Deployment support method, deployment support system, and data center

Abstract

To provide an arrangement support method and an arrangement support system for efficiently constructing a data center and the data center constructed by them.SOLUTION: The total rated power of a plurality of kinds of servers installed on a floor is specified, the total weight of the servers installed on the floor is predicted according to the total rated power, and the total weight is distributed to the plurality of kinds of servers at a constitution ratio corresponding to the kinds and classified into a plurality of heavy high-density servers L11, and a plurality of light medium-density servers L12 and low-density servers L13. In a building, the positions of a plurality of beams b1 supporting a floor b2 are specified, a plurality of first servers is placed directly above the beams, and the plurality of medium-density servers L12 and the low-density servers L13 are placed between the plurality of high-density servers L11.SELECTED DRAWING: Figure 4

Description

Technical Field

[0004]

[0001] The present disclosure relates to an arrangement support method, an arrangement support system, and a data center for assisting in the construction of a data center.

Background Art

[0002] In a data center, a large amount of power and communication are drawn into the site. For this reason, the data center has a large area for arranging many servers. Each server is housed in a server rack. However, due to the progress of server densification, the weight per rack of each server tends to increase. Therefore, the seismic performance required for the building is also increasing. Further, since each server generates heat by consuming a large amount of power, it is necessary to consider the internal structure of the data center such as air conditioning. Therefore, technologies for constructing a data center using the hot aisle - cold aisle method have been studied (see, for example, Patent Document 1).

[0003] Also, building structures for data centers have been studied (see, for example, Patent Document 2). In the technology disclosed in this document, it has a beam connecting the first columns of the building and a truss beam connecting the second columns arranged in the building with a span longer than the span of the first columns. An outside air intake section for taking in outside air is provided in a chimney arranged outside the first columns.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] Due to the closure of existing data center facilities as they age, there is a shortage of urban data centers in central Tokyo. However, securing land for constructing large-scale data centers in urban areas is difficult. Furthermore, excessive investment in equipment relative to the load-bearing capacity of the servers used in data centers would result in a significant financial burden. [Means for solving the problem]

[0006] A placement support method to solve the above problem includes the steps of: identifying the number of servers to be installed on the floor and the total rated power; predicting the total weight of the servers to be installed on the floor according to the total rated power; distributing the total weight to each server in the number of servers according to a predetermined proportion to classify them into a plurality of heavy first servers and a plurality of light second servers; identifying the locations of a plurality of beams supporting the floor in the building; placing the plurality of first servers directly above the beams; and placing the plurality of second servers between the plurality of first servers. [Effects of the Invention]

[0007] According to this disclosure, data centers can be built efficiently. [Brief explanation of the drawing]

[0008] [Figure 1] This is an explanatory diagram of the placement support system of an embodiment. [Figure 2] This is an explanatory diagram of the hardware configuration of the embodiment. [Figure 3] This is an explanatory diagram of the procedure for the placement support method of the embodiment. [Figure 4] This is an explanatory diagram of the server arrangement in an embodiment, where (a) is the data center specifications, (b) is the server rack classification, and (c) is an explanatory diagram of the server rack layout. [Modes for carrying out the invention]

[0009] The following describes one embodiment of the deployment support method using Figures 1 to 4. In this embodiment, a group of small data centers is constructed by renovating multiple existing buildings used for office purposes. These data centers are then connected by dedicated lines to realize a virtual large-scale data center. The deployment support method, deployment support system, and data center used in this case will be described below. In this embodiment, as shown in Figure 1, the deployment support system A1 uses user terminals 10 and support servers 20 that are interconnected via a network.

[0010] (Description of hardware configuration) Figure 2 illustrates the hardware configuration of the information processing device H10, which comprises the user terminal 10 and the support server 20. The information processing device H10 includes a communication device H11, an input device H12, a display device H13, a storage device H14, and a processor H15. Note that this hardware configuration is just one example, and it can be implemented using other hardware.

[0011] Communication device H11 is an interface that establishes a communication path with other devices and performs data transmission and reception, such as a network interface or a wireless interface.

[0012] The input device H12 is a device that accepts input of various types of information, such as a mouse or keyboard. The display device H13 is a display that shows various types of information. A touch panel display may be used as both the input device H12 and the display device H13.

[0013] The storage device H14 is a storage device that stores data and various programs for executing various functions of the user terminal 10 and the support server 20. Examples of storage devices H14 include ROM, RAM, and hard disks.

[0014] Processor H15 controls each process in user terminal 10 and support server 20 by using programs and data stored in storage device H14. Examples of processor H15 include, for example, a CPU, an MPU, etc. This processor H15 expands a program stored in a ROM or the like to a RAM and executes various processes for each process.

