Model training method and machine room storage battery standby power duration prediction method and device

Abstract

The embodiment of the invention provides a model training method and a machine room storage battery standby power duration prediction method and device. The method can be used in artificial intelligence technology field. The method comprises the steps of obtaining a first training sample; according to the discharge duration and the standard discharge curve information, standard energy of the first machine room storage battery is determined, and according to the discharge duration and the actual discharge curve information, actual energy of the first machine room storage battery is determined; determining the actual capacity of the storage battery of the first machine room according to the standard energy, the actual energy and the standard capacity; according to the actual capacity and the performance influence factor information, the standby power duration of the storage battery of the first machine room is determined; and according to the standby power duration and the feature information of the first machine room storage battery, training to obtain a standby power duration prediction model of the machine room storage battery. The method is used for achieving the effect of improving the standby power duration prediction accuracy of the storage battery of the machine room.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a model training method, a method and a device for predicting the backup power duration of a computer room battery. Background Art

[0002] With the rapid development of communication technology, users have put forward higher requirements for the stability and quality of network services. In this case, the importance of computer room batteries as key backup power sources in communication networks has become increasingly prominent. In the event of a power outage in the computer room, the battery can quickly provide continuous power supply to the equipment in the computer room to ensure that the normal operation of the network system is not affected. Therefore, it is particularly important to predict the backup time of the computer room battery.

[0003] Currently, the way to predict the backup power duration is usually to manually discharge the battery when it is placed in the computer room and record the usable time, or to estimate its endurance time based on past usage.

[0004] However, the existing method for predicting the backup time of the battery in the computer room has the problem of insufficient accuracy. Summary of the invention

[0005] The embodiments of the present application provide a model training method, a method and a device for predicting the backup power duration of a computer room battery, so as to solve the problem of inaccurate prediction of the backup power duration of the battery.

[0006] In a first aspect, an embodiment of the present application provides a model training method, comprising:

[0007] Acquire a first training sample, where the first training sample includes discharge duration, standard capacity, performance influencing factor information, standard discharge curve information, and actual discharge curve information of a storage battery in a first computer room;

[0008] Determine the standard energy of the storage battery in the first computer room according to the discharge time and the standard discharge curve information, and determine the actual energy of the storage battery in the first computer room according to the discharge time and the actual discharge curve information;

[0009] Determine the actual capacity of the battery in the first machine room based on the standard energy, actual energy and standard capacity;

[0010] Determine the backup time of the battery in the first equipment room based on the actual capacity and performance influencing factors;

[0011] According to the backup power duration and the characteristic information of the battery in the first computer room, a backup power duration prediction model of the battery in the computer room is trained.

[0012] In a possible implementation manner, training a backup power duration prediction model for a computer room battery also includes:

[0013] Acquire a second training sample, where the second training sample includes alarm information of a battery in a second computer room;

[0014] If the alarm information includes the power outage alarm information of the machine room and the disconnection alarm information of the base station, the power outage alarm time of the machine room and the disconnection time of the base station are obtained. The power outage alarm information of the machine room indicates that the second machine room battery is started to be used, and the disconnection alarm information of the base station indicates that the second machine room battery is stopped to be used.

[0015] According to the difference between the power outage alarm time of the equipment room and the base station disconnection time, the actual backup time of the battery in the second equipment room is determined;

[0016] According to the actual backup power duration and the characteristic information of the battery in the second computer room, a backup power duration prediction model of the battery in the computer room is trained.

[0017] In a possible implementation, determining the backup power duration of the battery in the first computer room according to the actual capacity and the performance influencing factor information includes:

[0018] According to the temperature information, the temperature coefficient information and the discharge capacity coefficient information in the performance influencing factor information, the actual capacity is adjusted to obtain the dischargeable capacity of the battery in the first computer room;

[0019] The backup power duration of the battery in the first computer room is determined according to the dischargeable capacity, the safety factor information, and the load current information in the performance influencing factor information.

[0020] In a possible implementation, determining the actual capacity of the battery in the first computer room according to the standard energy, the actual energy and the standard capacity includes:

[0021] Determine energy ratio information according to the ratio of standard energy to actual energy;

[0022] According to the energy ratio information and the standard capacity, the actual capacity of the battery in the first computer room is determined.

