thanks to which the stable frequency of rotation of the rotor shaft of the synchronous electric machine is maintained. A flywheel keeps up to one minute at full electric load without a diesel.
After the mains voltage fails, the DRUPS control system sends a signal to start the diesel engine. The kinetic energy of the flywheel, in addition to maintaining the output voltage, is used to output the diesel engine crankshaft to the operating frequency. After 50 ms after a power failure, the diesel engine begins to work, which within a few seconds goes into normal operation - the flywheel is already spinning.
Independent power supply of the facility in the event of a power failure from the substation is provided by diesel-rotary UPSs Hitec Power Protection of 1670 kVA with 4 / 3N redundancy scheme. And no batteries to power the IT load.
Power supply cables and ventilation duct.
Once a month, diesel engines are started to check their performance. The estimated stock of diesel fuel in the storage facility is 17 hours, taking into account the partial load of the machine rooms this time is much longer - up to 60 hours. Further, the fuel will be supplied from Moscow and, if necessary, from Ryazan. DataPro has concluded contracts with its suppliers.
Two tanks of 60 tons each are used for fuel storage, each of them is half filled. This is also made for backup: in case of an accident or repair of fuel lines and pumps.
The Dutch company Hitec Power Protection is one of the leading manufacturers of uninterruptible power solutions based on diesel rotary UPS. It was she who first patented the idea of ​​an UPS with a flywheel. Now under the protection of dynamic UPS Hitec Power Protection around the world is a fleet of equipment with a total capacity of more than 1.6 million kVA.
In the Russian data centers DRUPS - so far rare, but in the world systems based on diesel-rotary UPS due to their simplicity, reliability and energy efficiency are considered a good solution for powering high-power data centers (from 1 MW). A relatively small number of components and simplicity of design significantly increase the average time of trouble-free equipment. So at Hitec, the total service life of dynamic UPSs is at least 25 years. At the same time, depending on the amount of available fuel, diesel-rotary UPSs provide backup power for any period of time.
The Hitec installation includes: (1) diesel engine, (2) overrunning clutch, (3) generator, (4) energy storage, (5) flywheel. DRUPS Hitec is optimized for energy efficiency, and the declared input-output efficiency is 97%.
High energy efficiency of dynamic UPS is achieved due to the absence of the need for multiple voltage conversion - rectifiers, inverters, and so on. There is also no need for expensive and dangerous batteries, and therefore, in a special room for their placement, in the organization of its conditioning and, most importantly, in their regular replacement every 3-5 years.
Diesel rotary UPSs are considered the most economical and energy efficient solution to ensure uninterrupted and guaranteed power supply to large data centers. Until recently, according to research company Frost & Sullivan, rotary UPSs accounted for no more than 6% of the global UPS market. However, according to forecasts, their share should increase substantially as the size of the data center increases.
Distinctive features of DRUPS.
For a diesel rotary UPS, an average of 40–60% less space is required than a conventional static UPS with a similar diesel generator set. A single DRUPS unit is used instead of a system of backup DGS, static UPS, battery cabinets, switchboards, air conditioning systems, etc. The data center area is optimally used.
Thanks to DRUPS, virtually all quality problems are under control. The installation provides filtering of all network and load interference, feeds capacitive and inductive loads, with a power factor of 0.98.
Electric power from the city network, passing through the choke, feeds a synchronous motor-generator. The alternator shaft rotates at 1500 rpm. In normal operation, the synchronous generator performs the function of a stabilizer and a voltage filter: eliminates harmonic distortions and power interruptions, impulse noise, eliminates surges and voltage dips. Thanks to him, the frequency and amplitude of the output voltage supplied to the load are consistently stable.
Unlike static UPSs, DRUPS is optimally used for powering air conditioners whose compressors are characterized by very high starting currents. DRUPS can reduce investments in air conditioning, because they do not require strict climate control. This affects the reduction in operating costs and the final cost of rent for consumers.
