Data center rack selling price determination method and device and computer equipment
By obtaining the demand information of the target object and data center resource parameters, and using the preset model to determine the initial selling price of the data center rack and adjust it, the problem of low accuracy of power load prediction in the existing technology is solved, and a higher Price prediction accuracy.
Patent Information
- Application Number
- CN202411053851.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-15
AI Technical Summary
The existing power load prediction technology cannot accurately predict the power load of new users of data centers, resulting in low accuracy of power forecasting and ineffective analysis of data centers' own resource data.
By obtaining the demand information of the target object, determining its multiple characteristic parameters, and using the preset model to determine the load and initial selling price of the target rack based on these parameters, adjusting the selling price based on the resource parameters of the data center, and using the price adjustment coefficient Adjust the initial selling price to obtain the target selling price.
The accuracy of data center rack price prediction is improved, and the problem of low price accuracy caused by the prediction model in the prior art can only predict the user-side electricity load.
Smart Images

Figure CN118967243A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to a method, device and computer equipment for determining the selling price of a data center rack. Background Art
[0002] At present, the demand for IDC (Internet Data Center) business racks is developing rapidly, but with the influx of a large amount of capital, there is an oversupply of data center racks. Under the background of the homogenization of resource allocation and service levels of various IDC service providers, the cost of providing IDC services has been determined through the prediction of power load. However, the existing power load prediction technology mainly stands from the perspective of power supply and operators, and predicts the power load level in the future stage based on historical time series energy consumption data. However, this technology cannot be applied to the load prediction of new users in the data center. At the same time, the model used can only complete the reasonable cost estimation for a single project, and does not combine the resource data that the data center itself can provide for analysis, resulting in a low accuracy rate of power load prediction, which in turn leads to a low accuracy of the predicted final selling price. Summary of the invention
[0003] The embodiments of the present application provide a method, apparatus and computer equipment for determining a data center rack selling price, so as to at least solve the technical problem that the prediction model in the related art can only predict the power load on the user side, resulting in low accuracy of the predicted selling price.
[0004] According to one aspect of an embodiment of the present application, a method for determining a selling price of a data center rack is provided, comprising: obtaining demand information of a target object, determining a plurality of first characteristic parameters of the target object based on the demand information, and using a preset model to determine a required load of a target rack corresponding to the demand information based on the first characteristic parameters; determining an initial selling price of the target rack based on the required load of the target rack; obtaining a plurality of second characteristic parameters of the data center, and determining a selling price adjustment coefficient corresponding to the target rack based on the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize an indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide; and adjusting the initial selling price using the selling price adjustment coefficient to obtain a target selling price.
[0005] Optionally, determining multiple first characteristic parameters of the target object according to the demand information includes: extracting target information from the demand information, the target information including: the industry type of the target object, the equipment configuration information in the target rack, the business type and business scale required to be carried by the server in the target rack, and the traffic required to be opened for the equipment in the target rack; determining the first characteristic parameter according to the target information, the first characteristic parameter including: industry characteristics, a first quantitative indicator, a second quantitative indicator and a third quantitative indicator, the first quantitative indicator is used to represent the quantitative indicator of the equipment configuration in the target rack, the second quantitative indicator is used to represent the quantitative indicator of the business type and business scale required to be carried by the server in the target rack, and the third quantitative indicator is used to represent the quantitative indicator of the traffic required to be opened for the equipment in the target rack.
[0006] Optionally, a preset model is used to determine the required load of the target rack corresponding to the demand information based on the first characteristic parameter, including: using the preset model to extract features of the first characteristic parameter to obtain a feature vector, and normalizing the feature vector to obtain a target feature vector; processing the target feature vector in turn through multiple control gates in the preset model to obtain a final result, and the final result is used to represent the required load of the target rack, wherein the control gate is used to control the information flow and data update in the preset model.
[0007] Optionally, the target feature vector is processed in sequence through multiple control gates in the preset model to obtain a final result, including: using a reset gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain a first output value of the reset gate; using an input activation gate among the multiple control gates to multiply the first output value with the predicted value at the previous moment, and then combining it with the target feature vector, and then performing a logical operation to obtain a second output value of the input activation gate; using an update gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain a third output value of the update gate; using a final output gate among the multiple control gates to combine the second output, the third output value and the predicted value at the previous moment to obtain the final result.