[0023] In a possible implementation, the feature information is obtained by:

[0024] Obtain information about the status and performance of the computer room;

[0025] Cleaning the computer room status performance information to obtain computer room status performance cleaning information;

[0026] Standardize the cleaning information of the computer room status and performance to obtain the target computer room status and performance information;

[0027] According to the state performance information of the target computer room, characteristic information of the battery in the first computer room is determined.

[0028] In a possible implementation manner, determining characteristic information of the battery in the first computer room according to the state performance information of the target computer room includes:

[0029] Determine time change trend information according to time characteristic state performance information in the target computer room state performance information;

[0030] Determine the standard discharge time of the battery in the first equipment room based on the standard capacity and performance influencing factors;

[0031] According to the time variation trend information, the standard discharge duration and the target computer room status performance information, characteristic information of the battery in the first computer room is determined.

[0032] In a second aspect, an embodiment of the present application provides a method for predicting the backup power duration of a battery in a computer room, comprising:

[0033] Obtain characteristic information of the battery in the equipment room to be tested;

[0034] The characteristic information is input into the backup power duration prediction model to obtain the predicted backup power duration of the battery in the computer room to be tested, wherein the backup power duration prediction model is a backup power duration prediction model trained according to the model training method according to any one of claims 1 to 6.

[0035] In a third aspect, an embodiment of the present application provides a model training device, comprising:

[0036] An acquisition module, used to acquire a first training sample, where the first training sample includes the discharge duration, standard capacity, performance influencing factor information, standard discharge curve information, and actual discharge curve information of the battery in the first computer room;

[0037] A first determination module is used to determine the standard energy of the first computer room battery according to the discharge time and the standard discharge curve information, and to determine the actual energy of the first computer room battery according to the discharge time and the actual discharge curve information;

[0038] A second determination module is used to determine the actual capacity of the battery in the first computer room according to the standard energy, the actual energy and the standard capacity;

[0039] A third determination module is used to determine the backup power duration of the battery in the first computer room according to the actual capacity and performance influencing factor information;

[0040] The training module is used to train a prediction model for the backup power duration of the battery in the computer room according to the backup power duration and characteristic information of the battery in the first computer room.

[0041] In a fourth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0042] Memory stores computer-executable instructions;

[0043] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0044] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0045] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0046] The model training method, the backup power time prediction method and the device for the computer room battery provided in the embodiments of the present application obtain a first training sample, wherein the first training sample includes the discharge time, standard capacity, performance influencing factor information, standard discharge curve information and actual discharge curve information of the first computer room battery; the standard energy of the first computer room battery is determined according to the discharge time and the standard discharge curve information, and the actual energy of the first computer room battery is determined according to the discharge time and the actual discharge curve information; the actual capacity of the first computer room battery is determined according to the standard energy, actual energy and standard capacity; the backup power time of the first computer room battery is determined according to the actual capacity and the performance influencing factor information; and the backup power time is determined according to the backup power time. and the characteristic information of the battery in the first computer room, and train a backup power time prediction model for the computer room battery; obtain the characteristic information of the battery in the computer room to be tested; input the characteristic information into the backup power time prediction model to obtain a means of predicting the backup power time of the battery in the computer room to be tested, so that the actual capacity of the battery in the computer room can be obtained by combining the standard discharge curve information and the actual discharge curve information, and then the backup power time of the battery in the computer room can be predicted; the backup power time prediction model can be trained according to the prediction result and the characteristic information; when it is necessary to predict the backup power time of the battery in the computer room to be tested, its characteristic information is input into the backup power time prediction model to obtain the predicted backup power time, thereby achieving the effect of improving the accuracy of the backup power time prediction of the computer room battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] Figure 1 A flowchart of a model training method provided in an embodiment of the present application;

[0049] Figure 2 A flow chart of a method for predicting the backup power duration of a computer room battery provided in an embodiment of the present application;

[0050] Figure 3 A flowchart of another model training method provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the structure of a model training device provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0053] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0055] First, the terms involved in this application are explained:

[0056] Computer room battery: refers to an energy storage device used in data centers, server rooms, etc. as part of an uninterruptible power supply system to provide temporary power support when the main power fails. The main function of this type of battery is to quickly take over the power supply when the power is interrupted, ensuring that the equipment in the computer room can continue to operate until the main power is restored or the emergency generator set is started.