Diesel dynamic uninterruptible power supply has a high level of self-diagnosis of the system, allowing you to track and prevent malfunctions in a timely manner. When repairing one of the six DRUPS, the data center will continue to function as usual, and with redundancy. The load is distributed between the rest of the UPS. This was tested even when simulating the full load of the data center. ( 60% ), DRUPS . DRUPS.
DataPro places projects from one rack, and the client should also independently agree on cooperation with telecom operators.
HOSTKEY is the official retail partner of DataPro. If you need to place equipment, rent dedicated servers or implement a complex converged project under a high SLA in a DataPro certified Tier III data center, please contact us.
Placing 1U equipment in our racks (modern server with any power supply, not twin) with a reserved dedicated Internet access channel of 100 Mbit / s costs 4,000 rubles. , 40000 . in year. You can rent the whole rack, 1/2 or a quarter of the standard rack, including under the seal. , .
We offer for rent in DataPro any dedicated Supermicro or HP servers , HP / Dell disk shelves and network infrastructure (VLAN) from 100 Mbit / s to 10 Gbit / s (including protection and routers) at reasonable prices. You can create a hybrid solution consisting of your servers, leased servers and network infrastructure. HOSTKEY provides the highest SLA for servicing customers' own equipment.
— 2016 10% — DataPro.
DataPro on Aviamotornaya Street is one of the most reliable data centers in Russia that has received Uptime Design and Facility certification. Today we will talk a little about the project and consider as closely as possible the technical implementation and features of the power supply system.
A bit about the DataPro project
The data center at Aviamotornaya 69 is the second data center built by DataPro, which specializes in providing services to commercial data centers.
International certification of Uptime Design and Facility means that the data center is designed and built in accordance with all applicable standards for the Tier III reliability category. The next level in 2016 will be Uptime Operations certification, confirming that all the procedures and procedures implemented in the data center comply with the requirements. The maximum downtime for a data center of this level is 1.6 hours per year.
Briefly about the levels of reliability
The higher the level of reliability of the data center, the more it costs during construction and operation. The cost of renting a rack in it cannot be small. However, such costs are not significant for business-critical applications and when choosing a data center, you need to pay attention to its certification. Only it can serve as a basis for statements that the data center really has a Tier III reliability level and actually corresponds to it. However, for many minor tasks, a data center with a Tier II level of reliability or even Tier I will suffice.
')
Data Processing Centers are designed to ensure the smooth operation of all of the company's critical IT processes. Underestimating and overestimating the effects of downtime have the same negative effect on costs, since financial losses are possible in both cases, either when the critical systems are idle and the business is stopped, or because of an unjustified overpayment for the service.
Tier I, according to the Uptime Institute, is a dedicated, non-redundant data center infrastructure. Usually this is one or two air conditioners and UPS without diesel. If something breaks down or not electricity - this is an emergency. Any service is easy to provide. Issue price of about $ 10,000 capital costs per rack 5 kW.
Tier II provides basic redundancy, that is, power and cooling systems have redundant components and powers. Usually there are several air conditioners in N + 1 mode, one industrial UPS and possibly diesel. Electricity is supplied through AVR from 1-2 inputs. Room - room or hangar, usually in the lease. Maintenance is often difficult or creates the danger of an accident during even routine maintenance. Issue price of about $ 20,000 capital costs per rack 5 kW.
Tier III means the reservation of all engineering subsystems, the possibility of carrying out any operations, scheduled repairs and equipment replacement without stopping services. This means N + 2 for air conditioners, 2 inputs per rack from different UPS systems, a reserve for diesel engines, two inputs and specially prepared premises in the property. The price of the issue is about $ 30,000 of the capital cost of a 5 kW rack without real estate prices.
Finally, Tier IV means fault tolerance, the ability to withstand a single unplanned emergency event, such as a fire or explosion.
