Cabinet racking method, device and equipment and storage medium

Through the resource information and optimization indicators of the computer cabinet, the target cabinet is automatically determined, which solves the problems of dispersed equipment on-shelf locations and low power supply resource utilization in traditional methods, and achieves more efficient resource utilization and operational safety.

CN119065913APending Publication Date: 2024-12-03NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310625866.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In data centers, traditional cabinet shelving methods rely too much on the subjective judgment of operation and maintenance personnel, resulting in dispersed equipment shelving locations, low power supply resource utilization, and mismatched power supply resource usage, affecting the operating safety and efficiency of the cabinet.

Method used

By obtaining the rated and used resource information of each available cabinet, determine the cabinet to be selected, and calculate the optimization indicators based on the rated, used and required resource information, build an evaluation matrix, calculate the weight coefficient of the optimization indicators for different attributes, and select the optimal closeness level. The cabinet with the largest value is the target cabinet.

Benefits of technology

It improves the concentration rate of equipment on-shelf locations and the utilization rate of cabinet power supply resources, ensures the matching and use of power supply resources, and reduces operation and maintenance costs and risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065913A_ABST
    Figure CN119065913A_ABST
Patent Text Reader

Abstract

The invention relates to a cabinet racking method and device, equipment and a storage medium. According to the main technical scheme, the method comprises the following steps: acquiring rated resource information and used resource information of each available cabinet, and determining a to-be-selected cabinet from the available cabinets according to the rated resource information and the used resource information of each available cabinet; obtaining demand resource information of each to-be-selected cabinet and resource information of a phase where the to-be-selected cabinet is located after being put on a shelf; determining an optimization index of each to-be-selected cabinet according to the rated resource information, the used resource information and the required resource information of each to-be-selected cabinet and the resource information of the phase where the to-be-selected cabinet is located after the to-be-selected cabinet is racked; constructing an evaluation matrix according to the optimization indexes of the to-be-selected cabinets, and calculating weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix; and according to the optimization indexes of the to-be-selected cabinets and the weight coefficients corresponding to the optimization indexes with different attributes, determining a target racking cabinet. According to the invention, the effects of improving the equipment racking position concentration rate, the cabinet power supply resource interest rate and the power supply resource utilization rate can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of cabinets, and in particular to a cabinet mounting method, device, equipment and storage medium. Background Art

[0002] Data centers are global collaborative networks of specific devices used to transmit, accelerate, display, calculate, and store data information on the Internet network infrastructure. Large data centers have a huge number of devices and tens of thousands of servers. Therefore, how to put the equipment on the best cabinet to keep the data center computer room running more economically and efficiently has always troubled operation and maintenance personnel. Since the equipment involves multiple different indicators during the racking process, these indicators can be divided into two categories: the first category is mandatory requirements that must be met, and the available resource conditions of the cabinet must meet the actual racking requirements of the network equipment; the second category is indicators that can be further optimized. On the basis of the available resources of the cabinet meeting the conditions, cabinets and U positions with relatively better indicators are selected to achieve optimization of power system resource utilization and operation safety.

[0003] In the traditional implementation method, for the second type of indicators that can be further optimized, the operation and maintenance personnel generally screen out the indicators to be optimized based on their work experience, and preset weight values ​​for different optimization indicators based on their work experience. The preset weight values ​​for the optimization indicators that are considered to be more important will be relatively large, and the preset weight values ​​for the indicators that are considered to be less important will be relatively small. Then, the best cabinet can be selected for shelving operation based on the screened optimization indicators and the preset weight values.

[0004] However, the above method relies too much on the subjective judgment and work experience of the operation and maintenance personnel. In the actual operation and maintenance process, the business capabilities of the computer room operation and maintenance personnel vary greatly. If they lack the ability or experience, the selected optimization indicators will have little effect and the weight ratio given will be unreasonable, which will affect the final cabinet rack location, leading to a series of problems such as scattered equipment rack locations, low cabinet power supply resource rates, and mismatched power supply resource usage. Summary of the invention

[0005] Based on this, the present application provides a cabinet racking method, device, equipment and storage medium, which determines the rack cabinet by determining the optimization index and calculating the weight value of the optimization index, thereby achieving the effect of improving the equipment racking location concentration rate, cabinet power supply resource interest rate and power supply resource utilization rate.

[0006] In a first aspect, a cabinet mounting method is provided, the method comprising:

[0007] Acquire rated resource information and used resource information of each available cabinet, and determine a cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet;

[0008] Obtain the required resource information of each cabinet to be selected and the corresponding resource information after being put on the shelf;

[0009] Determine the optimization index of each cabinet to be selected based on the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected;

[0010] An evaluation matrix is ​​constructed according to the optimization index of each candidate cabinet, and weight coefficients corresponding to the optimization indexes of different attributes are calculated according to the evaluation matrix;

[0011] The target rack is determined based on the optimization index of each candidate rack and the weight coefficients corresponding to the optimization indexes of different attributes.

[0012] According to an achievable method in an embodiment of the present application, the phase resource information after being put on the shelf includes the phase power value of the cabinet after being put on the shelf and the three-phase power average value of the line where the cabinet is located after being put on the shelf. The optimization index of each cabinet to be selected is determined according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf, including:

[0013] According to the rated resource information, used resource information and required resource information of each cabinet to be selected, the resource imbalance optimization index of each cabinet to be selected is calculated;

[0014] According to the phase power value of each candidate cabinet after being put on the rack and the average three-phase power of the line where the cabinet is located after being put on the rack, the optimization index of the three-phase imbalance degree of each candidate cabinet after being put on the rack is calculated.

[0015] According to an achievable method in an embodiment of the present application, the rated resource information includes a cabinet rated power value and a cabinet rated U-bit value, the used resource information includes a cabinet used power value and a cabinet used U-bit value, and the required resource information includes a required power value and a required U-bit value. According to the rated resource information, the used resource information, and the required resource information of each cabinet to be selected, the resource imbalance optimization index of each cabinet to be selected is calculated, including:

[0016] According to the used power value, required power value and rated power value of each cabinet to be selected, the optimization index of power supply utilization rate of each cabinet to be selected after being put on the rack is calculated;

[0017] According to the used U-bit value, required U-bit value and rated U-bit value of each cabinet to be selected, the optimization index of the space utilization rate of each cabinet to be selected after being put on the shelf is calculated;

[0018] According to the optimization index of power supply utilization rate after being put on the rack and the optimization index of space utilization rate after being put on the rack of each candidate cabinet, the optimization index of resource imbalance degree of each candidate cabinet is calculated.

