Power supply early warning method, device and equipment and storage medium

Abstract

The invention discloses a power supply early warning method and device, equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: screening out target equipment with the highest current power consumption in a plurality of local equipment, and carrying out the power mode switching of the target equipment; collecting current power supply state information corresponding to the target equipment in the power supply mode switching process, and performing deep learning based on the current power supply state information to obtain a current power supply life model curve corresponding to the target equipment; and analyzing the current power supply state information based on the current power supply life model curve to determine a power supply life evaluation value corresponding to the target equipment, and determining whether to generate power supply early warning information for power supply early warning based on the power supply life evaluation value. Therefore, early warning analysis is carried out according to the data collected in real time in the power supply mode switching process, so that the accuracy of power supply early warning is effectively improved, and the situation that power supply operation is carried out due to the fact that the current power supply state is unstable, and accidents are caused is avoided.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a power supply early warning method, device, equipment and storage medium. Background Art

[0002] At present, the power supply of equipment in the computer room generally adopts 1+1 redundant configuration. In order to meet the increasing power consumption requirements of the equipment, the rated power of the equipment power supply has also increased. During the maintenance of the power supply terminal line in the data center computer room and the fixed-point maintenance and replacement of the equipment power supply, the working equipment power supply needs to be switched between the main and standby power supplies, and the main power supply needs to take over all the workloads of the system. If the output current of the main power supply jumps instantly, the output voltage of the main power supply may fluctuate beyond the specification value with the sudden change of the output current, and even the power supply hardware may be damaged. If the actual status of the power supply cannot be monitored in real time during the alternating main and standby switching process, it may seriously cause the redundant power supply of the equipment to lose power and cause the system to shut down, resulting in equipment interruption and even data loss, which seriously affects the safety and stability of the equipment system.

[0003] It can be seen that how to perform accurate power supply early warning is a problem that technical personnel in this field need to solve. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a power warning method, device, equipment and storage medium, which can perform warning analysis based on the data collected in real time during the power mode switching process, effectively improve the accuracy of the power warning, and thus avoid accidents caused by power operations due to the current unstable power state. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses a power supply early warning method, comprising:

[0006] Filter out a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device;

[0007] Collecting current power state information corresponding to the target device during the power mode switching process, and performing deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device;

[0008] The current power state information is analyzed based on the current power life model curve to determine a power life evaluation value corresponding to the target device, and based on the power life evaluation value, it is determined whether to generate power warning information for power warning.

[0009] Optionally, the step of screening out a target device with the highest current power consumption among a plurality of local devices and switching a power mode of the target device includes:

[0010] Counting the input power consumption of a plurality of local devices, so as to determine a target device having the highest current power consumption among the plurality of devices based on the input power consumption;

[0011] Sending a power mode switching instruction to switch the power mode of each power supply of the target device, and reading the input power and output power of the current working power supply of the target device;

[0012] If the current working power supply is in a standby state and the output power is greater than a preset output power threshold, the power mode of the current working power supply is switched to a working state, and each power supply corresponding to the target device is enabled, and then the input power is set to zero;

[0013] If a mode switching failure occurs during the power mode switching process corresponding to the power mode switching instruction, jump to the step of issuing the power mode switching instruction to switch the power modes of each power supply of the target device, and read the input power and output power of the current working power supply of the target device.

[0014] Optionally, the issuing of a power mode switching instruction to switch the power mode of each power source of the target device includes:

[0015] Based on the first power mode switching instruction, the second power mode switching instruction, the third power mode switching instruction and the fourth power mode switching instruction issued in sequence, the corresponding power switching plans are executed in sequence to switch the power modes of the respective power supplies of the target device;

[0016] The first power mode switching instruction is used to switch the first power supply of the target device to a working state and the second power supply to a standby state, and to record the first input power and the first output power of the first power supply and the second power supply respectively;

[0017] The second power mode switching instruction is used to switch both the first power supply and the second power supply to a working state, and to record the second input power and the second output power of the first power supply and the second power supply respectively;

[0018] The third power mode switching instruction is used to switch the first power supply to a standby state and the second power supply to a working state, and to record a third input power and a third output power of the first power supply and the second power supply respectively;

[0019] The fourth power mode switching instruction is used to switch the first power supply and the second power supply to the working state again, and respectively record the fourth input power and the fourth output power of the first power supply and the second power supply.

[0020] Optionally, collecting current power state information corresponding to the target device during the power mode switching process, and performing deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device, includes:

[0021] Generate a timestamp check code, and collect current power state information corresponding to the target device during the power mode switching process; the current power state information includes current power temperature information, current output voltage information, and current output current information corresponding to the target device;

[0022] Using the timestamp check code as verification information of the current power state information;

[0023] The current power status information and the verification information are input into a deep learning module so that the deep learning module verifies the current power status information based on the verification information, and generates a current power life model curve corresponding to the target device based on the current power status information after the verification is passed.