[0008] Optionally, determining the initial selling price of the target rack based on the required load of the target rack includes: determining the electricity cost corresponding to the target rack based on the required load of the rack; obtaining a preset profit margin corresponding to the target rack and the income corresponding to the target rack; determining the initial selling price of the target rack based on the electricity cost, the preset profit margin corresponding to the target rack, and the income corresponding to the target rack.
[0009] Optionally, determining the selling price adjustment coefficient corresponding to the target rack according to the second characteristic parameter includes: obtaining the second characteristic parameter, the second characteristic parameter at least including: a first sub-parameter and a second sub-parameter, the first sub-parameter including: the load power required by the target object, the cooling capacity required by the target object and the business area required by the target object, and the second sub-parameter including: a preset total load power, a preset total cooling capacity and a preset total business area; determining a first proportion vector according to the first sub-parameter, and determining a second proportion vector according to the second sub-parameter, the first proportion vector being used to represent the proportion of various resources in the first sub-parameter, and the second proportion vector being used to represent the proportion of various resources in the second sub-parameter; when the demand for multiple resources in the first sub-parameter is lower than a preset threshold, obtaining the cosine similarity of the first proportion vector and the second proportion vector; determining the selling price adjustment coefficient according to the cosine similarity.
[0010] Optionally, the method also includes: in the case that there are resources in the first sub-parameter whose demand is higher than a preset threshold, obtaining a third sub-parameter, the third sub-parameter including at least: allocable load power, allocable cooling capacity and allocable business area; determining a third proportion vector based on the third sub-parameter, the third proportion vector being used to represent the proportion of various allocable resources in the third sub-parameter; determining the cosine similarity between the third proportion vector and the second proportion vector; and determining the selling price adjustment coefficient based on the cosine similarity.
[0011] According to another aspect of an embodiment of the present application, a device for determining a price of a rack in a data center is also provided, including: an acquisition module, used to acquire demand information of a target object, determine multiple first characteristic parameters of the target object according to the demand information, and use a preset model to determine the required load of the target rack corresponding to the demand information according to the first characteristic parameters; a first determination module, used to determine the initial selling price of the target rack according to the required load of the target rack; a second determination module, used to determine multiple second characteristic parameters of the data center according to the demand information, and determine the selling price adjustment coefficient corresponding to the target rack according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize the indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide; an adjustment module, used to adjust the initial selling price using the selling price adjustment coefficient to obtain a target selling price.
[0012] According to another aspect of the embodiment of the present application, a computer device is also provided, including: a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the above-mentioned data center rack price determination method.
[0013] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned data center rack price determination method by running the computer program.
[0014] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which, when executed by a processor, implement the above-mentioned method for determining the selling price of a data center rack.
[0015] In an embodiment of the present application, demand information of a target object is obtained, multiple first characteristic parameters of the target object are determined according to the demand information, and a preset model is used to determine the required load of a target rack corresponding to the demand information according to the first characteristic parameters; an initial selling price of the target rack is determined according to the required load of the target rack; second characteristic parameters of multiple data centers are obtained, and a selling price adjustment coefficient corresponding to the target rack is determined according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize an indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide; the initial selling price is adjusted using the selling price adjustment coefficient to obtain a target selling price, thereby achieving the technical effect of predicting the selling price of the data center rack according to a combination of the first characteristic parameter and the second characteristic parameter, thereby achieving the technical effect of improving the accuracy of selling price prediction, and further solving the technical problem in the related art that the prediction model can only predict the power load on the user side, resulting in low accuracy of the predicted selling price. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0017] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a method for determining a data center rack price according to an embodiment of the present application;
[0018] Figure 2 is a flow chart of a method for determining a data center rack price according to an embodiment of the present application;
[0019] Figure 3 It is a schematic diagram of a process of predicting the power load of a target rack according to a preset model in an embodiment of the present application;
[0020] Figure 4 It is a structural diagram of a data center rack price determination device according to an embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0023] The information collected in the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.
[0024] In order to solve the problems existing in the related art, the embodiment of the present application provides a method for determining the price of a data center rack. The method can be run on Figure 1 In the computer terminal shown, the computer terminal is explained below.