[0019] According to an achievable method in an embodiment of the present application, an evaluation matrix is ​​constructed according to the optimization index of each cabinet to be selected, and weight coefficients corresponding to the optimization indexes of different attributes are calculated according to the evaluation matrix, including:

[0020] An evaluation matrix is ​​constructed according to the optimization index of each candidate cabinet, and the evaluation matrix is ​​assimilated to obtain an assimilated matrix;

[0021] Normalize the assimilation matrix to obtain a normalized matrix;

[0022] According to the normalized matrix, the weight coefficients corresponding to the optimization indicators of different attributes are calculated.

[0023] According to an achievable method in an embodiment of the present application, weight coefficients corresponding to optimization indicators of different attributes are calculated based on a normalized matrix, including:

[0024] According to the normalized matrix, the characteristic weight values ​​of the optimization indicators of different attributes are calculated;

[0025] According to the feature weight value, the information entropy of the optimization index of different attributes is calculated;

[0026] According to the information entropy, the weight coefficients corresponding to the optimization indicators of different attributes are calculated.

[0027] According to an achievable method in an embodiment of the present application, a target rack is determined according to the optimization index of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes, including:

[0028] According to the normalized matrix, the optimal and worst targets of the optimization indicators of different attributes are determined;

[0029] According to the optimization index of each candidate cabinet, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes, the optimal closeness value of each candidate cabinet is calculated;

[0030] The candidate cabinet with the largest optimal proximity value is selected as the target rack cabinet.

[0031] According to an achievable method in an embodiment of the present application, the optimal closeness value of each cabinet to be selected is calculated according to the optimization index of each cabinet to be selected, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes, including:

[0032] According to the optimization index of each candidate cabinet, the optimal target of the optimization index of different attributes and the corresponding weight coefficient, the optimal proximity value of each candidate cabinet is calculated;

[0033] According to the optimization index of each candidate cabinet, the worst target of the optimization index of different attributes and the corresponding weight coefficient, the worst proximity value of each candidate cabinet is calculated;

[0034] According to the optimal proximity value and the worst proximity value of each candidate cabinet, the optimal proximity value of each candidate cabinet is calculated.

[0035] In a second aspect, a cabinet mounting device is provided, the device comprising:

[0036] A first acquisition module is used to acquire rated resource information and used resource information of each available cabinet, and determine a cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet;

[0037] The second acquisition module is used to obtain the required resource information of each cabinet to be selected and the phase resource information after being put on the shelf;

[0038] The first calculation module is used to determine the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected;

[0039] A second calculation module is used to construct an evaluation matrix according to the optimization index of each cabinet to be selected, and calculate the weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix;

[0040] The rack cabinet determination module is used to determine the target rack cabinet according to the optimization index of each candidate cabinet and the weight coefficient corresponding to the optimization index of different attributes.

[0041] In a third aspect, a computer device is provided, comprising:

[0042] at least one processor; and

[0043] a memory communicatively connected to at least one processor; wherein,

[0044] The memory stores computer instructions that can be executed by at least one processor, and the computer instructions are executed by at least one processor to enable the at least one processor to execute the method involved in the first aspect above.

[0045] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, characterized in that the computer instructions are used to enable a computer to execute the method involved in the above-mentioned first aspect.

[0046] According to the technical content provided by the embodiment of the present application, the rated resource information and used resource information of each available cabinet are obtained, and the cabinet to be selected is determined from the available cabinets according to the rated resource information and used resource information of each available cabinet; the required resource information and the phase resource information after being put on the shelf of each cabinet to be selected are obtained; the optimization index of each cabinet to be selected is determined according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected; an evaluation matrix is ​​constructed according to the optimization index of each cabinet to be selected, and the weight coefficient corresponding to the optimization index of different attributes is calculated according to the evaluation matrix; the target cabinet to be put on the shelf is determined according to the optimization index of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes. The above operation, by determining the optimization index and calculating the weight value of the optimization index to determine the target cabinet to be put on the shelf, is convenient for guiding the staff to perform the shelf operation on the network equipment to be put on the shelf based on the determined target cabinet to be put on the shelf, thereby achieving the effect of improving the concentration rate of the equipment shelf position, the cabinet power supply resource rate and the power supply resource utilization rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A diagram of an application environment of a cabinet mounting method in an embodiment;

[0048] Figure 2 A schematic diagram of a process of mounting a cabinet on a rack in one embodiment;

[0049] Figure 3 A schematic diagram of a preferred process of a cabinet mounting method in one embodiment;

[0050] Figure 4 A structural block diagram of a cabinet mounting device in an embodiment;

[0051] Figure 5 FIG. 4 is a schematic structural diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The present application provides a cabinet mounting method, which can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The server 104 obtains the rated resource information and used resource information of each available cabinet, and determines the cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet; obtains the required resource information and the phase resource information of each cabinet to be selected after being put on the shelf; determines the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information of each cabinet to be selected after being put on the shelf; constructs an evaluation matrix according to the optimization index of each cabinet to be selected, and calculates the weight coefficient corresponding to the optimization index of different attributes according to the evaluation matrix; determines the target cabinet to be put on the shelf according to the optimization index of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes. Then, the target cabinet to be put on the shelf information is pushed to the terminal 102 for display on the terminal 102, so as to guide the staff to perform the operation of putting the network equipment to be put on the shelf according to the target cabinet information. The terminal 102 may be, but is not limited to, various personal computers, laptop computers, smart phones, and tablet computers, and the server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0054] In one embodiment, Figure 2 As shown, a cabinet mounting method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0055] Step S201: obtaining rated resource information and used resource information of each available cabinet, and determining a cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet.

[0056] The rated resource information includes, but is not limited to, the rated power value of the cabinet, the cooling capacity value of the cabinet, the load-bearing capacity value of the cabinet, the number and specification value of the cabinet power sockets, the rated U-bit value of the cabinet, and the continuous U-bit space value, etc. The used resource information includes, but is not limited to, the used power value of the cabinet, the current cooling value of the cabinet, the current load-bearing value of the cabinet, the number of power sockets used in the cabinet, the U-bit value of the cabinet, and the used continuous U-bit space value, etc.

[0057] Specifically, a cabinet to be selected is determined from the available cabinets according to the rated resource information and used resource information of each available cabinet. Here, the selection of the cabinet to be selected is determined by the mandatory parameters that the cabinet must meet. After obtaining the rated resource information and used resource information of each available cabinet, the rated resource information and the used resource information of each available cabinet are subjected to a difference operation to obtain the remaining resource information of each available cabinet. For example, the cabinet rated power value of the i-th available cabinet is subjected to a difference operation with the used power value of the corresponding cabinet to obtain the remaining available power value of the available cabinet, and so on to obtain the remaining resource information of each available cabinet. When the remaining resource information of the available cabinets meets the requirements of the network equipment to be put on the shelf, the available cabinet is listed as a cabinet to be selected. It should be noted that it is not recommended to determine as a cabinet to be selected an available cabinet that has generated local hot spots or whose cabinet temperature is higher than the operating requirements of the network equipment to be put on the shelf in consideration of the cooling effect.