If the data center of the first level does not provide for redundancy, then the second adds redundancy of the main engineering systems, but not the “ways of delivery” of the service — electricity and data network channels. Reservation of the latter is implemented in the data center of the third level, which allows for maintenance work without stopping it. The fourth level assumes reservation (N + 1 and above) of all main systems and fault tolerance upon the occurrence of the worst event. The average estimated annual data center idle time varies from 28.8 hours for the first level to 0.8 hours for the fourth level data center, while the actual availability rate is from 99.67 to 99.99%.
Thus, in the data center with the Tier III reliability level, it is possible to simultaneously operate and maintain the data center, up to the replacement of the system components and the failed equipment, and the addition of systems. This makes it possible to carry out planned repair work and equipment replacement without stopping services — imperceptible to customers.
The redundancy of all engineering subsystems (Concurrent Maintainability) significantly increases the reliability of the data center. In order to achieve this level, it is necessary to design and build two pipelines for the cooling system, to ensure that all equipment operates with spare capacity, taking into account the breakdown or preventive maintenance of the power supply system. In such a data center there are several ways of power distribution and cooling, but only one of them is active. In the Tier III data center, components are backed up using the “N + 1” scheme. As a result, the resiliency ratio is 99.982%, which is expressed in the possible downtime per year of 1.6 hours.
')
Data Processing Centers are designed to ensure the smooth operation of all of the company's critical IT processes. Underestimating and overestimating the effects of downtime have the same negative effect on costs, since financial losses are possible in both cases, either when the critical systems are idle and the business is stopped, or because of an unjustified overpayment for the service.
Tier I, according to the Uptime Institute, is a dedicated, non-redundant data center infrastructure. Usually this is one or two air conditioners and UPS without diesel. If something breaks down or not electricity - this is an emergency. Any service is easy to provide. Issue price of about $ 10,000 capital costs per rack 5 kW.
Tier II provides basic redundancy, that is, power and cooling systems have redundant components and powers. Usually there are several air conditioners in N + 1 mode, one industrial UPS and possibly diesel. Electricity is supplied through AVR from 1-2 inputs. Room - room or hangar, usually in the lease. Maintenance is often difficult or creates the danger of an accident during even routine maintenance. Issue price of about $ 20,000 capital costs per rack 5 kW.
Tier III means the reservation of all engineering subsystems, the possibility of carrying out any operations, scheduled repairs and equipment replacement without stopping services. This means N + 2 for air conditioners, 2 inputs per rack from different UPS systems, a reserve for diesel engines, two inputs and specially prepared premises in the property. The price of the issue is about $ 30,000 of the capital cost of a 5 kW rack without real estate prices.
Finally, Tier IV means fault tolerance, the ability to withstand a single unplanned emergency event, such as a fire or explosion.
If the data center of the first level does not provide for redundancy, then the second adds redundancy of the main engineering systems, but not the “ways of delivery” of the service — electricity and data network channels. Reservation of the latter is implemented in the data center of the third level, which allows for maintenance work without stopping it. The fourth level assumes reservation (N + 1 and above) of all main systems and fault tolerance upon the occurrence of the worst event. The average estimated annual data center idle time varies from 28.8 hours for the first level to 0.8 hours for the fourth level data center, while the actual availability rate is from 99.67 to 99.99%.
Thus, in the data center with the Tier III reliability level, it is possible to simultaneously operate and maintain the data center, up to the replacement of the system components and the failed equipment, and the addition of systems. This makes it possible to carry out planned repair work and equipment replacement without stopping services — imperceptible to customers.
The redundancy of all engineering subsystems (Concurrent Maintainability) significantly increases the reliability of the data center. In order to achieve this level, it is necessary to design and build two pipelines for the cooling system, to ensure that all equipment operates with spare capacity, taking into account the breakdown or preventive maintenance of the power supply system. In such a data center there are several ways of power distribution and cooling, but only one of them is active. In the Tier III data center, components are backed up using the “N + 1” scheme. As a result, the resiliency ratio is 99.982%, which is expressed in the possible downtime per year of 1.6 hours.