[0025] The data center rack price determination method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a method for determining the price of a data center rack is shown. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0026] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0027] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the data center rack price determination method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned data center rack price determination method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0028] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0029] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .
[0030] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.
[0031] In the above operating environment, an embodiment of the present application provides an embodiment of a method for determining the selling price of a data center rack. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0032] Figure 2 is a flow chart of a method for determining a data center rack price according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:
[0033] Step S202, acquiring demand information of a target object, determining a plurality of first characteristic parameters of the target object according to the demand information, and using a preset model to determine a required load of a target rack corresponding to the demand information according to the first characteristic parameters.
[0034] In the above step S202, the demand information of the target object at least includes: the business demand, flow demand and configuration information of the equipment in the rack of the target object.
[0035] Step S204: determining an initial selling price of the target rack according to the required load of the target rack.
[0036] In the above step S204, the power consumption can be determined according to the load required by the target rack, and then the electricity cost can be determined, and the initial selling price can be determined based on the electricity cost.
[0037] Step S206, obtaining a plurality of second characteristic parameters of the data center, and determining a price adjustment coefficient corresponding to the target rack according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize an indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide;
[0038] In the above step S206, the second characteristic parameter can be determined according to the power usage rate, cooling usage rate and area usage rate of the data center.
[0039] It should be noted that the cooling capacity of a data center refers to the refrigeration capacity used for cooling in the data center, the area of a data center refers to the area used by the data center to store racks, and the power consumption of a data center refers to the power consumption of the data center for racks.
[0040] Step S208: adjusting the initial selling price using the selling price adjustment coefficient to obtain a target selling price.
[0041] Through the above steps S202 to S208, the demand information of the target object is obtained, and multiple first characteristic parameters of the target object are determined according to the demand information, and the required load of the target rack corresponding to the demand information is determined according to the first characteristic parameters by using a preset model; the initial selling price of the target rack is determined according to the required load of the target rack; the second characteristic parameters of multiple data centers are obtained, and the selling price adjustment coefficient corresponding to the target rack is determined according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize the index corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the number of resources that the data center can provide; the initial selling price is adjusted by using the selling price adjustment coefficient to obtain the target selling price, and the selling price of the data center rack is predicted by combining the first characteristic parameter and the second characteristic parameter at the same time, thereby achieving the technical effect of improving the accuracy of the selling price prediction, and further solving the technical problem that the prediction model in the related technology can only predict the power load on the user side, resulting in low accuracy of the predicted selling price. The following is a detailed description.
[0042] In step S202 of the above-mentioned method for determining the selling price of a data center rack, multiple first characteristic parameters of the target object are determined based on the demand information, including: extracting target information from the demand information, the target information including: the industry type of the target object, the equipment configuration information in the target rack, the business type and business scale that the server in the target rack needs to carry, and the traffic that the equipment in the target rack needs to open; determining the first characteristic parameter based on the target information, the first characteristic parameter including: industry characteristics, a first quantitative indicator, a second quantitative indicator and a third quantitative indicator, the first quantitative indicator is used to represent the quantitative indicator of the equipment configuration in the target rack, the second quantitative indicator is used to represent the quantitative indicator of the business type and business scale that the server in the target rack needs to carry, and the third quantitative indicator is used to represent the quantitative indicator of the traffic that the equipment in the target rack needs to open.
[0043] It should be noted that for the industry type of the target object, for example, financial industry customers are restricted by their own audits and make more full use of the purchased load capacity; for the equipment configuration information in the target rack, for example, servers with different processor chips have lower energy consumption, storage devices have lower power consumption, etc.; for the business type and scale that the servers in the target rack need to carry, for example, racks that carry dynamic businesses such as data analysis consume more power than racks that carry static businesses such as data storage; for the traffic that needs to be opened for the equipment in the target rack, for example, the energy consumption of the two situations where the traffic is interactive input and output and the traffic is downloading data are not the same.