[0058] Step S203: Obtain the required resource information of each cabinet to be selected and the corresponding resource information after being put on the shelf.

[0059] Among them, the required resource information includes but is not limited to the required power value and the required U-bit value; the phase resource information after being put on the shelf represents the power supply, voltage and power information of the phase line where the cabinet is located after the network equipment to be put on the shelf is located, including but not limited to the phase power value of the cabinet after being put on the shelf and the three-phase power average value of the line where the cabinet is located after being put on the shelf.

[0060] Specifically, during the design process of the AC power supply system of the data room, the cabinets will be connected to the ABC three-phase power as evenly as possible according to the rated capacity value of the cabinets. The ABC three-phase power is used to distinguish the power phase sequence, and the phase sequence is generally distinguished by color in the power. It should be emphasized that the reason for obtaining the phase resource information of each cabinet to be selected after being put on the shelf is that the power of the network equipment running after the ABC three-phase is put on the shelf affects the load capacity of the three-phase UPS (uninterruptible power supply), which in turn affects the overall power supply capacity of the cabinet to be selected. Among them, UPS three-phase refers to an uninterruptible power supply with three-phase AC mains input. The so-called three-phase means that the voltage between phases is the line voltage, which is 380V; the voltage between the phase and the neutral point is called the phase voltage, which is 220V, and is mainly used for uninterruptible power supply.

[0061] Step S205: determining the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected.

[0062] The optimization index refers to a non-mandatory index that can be further optimized, and the optimization index includes an optimization index attribute and an optimization index value.

[0063] Here, the equipment will involve multiple different indicators in the process of being put on the shelf. Generally, these indicators can be divided into two categories. The first category is the mandatory indicators that must be met. The available resource information of the cabinet must meet the needs of the network equipment to be put on the shelf. These indicators can be used to determine the cabinets to be selected; the second category is the indicators that can be optimized. On the basis of the available resources of the cabinet, the optimization indicators of each cabinet to be selected are determined by calculating and selecting some indicators, and then the relatively better cabinet can be determined based on the optimization indicators to achieve the optimization of the use of the overall power system resources and operational safety.

[0064] Specifically, by analyzing and calculating the rated resource information, used resource information, required resource information, and the phase resource information after being put on the shelf of each cabinet to be selected, the optimization index attributes and each optimization index value of each cabinet to be selected can be obtained. Here, since the cabinet to be selected is screened out from the available cabinets, the rated resource information and used resource information of the cabinet to be selected are the rated resource information and used resource information of the screened available cabinets.

[0065] Step S207: constructing an evaluation matrix according to the optimization index of each cabinet to be selected, and calculating weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix.

[0066] Specifically, an evaluation matrix is ​​constructed based on the optimization index of each candidate cabinet. Assume that n cabinets are determined from the available cabinets as candidate cabinets; each candidate cabinet involves m optimization indexes in the optimization process, and X ij The value of the optimization index of the jth attribute of the i-th candidate cabinet is represented, that is, i = 1, 2, ..., n; j = 1, 2, ..., m, then the evaluation matrix formed by the optimization index of each candidate cabinet can be expressed as follows:

[0067]

[0068] Among them, X 11 represents the optimization index value of the first attribute of the first candidate cabinet, X 1m represents the optimization index value of the mth attribute of the first candidate cabinet; and so on, X n1 represents the optimization index value of the first attribute of the nth candidate cabinet, X nmRepresents the optimization index value of the mth attribute of the nth cabinet to be selected. It should be noted here that the optimization index attributes of each cabinet to be selected are the same, that is, the optimization index attributes of the first cabinet to be selected and the nth cabinet to be selected are the same, but the optimization index values ​​corresponding to the attributes of each cabinet to be selected are different. Therefore, the weight coefficients corresponding to the optimization indicators of different attributes can be calculated according to the evaluation matrix. Assuming that the optimization index attributes of the first cabinet to be selected include A, B, C and D, since the optimization index attributes of each cabinet to be selected are the same, the optimization index attributes of the nth cabinet to be selected also include A, B, C and D, and then the weight coefficients corresponding to the optimization indicators of different attributes can be calculated, that is, the weight coefficients corresponding to A, B, C and D respectively. At this time, you don’t need to pay attention to which cabinet to select.

[0069] Step S209: Determine the target rack to be put on the shelf according to the optimization index of each rack to be selected and the weight coefficients corresponding to the optimization indexes of different attributes.

[0070] Here, according to the optimization index of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes, that is, by analyzing and calculating the optimization index value of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes, the final target rack can be determined, and the target rack is the optimal rack. Further, after determining the target rack, the network equipment to be mounted can be controlled to be mounted to the target rack according to the information of the target rack. Furthermore, the target rack information can also be pushed to the terminal for display at the terminal, so as to facilitate the guidance of the staff to perform the racking operation on the network equipment to be mounted based on the target rack information.

[0071] It can be seen that the embodiment of the present application obtains the rated resource information and used resource information of each available cabinet, and determines the cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet; obtains the required resource information and the phase resource information after being put on the shelf of each cabinet to be selected; determines the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected; constructs an evaluation matrix according to the optimization index of each cabinet to be selected, and calculates the weight coefficient corresponding to the optimization index of different attributes according to the evaluation matrix; determines the target cabinet to be put on the shelf according to the optimization index of each cabinet to be selected and the weight coefficient corresponding to the optimization index of different attributes. The above operation, by determining the optimization index and calculating the weight value of the optimization index to determine the target cabinet to be put on the shelf, is convenient for guiding the staff to perform the shelf operation on the network equipment to be put on the shelf based on the determined target cabinet to be put on the shelf, thereby achieving the effect of improving the concentration rate of equipment shelf position, the cabinet power supply resource rate and the power supply resource utilization rate.

[0072] First, the above step S205, namely "determining the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf" is described in detail in combination with the embodiment.

[0073] In one embodiment, the resource imbalance optimization index of each cabinet to be selected is calculated based on the rated resource information, used resource information and required resource information of each cabinet to be selected; the three-phase imbalance optimization index of each cabinet to be selected after being put on the shelf is calculated based on the phase power value of the cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf.

[0074] Among them, the resource imbalance optimization index is used to measure the differences in the use of power resources and space resources of the selected cabinets. The lower the resource imbalance optimization index value, the better the power and space matching. The three-phase imbalance optimization index after racking represents the imbalance of the UPS three-phase power resources of the network equipment after racking, which is used to measure the uneven distribution of the UPS three-phase power resources.