[0015] Processor H15 is not limited to performing software processing for all processes it executes. For example, processor H15 may include a dedicated hardware circuit (for example, an application-specific integrated circuit: ASIC) that performs hardware processing for at least a part of the processes it executes. That is, processor H15 may be configured as follows.

[0016] 〔1〕One or more processors that operate according to a computer program (software) 〔2〕One or more dedicated hardware circuits that execute at least a part of various processes 〔3〕A circuit (circuitry) including a combination thereof The processor includes a CPU and memories such as a RAM and a ROM, and the memories store program codes or instructions configured to cause the CPU to execute processes. The memory, that is, the computer-readable medium, includes any available medium that can be accessed by a general-purpose or dedicated computer.

[0017] (System configuration) Next, each function of placement support system A1 will be described using FIG. 1. User terminal 10 is a computer terminal used by a designer who determines the placement of a server. The designer accesses support server 20 using user terminal 10.

[0018] Support server 20 is a computer system that executes a process for supporting server placement design. This support server 20 includes a control unit 21, a basic information storage unit 22, a data center information storage unit 23, and a building information storage unit 24.

[0019] The control unit 21 performs processes (processes including an acquisition stage, a design support stage, etc.) described later. By executing a processing program for this purpose, the control unit 21 functions as an acquisition unit 211, a design support unit 212, etc.

[0020] The acquisition unit 211 acquires various information from the user terminal 10. The design support unit 212 supports the design of a data center in which a server is arranged in an existing building. Here, it is also possible to use BIM (Building Information Modeling).

[0021] Information for supporting the placement of the server is recorded in the basic information storage unit 22. In this embodiment, weight calculation information and server configuration information are recorded. The weight calculation information is information for calculating the total weight from the total rated power. In this embodiment, as the weight calculation information, a table in which the total weight of the servers is recorded for each capacity range of the total rated power is used.

[0022] The server configuration information is information for calculating the composition ratio of server racks with different weights according to the type of server. For example, assume a case where a plurality of types of servers (high-density servers, medium-density servers, low-density servers) are used as server racks. Medium-density servers are lighter than high-density servers, and low-density servers are even lighter than medium-density servers. In this embodiment, the high-density server functions as the first server with a heavy weight, and the medium-density server and the low-density server function as the second server. In this case, as the server configuration information of the data center, a table in which the composition ratio (n1:n2:n3) according to the types of high-density servers, medium-density servers, and low-density servers is recorded is used.

[0023] Data center management information regarding the data center to be constructed is recorded in the data center information storage unit 23. As the data center management information, information regarding the center identifier, building identifier, total rated power per floor, and the number of servers is recorded.

[0024] The center identifier is an identifier used to identify the data center that is planned to be built. The building identifier is an identifier used to identify the building on which this data center will be constructed. In this embodiment, an existing building is used as the building on which the data center will be constructed.

[0025] A floor is a level within an existing building where servers are located. The total rated power is the sum of the rated power used by each server planned to be placed on this floor. The number of servers refers to the number of servers planned to be placed on this floor.

[0026] The building information storage unit 24 records building management information for buildings to be converted into data centers. This building management information is recorded when a building to be constructed as a data center is registered. The building management information includes a building identifier and design drawings for each floor.

[0027] The building identifier is an identifier used to identify the existing building on which this data center will be constructed. A floor is a level within an existing building where servers are located. The design drawings record the arrangement and size of the building's structural members (foundation, columns, beams, floors, walls, etc.). Using these design drawings, the load-bearing capacity of a floor can be calculated.

[0028] (Design process) Next, we will explain the design process using Figures 3 and 4. First, the control unit 21 of the support server 20 performs the process of acquiring server information (step S11). Specifically, the acquisition unit 211 of the control unit 21 acquires server information from the user terminal 10.

[0029] In this embodiment, as shown in Figure 4(a), the total rated power GP and the number of servers GN are obtained as server information for each server housed in the server rack L1 installed on one floor.

[0030] Next, the control unit 21 of the support server 20 performs a total weight prediction process from the rated power information (step S12). Specifically, the design support unit 212 of the control unit 21 predicts the total weight WT from the total rated power GP using the weight calculation information recorded in the basic information storage unit 22.

[0031] Next, the control unit 21 of the support server 20 performs a prediction process for the weight of each server (step S13). Specifically, the design support unit 212 of the control unit 21 obtains the configuration ratio according to the type of server rack from the server configuration information recorded in the basic information storage unit 22.

[0032] As shown in Figure 4(b), the composition ratio (Rn1:Rn2:Rn3) of the server rack, consisting of high-density server L11, medium-density server L12, and low-density server L13, is obtained. In this case, the following equation holds true.

[0033] x1:x2:x3=Rn1:Rn2:Rn3 x1 + x2 + x3 = GN This allows us to calculate the number of high-density servers, medium-density servers, and low-density servers (x1, x2, x3).