[0044] Specifically, the first characteristic parameter includes:
[0045] Industry characteristics, x fi :Feature, describing the user's industry type;
[0046] The first quantitative indicator, x ai :Allocation (configuration), a quantitative indicator describing the types of services carried by the server and the existing cabinet collocation and resource matching;
[0047] The second quantitative indicator, x si : Scale, a quantitative indicator that describes the user service type and carrying scale;
[0048] The third quantitative indicator, x bi :Bandwidth, a quantitative indicator that describes user bandwidth or line opening traffic.
[0049] In some embodiments of the present application, a preset model is used to determine the required load of the target rack corresponding to the demand information based on the first characteristic parameter, including: using the preset model to extract features of the first characteristic parameter to obtain a feature vector, and normalizing the feature vector to obtain a target feature vector; processing the target feature vector in turn through multiple control gates in the preset model to obtain a final result, and the final result is used to represent the required load of the target rack, wherein the control gate is used to control the information flow and data update in the preset model.
[0050] Specifically, the feature vector is as follows:
[0051] x i =[x fi ,x ai ,x si ,x bi ]
[0052] x i Normalization is performed to obtain the target feature vector. The normalization process is as follows: for each data item, calculate the ratio of the difference between each data item and the minimum value within the range of the data, normalize the range of each feature data item to the interval [0,1], and obtain the target feature vector.
[0053] The specific process of processing the target feature vector through multiple control gates in the preset model in sequence to obtain the final result includes: using a reset gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain the first output value of the reset gate; using an input activation gate among the multiple control gates to multiply the first output value with the predicted value at the previous moment, and then performing a logical operation to obtain the second output value of the input activation gate; using an update gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain the third output value of the update gate; using a final output gate among the multiple control gates to combine the second output, the third output value and the predicted value at the previous moment to obtain the final result.
[0054] like Figure 3 As shown, the preset model includes: a reset gate, an input activation gate, an update gate, and a final output gate.
[0055] Among them, the reset gate is used to convert the current target feature vector x t and the predicted value y at the previous momentt-1 , and combine them into a vector [x t ,y t-1 ], and then reset the gate weight vector W r Perform dot product operation and compare with the corresponding deviation term b t Add, and finally transform through sigmoid function to get the first output value r of reset gate t , the value is between [0,1].
[0056] Through multiple layers and multiple iterations of the neural network, the influence coefficient of the feature quantity and predicted power load at the previous moment on the power load prediction at the current moment is finally determined, so as to confirm the accurate input proportion of known data when predicting unknown power consumption. The influence of the information at the previous moment on the current moment is controlled so that the new information can affect the current state without interference.
[0057] The complete operation is as follows:
[0058] r t =σ(W r [x t ,y t-1 ]+b t )
[0059] Where σ represents the nonlinear activation function (sigmoid function).
[0060] The input activation gate is used to calculate the coefficient r based on the reset gate. t , and the predicted value y at the previous moment t-1 Multiply it again with the target feature vector x at the current moment t Combining them, we get the vector [x t ,r t ·y t-1 ], the deviation term b from the input activation gate a After addition, the weight vector W of this layer a Perform a dot product operation and then use the tanh function to convert it to get the second output value a t , the final value of this layer is between [-1,1], which increases the expressive power of the network.
[0061] Through multiple layers and multiple iterations of the neural network, according to the coefficients calculated by the reset gate and the predicted power load at the previous moment, after function conversion, the specific values of the part that needs to be updated in the calculation of the predicted value are combined with the next layer update gate u t Combined.
[0062] The complete operation is as follows:
[0063] a t =tanh(W a[x t ,r t ·y t-1 +b a ])
[0064] The update gate is used to update the current target feature vector x t and the predicted value y at the previous moment t-1 , and combine them into a vector [x t ,y t-1 ], and then with the weight vector W of this layer u Perform dot product operation with the bias term b of this layer u After addition, the third output value u is obtained by conversion through the sigmoid function t .
[0065] Through multiple layers and multiple iterations of the neural network, the power consumption that needs to be predicted is finally confirmed to be consistent with the proportion used for data update. The update gate transfers part of the state of the previous moment to the current moment, while allowing new information to enter. t Combined values.
[0066] The complete operation is as follows:
[0067] u t =σ(W u [x t ,y t-1 ]+b u )
[0068] The final output gate is used to update the update ratio u calculated by the update gate t , update the update value a calculated by the activation gate t , and the predicted value y at the previous moment t-1 By adding a certain proportion of old data to the new data that needs to be updated, the nonlinear activation function calculates the current prediction value y t .