[0057] In the prior art, batteries are often manually discharged and tested to record the usable time, or their endurance is estimated based on past usage. However, the quality and service life of batteries in different computer rooms vary. At the same time, as the frequency and duration of use increase, the capacity of the battery will also change. Manual testing or estimation has the technical problem of insufficient prediction accuracy.

[0058] The model training method, the method and device for predicting the backup power time of the computer room battery provided in the present application obtain the actual capacity of the computer room battery through the standard discharge curve information and the actual discharge curve information, and then predict the backup power time of the computer room battery. A backup power time prediction model is obtained by training based on the prediction result and the characteristic information. When it is necessary to predict the backup power time of the computer room battery to be tested, its characteristic information is input into the backup power time prediction model to obtain a technical means for predicting the backup power time, thereby solving the technical problem of inaccurate prediction of the backup power time of the computer room battery.

[0059] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0060] Figure 1 The flowchart of the model training method provided in the embodiment of the present application is shown in FIG. The execution subject of the present method can be a server or other servers, and this embodiment is not particularly limited here. Figure 1 As shown, the method may include:

[0061] S101. Obtain a first training sample, where the first training sample includes discharge duration, standard capacity, performance influencing factor information, standard discharge curve information, and actual discharge curve information of a storage battery in a first computer room.

[0062] The first computer room battery may refer to a battery that supplies power after a power outage in the computer room and that resumes supplying power to the computer room before the electric energy is consumed.

[0063] The discharge time refers to the length of time the battery continues to discharge from the time the power is cut off in the equipment room to the time the power is restored in the equipment room.

[0064] Standard capacity refers to the total amount of electrical energy that a battery can provide under specific discharge conditions, and is usually provided by the battery manufacturer.

[0065] The performance influencing factor information may refer to internal and external conditions and variables that can directly or indirectly affect the battery performance, such as safety factor, battery temperature coefficient, etc.

[0066] The standard discharge curve information may refer to information of a discharge curve graph of a battery under ideal conditions, which represents the relationship between voltage and time at a specific discharge current, and is usually provided by a battery manufacturer.

[0067] The actual discharge curve information may refer to information of a discharge curve of a battery under actual use conditions, which indicates the relationship between voltage changes over time under actual discharge current, and may be obtained by recording voltage changes of the battery under actual conditions.

[0068] S102: Determine the standard energy of the storage battery in the first computer room according to the discharge time and the standard discharge curve information, and determine the actual energy of the storage battery in the first computer room according to the discharge time and the actual discharge curve information.

[0069] Among them, the method for determining the standard energy of the battery in the first computer room may include drawing a straight line vertically at the corresponding horizontal axis in the standard discharge curve diagram according to the discharge time. The area of ​​the figure enclosed by the straight line, the standard discharge curve diagram and the horizontal and vertical axes represents the standard discharge energy of the battery in the time period. Specifically, this area represents the total amount of electrical energy released by the battery in this period of time, that is, the standard energy of the battery in the first computer room.

[0070] The method for determining the actual energy of the battery in the first computer room may include drawing a straight line vertically at the corresponding horizontal axis in the actual discharge curve graph according to the discharge time. The area of ​​the figure enclosed by the straight line, the actual discharge curve graph and the horizontal and vertical axes represents the actual discharge energy of the battery in the time period. Specifically, this area represents the total amount of electrical energy actually released by the battery in this period, that is, the actual energy of the battery in the first computer room.

[0071] S103: Determine the actual capacity of the battery in the first computer room according to the standard energy, the actual energy and the standard capacity.

[0072] Among them, the actual capacity of the battery in the first computer room refers to the total amount of electric energy that the battery can provide under actual conditions of use. Since the capacity of the battery will be affected by many factors, such as ambient temperature, age, number of charge and discharge cycles, and charging status, the actual capacity is usually smaller than the standard capacity.