[0075] In a feasible manner, the resource imbalance optimization index value of each cabinet to be selected is calculated based on the rated resource information, used resource information and required resource information of each cabinet to be selected. Here, the resource imbalance optimization index value of each cabinet to be selected is calculated because if the number of U bits and the number of cabinet power supply sockets of some cabinets to be selected have been used by more than 80%, but the actual maximum operating power of the cabinet to be selected is less than 50%; or the used power of the cabinet to be selected has reached the rated value, but there are still many remaining U bits that are not used. No matter which of the above situations may cause waste of cabinet capacity and resources to a certain extent, therefore, resource waste can be avoided by optimizing the resource imbalance index.

[0076] In another achievable method, the three-phase imbalance optimization index of each cabinet after being put on the shelf is calculated according to the phase power value of each cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf. Here, after each cabinet is put on the shelf, the phase power value of the cabinet and the average three-phase power of the line where the cabinet is located can be directly obtained, and the absolute value of the difference between the phase power value of each cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf is calculated, and then the three-phase imbalance optimization index value of each cabinet after being put on the shelf can be obtained. It should be noted that the reason for selecting the three-phase imbalance optimization index after being put on the shelf is that the three-phase imbalance optimization index after being put on the shelf can be used to measure the uneven use of the three-phase power resources of the UPS. The higher the value of the three-phase imbalance optimization index after being put on the shelf, the lower the load capacity of the UPS; the lower the value of the three-phase imbalance optimization index after being put on the shelf, the better the matching of power resources and space. Moreover, when the UPS load capacity is low, frequent alarms will occur, thereby increasing the operation and maintenance risks and costs of power facilities.

[0077] Specifically, the specific expression of the optimization index value of the three-phase imbalance degree of the selected cabinet after being put on the rack is as follows:

[0078] The optimization index value of the three-phase imbalance after racking = | the power value of the phase where the cabinet is located after racking - the average power value of the three-phase power of the line where the cabinet is located after racking | * 100%

[0079] Through the above expression, the three-phase imbalance optimization index of each candidate cabinet after being put into the rack and the corresponding optimization index value can be obtained.

[0080] The above operation can calculate the resource imbalance optimization index of each candidate cabinet and the three-phase imbalance optimization index of each candidate cabinet after being put into the rack, thereby achieving the effect of avoiding resource waste and reducing the risk and cost of power facility operation and maintenance.

[0081] In one embodiment, based on the rated resource information, used resource information and required resource information of each cabinet to be selected, the resource imbalance optimization index of each cabinet to be selected is calculated, including: based on the cabinet used power value, required power value and cabinet rated power value of each cabinet to be selected, the power supply utilization optimization index of each cabinet to be selected after being put on the shelf is calculated; based on the cabinet used U-bit value, required U-bit value and cabinet rated U-bit value of each cabinet to be selected, the space utilization optimization index of each cabinet to be selected after being put on the shelf is calculated; based on the power supply utilization optimization index and the space utilization optimization index of each cabinet to be selected after being put on the shelf.

[0082] In one achievable manner, based on the used power value, required power value and rated power value of each cabinet to be selected, the optimized index of power supply utilization rate after racking of each cabinet to be selected is calculated, and the optimized index of power supply utilization rate after racking can be used to measure the power supply utilization rate of the cabinet to be selected after racking. The higher the power supply utilization rate after racking, the more fully the cabinet is used. Based on the used U-bit value, required U-bit value and rated U-bit value of each cabinet to be selected, the optimized index of space utilization rate after racking of each cabinet to be selected is calculated, and the optimized index of space utilization rate after racking can be used to measure the space utilization rate of the cabinet to be selected after racking. The higher the space utilization rate after racking, the more concentrated the network equipment is deployed. Here, the reason why we need to calculate the optimized index value of power supply utilization after being put on the shelf and the optimized index value of space utilization after being put on the shelf is that most network equipment is currently distributed in multiple different cabinets when being put on the shelf, resulting in a low cabinet shelf rate. However, in order to ensure the operation of the network equipment that has been put on the shelf, all cabinets and their upstream power supplies and refrigeration equipment at various locations in the computer room must ensure normal operation, which in turn leads to large equipment losses and increases the daily maintenance costs of operation and maintenance personnel.

[0083] Specifically, the specific expressions of the optimized index value of the power supply utilization rate and the optimized index value of the space utilization rate of the selected cabinet after being put on the rack are as follows:

[0084] Power utilization value after racking = (cabinet power used + required power) / cabinet rated power * 100%

[0085] Space utilization value after racking = (U-slot value used by the cabinet + U-slot value required) / Rated U-slot value of the cabinet * 100%

[0086] Through the above expressions, the power utilization optimization index of each candidate cabinet after being put on the shelf and the corresponding optimization index value and the space utilization optimization index of each candidate cabinet after being put on the shelf and the corresponding optimization index value can be obtained.

[0087] In another achievable manner, the resource imbalance optimization index of each cabinet to be selected is calculated based on the power utilization optimization index after being put on the shelf and the space utilization optimization index after being put on the shelf of each cabinet to be selected. Here, after obtaining the power utilization optimization index after being put on the shelf and the space utilization optimization index after being put on the shelf, the resource imbalance optimization index value of the cabinet to be selected can be obtained based on the absolute value of the difference between the power utilization optimization index value after being put on the shelf of the cabinet to be selected and the corresponding space utilization optimization index value after being put on the shelf.

[0088] Specifically, the specific expression of the resource imbalance optimization index value of the cabinet to be selected can be expressed as follows:

[0089] Resource imbalance optimization index value = |Power supply utilization optimization index value after putting on the shelf - Space utilization optimization index value after putting on the shelf |

[0090] Through the above expression, the resource imbalance optimization index of each cabinet to be selected and the corresponding optimization index value can be obtained.

[0091] The above operation can calculate the optimized index value of power supply utilization rate after racking, the optimized index value of space utilization rate after racking and the optimized index of resource imbalance of each candidate cabinet, thereby achieving the effect of improving the rack location concentration rate and avoiding waste of power resources.

[0092] Next, the above step S207, ie, "constructing an evaluation matrix according to the optimization index of each cabinet to be selected, and calculating weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix" is described in detail in conjunction with the embodiment.

[0093] In one embodiment, an evaluation matrix is ​​constructed according to the optimization index of each cabinet to be selected, and the evaluation matrix is ​​assimilated to obtain an assimilation matrix; the assimilation matrix is ​​normalized to obtain a normalized matrix; and the weight coefficients corresponding to the optimization indexes of different attributes are calculated according to the normalized matrix.