In 2015, DataPro Data Center on Aviamotor was awarded the best project of the year. In September, the first in Russia presentation of awards of professional awards in the field of data center construction took place. The competition program was attended by 19 data centers applying for prizes in five nominations. The international jury recognized DataPro's data center as the most ambitious and innovative and awarded DataPro the main Russian Data Center Awards 2015 award .
More about the project and plans
DataPro Data Center on Aviamotornaya Street in Moscow, commissioned in 2014. The implementation of this ambitious project from the entrance to the site to the placement of the equipment in the main hall of the first client equipment took only eight months. To build a building was not required. The former building of the Avtoframos enterprise and the surrounding area were converted under the data center.
Despite the very difficult market conditions, due to the flexibility of the strategy, DataPro managed to reach a high level of occupancy in less than a year. The first stage of the DataPro data center with 850 racks (eight engine rooms) is already 80% full. Now started the construction of the second stage of 500 racks. Potential capacity of the object - 3000 racks. The plans - the construction of another data center in Moscow for 1000 racks.
The participation of an experienced team of designers allowed us to make a choice in favor of a modular architecture along with the use of some of the most modern and energy-efficient engineering solutions in the field of data center construction. In Russia now there are only three or four such sites.
DataPro customers rent from 1 to 100 racks. An important task for owners of commercial data centers is to learn how to work with large high-tech customers. One of these DataPro anchor clients is Mail.Ru Group. This company adheres to the strategy of renting commercial data centers, rather than building its own - it focuses on its own business goals, without getting into a complex and expensive infrastructure. Another well-known client is RBC, which rents several dozens of stalls. There are among the clients and a significant number of well-known international companies such as Samsung, Chronopay, etc. There are also customers, but the share of such customers in the data center budget is still small.
Despite the very difficult market conditions, due to the flexibility of the strategy, DataPro managed to reach a high level of occupancy in less than a year. The first stage of the DataPro data center with 850 racks (eight engine rooms) is already 80% full. Now started the construction of the second stage of 500 racks. Potential capacity of the object - 3000 racks. The plans - the construction of another data center in Moscow for 1000 racks.
The participation of an experienced team of designers allowed us to make a choice in favor of a modular architecture along with the use of some of the most modern and energy-efficient engineering solutions in the field of data center construction. In Russia now there are only three or four such sites.
DataPro customers rent from 1 to 100 racks. An important task for owners of commercial data centers is to learn how to work with large high-tech customers. One of these DataPro anchor clients is Mail.Ru Group. This company adheres to the strategy of renting commercial data centers, rather than building its own - it focuses on its own business goals, without getting into a complex and expensive infrastructure. Another well-known client is RBC, which rents several dozens of stalls. There are among the clients and a significant number of well-known international companies such as Samsung, Chronopay, etc. There are also customers, but the share of such customers in the data center budget is still small.
Why is it worth placing the equipment in a certified Tier III data center?
For most tasks, this is the only option in which you do not need to look for any compromises.
Certificates of the international institute Uptime Institute cannot be purchased. All the technologies and solutions used are certified; this guarantees maximum resiliency of the data center to ensure the business continuity of customers. All this leads to guaranteed availability of resources and is an insurance against unexpected situations.
In the end, the cost of placing equipment in the data center of this level may be somewhat higher. What does the user pay for?
The cost is caused not just by the way, the user pays not for the “status”, but for confidence in the availability of resources, confirmed by professionals.
Alternatives and what the cost is formed from
Building your own data center is only suitable for large-scale or non-standard projects. Often, companies and organizations are trying to build their own server and "data centers", but only in very rare cases, such projects can come close in their technical level to well-designed and even more so to certified commercial data center. Economically inexpedient is usually considered the operation of any of its own sites for less than 40-50 racks. Savings on the cost of such a project compared to placing equipment in a commercial data center are achieved with a scale of 100 racks, since the operating costs for duty shift, security, equipment depreciation, utility bills, etc. are high.