[0073] In the embodiment of the present application, the actual capacity of the battery in the first computer room is determined according to the standard energy, the actual energy and the standard capacity. The method may include:

[0074] Determine energy ratio information according to the ratio of standard energy to actual energy;

[0075] According to the energy ratio information and the standard capacity, the actual capacity of the battery in the first computer room is determined.

[0076] The energy ratio information may refer to the ratio information between the discharge energy of the battery under actual use conditions and the discharge energy under standard conditions.

[0077] The method for determining the actual capacity of the battery in the first computer room may include multiplying the standard capacity and the ratio in the energy ratio information. The ratio of the actual energy to the standard energy in the same time period may be approximately equal to the ratio of the actual capacity to the standard capacity, so the result obtained by multiplying the standard capacity and the ratio in the energy ratio information is the actual capacity.

[0078] S104: Determine the backup power duration of the battery in the first computer room according to the actual capacity and performance influencing factor information.

[0079] The backup time of the battery in the first computer room may refer to the length of time that the battery can continue to provide power to the load when the computer room loses power.

[0080] In the embodiment of the present application, the method for determining the backup power duration of the battery in the first computer room according to the actual capacity and the performance influencing factor information may include:

[0081] According to the temperature information, the temperature coefficient information and the discharge capacity coefficient information in the performance influencing factor information, the actual capacity is adjusted to obtain the dischargeable capacity of the battery in the first computer room;

[0082] The backup power duration of the battery in the first computer room is determined according to the dischargeable capacity, the safety factor information, and the load current information in the performance influencing factor information.

[0083] Among them, the method for obtaining the dischargeable capacity of the battery in the first computer room may include multiplying the difference between the temperature information and the preset temperature with the temperature coefficient information and then adjusting it, and then multiplying the adjusted result with the discharge capacity information and the actual capacity, and the result obtained is the dischargeable capacity.

[0084] The method for determining the backup power duration of the storage battery in the first computer room may include first multiplying the safety factor information and the load current information, and then dividing the dischargeable capacity by the product, and the result obtained is the backup power duration.

[0085] The overall calculation formula can be as follows:

[0086]

[0087] in, is the actual capacity of the battery, is the discharge capacity coefficient, is the temperature coefficient, is the temperature, is the safety factor, is the load current, For power backup time.

[0088] S105. According to the backup power duration and the characteristic information of the battery in the first computer room, a backup power duration prediction model of the battery in the computer room is obtained by training.

[0089] Among them, the characteristic information of the battery in the first computer room may refer to the information of the battery in the first computer room and the computer room where it is located that can affect the performance of the battery, for example, data information, dynamic environment performance data information and computer room business volume indicator data information, etc. Among them, the data information may include computer room space data information, battery resource data information and computer room equipment resource data information, etc. The computer room space data information may include computer room ID, computer room name, computer room type, computer room level, etc. The battery resource data information may include battery manufacturer, battery type, battery nominal capacity, etc., battery commissioning time, battery service life, etc. The computer room equipment resource data information may include the total number of BBU (Baseband Unit) equipment, the total number of dynamic environment equipment, the total number of switching power supply modules, the total number of transmission boards, OLT (Optical Line The total number of optical line terminals (OTCs), the total number of air conditioners in the computer room, etc.; the dynamic environment performance data information may include the real-time performance data information of the battery and the performance data information of the computer room environment. The real-time performance data information of the battery may include the load current, the output DC voltage, etc., and the performance data information of the computer room environment may include the temperature of the computer room, the humidity of the computer room, etc.; the computer room business volume indicator data information may include the average utilization of uplink PRB (Physical Resource Block), the average number of RRC (Radio Resource Control) connections, the average utilization of downlink PRB, the average utilization of uplink PUSCH (Physical Uplink Shared Channel) channel PRB, the average utilization of downlink PUSCH channel PRB, air interface downlink business traffic, air interface uplink business traffic, uplink PDCP (Packet Data Convergence Protocol) layer user plane traffic, downlink PDCP layer user plane traffic, the average number of RRC connection users, the number of broadband cells, etc.