[0094] Here, from the above, we can see that the evaluation matrix can be specifically expressed as follows:

[0095]

[0096] The optimization index attributes of each cabinet to be selected are respectively the power supply utilization optimization index after being put on the rack, the space utilization optimization index after being put on the rack, the resource imbalance optimization index and the three-phase imbalance optimization index after being put on the rack, that is, m=4.

[0097] The evaluation matrix is ​​assimilated to obtain the assimilation matrix. Since the higher the optimization index value of the power utilization rate after being put on the shelf and the optimization index value of the space utilization rate after being put on the shelf are, the better the index is, therefore, the attribute optimization index of the power utilization rate after being put on the shelf and the attribute optimization index of the space utilization rate after being put on the shelf are both extremely large indicators. The specific optimization index value remains unchanged during assimilation. Assume that, using y ij represents the assimilated value of the jth optimization index of the i-th candidate cabinet, that is, y ij =X ij The lower the resource imbalance optimization index value and the three-phase imbalance optimization index value after listing, the better the index is. Therefore, the resource imbalance attribute optimization index and the three-phase imbalance attribute optimization index after listing are both very small indicators. When assimilated, the specific optimization index value is taken inversely, that is,

[0098]

[0099] Therefore, after assimilation of the evaluation matrix, the assimilation matrix can be obtained as follows:

[0100]

[0101] Among them, y 11 represents the assimilated value of the optimization index of the first attribute of the first candidate cabinet, y 1m represents the optimized index assimilation value of the mth attribute of the first candidate cabinet; and so on, y n1 represents the optimized index assimilation value of the first attribute of the nth candidate cabinet, y nm represents the optimized index assimilation value of the mth attribute of the nth candidate cabinet, and in this embodiment, y 1m That is equal to y 14 ;y nm That is equal to y n4 .

[0102] The assimilation matrix is ​​normalized to obtain a normalized matrix. Here, in order to eliminate the influence of the differences in optimization indicators of different attributes, the assimilation matrix is ​​normalized. The specific normalization expression can be expressed as follows:

[0103]

[0104] Among them, z ij represents the normalized value of the optimization index of the jth attribute of the i-th cabinet to be selected, and n represents the number of cabinets to be selected. Therefore, by normalizing the assimilation matrix, the normalized matrix obtained can be specifically expressed as follows:

[0105]

[0106] Among them, z 11 represents the normalized value of the optimization index of the first attribute of the first candidate cabinet; 1m represents the normalized value of the optimization index of the mth attribute of the first candidate cabinet; and so on, z n1 represents the normalized value of the optimization index of the first attribute of the nth candidate cabinet; nm Indicates the normalized value of the optimization index of the mth attribute of the nth candidate cabinet.

[0107] According to the normalized matrix, the weight coefficients corresponding to the optimization indicators of different attributes are calculated. Here, the normalized values ​​of the optimization indicators of different attributes of each cabinet to be selected can be obtained through the normalized matrix, and then the weight coefficients corresponding to the optimization indicators of different attributes can be calculated based on the normalized values ​​of the optimization indicators of different attributes of each cabinet to be selected. It should be emphasized that since the optimization indicators of each cabinet to be selected are the optimization indicators of the four attributes of the power supply utilization optimization indicator after being put on the shelf, the space utilization optimization indicator after being put on the shelf, the resource imbalance optimization indicator, and the three-phase imbalance optimization indicator after being put on the shelf, therefore, the weight coefficient of the power supply utilization optimization indicator after being put on the shelf, the weight coefficient of the space utilization optimization indicator after being put on the shelf, the weight coefficient of the resource imbalance optimization indicator, and the weight coefficient of the three-phase imbalance optimization indicator after being put on the shelf can be obtained, and the weight coefficients corresponding to the optimization indicators of different attributes of each cabinet to be selected are the same.

[0108] The above operation, by assimilation and normalization operations on the evaluation matrix in turn, obtains a normalized matrix, which makes it easier to calculate the weight coefficients corresponding to the optimization indicators of different attributes, and thus makes it easier to obtain accurate and objective weight coefficients.

[0109] In one embodiment, weight coefficients corresponding to optimization indicators of different attributes are calculated based on a normalized matrix, including: characteristic weight values ​​of optimization indicators of different attributes are calculated based on the normalized matrix; information entropy of optimization indicators of different attributes is calculated based on the characteristic weight values; weight coefficients corresponding to optimization indicators of different attributes are calculated based on the information entropy.

[0110] Here, according to the normalized matrix, the characteristic weight values ​​of the optimization indicators of different attributes can be calculated. Assume that the characteristic weight value of the jth optimization indicator of the i-th cabinet to be selected is P ij If P ij The specific expression can be expressed as follows:

[0111]

[0112] By analogy, characteristic weight values ​​of optimization indicators of different attributes of each candidate cabinet can be obtained.

[0113] According to the feature weight value, the information entropy of the optimization index of different attributes is calculated. Here, for each optimization index with the same attribute, the greater the difference in the normalized values ​​of the optimization indexes of the selected cabinets, the greater the difference in the corresponding optimization index values ​​of the attribute, and the greater the amount of information reflected by the optimization index of the attribute, and the smaller the information entropy. Assume that the information entropy of the jth optimization index is expressed by e j Represented as follows, the expression of the information entropy of the jth optimization index can be expressed as follows:

[0114]

[0115] It can be seen that the optimization index values ​​of the same attributes of each candidate cabinet are integrated here. Therefore, the information entropy of optimization indicators of different attributes can be obtained through the above expression. At this time, the candidate cabinets can be ignored, mainly to obtain the corresponding weight coefficients of optimization indicators of different attributes.

[0116] According to the information entropy, the weight coefficients corresponding to the optimization indicators of different attributes can be calculated. Here, according to the information entropy of each optimization indicator, the importance of the optimization indicators corresponding to different attributes can be obtained. Assume that the importance of the jth optimization indicator is expressed by d j Represented, the expression of the importance of the j-th optimization index can be expressed as follows:

[0117] d j =1-e j

[0118] From the above expression, we can know that d j The larger the value is, the smaller the information entropy of the optimization index of the attribute is, the more important it is in the evaluation of the optimization index of the attribute, and the larger the weight coefficient is. Therefore, assuming that the weight coefficient of the optimization index of the jth attribute is w j If , then the expression of the weight coefficient of the optimization index of the jth attribute can be expressed as follows:

[0119]

[0120] in, This is a restriction condition. In this embodiment, there are four optimization indicators for different attributes, so m=4, that is, the sum of the weight coefficients of the optimization indicators of these four attributes is 1.

[0121] Through the above calculations, the weight coefficients of the power supply utilization optimization index after being put on the shelf, the weight coefficients of the space utilization optimization index after being put on the shelf, the weight coefficients of the resource imbalance optimization index and the weight coefficients of the three-phase imbalance optimization index after being put on the shelf can be obtained respectively.