Accordingly, in this case, you have to spend a lot of time and money on immersion in the datacenter, design and implementation. At the same time, this experience is obligatory, since in the future there may be many “underwater” stones and a “rake”. By making this decision, the company is quite at risk of getting an expensive and whimsical toy.
Placing equipment in an uncertified data center
This option is most often chosen in a limited budget. But, in order to choose the best option, one also has to become an expert in TSODostroitelstvo, since assess the infrastructure of the data center and the conditions of accommodation will have to independently.
Placing the equipment in a Tier III DataPro certified data center will ensure that life support systems are fault tolerant and the possibility of force majeure tends to zero.
One of the main problems of IT outsourcing in our country is the problem of trust in the service provider. When choosing a data center, you need to pay attention not only to the data center certification, but also to the outsourcer's business transparency, its direct ownership of the building, permits for the allocated electricity capacity, long-term registration of the adjacent territory, the possibility of further development of the site. DataPro meets these requirements. The data center building is owned by DataPro - customers are insured against many surprises, since no one is immune from force majeure, there are fairly common cases when the building owners or city authorities evicted the data center to the street with a 1-2 month notice.
For the financial sector. The demand for Tier III data center services is facilitated by the existence in Russia of appropriate clear regulatory standards for financial institutions. At the same time, the number of false statements by companies that they have a Tier III “level” data center also increases. Sometimes they talk about "compatibility" with the requirements of a certificate of international level of reliability Tier III. After all, data center certification becomes a competitive advantage.
Is this the cost?
Design
Here everything is clear, the higher the competence and experience of the developers, the higher the cost of the project.
Directly construction
It all depends on the original project - the value of real estate, engineering systems used, and the estimated redundancy, etc.
If we take the estimated total costs for the purchase of elements of engineering systems and their installation, it turns out that, without regard to real estate, commissioning a single rack of 5 kW costs:
Exploitation
This includes the costs of utilities, wages, depreciation of equipment, maintenance, etc. It is logical that the higher the reliability category of the data center, the higher the operating costs. After all, for example, third-party certified specialists are most often involved in carrying out maintenance work. It is also worth noting that a significant factor affecting operating costs is the scale of the project - the larger the project, the cheaper the cost of maintenance per rack (all other things being equal).
Certification
It would seem, think, get a certificate. But in practice it is a very long and laborious process.
The process of assessing the quality of the project by the Uptime Institute begins with an analysis of the documentation, which serves as the basis for obtaining a certificate for a design project. At this stage, the project documentation is transferred to the Uptime Institute. It should provide answers to specific questions that concern all engineering systems, including building and planning, the topology of the location of telecommunication and engineering networks, operating modes of equipment, etc.
The process of obtaining a certificate of Uptime Facility on the shoulder a little - it is expensive and takes several months of hard work. It is required to conduct data center testing under full load, for which the “ballast” is connected - resistive load modules equivalent to the load of the required power, in blocks of 500 kW and more. Heat engines are used to inspect machine rooms. Failure of one of the cooling and power supply systems is simulated. It checks how everything works at full load, how switching occurs under load. Such serious testing helps to identify bottlenecks in advance, even before the data center is put into commercial operation.
Accordingly, in this case, you have to spend a lot of time and money on immersion in the datacenter, design and implementation. At the same time, this experience is obligatory, since in the future there may be many “underwater” stones and a “rake”. By making this decision, the company is quite at risk of getting an expensive and whimsical toy.
Placing equipment in an uncertified data center
This option is most often chosen in a limited budget. But, in order to choose the best option, one also has to become an expert in TSODostroitelstvo, since assess the infrastructure of the data center and the conditions of accommodation will have to independently.
Placing the equipment in a Tier III DataPro certified data center will ensure that life support systems are fault tolerant and the possibility of force majeure tends to zero.