[0090] In the embodiment of the present application, a backup power duration prediction model of a computer room battery is obtained through training, and the method may further include:

[0091] Acquire a second training sample, where the second training sample includes alarm information of a battery in a second computer room;

[0092] If the alarm information includes the power outage alarm information of the machine room and the disconnection alarm information of the base station, the power outage alarm time of the machine room and the disconnection time of the base station are obtained. The power outage alarm information of the machine room indicates that the second machine room battery is started to be used, and the disconnection alarm information of the base station indicates that the second machine room battery is stopped to be used.

[0093] According to the difference between the power outage alarm time of the equipment room and the base station disconnection time, the actual backup time of the battery in the second equipment room is determined;

[0094] According to the actual backup power duration and the characteristic information of the battery in the second computer room, a backup power duration prediction model of the battery in the computer room is trained.

[0095] The second computer room battery may refer to a battery that supplies power after a power outage in the computer room and completely consumes the electrical energy before power is restored in the computer room.

[0096] The alarm information may refer to the alarm information received by the battery when an abnormal situation occurs in the machine room or the battery itself.

[0097] When the power outage alarm information of the computer room is received, it indicates that there is a power outage in the computer room, and the switch power supply will switch the AC power supply to the battery power supply, that is, the battery will start to be used; when the base station disconnection alarm information is received, it indicates that the power in the battery has been completely consumed, that is, the battery will stop being used.

[0098] The method for determining the actual backup power duration of the battery in the second computer room may include subtracting the power outage alarm time of the computer room from the base station disconnection time, and the time difference between the two warnings is the actual backup power duration.

[0099] In this embodiment of the present application, the feature information may be obtained in the following manner:

[0100] Obtain information about the status and performance of the computer room;

[0101] Cleaning the computer room status performance information to obtain computer room status performance cleaning information;

[0102] Standardize the cleaning information of the computer room status and performance to obtain the target computer room status and performance information;

[0103] According to the state performance information of the target computer room, characteristic information of the battery in the first computer room is determined.

[0104] The computer room status performance information may refer to unprocessed batteries and information in the computer room where the batteries are located that may affect the battery performance.

[0105] The method for obtaining the computer room status performance cleaning information may include supplementing the missing values ​​in the computer room status performance information, removing abnormal values, etc.

[0106] The method for obtaining the target computer room status performance information may include standardizing the computer room status performance cleaning information to make the data distribution of different characteristics consistent.

[0107] In the embodiment of the present application, the method for determining the characteristic information of the battery in the first computer room according to the state performance information of the target computer room may include:

[0108] Determine time change trend information according to time characteristic state performance information in the target computer room state performance information;

[0109] Determine the standard discharge time of the battery in the first equipment room based on the standard capacity and performance influencing factors;

[0110] According to the time variation trend information, the standard discharge duration and the target computer room status performance information, characteristic information of the battery in the first computer room is determined.

[0111] Among them, the method for determining the time change trend information may include constructing time series features such as moving average, difference, etc. for time-dependent time characteristic state performance information, such as load current, computer room temperature, etc., to capture the time change trend of the data and obtain the time change trend information.

[0112] The method for determining the standard discharge time of the battery in the first computer room may include determining according to the formula:

[0113]

[0114] in, is the standard capacity of the battery, is the discharge capacity coefficient, is the temperature coefficient, is the temperature, is the safety factor, is the load current, For power backup time.

[0115] The characteristic information of the battery in the first computer room includes time change trend information, standard discharge duration and target computer room status performance information. Using the time change trend information, standard discharge duration and target computer room status performance information as characteristic information to train the model can improve the accuracy of the model.

[0116] The above-mentioned method for acquiring characteristic information of the battery in the first computer room and the method for processing the characteristic information are also applicable to acquiring and processing characteristic information of the battery in the second computer room.

[0117] The model training method provided in the embodiment of the present application can combine the standard discharge curve information and the actual discharge curve information to obtain the actual capacity of the computer room battery, and then predict the backup power time of the computer room battery. The backup power time prediction model is trained based on the prediction result and the characteristic information. When it is necessary to predict the backup power time of the computer room battery to be tested, its characteristic information is input into the backup power time prediction model to obtain the predicted backup power time, thereby achieving the effect of improving the accuracy of the backup power time prediction of the computer room battery.