[0122] The above operations, based on the normalized matrix, calculate the characteristic weight values, information entropy and weight coefficients of the optimization indicators of different attributes in turn, which provides further guarantee for objectively and accurately evaluating the optimization indicators of each attribute, so as to achieve the effect of optimizing the cabinet power supply utilization optimization index, cabinet space utilization optimization index, cabinet resource imbalance optimization index and three-phase imbalance optimization index after being put on the shelf.

[0123] Finally, the above step S209, namely "determining the target rack to be put on the shelf according to the optimization index of each rack to be selected and the weight coefficients corresponding to the optimization indexes of different attributes" is described in detail in conjunction with the embodiment.

[0124] According to the normalized matrix, the optimal target and the worst target of the optimization indicators of different attributes are determined; according to the optimization indicators of each candidate cabinet, the optimal target and the worst target of the optimization indicators of different attributes and the corresponding weight coefficients, the optimal closeness value of each candidate cabinet is calculated; the candidate cabinet with the largest optimal closeness value is selected as the target cabinet.

[0125] Here, the optimal and worst targets of the optimization indicators of different attributes are determined according to the normalized matrix. The optimal target is the maximum value of each column in the normalized matrix Z, that is, the maximum value of the optimization indicators of different attributes in the n candidate cabinets can be expressed as Z. best The worst target is the minimum value of each column in the normalized matrix Z, that is, the minimum value of the optimization index of each different attribute in the n candidate cabinets can be expressed by Z worst Specifically, Z best and Z worst The specific expressions are as follows:

[0126] Z best =[max(z 11 ,z 21 , …, z n1 ),max(z 12 ,z 22 , …, z n2 ), ..., max(z 1m ,z 2m , …, z nm )]

[0127] Z worst =[min(z 11 ,z 21 , …, z n1 ),min(z 12 ,z 22 , …, z n2 ), ..., min(z 1m ,z 2m , …, z nm )]

[0128] According to the optimization index of each candidate cabinet, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes, the optimal closeness value of each candidate cabinet can be calculated and can be used as C i Indicates; select the candidate cabinet with the largest optimal proximity value as the target rack cabinet, that is, C i The larger the value is, the closer the candidate cabinet is to the optimal target. It will be determined as the target cabinet, and the information of the target cabinet will be pushed to the terminal for display, which means it is the recommended cabinet to guide the staff to install the network equipment to be installed in the target cabinet.

[0129] The above operation comprehensively considers the optimization index of each candidate cabinet, the optimal target of the optimization index of different attributes, the worst target and the corresponding weight coefficient to obtain the optimal closeness value of each candidate cabinet, and then determines the target cabinet to be put on the shelf, so as to achieve the effect of improving the power supply utilization rate, space utilization rate, resource imbalance and three-phase imbalance after the cabinet is put on the shelf.

[0130] In one embodiment, the optimal proximity value of each cabinet to be selected is calculated based on the optimization index of each cabinet to be selected, the optimal target, the worst target of the optimization index of different attributes and the corresponding weight coefficient, including: the optimal proximity value of each cabinet to be selected is calculated based on the optimization index of each cabinet to be selected, the optimal target of the optimization index of different attributes and the corresponding weight coefficient; the worst proximity value of each cabinet to be selected is calculated based on the optimization index of each cabinet to be selected, the worst target of the optimization index of different attributes and the corresponding weight coefficient; the optimal proximity value of each cabinet to be selected is calculated based on the optimal proximity value and the worst proximity value of each cabinet to be selected.

[0131] The best proximity value indicates how close the current candidate cabinet is to the best target; the worst proximity value indicates how close the current candidate cabinet is to the worst target.

[0132] Here, according to the optimization index of each candidate cabinet, the optimal target of the optimization index of different attributes and the corresponding weight coefficient, the optimal proximity value of each candidate cabinet is calculated. Assume that the optimal proximity value of the i-th candidate cabinet is expressed by D i,best If D i,best The expression can be expressed as follows:

[0133]

[0134] Among them, Z j,best Represents the optimal target of the optimization indicator for the jth attribute.

[0135] According to the optimization index of each candidate cabinet, the worst target of the optimization index of different attributes and the corresponding weight coefficient, the worst proximity value of each candidate cabinet is calculated. Assume that the worst proximity value of the i-th candidate cabinet is represented by D i,worst If D i,worst The expression can be expressed as follows:

[0136]

[0137] Among them, Z j,worst represents the worst objective of the jth optimization indicator.

[0138] According to the optimal proximity value and the worst proximity value of each candidate cabinet, the optimal proximity value of each candidate cabinet is calculated. From the above, it can be seen that the optimal proximity value of the i-th candidate cabinet can be expressed as C i If C i The expression can be expressed as follows:

[0139]

[0140] Through the above expression, the optimal proximity value of each candidate cabinet can be obtained, and then the candidate cabinet with the largest optimal proximity value is selected as the target rack cabinet.

[0141] The above operation determines the target rack based on the optimal proximity value finally obtained, so that the target rack takes into account the optimization indicators of different attributes of each candidate cabinet and the corresponding weight coefficients. Since the optimization indicators of different attributes and the corresponding weight coefficients are obtained through objective calculation, it is possible to achieve the effect of improving the power supply utilization rate, space utilization rate, resource imbalance and three-phase imbalance of the cabinet after racking.

[0142] In combination with the implementation method in the above embodiment, Figure 3 An example of a preferred method flow provided in the embodiment of the present application is described. Figure 3 As shown, the method may include the following steps:

[0143] Step S301, obtain the rated resource information and used resource information of each available cabinet, and determine the cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet; wherein the rated resource information includes the rated power value of the cabinet and the rated U-bit value of the cabinet; the used resource information includes the used power value of the cabinet and the used U-bit value of the cabinet.

[0144] Step S302, obtain the required resource information of each cabinet to be selected and the phase resource information after being put on the shelf; wherein the required resource information includes the required power value and the required U-bit value; the phase resource information after being put on the shelf includes the phase power value of the cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf.

[0145] Step S303 , calculating the post-racking power supply utilization optimization index of each cabinet to be selected according to the cabinet used power value, the required power value and the cabinet rated power value of each cabinet to be selected.

[0146] Step S304 , calculating the post-shelf space utilization optimization index of each candidate cabinet according to the cabinet used U-bit value, the required U-bit value and the cabinet rated U-bit value of each candidate cabinet.

[0147] Step S305 , calculating the resource imbalance optimization index of each candidate cabinet according to the power supply utilization optimization index and the space utilization optimization index of each candidate cabinet after being put on the shelf.

[0148] Step S306, calculating the optimization index of the three-phase imbalance degree of each candidate cabinet after being put on the rack according to the phase power value of each candidate cabinet after being put on the rack and the average three-phase power of the line where the cabinet is located after being put on the rack.