One of the main problems of IT outsourcing in our country is the problem of trust in the service provider. When choosing a data center, you need to pay attention not only to the data center certification, but also to the outsourcer's business transparency, its direct ownership of the building, permits for the allocated electricity capacity, long-term registration of the adjacent territory, the possibility of further development of the site. DataPro meets these requirements. The data center building is owned by DataPro - customers are insured against many surprises, since no one is immune from force majeure, there are fairly common cases when the building owners or city authorities evicted the data center to the street with a 1-2 month notice.
For the financial sector. The demand for Tier III data center services is facilitated by the existence in Russia of appropriate clear regulatory standards for financial institutions. At the same time, the number of false statements by companies that they have a Tier III “level” data center also increases. Sometimes they talk about "compatibility" with the requirements of a certificate of international level of reliability Tier III. After all, data center certification becomes a competitive advantage.
Is this the cost?
Design
Here everything is clear, the higher the competence and experience of the developers, the higher the cost of the project.
Directly construction
It all depends on the original project - the value of real estate, engineering systems used, and the estimated redundancy, etc.
If we take the estimated total costs for the purchase of elements of engineering systems and their installation, it turns out that, without regard to real estate, commissioning a single rack of 5 kW costs:
- For Tier I data center - about $ 10,000
- For Tier II data center - about $ 20,000
- For Tier III data center - about 30,000 dollars
Exploitation
This includes the costs of utilities, wages, depreciation of equipment, maintenance, etc. It is logical that the higher the reliability category of the data center, the higher the operating costs. After all, for example, third-party certified specialists are most often involved in carrying out maintenance work. It is also worth noting that a significant factor affecting operating costs is the scale of the project - the larger the project, the cheaper the cost of maintenance per rack (all other things being equal).
Certification
It would seem, think, get a certificate. But in practice it is a very long and laborious process.
The process of assessing the quality of the project by the Uptime Institute begins with an analysis of the documentation, which serves as the basis for obtaining a certificate for a design project. At this stage, the project documentation is transferred to the Uptime Institute. It should provide answers to specific questions that concern all engineering systems, including building and planning, the topology of the location of telecommunication and engineering networks, operating modes of equipment, etc.
The process of obtaining a certificate of Uptime Facility on the shoulder a little - it is expensive and takes several months of hard work. It is required to conduct data center testing under full load, for which the “ballast” is connected - resistive load modules equivalent to the load of the required power, in blocks of 500 kW and more. Heat engines are used to inspect machine rooms. Failure of one of the cooling and power supply systems is simulated. It checks how everything works at full load, how switching occurs under load. Such serious testing helps to identify bottlenecks in advance, even before the data center is put into commercial operation.
DataPro Infrastructure
In the following materials we will describe in detail all the life support systems of this data center. And today we will briefly review the main elements of the infrastructure and talk in detail about the power supply.
The average size of the machine room in the DataPro data center is 180 square meters. m, it is designed for about 100 racks or can be divided into several enclosures. There are eight such halls now. The building provides space for technical personnel, equipment storage, loading and unloading, catering. Clients can not only rent a rack, but also create a backup office, where the client’s critical personnel will continue to work in the event of an emergency.
Eight Schneider Electric Ecobreeze units are currently used for cooling server rooms and auxiliary technological premises of the data center. The temperature regime in the halls is maintained at + 25 ° C at a humidity of 40–60%. The use of this modular cooling system in combination with other engineering solutions made it possible to achieve a high PUE rate, the total average annual value of which does not exceed 1.3. In the next article we will tell about Ecobreeze in more detail.
A fiber optic link is connected to the data center via two independent routes, connecting it with all the largest telecommunications centers in Moscow and traffic exchange points. The technology platform policy is neutral with respect to telecom operators, so there are more than 10 telecom operators on the site (Garstelecom, Mastertel, RETN, Macomnet, MTS, Beeline, Orange Business Services, etc.).