[0069] It can be understood that the predicted value y at the current moment obtained when the preset model converges t For the final result.
[0070] In some embodiments of the present application, the initial selling price of the target rack is determined based on the required load of the target rack, including: determining the electricity cost corresponding to the target rack based on the required load of the rack; obtaining a preset profit margin corresponding to the target rack and the income corresponding to the target rack; and determining the initial selling price of the target rack based on the electricity cost, the preset profit margin corresponding to the target rack, and the income corresponding to the target rack.
[0071] In actual application scenarios, the final results of the preset model and the preset profit margin are used for analysis to obtain the initial selling price.
[0072] In some embodiments of the present application, determining the selling price adjustment coefficient corresponding to the target rack according to the second characteristic parameter includes: obtaining the second characteristic parameter, the second characteristic parameter at least including: a first sub-parameter and a second sub-parameter, the first sub-parameter including: the load power required by the target object, the cooling capacity required by the target object, and the business area required by the target object, and the second sub-parameter including: a preset total load power, a preset total cooling capacity, and a preset total business area; determining a first proportion vector according to the first sub-parameter, and determining a second proportion vector according to the second sub-parameter, the first proportion vector being used to represent the proportion of various resources in the first sub-parameter, and the second proportion vector being used to represent the proportion of various resources in the second sub-parameter; when the demand for multiple resources in the first sub-parameter is lower than a preset threshold, obtaining the cosine similarity of the first proportion vector and the second proportion vector; determining the selling price adjustment coefficient according to the cosine similarity.
[0073] It should be noted that the preset total load power, preset total cooling capacity and preset total business area respectively represent the initial resource information that the data center can provide, for example: the preset total load power, preset total cooling capacity and preset total business area of the data center.
[0074] It can be understood that the business area is the area of the data center used to store racks, the initial design total IT load power is recorded as Pi, the total cooling capacity is recorded as Ai, and the total business area area is recorded as Bi.
[0075] In an optional manner, the load power required by the target object in the first sub-parameter, the cooling capacity required by the target object, and the service area required by the target object are recorded as Pr, Ar, and Br, respectively.
[0076] When the demand for multiple resources in the first sub-parameter is lower than the preset threshold, it is encouraged to allocate Pr:Ar:Br according to Pi:Ai:Bi, and the cosine similarity between the first proportion vector (Pr,Ar,Br) and the second proportion vector (Pi,Ai,Bi) is calculated.
[0077] Specifically, step 1: calculate the dot product (dp) of the first scale vector and the second scale vector:
[0078] dp=Pr*Pi+Ar*Ai+Br*Bi;
[0079] Step 2: Calculate the magnitude of the first scaled vector and the second scaled vector:
[0080] The magnitude of the first scale vector:
[0081] The magnitude of the second scale vector:
[0082] Step 3: Calculate the cosine similarity between the first scaled vector and the second scaled vector:
[0083] cs = dp / (|Vr| * |Vi|);
[0084] Step 4: Get the preset interval of the price adjustment coefficient: [Thl, ThH], and convert the cosine similarity into data within the preset interval:
[0085] The selling price adjustment factor is determined by the following formula:
[0086] Discount=Thl+(ThH-Thl)*((cs+1) / 2);
[0087] In the case where there are resources in the first sub-parameter whose demand is higher than a preset threshold, a third sub-parameter is obtained, and the third sub-parameter at least includes: allocable load power, allocable cooling capacity and allocable business area; a third proportion vector is determined according to the third sub-parameter, and the third proportion vector is used to represent the proportion of various allocable resources in the third sub-parameter; the cosine similarity between the third proportion vector and the second proportion vector is determined; and the selling price adjustment coefficient is determined according to the cosine similarity.