[0118] Figure 2 A flow chart of a method for predicting the backup time of a battery in a computer room provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0119] S201. Obtain characteristic information of the battery in the computer room to be tested.

[0120] The battery in the computer room to be tested may refer to a battery whose backup power duration needs to be predicted, and the characteristic information of the battery in the computer room to be tested may refer to the information of the battery in the computer room to be tested and the information in the computer room where the battery is located that can affect the performance of the battery.

[0121] S202: Input the characteristic information into a backup power duration prediction model to obtain a predicted backup power duration of the battery in the computer room to be tested.

[0122] The predicted backup time of the battery in the computer room to be tested may refer to the backup time of the battery obtained by the model according to the characteristic information.

[0123] The backup power duration prediction model may refer to any model in the above-mentioned model training method.

[0124] The method for predicting the backup power duration of a computer room battery provided in an embodiment of the present application can input characteristic information of the computer room battery to be tested into a backup power duration prediction model, thereby obtaining a prediction result of its backup power duration.

[0125] Figure 3 A flow chart of another model training method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method includes:

[0126] S301. Obtain training samples, where the training samples include discharge duration, standard capacity, performance influencing factor information, feature information, alarm information, standard discharge curve information, and actual discharge curve information of the battery in the computer room.

[0127] The training samples may refer to battery samples that provide power after a power outage in a computer room.

[0128] S302: Clean and standardize the feature information to obtain target feature information.

[0129] The target feature information may refer to feature data that has been cleaned and standardized and has a unified format and is easy to analyze.

[0130] S303: If the alarm information includes the power outage alarm information of the computer room and the base station disconnection alarm information, the actual backup power duration of the battery in the computer room is determined according to the difference between the power outage alarm time of the computer room and the base station disconnection time.

[0131] Among them, the power outage alarm information of the computer room indicates the start of using the computer room battery, and the base station disconnection alarm information indicates the end of using the computer room battery. If the alarm information includes the power outage alarm information of the computer room and the base station disconnection alarm information, it means that the computer room battery will be completely consumed before the power supply of the computer room is restored.

[0132] S304. If the alarm information does not include both the computer room power outage alarm information and the base station disconnection alarm information, the theoretical backup power duration of the computer room battery is determined according to the discharge duration, standard capacity, performance influencing factor information, standard discharge curve information and actual discharge curve information.

[0133] Among them, if the alarm information does not include both the computer room power outage alarm information and the base station disconnection alarm information, it means that the battery in the computer room has not consumed all the power before the power supply to the computer room is restored.

[0134] S305: According to the target feature information, the actual backup power duration and the theoretical backup power duration, a backup power duration prediction model of the computer room battery is trained.

[0135] Another model training method provided in an embodiment of the present application can distinguish two types of training samples according to the alarm information in the training samples, one of which is a battery that has completely consumed power before the power supply to the computer room is restored, and the other is a battery that has not been completely consumed before the power supply to the computer room is restored. The two types of training samples are processed differently, and a backup power time prediction model is obtained through comprehensive training to improve the accuracy of the prediction.

[0136] Figure 4 This is a schematic diagram of the structure of the model training device provided in the embodiment of the present application. Figure 4 As shown, the model training device 40 includes: an acquisition module 401, a first determination module 402, a second determination module 403, a third determination module 404 and a training module 405. Among them:

[0137] An acquisition module 401 is used to acquire a first training sample, where the first training sample includes a discharge duration, a standard capacity, performance influencing factor information, a standard discharge curve information, and an actual discharge curve information of a battery in a first computer room;

[0138] The first determination module 402 is used to determine the standard energy of the storage battery in the first computer room according to the discharge time and the standard discharge curve information, and to determine the actual energy of the storage battery in the first computer room according to the discharge time and the actual discharge curve information;

[0139] The second determination module 403 is used to determine the actual capacity of the battery in the first computer room according to the standard energy, the actual energy and the standard capacity;

[0140] The third determination module 404 is used to determine the backup power duration of the battery in the first computer room according to the actual capacity and the performance influencing factor information;

[0141] The training module 405 is used to train a prediction model for the backup power duration of the battery in the computer room according to the backup power duration and characteristic information of the battery in the first computer room.