Considerable attention is paid to security: security is responsible for the security of the data center itself and the surrounding area. The security system includes more than 350 network cameras. The data center also provides advanced methods for preventing ignition: a super early Vesda smoke detection system and an automatic gas fire extinguishing system based on freon-227.
Data Center Power Supply
Power supply - the basis of reliable data center operation. It should be uninterrupted, for which uninterruptible power supplies (UPS) are traditionally used, and guaranteed, for which diesel generator sets (DGS) are used, supporting the work of the data center during a prolonged power outage.
The DataPro data center has two independent inputs of 10 kV from the Mosenergo substation, and the cables are laid in different collectors, provide the necessary electrical power to the facility. Power is supplied to consumers through a group of step-down transformers. These dry transformers are constantly in operation in the presence of power from the city substation.
Now the allowed and connected data center power is 6 MW. Another 8 MW of power is in the process of registration. The power supply of the data center is actually reserved under the 2N scheme. For example, even at a 100% load in the event of an accident of a power supply panel, transformer, DRUPS, the entire turbine hall will be powered from the second input / shield. It is assumed that customers use equipment with redundant power supplies or rack-mount ATS.
Here are the main components of the data center power supply system. On the right - transformers, on the left diesel rotor UPS (DRUPS).
For powering the data center dry transformers rated at 1600 kVA each are used. They convert 10 kV at the input to 0.4 kV at the output.
Part of the data center power system circuitry.
Diesel rotary ups
Traditionally, in the event of the disappearance of the city network voltage, the UPS batteries must maintain the power supply of the equipment until the diesel generator set is fully started, which can provide the entire data center with electricity. This process usually takes from 20-30 seconds to 2 minutes, on which the power of the UPS and the capacity of the batteries are calculated.
The DataPro data center uses a different, more economical approach for its scale. The main components of the DataPro data center infrastructure were power supply solutions for diesel rotary UPSs manufactured by Hitec Power Protection (currently four units) and Euro-Diesel (two cars). A service contract with two different vendors allows you to optimize prices and compare services.
In essence, a diesel rotary or dynamic UPS (DRUPS) of these manufacturers is a diesel engine assembled coaxially on one shaft, an electromagnetic clutch, a synchronous electric machine and a dynamic flywheel. A decoupling choke connects the mains voltage input to the “clean” voltage output of the UPS system. It provides a high degree of isolation between the input and output, blocking the passage of harmonics and transients.
If there is an external power supply, the UPS synchronous electric machine operates in the electric motor mode, rotating the rotor of the flywheel. When the parameters of the network outside the set limits, it goes into generator mode, maintaining a continuous sinusoidal voltage on the load. The source of energy during the transition process is the flywheel, thanks to which the stable frequency of rotation of the rotor shaft of the synchronous electric machine is maintained. A flywheel keeps up to one minute at full electric load without a diesel.
After the mains voltage fails, the DRUPS control system sends a signal to start the diesel engine. The kinetic energy of the flywheel, in addition to maintaining the output voltage, is used to output the diesel engine crankshaft to the operating frequency. After 50 ms after a power failure, the diesel engine begins to work, which within a few seconds goes into normal operation - the flywheel is already spinning.
Independent power supply of the facility in the event of a power failure from the substation is provided by diesel-rotary UPSs Hitec Power Protection of 1670 kVA with 4 / 3N redundancy scheme. And no batteries to power the IT load.
Power supply cables and ventilation duct.
Once a month, diesel engines are started to check their performance. The estimated stock of diesel fuel in the storage facility is 17 hours, taking into account the partial load of the machine rooms this time is much longer - up to 60 hours. Further, the fuel will be supplied from Moscow and, if necessary, from Ryazan. DataPro has concluded contracts with its suppliers.
Two tanks of 60 tons each are used for fuel storage, each of them is half filled. This is also made for backup: in case of an accident or repair of fuel lines and pumps.