[0088] Taking the allocable load power, allocable cooling capacity and allocable business area in the third sub-parameter as Pm, Am and Bm respectively, the price adjustment coefficient can be determined in the following way:
[0089] It is encouraged that Pr:Ar:Br is consistent with Pm:Am:Bm, the cosine similarity between the third scale vector and the second scale vector is determined, and the first coefficient is determined according to the cosine similarity between the third scale vector and the second scale vector:
[0090]
[0091] The second coefficient is determined according to the following formula:
[0092] DisB=Th1+(ThH-Th1)*(1-e -kb*max((Pr / Pm)-(Br / Bm),0) )
[0093] The third coefficient is determined according to the following formula:
[0094] DisC=Th1+(ThH-Th1)*(1-e -kc*max((Pr / Ar)-(Pm / Am),0) )
[0095] The preset weights of the first coefficient, the second coefficient and the third coefficient are obtained, which are WA, WB, and WC respectively, wherein WA+WB+WC=1, and the price adjustment coefficient is determined by the following formula:
[0096] Discount=DisA*WA+DisB*WB+DisC*WC;
[0097] Figure 4 is a structural diagram of a data center rack price determination device according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:
[0098] An acquisition module 40 is used to acquire demand information of a target object, determine a plurality of first characteristic parameters of the target object according to the demand information, and determine a required load of a target rack corresponding to the demand information according to the first characteristic parameters using a preset model;
[0099] A first determining module 42, configured to determine an initial selling price of the target rack according to a required load of the target rack;
[0100] A second determination module 44 is used to determine a plurality of second characteristic parameters of the data center according to the demand information, and determine a price adjustment coefficient corresponding to the target rack according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize an indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide;
[0101] The adjustment module 46 is used to adjust the initial selling price using the selling price adjustment coefficient to obtain a target selling price.
[0102] Through the above-mentioned data center rack price determination device, by obtaining demand information of the target object, multiple first characteristic parameters of the target object are determined according to the demand information, and a preset model is used to determine the required load of the target rack corresponding to the demand information according to the first characteristic parameters; the initial selling price of the target rack is determined according to the required load of the target rack; multiple second characteristic parameters of the data center are obtained, and the selling price adjustment coefficient corresponding to the target rack is determined according to the second characteristic parameter, wherein the first characteristic parameter is at least used to characterize the indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the number of resources that the data center can provide; the initial selling price is adjusted by using the selling price adjustment coefficient to obtain the target selling price, thereby achieving the technical effect of predicting the selling price of the data center rack according to the combination of the first characteristic parameter and the second characteristic parameter at the same time, thereby achieving the technical effect of improving the accuracy of the selling price prediction, and further solving the technical problem in the related technology that the prediction model can only predict the power load on the user side, resulting in low accuracy of the predicted selling price.
[0103] The acquisition module 40 in the above-mentioned data center rack price determination device includes: a first characteristic parameter submodule, which is used to determine multiple first characteristic parameters of the target object according to the demand information, including: extracting target information from the demand information, the target information including: the industry type of the target object, the equipment configuration information in the target rack, the business type and business scale that the server in the target rack needs to carry, and the traffic that the equipment in the target rack needs to open; determining the first characteristic parameter according to the target information, the first characteristic parameter including: industry characteristics, a first quantitative indicator, a second quantitative indicator and a third quantitative indicator, the first quantitative indicator is used to represent the quantitative indicator of the equipment configuration in the target rack, the second quantitative indicator is used to represent the quantitative indicator of the business type and business scale that the server in the target rack needs to carry, and the third quantitative indicator is used to represent the quantitative indicator of the traffic that the equipment in the target rack needs to open.
[0104] The first characteristic parameter submodule includes: a first determination unit, which is used to use a preset model to determine the required load of the target rack corresponding to the demand information according to the first characteristic parameter, including: using the preset model to extract features of the first characteristic parameter to obtain a feature vector, and normalizing the feature vector to obtain a target feature vector; processing the target feature vector in turn through multiple control gates in the preset model to obtain a final result, and the final result is used to represent the required load of the target rack, wherein the control gate is used to control the information flow and data update in the preset model.
[0105] The first determination unit includes: a processing subunit, which is used to process the target feature vector through multiple control gates in the preset model in sequence to obtain a final result, including: using a reset gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain a first output value of the reset gate; using an input activation gate among the multiple control gates to multiply the first output value with the predicted value at the previous moment, and after combining it with the target feature vector, performing a logical operation to obtain a second output value of the input activation gate; using an update gate among the multiple control gates to combine the target feature vector with the predicted value at the previous moment, and then performing a logical operation to obtain a third output value of the update gate; using a final output gate among the multiple control gates to combine the second output, the third output value and the predicted value at the previous moment to obtain the final result.