[0142] In the embodiment of the present application, the second determining module 403 may also be used to:

[0143] Determine energy ratio information according to the ratio of standard energy to actual energy;

[0144] According to the energy ratio information and the standard capacity, the actual capacity of the battery in the first computer room is determined.

[0145] In the embodiment of the present application, the third determining module 404 may also be used to:

[0146] According to the temperature information, the temperature coefficient information and the discharge capacity coefficient information in the performance influencing factor information, the actual capacity is adjusted to obtain the dischargeable capacity of the battery in the first computer room;

[0147] The backup power duration of the battery in the first computer room is determined according to the dischargeable capacity, the safety factor information, and the load current information in the performance influencing factor information.

[0148] In the embodiment of the present application, the training module 405 may also be used for:

[0149] Acquire a second training sample, where the second training sample includes alarm information of a battery in a second computer room;

[0150] If the alarm information includes the power outage alarm information of the machine room and the disconnection alarm information of the base station, the power outage alarm time of the machine room and the disconnection time of the base station are obtained. The power outage alarm information of the machine room indicates that the second machine room battery is started to be used, and the disconnection alarm information of the base station indicates that the second machine room battery is stopped to be used.

[0151] According to the difference between the power outage alarm time of the equipment room and the base station disconnection time, the actual backup time of the battery in the second equipment room is determined;

[0152] According to the actual backup power duration and the characteristic information of the battery in the second computer room, a backup power duration prediction model of the battery in the computer room is trained.

[0153] In the embodiment of the present application, the training module 405 may also be used for:

[0154] Obtain information about the status and performance of the computer room;

[0155] Cleaning the computer room status performance information to obtain computer room status performance cleaning information;

[0156] Standardize the cleaning information of the computer room status and performance to obtain the target computer room status and performance information;

[0157] According to the state performance information of the target computer room, characteristic information of the battery in the first computer room is determined.

[0158] In the embodiment of the present application, the training module 405 may also be used for:

[0159] Determine time change trend information according to time characteristic state performance information in the target computer room state performance information;

[0160] Determine the standard discharge time of the battery in the first equipment room based on the standard capacity and performance influencing factors;

[0161] According to the time variation trend information, the standard discharge duration and the target computer room status performance information, characteristic information of the battery in the first computer room is determined.

[0162] As can be seen from the above, the model training device of the embodiment of the present application consists of an acquisition module 401, which is used to acquire a first training sample, and the first training sample includes the discharge time, standard capacity, performance influencing factor information, standard discharge curve information and actual discharge curve information of the battery in the first computer room; a first determination module 402, which is used to determine the standard energy of the battery in the first computer room according to the discharge time and the standard discharge curve information, and to determine the actual energy of the battery in the first computer room according to the discharge time and the actual discharge curve information; a second determination module 403, which is used to determine the actual capacity of the battery in the first computer room according to the standard energy, actual energy and standard capacity; a third determination module 404, which is used to determine the backup power time of the battery in the first computer room according to the actual capacity and performance influencing factor information; a training module 405, which is used to train a backup power time prediction model for the battery in the computer room according to the backup power time and the characteristic information of the battery in the first computer room. Therefore, the embodiment of the present application can combine the standard discharge curve information and the actual discharge curve information to obtain the actual capacity of the computer room battery, and then predict the backup power time of the computer room battery. A backup power time prediction model is trained based on the prediction results and feature information. When it is necessary to predict the backup power time of the computer room battery to be tested, its feature information is input into the backup power time prediction model to obtain the predicted backup power time, thereby achieving the effect of improving the accuracy of the backup power time prediction of the computer room battery.

[0163] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0164] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0165] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0166] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0167] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0168] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0169] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0170] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0171] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0172] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0173] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0174] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional unit in each embodiment of the present invention 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.