The Dutch company Hitec Power Protection is one of the leading manufacturers of uninterruptible power solutions based on diesel rotary UPS. It was she who first patented the idea of ​​an UPS with a flywheel. Now under the protection of dynamic UPS Hitec Power Protection around the world is a fleet of equipment with a total capacity of more than 1.6 million kVA.
In the Russian data centers DRUPS - so far rare, but in the world systems based on diesel-rotary UPS due to their simplicity, reliability and energy efficiency are considered a good solution for powering high-power data centers (from 1 MW). A relatively small number of components and simplicity of design significantly increase the average time of trouble-free equipment. So at Hitec, the total service life of dynamic UPSs is at least 25 years. At the same time, depending on the amount of available fuel, diesel-rotary UPSs provide backup power for any period of time.
The Hitec installation includes: (1) diesel engine, (2) overrunning clutch, (3) generator, (4) energy storage, (5) flywheel. DRUPS Hitec is optimized for energy efficiency, and the declared input-output efficiency is 97%.
High energy efficiency of dynamic UPS is achieved due to the absence of the need for multiple voltage conversion - rectifiers, inverters, and so on. There is also no need for expensive and dangerous batteries, and therefore, in a special room for their placement, in the organization of its conditioning and, most importantly, in their regular replacement every 3-5 years.
Diesel rotary UPSs are considered the most economical and energy efficient solution to ensure uninterrupted and guaranteed power supply to large data centers. Until recently, according to research company Frost & Sullivan, rotary UPSs accounted for no more than 6% of the global UPS market. However, according to forecasts, their share should increase substantially as the size of the data center increases.
Distinctive features of DRUPS.
For a diesel rotary UPS, an average of 40–60% less space is required than a conventional static UPS with a similar diesel generator set. A single DRUPS unit is used instead of a system of backup DGS, static UPS, battery cabinets, switchboards, air conditioning systems, etc. The data center area is optimally used.
Thanks to DRUPS, virtually all quality problems are under control. The installation provides filtering of all network and load interference, feeds capacitive and inductive loads, with a power factor of 0.98.
Electric power from the city network, passing through the choke, feeds a synchronous motor-generator. The alternator shaft rotates at 1500 rpm. In normal operation, the synchronous generator performs the function of a stabilizer and a voltage filter: eliminates harmonic distortions and power interruptions, impulse noise, eliminates surges and voltage dips. Thanks to him, the frequency and amplitude of the output voltage supplied to the load are consistently stable.
Unlike static UPSs, DRUPS is optimally used for powering air conditioners whose compressors are characterized by very high starting currents. DRUPS can reduce investments in air conditioning, because they do not require strict climate control. This affects the reduction in operating costs and the final cost of rent for consumers.
Diesel dynamic uninterruptible power supply has a high level of self-diagnosis of the system, allowing you to track and prevent malfunctions in a timely manner. When repairing one of the six DRUPS, the data center will continue to function as usual, and with redundancy. The load is distributed between the rest of the UPS. This was tested even when simulating the full load of the data center. ( 60% ), DRUPS . DRUPS.
DataPro places projects from one rack, and the client should also independently agree on cooperation with telecom operators.
HOSTKEY is the official retail partner of DataPro. If you need to place equipment, rent dedicated servers or implement a complex converged project under a high SLA in a DataPro certified Tier III data center, please contact us.
Placing 1U equipment in our racks (modern server with any power supply, not twin) with a reserved dedicated Internet access channel of 100 Mbit / s costs 4,000 rubles. , 40000 . in year. You can rent the whole rack, 1/2 or a quarter of the standard rack, including under the seal. , .
We offer for rent in DataPro any dedicated Supermicro or HP servers , HP / Dell disk shelves and network infrastructure (VLAN) from 100 Mbit / s to 10 Gbit / s (including protection and routers) at reasonable prices. You can create a hybrid solution consisting of your servers, leased servers and network infrastructure. HOSTKEY provides the highest SLA for servicing customers' own equipment.
— 2016 10% — DataPro.
Source: https://habr.com/ru/post/277355/
All Articles