[0106] The first determination module 42 includes: a selling price submodule, which is used to determine the initial selling price of the target rack according to the required load of the target rack, including: determining the electricity cost corresponding to the target rack according to the required load of the rack; obtaining the preset profit margin corresponding to the target rack and the income corresponding to the target rack; determining the initial selling price of the target rack according to the electricity cost, the preset profit margin corresponding to the target rack and the income corresponding to the target rack.
[0107] The adjustment module 46 includes: an adjustment submodule, which is used to determine the selling price adjustment coefficient corresponding to the target rack according to the second characteristic parameter, including: obtaining the second characteristic parameter, the second characteristic parameter at least including: a first subparameter and a second subparameter, the first subparameter including: the load power required by the target object, the cooling capacity required by the target object and the business area required by the target object, and the second subparameter including: a preset total load power, a preset total cooling capacity and a preset total business area; determining a first proportion vector according to the first subparameter, and determining a second proportion vector according to the second subparameter, the first proportion vector is used to represent the proportion of various resources in the first subparameter, and the second proportion vector is used to represent the proportion of various resources in the second subparameter; when the demand for multiple resources in the first subparameter is lower than a preset threshold, obtaining the cosine similarity of the first proportion vector and the second proportion vector; determining the selling price adjustment coefficient according to the cosine similarity.
[0108] The adjustment submodule includes: an adjustment unit, which is used to obtain a third sub-parameter when there is a resource with a demand higher than a preset threshold in the first sub-parameter, and the third sub-parameter at least includes: allocable load power, allocable cooling capacity and allocable business area; determine a third proportion vector according to the third sub-parameter, and the third proportion vector is used to represent the proportion of various allocable resources in the third sub-parameter; determine the cosine similarity between the third proportion vector and the second proportion vector; and determine the selling price adjustment coefficient according to the cosine similarity.
[0109] It should be noted that Figure 4 The data center rack price determination device is used to perform Figure 2 The method for determining the selling price of a data center rack is shown, so the relevant explanations in the above-mentioned method for determining the selling price of a data center rack are also applicable to the device for determining the selling price of a data center rack, and will not be repeated here.
[0110] An embodiment of the present application also provides a computer device, including: a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the above-mentioned data center rack price determination method.
[0111] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned data center rack price determination method by running the computer program.
[0112] An embodiment of the present application also provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for determining the selling price of a data center rack in the present application are implemented.
[0113] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the method for determining the selling price of a data center rack in the present application.
[0114] An embodiment of the present application also provides a computer program, which, when executed by a processor, implements the steps of the method for determining the selling price of a data center rack in the present application.
[0115] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0116] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.
[0117] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0119] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.
[0121] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for determining the price of a data center rack, characterized in that: include: Acquire demand information of a target object, determine a plurality of first characteristic parameters of the target object according to the demand information, and use a preset model to determine a required load of a target rack corresponding to the demand information according to the first characteristic parameters; Determine the initial selling price of the target rack according to the required load of the target rack; Acquire multiple second characteristic parameters of the data center, and determine the price adjustment coefficient corresponding to the target rack according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize the index corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize the amount of resources that the data center can provide; The initial selling price is adjusted using the selling price adjustment coefficient to obtain a target selling price.
2. The method according to claim 1, characterized in that Determining a plurality of first characteristic parameters of the target object according to the demand information includes: Extracting target information from the demand information, the target information including: the industry type of the target object, the equipment configuration information in the target rack, the business type and business scale that the server in the target rack needs to carry, and the traffic that the equipment in the target rack needs to open; The first characteristic parameter is determined according to the target information, and the first characteristic parameter includes: industry characteristics, a first quantitative indicator, a second quantitative indicator and a third quantitative indicator. The first quantitative indicator is used to represent the quantitative indicator of the equipment configuration in the target rack, the second quantitative indicator is used to represent the quantitative indicator of the business type and business scale that the server in the target rack needs to carry, and the third quantitative indicator is used to represent the quantitative indicator of the traffic that the equipment in the target rack needs to open.