[0034] Next, the design support unit 212 obtains the weight ratio (Rw1:Rw2:Rw3) of the high-density server L11, the medium-density server L12, and the low-density server L13 from the server configuration information recorded in the basic information storage unit 22. In this case, the following equation holds true.

[0035] W1:W2:W3=Rw1:Rw2:Rw3 W1·x1 + W2·x2 + W3·x3 = WT By solving this equation, we can calculate the weights (W1, W2, W3) of the high-density server L11, the medium-density server L12, and the low-density server L13.

[0036] Next, the control unit 21 of the support server 20 performs beam location identification processing (step S14). Specifically, the design support unit 212 of the control unit 21 obtains building structural information from the building information storage unit 24. The design support unit 212 displays the building structural information on the display device H13 of the user terminal 10. In this case, the designer specifies the floor on which the data center will be constructed. In this case, the design support unit 212 identifies the beam locations of the main beams and secondary beams that support the floor of the specified floor in the structural information.

[0037] Next, the control unit 21 of the support server 20 performs server placement processing according to the weight of each server (step S15). Specifically, the design support unit 212 of the control unit 21 places the high-density servers on the floor directly above the beams. Here, we assume that the number of high-density servers is less than the number of beams. The design support unit 212 then generates a server placement layout in which medium-density servers L12 and low-density servers L13 are placed between the high-density servers L11. Here, a standardized size of server racks (e.g., 19 inches) is used. The spacing between servers is adjusted and rearranged so that the medium-density servers L12 and low-density servers L13 fit between the high-density servers L11, and the high-density servers L11 are directly above the beams.

[0038] Next, the control unit 21 of the support server 20 performs load-bearing capacity calculation processing according to the beam position (step S16). Specifically, the design support unit 212 of the control unit 21 calculates the required load-bearing capacity of the floor when the weight of each server is transmitted to each beam, according to the weight and arrangement of the high-density servers, medium-density servers, and low-density servers.

[0039] Next, the control unit 21 of the support server 20 performs reinforcement processing as needed (step S17). Specifically, the design support unit 212 of the control unit 21 obtains the allowable load of the existing building's floor according to the building's structural information recorded in the building information storage unit 24. Then, the design support unit 212 compares the calculated load capacity with the allowable load. If the load capacity exceeds the allowable load, the design support unit 212 outputs a proposal for floor reinforcement. As shown in Figure 4(c), a support frame 12 that spans the beams b1 can be used to reinforce the floor b2 between the beams b1.

[0040] Then, according to the arrangement of high-density, medium-density, and low-density servers determined by the design process, a data center is constructed in the existing building. In this case, the various servers used in the data center are classified into high-density, medium-density, and low-density servers according to their type, and arranged according to the layout of high-density, medium-density, and low-density servers.

[0041] According to this embodiment, the following effects can be obtained. (1) In this embodiment, the control unit 21 of the support server 20 performs a total weight prediction process from the rated power information (step S12). In this case, the weight calculation information recorded in the basic information storage unit 22 is used. The weight of a server rack increases according to its rated power. This makes it possible to predict the total weight from the total rated power of the servers used in the data center using the weight calculation information.

[0042] (2) In this embodiment, the control unit 21 of the support server 20 performs a prediction process for the weight of each server (step S13). In this case, the server configuration information recorded in the basic information storage unit 22 is used. The types of servers used in a data center are predetermined to some extent. For this reason, the composition ratio of the types of servers to be placed in the data center can also be determined statistically within a predetermined range. Therefore, the weight of heavy, high-density servers to light, low-density servers can be predicted using the server configuration information.

[0043] (3) In this embodiment, the control unit 21 of the support server 20 performs beam position identification processing (step S14) and server placement processing according to the weight of each server (step S15). This makes it possible to place heavier servers on beams to ensure load-bearing capacity. On the other hand, by placing lighter servers between beams, the load can be distributed.

[0044] (4) In this embodiment, the control unit 21 of the support server 20 performs load-bearing capacity calculation processing (step S16) according to the beam position, and reinforcement processing (step S17) as necessary. This makes it possible to determine whether reinforcement is necessary, taking into account the load-bearing capacity of the floor due to the server racks arranged according to the type of server.

[0045] This embodiment can be implemented with the following modifications. This embodiment and the following modifications can be combined with each other to the extent that they do not contradict each other technically. In the above embodiment, the deployment support method was executed using the user terminal 10 and the support server 20. Steps S11 to S17 may also be performed manually. In the above embodiment, multiple second servers are placed between multiple first servers. In Figure 4(c), two second servers (medium-density server L12, low-density server L13) are placed between the first servers (high-density server L11). As long as second servers can be placed between first servers, the number of second servers between first servers is not limited.