[0176] If the function 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0177] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0178] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A model training method, characterized in that: include: Acquire a first training sample, where the first training sample includes discharge duration, standard capacity, performance influencing factor information, standard discharge curve information, and actual discharge curve information of a storage battery in a first computer room; Determine the standard energy of the first computer room battery according to the discharge time and the standard discharge curve information, and determine the actual energy of the first computer room battery according to the discharge time and the actual discharge curve information; Determining the actual capacity of the first computer room battery according to the standard energy, the actual energy and the standard capacity; Determining the backup power duration of the first computer room battery according to the actual capacity and the performance influencing factor information; A backup power duration prediction model for the computer room battery is trained based on the backup power duration and the characteristic information of the first computer room battery.

2. The method according to claim 1, characterized in that The training obtains a backup power duration prediction model for the battery in the computer room, and further includes: Acquire a second training sample, where the second training sample includes alarm information of a battery in a second computer room; If the alarm information includes the power outage alarm information of the computer room and the disconnection alarm information of the base station, the power outage alarm time of the computer room and the disconnection time of the base station are obtained, wherein the power outage alarm information of the computer room indicates the start of using the second computer room battery, and the disconnection alarm information of the base station indicates the end of using the second computer room battery; Determine the actual backup power duration of the battery in the second computer room according to the difference between the power outage alarm time of the computer room and the off-station time of the base station; According to the actual backup power duration and the characteristic information of the second computer room battery, a backup power duration prediction model of the computer room battery is trained.

3. The method according to claim 1 or 2, characterized in that: The determining, according to the actual capacity and the performance influencing factor information, the backup power duration of the first computer room battery includes: According to the temperature information, the temperature coefficient information and the discharge capacity coefficient information in the performance influencing factor information, the actual capacity is adjusted to obtain the dischargeable capacity of the first computer room battery; The backup power duration of the first computer room storage battery is determined according to the dischargeable capacity and the safety factor information and the load current information in the performance influencing factor information.

4. The method according to claim 1 or 2, characterized in that: The determining the actual capacity of the first computer room storage battery according to the standard energy, the actual energy and the standard capacity includes: Determining energy ratio information according to the ratio of the standard energy to the actual energy; The actual capacity of the first computer room battery is determined according to the energy ratio information and the standard capacity.

5. The method according to claim 1 or 2, characterized in that: The characteristic information is obtained by: Obtain information about the status and performance of the computer room; Cleaning the computer room status performance information to obtain computer room status performance cleansing information; Standardizing the computer room status performance cleaning information to obtain target computer room status performance information; According to the target computer room status performance information, characteristic information of the battery in the first computer room is determined.

6. The method according to claim 5, characterized in that The determining, according to the target computer room status performance information, characteristic information of the first computer room battery includes: Determine time change trend information according to the time characteristic state performance information in the target computer room state performance information; Determine a standard discharge time of the battery in the first computer room according to the standard capacity and the performance influencing factor information; Characteristic information of the first computer room battery is determined according to the time variation trend information, the standard discharge duration and the target computer room status performance information.

7. A method for predicting the backup time of a battery in a computer room, characterized in that: include: Obtain characteristic information of the battery in the equipment room to be tested; The characteristic information is input into a backup power duration prediction model to obtain the predicted backup power duration of the battery in the computer room to be tested, wherein the backup power duration prediction model is a backup power duration prediction model trained according to the model training method according to any one of claims 1 to 6.

8. A model training device, characterized in that: include: An acquisition module, used to acquire a first training sample, wherein the first training sample includes a discharge duration, a standard capacity, performance influencing factor information, a standard discharge curve information, and an actual discharge curve information of a storage battery in a first computer room; A first determination module is used to determine the standard energy of the first computer room battery according to the discharge time and the standard discharge curve information, and to determine the actual energy of the first computer room battery according to the discharge time and the actual discharge curve information; A second determination module, used to determine the actual capacity of the first computer room battery according to the standard energy, the actual energy and the standard capacity; A third determination module, configured to determine the backup power duration of the first computer room battery according to the actual capacity and the performance influencing factor information; The training module is used to train a backup power duration prediction model for the computer room battery according to the backup power duration and the characteristic information of the first computer room battery.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6, and / or to implement the method according to claim 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method according to any one of claims 1 to 6, and / or to implement the method according to claim 7.

11. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6, and / or, implements the method according to claim 7.

Images