[0149] Step S307: construct an evaluation matrix according to the optimization index of each candidate cabinet, and perform assimilation processing on the evaluation matrix to obtain an assimilated matrix.

[0150] Step S308: normalize the assimilation matrix to obtain a normalized matrix.

[0151] Step S309: Calculate the characteristic weight values ​​of the optimization indicators of different attributes according to the normalized matrix.

[0152] Step S310, calculating the information entropy of the optimization indexes of different attributes according to the feature weight values.

[0153] Step S311, calculating the weight coefficients corresponding to the optimization indicators of different attributes according to the information entropy.

[0154] Step S312, determining the best target and the worst target of the optimization indicators of different attributes according to the normalized matrix.

[0155] Step S313 , calculating the optimal proximity value of each cabinet to be selected according to the optimization index of each cabinet to be selected, the optimal target of the optimization index of different attributes and the corresponding weight coefficient.

[0156] Step S314, calculating the worst proximity value of each candidate cabinet according to the optimization index of each candidate cabinet, the worst target of the optimization index of different attributes and the corresponding weight coefficient.

[0157] Step S315 , calculating the optimal proximity value of each candidate cabinet according to the optimal proximity value and the worst proximity value of each candidate cabinet.

[0158] Step S316, selecting the candidate cabinet with the largest optimal proximity value as the target rack.

[0159] It should be understood that although Figure 2-Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in the application, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-Figure 3At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0160] The above method embodiments can be applied to a variety of application scenarios, for example, including but not limited to application scenarios of controlling the network devices to be put on the shelves.

[0161] Figure 4 A schematic diagram of a cabinet mounting device provided in an embodiment of the present application, which can be arranged on Figure 1 The server in the application environment shown is used to execute Figure 2-Figure 3 The method flow shown in Figure 4 As shown, the device may include: a first acquisition module 401, a second acquisition module 403, a first calculation module 405, a second calculation module 407, and a rack cabinet determination module 409. The main functions of each component module are as follows:

[0162] The first acquisition module 401 is used to acquire the rated resource information and the used resource information of each available cabinet, and determine the cabinet to be selected from the available cabinets according to the rated resource information and the used resource information of each available cabinet;

[0163] The second acquisition module 403 is used to obtain the required resource information of each cabinet to be selected and the phase resource information after being put on the shelf;

[0164] The first calculation module 405 is used to determine the optimization index of each cabinet to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each cabinet to be selected;

[0165] The second calculation module 407 is used to construct an evaluation matrix according to the optimization index of each cabinet to be selected, and calculate the weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix;

[0166] The rack-mounted cabinet determining module 409 is used to determine a target rack-mounted cabinet according to the optimization index of each candidate cabinet and the weight coefficients corresponding to the optimization indexes of different attributes.

[0167] In one embodiment, the phase resource information after the cabinet is put on the shelf includes the phase power value of the cabinet after the cabinet is put on the shelf and the average three-phase power of the line where the cabinet is put on the shelf. The first calculation module 405 is also used for:

[0168] According to the rated resource information, used resource information and required resource information of each cabinet to be selected, the resource imbalance optimization index of each cabinet to be selected is calculated;

[0169] According to the phase power value of each candidate cabinet after being put on the rack and the average three-phase power of the line where the cabinet is located after being put on the rack, the optimization index of the three-phase imbalance degree of each candidate cabinet after being put on the rack is calculated.

[0170] In one embodiment, the rated resource information includes the cabinet rated power value and the cabinet rated U-bit value, the used resource information includes the cabinet used power value and the cabinet used U-bit value, the required resource information includes the required power value and the required U-bit value, and the first calculation module 405 is further used to:

[0171] According to the used power value, required power value and rated power value of each cabinet to be selected, the optimization index of power supply utilization rate of each cabinet to be selected after being put on the rack is calculated;

[0172] According to the used U-bit value, required U-bit value and rated U-bit value of each cabinet to be selected, the optimization index of the space utilization rate of each cabinet to be selected after being put on the shelf is calculated;

[0173] According to the optimization index of power supply utilization rate after being put on the rack and the optimization index of space utilization rate after being put on the rack of each candidate cabinet, the optimization index of resource imbalance degree of each candidate cabinet is calculated.

[0174] In one embodiment, the second calculation module 407 is further configured to:

[0175] An evaluation matrix is ​​constructed according to the optimization index of each candidate cabinet, and the evaluation matrix is ​​assimilated to obtain an assimilated matrix;

[0176] Normalize the assimilation matrix to obtain a normalized matrix;

[0177] According to the normalized matrix, the weight coefficients corresponding to the optimization indicators of different attributes are calculated.

[0178] In one embodiment, the second calculation module 407 is further configured to:

[0179] According to the normalized matrix, the characteristic weight values ​​of the optimization indicators of different attributes are calculated;

[0180] According to the feature weight value, the information entropy of the optimization index of different attributes is calculated;

[0181] According to the information entropy, the weight coefficients corresponding to the optimization indicators of different attributes are calculated.

[0182] In one embodiment, the rack cabinet determination module 409 is further used to:

[0183] According to the normalized matrix, the optimal and worst targets of the optimization indicators of different attributes are determined;

[0184] According to the optimization index of each candidate cabinet, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes, the optimal closeness value of each candidate cabinet is calculated;

[0185] The candidate cabinet with the largest optimal proximity value is selected as the target rack cabinet.

[0186] In one embodiment, the rack cabinet determination module 409 is further used to:

[0187] According to the optimization index of each candidate cabinet, the optimal target of the optimization index of different attributes and the corresponding weight coefficient, the optimal proximity value of each candidate cabinet is calculated;

[0188] According to the optimization index of each candidate cabinet, the worst target of the optimization index of different attributes and the corresponding weight coefficient, the worst proximity value of each candidate cabinet is calculated;

[0189] According to the optimal proximity value and the worst proximity value of each candidate cabinet, the optimal proximity value of each candidate cabinet is calculated.

[0190] The same or similar parts between the above embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0191] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described in this article within the scope permitted by applicable laws and regulations, provided that the applicable laws and regulations of the country are met (for example, the user's explicit consent, effective notification to the user, and the user's explicit authorization, etc.).

[0192] According to an embodiment of the present application, the present application also provides a computer device and a computer-readable storage medium.

[0193] like Figure 5 , is a block diagram of a computer device according to an embodiment of the present application. The computer device is intended to represent various forms of digital computers or mobile devices. The digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smart phone, a wearable device, etc.