[0046] In the above embodiment, high-density servers, medium-density servers, and low-density servers were assumed as types of server racks, but the types are not limited to three. If there are multiple types, two or four or more types may be used. In this case, weight calculation information and server configuration information corresponding to the type are recorded in the basic information storage unit 22. Then, one or more lighter second servers are placed between multiple heavier first servers.

[0047] In the above embodiment, a user terminal 10 and a support server 20 are used. The hardware configuration is not limited to this. For example, the user terminal 10 may be equipped with a control unit 21, a basic information storage unit 22, a data center information storage unit 23, and a building information storage unit 24, and the design processing may be performed on the user terminal 10.

[0048] • The above embodiment assumes the construction of a data center in an existing building. It may also be applied to server placement when constructing a data center in part of a newly constructed building. In the above embodiment, the control unit 21 of the support server 20 performs server placement processing according to the weight of each server (step S15). Here, the load-bearing capacity distribution (load-bearing capacity map) of the floor where the servers are to be installed may be calculated by structural calculations of the building. Then, using the load-bearing capacity map, high-density servers are preferentially placed in areas with high load-bearing capacity, and medium-density and low-density servers are distributed to areas with low load-bearing capacity. Furthermore, using the load-bearing capacity map, load-bearing capacity calculation processing (step S16) is performed according to the beam position, and reinforcement processing (step S17) is performed as needed. Alternatively, the control unit 21 of the support server 20 may calculate the minimum necessary reinforcement and layout relative to the total weight by repeating the server placement processing (step S15) and reinforcement processing (step S17).

[0049] In the above embodiment, the control unit 21 of the support server 20 performs a prediction process for the weight of each server (step S13). If the weights of high-density servers, medium-density servers, and low-density servers can be estimated, the number of each server may be calculated from the total weight WT and the server configuration ratio. For example, let the high-density servers, medium-density servers, and low-density servers be defined by their weights (W1, W2, W3) and number (x1, x2, x3), respectively. x1:x2:x3=Rn1:Rn2:Rn3 W1·x1 + W2·x2 + W3·x3 = WT

[0050] In this case, the number of units (x1, x2, x3) is calculated using the following formula. x1 = α·Rn1 x² = α·Rn² x³ = α·Rn³ α=WT / (W1·Rn1+W2·Rn2+W3·Rn3) Note that the decimal part of the number of units (x1, x2, x3) will be truncated. This allows us to calculate the number of servers needed for each server based on the total weight (WT) and server configuration ratio, provided that the weights of the heavier first server and the lighter second server are known. Then, by arranging the second servers between the first servers, we can achieve a layout that takes load capacity into consideration. [Explanation of symbols]

[0051] A1... Placement support system, L11... High-density server, L12... Medium-density server, L13... Low-density server, 10... User terminal, 20... Support server, 21... Control unit, 211... Acquisition unit, 212... Design support unit, 22... Basic information storage unit, 23... Data center information storage unit, 24... Building information storage unit.

Claims

1. A computer, The steps include determining the total rated power of multiple types of servers installed on the floor, The steps include predicting the total weight of multiple types of servers to be installed on the floor according to the total rated power, The steps include: distributing the total weight among the multiple types of servers in proportions corresponding to each type, thereby classifying them into multiple heavy first servers and multiple light second servers; In the building layout, the steps include identifying the positions of multiple beams that support the floor, In the above layout, the steps include: positioning the plurality of first servers directly above the beams of the building; A deployment support method characterized by performing the step of arranging the plurality of second servers between the plurality of first servers in the above-mentioned layout.

2. The layout support method according to Claim 1, characterized in that the computer further performs the step of calculating the load capacity at the beam positions of the building after the step of arranging the plurality of second servers in the layout, and outputting a proposal to reinforce the beams by using a frame spanning between the plurality of beams according to the load capacity of the building.

3. A placement support system comprising a control unit that assists in determining the placement of servers, The control unit, Identify the total rated power of multiple types of servers installed on the floor, Based on the total rated power, the total weight of the multiple types of servers to be installed on the floor is predicted. The total weight is distributed among the multiple types of servers in proportions corresponding to each type, thereby classifying them into multiple heavy first servers and multiple light second servers. In a building, identify the locations of multiple beams that support the floor, A layout support system characterized by generating a layout in which the plurality of first servers are placed directly above the beam and the plurality of second servers are placed between the plurality of first servers.

4. The total weight corresponding to the total rated power of multiple types of servers installed on the floor is distributed among the multiple types of servers in a proportion corresponding to each type, thereby classifying them into multiple heavy first servers and multiple light second servers. In a building, identify the locations of multiple beams that support the floor, The plurality of first servers are placed directly above the beam, A data center characterized by having a plurality of second servers arranged between the plurality of first servers.

5. The data center according to claim 4, characterized in that it is reinforced by a frame spanning between the multiple beams, depending on the load-bearing capacity of the building.

Images