3. The method according to claim 2, characterized in that Determining the required load of the target rack corresponding to the demand information according to the first characteristic parameter using a preset model includes: Using the preset model to perform feature extraction on the first feature parameter to obtain a feature vector, and normalizing the feature vector to obtain a target feature vector; The target feature vector is processed sequentially through a plurality of control gates in the preset model to obtain a final result, and the final result is used to represent the required load of the target rack, wherein the control gate is used to control the information flow and data update in the preset model.
4. The method according to claim 3, characterized in that: The target feature vector is processed sequentially through a plurality of control gates in the preset model to obtain a final result, including: After combining the target feature vector with the predicted value at the previous moment by using a reset gate among the multiple control gates, a logic operation is performed to obtain a first output value of the reset gate; Using an input activation gate among the multiple control gates to multiply the first output value by the predicted value at the previous moment, and after combining with the target feature vector, performing a logical operation to obtain a second output value of the input activation gate; After combining the target feature vector with the prediction value at the previous moment by using an update gate among the multiple control gates, a logic operation is performed to obtain a third output value of the update gate; The final result is obtained by combining the second output, the third output value and the predicted value at the previous moment using a final output gate among the multiple control gates.
5. The method according to claim 1, characterized in that Determining the initial selling price of the target rack according to the required load of the target rack includes: Determining the electricity cost corresponding to the target rack according to the load required by the rack; Obtaining a preset profit margin corresponding to the target rack and an income corresponding to the target rack; The initial selling price of the target rack is determined according to the electricity cost, a preset profit margin corresponding to the target rack, and the income corresponding to the target rack.
6. The method according to claim 1, characterized in that Determining the selling price adjustment coefficient corresponding to the target rack according to the second characteristic parameter includes: Acquire the second characteristic parameter, the second characteristic parameter at least including: a first sub-parameter and a second sub-parameter, the first sub-parameter including: load power required by the target object, cooling capacity required by the target object, and business area required by the target object, the second sub-parameter including: a preset total load power, a preset total cooling capacity, and a preset total business area; Determine a first proportion vector according to the first sub-parameter, and determine a second proportion vector according to the second sub-parameter, the first proportion vector is used to represent the proportion of various resources in the first sub-parameter, and the second proportion vector is used to represent the proportion of various resources in the second sub-parameter; When the demand amounts of the multiple resources in the first sub-parameter are lower than a preset threshold, obtaining the cosine similarity of the first proportion vector and the second proportion vector; The selling price adjustment coefficient is determined according to the cosine similarity.
7. The method according to claim 6, characterized in that The method further comprises: In the case that there are resources with demand higher than a preset threshold in the first sub-parameter, a third sub-parameter is obtained, wherein the third sub-parameter includes at least: allocable load power, allocable cooling capacity, and allocable service area; Determine a third proportion vector according to the third sub-parameter, where the third proportion vector is used to represent the proportions of various allocatable resources in the third sub-parameter; determining a cosine similarity between the third scaled vector and the second scaled vector; The selling price adjustment coefficient is determined according to the cosine similarity.
8. A data center rack price determination device, characterized in that: include: An acquisition module, used to acquire demand information of a target object, determine a plurality of first characteristic parameters of the target object according to the demand information, and determine a required load of a target rack corresponding to the demand information according to the first characteristic parameters using a preset model; A first determining module, configured to determine an initial selling price of the target rack according to a required load of the target rack; a second determination module, configured to determine a plurality of second characteristic parameters of the data center according to the demand information, and determine a price adjustment coefficient corresponding to the target rack according to the second characteristic parameters, wherein the first characteristic parameter is at least used to characterize an indicator corresponding to the configuration information of the target rack, and the second characteristic parameter is at least used to characterize a quantity of resources that the data center can provide; The adjustment module is used to adjust the initial selling price using the selling price adjustment coefficient to obtain a target selling price.
9. A computer device, characterized in that: include: A memory and a processor, wherein the memory is used to store program instructions; The processor is connected to the memory and is used to execute the data center rack price determination method described in any one of claims 1 to 7.
10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method for determining the selling price of a data center rack described in any one of claims 1 to 7 is implemented.