[0194] like Figure 5As shown, the device 500 includes a computing unit 501, a ROM 502, a RAM 503, a bus 504, and an input / output (I / O) interface 505, and the computing unit 501, ROM 502 and RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0195] The computing unit 501 can perform various processes in the method embodiment of the present application according to the computer instructions stored in the read-only memory (ROM) 502 or the computer instructions loaded from the storage unit 508 to the random access memory (RAM) 503. The computing unit 501 can be various general and / or special processing components with processing and computing capabilities. The computing unit 501 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. In some embodiments, the method provided in the embodiment of the present application can be implemented as a computer software program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 508.

[0196] RAM 503 may also store various programs and data required for the operation of device 500. Part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509.

[0197] The input unit 506, output unit 507, storage unit 508 and communication unit 509 in the device 500 can be connected to the I / O interface 505. The input unit 506 can be, for example, a keyboard, a mouse, a touch screen, a microphone, etc. The output unit 507 can be, for example, a display, a speaker, an indicator light, etc. The device 500 can exchange information, data, etc. with other devices through the communication unit 509.

[0198] It should be noted that the device may also include other components necessary for normal operation, or may only include components necessary for implementing the solution of the present application, rather than all the components shown in the figure.

[0199] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0200] The computer instructions for implementing the method of the present application can be written in any combination of one or more programming languages. These computer instructions can be provided to the computing unit 501, so that when the computer instructions are executed by the computing unit 501 such as a processor, the steps involved in the method embodiment of the present application are executed.

[0201] The computer-readable storage medium provided in the present application may be a tangible medium that may contain or store computer instructions for executing the steps involved in the method embodiments of the present application. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, and other forms of storage media.

[0202] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A cabinet mounting method, characterized in that: The method comprises: Acquire rated resource information and used resource information of each available cabinet, and determine a cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet; Obtaining the required resource information of each of the cabinets to be selected and the resource information of the cabinet after being put on the shelf; Determine the optimization index of each of the cabinets to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each of the cabinets to be selected; Constructing an evaluation matrix according to the optimization index of each of the cabinets to be selected, and calculating weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix; The target rack is determined according to the optimization index of each of the to-be-selected racks and the weight coefficients corresponding to the optimization indexes of different attributes.

2. The method according to claim 1, characterized in that The phase resource information after being put on the shelf includes the phase power value of the cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf. The optimization index of each cabinet to be selected is determined according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf, including: Calculate the resource imbalance optimization index of each of the cabinets to be selected according to the rated resource information, used resource information and required resource information of each of the cabinets to be selected; According to the phase power value of each cabinet after being put on the shelf and the average three-phase power of the line where the cabinet is located after being put on the shelf, the optimization index of the three-phase imbalance degree of each cabinet after being put on the shelf is calculated.

3. The method according to claim 2, characterized in that The rated resource information includes the rated power value of the cabinet and the rated U-bit value of the cabinet, the used resource information includes the used power value of the cabinet and the used U-bit value of the cabinet, and the required resource information includes the required power value and the required U-bit value. The resource imbalance optimization index of each of the cabinets to be selected is calculated based on the rated resource information, used resource information and required resource information of each of the cabinets to be selected, including: Calculate the power utilization optimization index of each of the cabinets to be selected after being put on the rack according to the cabinet used power value, the required power value and the cabinet rated power value of each of the cabinets to be selected; Calculate the post-shelf space utilization optimization index of each of the candidate cabinets according to the cabinet used U-bit value, the required U-bit value and the cabinet rated U-bit value of each of the candidate cabinets; According to the optimization index of power supply utilization rate after being put on the shelf and the optimization index of space utilization rate after being put on the shelf of each of the cabinets to be selected, the optimization index of resource imbalance degree of each of the cabinets to be selected is calculated.

4. The method according to any one of claims 1 to 3, characterized in that: The step of constructing an evaluation matrix according to the optimization index of each of the cabinets to be selected, and calculating weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix, includes: Constructing an evaluation matrix according to the optimization index of each of the candidate cabinets, and performing assimilation processing on the evaluation matrix to obtain an assimilation matrix; Normalizing the assimilation matrix to obtain a normalized matrix; According to the normalized matrix, weight coefficients corresponding to the optimization indicators of different attributes are calculated.

5. The method according to claim 4, characterized in that The step of calculating weight coefficients corresponding to the optimization indicators of different attributes according to the normalized matrix includes: According to the normalized matrix, characteristic weight values ​​of the optimization indicators of different attributes are calculated; According to the feature weight values, the information entropy of the optimization index of different attributes is calculated; According to the information entropy, weight coefficients corresponding to the optimization indicators of different attributes are calculated.

6. The method according to claim 4, characterized in that The step of determining a target rack-mounted cabinet according to the optimization index of each of the cabinets to be selected and the weight coefficients corresponding to the optimization indexes of different attributes includes: Determining the optimal target and the worst target of the optimization index of different attributes according to the normalized matrix; Calculate the optimal closeness value of each of the cabinets to be selected according to the optimization index of each cabinet to be selected, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes; The candidate cabinet with the largest optimal proximity value is selected as the target rack.

7. The method according to claim 6, characterized in that The step of calculating the optimal proximity value of each of the cabinets to be selected according to the optimization index of each of the cabinets to be selected, the optimal target, the worst target and the corresponding weight coefficient of the optimization index of different attributes includes: Calculate the optimal proximity value of each of the cabinets to be selected according to the optimization index of each cabinet to be selected, the optimal target of the optimization index of different attributes and the corresponding weight coefficient; The worst proximity value of each of the cabinets to be selected is calculated according to the optimization index of each of the cabinets to be selected, the worst target of the optimization index of different attributes and the corresponding weight coefficient; The optimal proximity value of each of the cabinets to be selected is calculated according to the optimal proximity value and the worst proximity value of each of the cabinets to be selected.

8. A cabinet mounting device, characterized in that: The device comprises: A first acquisition module, configured to acquire rated resource information and used resource information of each available cabinet, and determine a cabinet to be selected from the available cabinets according to the rated resource information and used resource information of each available cabinet; The second acquisition module is used to obtain the required resource information of each of the cabinets to be selected and the phase resource information after being put on the shelf; A first calculation module is used to determine the optimization index of each of the cabinets to be selected according to the rated resource information, used resource information, required resource information and the phase resource information after being put on the shelf of each of the cabinets to be selected; A second calculation module is used to construct an evaluation matrix according to the optimization index of each of the cabinets to be selected, and calculate the weight coefficients corresponding to the optimization indexes of different attributes according to the evaluation matrix; The rack cabinet determination module is used to determine the target rack cabinet according to the optimization index of each of the candidate cabinets and the weight coefficients corresponding to the optimization indexes of different attributes.

9. A computer device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores computer instructions that can be executed by the at least one processor, and the computer instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: The computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Data center equipment putaway method and system based on dynamic load balancing

    CN121638798A