[0024] Optionally, generating a current power life model curve corresponding to the target device based on the current power state information includes:

[0025] Determine the output voltage during the power mode switching process according to the current output voltage information in the current power state information, and determine the average current sharing and the instantaneous current sharing during the power mode switching process according to the current output current information in the target power state information;

[0026] A current power supply life model curve corresponding to the target device is constructed based on the output voltage, the average current sharing and the instantaneous current sharing.

[0027] Optionally, analyzing the current power state information based on the current power life model curve to determine a power life evaluation value corresponding to the target device, and determining whether to generate power warning information for power warning based on the power life evaluation value includes:

[0028] Determine a power life limit interval of the target device based on the current power life model curve;

[0029] Calculating the sum of the output voltage at each moment in the output voltage multiplied by the preset influencing parameter to obtain the output voltage life influencing value;

[0030] Calculate the sum of the average average flow rate at each moment in the average average flow rate and the product of the preset influencing parameter to obtain the average average flow rate life influence value;

[0031] Calculating the sum of the product of the instantaneous average flow at each moment in the instantaneous average flow and the preset influence parameter to obtain the instantaneous average flow life influence value;

[0032] Based on the preset weights corresponding to the target devices, corresponding weight values ​​are respectively assigned to the output voltage lifetime impact value, the average average current lifetime impact value, and the instantaneous average current lifetime impact value;

[0033] Based on the weight value, weighted sum of the output voltage life impact value, the average average current life impact value and the instantaneous average current life impact value is performed, and the weighted sum result is determined as the power supply life assessment value corresponding to the power supply of the target device;

[0034] It is determined whether the power life evaluation value is within the power life limit interval. If the power life evaluation value is within the power life limit interval, power warning information is generated to perform a power warning.

[0035] Optionally, the determining whether to generate power warning information to perform power warning based on the power life evaluation value includes:

[0036] Based on the power life evaluation value, determine whether to generate power warning information. If so, generate power warning information for the target device, and transmit the power warning information to the front-end visualization page of the power warning system so as to display the warning through the front-end visualization page.

[0037] In a second aspect, the present application discloses a power supply early warning device, comprising:

[0038] A mode switching module is used to filter out a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device;

[0039] A curve construction module, used to collect current power state information corresponding to the target device during the power mode switching process, and perform deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device;

[0040] The life warning module is used to analyze the current power status information based on the current power life model curve to determine the power life evaluation value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life evaluation value.

[0041] In a third aspect, the present application discloses an electronic device, comprising:

[0042] Memory for storing computer programs;

[0043] A processor is used to execute the computer program to implement the steps of the aforementioned power supply early warning method.

[0044] In a fourth aspect, the present application discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the aforementioned power warning method are implemented.

[0045] In the present application, it is first necessary to screen out the target device with the highest current power consumption among several local devices, and switch the power mode of the target device; then, collect the current power status information corresponding to the target device during the power mode switching process, and perform deep learning based on the current power status information to obtain the current power life model curve corresponding to the target device; finally, analyze the current power status information based on the current power life model curve to determine the power life assessment value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life assessment value.

[0046] Beneficial effect: It can be seen that the method of the present application requires that after screening out the target device with the highest power consumption among several local devices, the target device is switched in power mode, and then the real-time power status information of the target device during the power mode switching process is collected, and a power life model curve is constructed based on the collected power status information, and finally the current power life evaluation value of the target device is determined according to the power model life curve, and a power warning is performed based on the power life evaluation value. In this way, the power status information during the power mode switching process can be collected, and a power life model curve can be constructed according to the collected power status information, and then the power life evaluation value can be determined according to the constructed power life model curve, and then it is determined whether to perform a power warning based on the obtained power life evaluation value. Since the warning analysis is performed based on the data collected in real time during the power mode switching process, the accuracy of the power warning is effectively improved, thereby avoiding the situation where power operations are performed due to the instability of the current power state, which leads to accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flow chart of a power supply early warning method provided by an embodiment of the present invention;

[0049] Figure 2 A power warning system architecture diagram provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of a power supply early warning device provided by an embodiment of the present invention;

[0051] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the prior art, during the process of power supply fixed-point maintenance, it is necessary to switch the power supply of the working equipment between the active and standby modes, and the active power supply needs to take over all the system workload. If the output current of the active power supply changes instantaneously, the output voltage of the active power supply may fluctuate beyond the specification value as the output current changes suddenly, and even the power supply hardware may be damaged. If the actual status of the power supply cannot be monitored in real time during the alternating active-standby switching process, it may seriously cause the redundant power supply of the equipment to lose power, causing the system to crash, resulting in equipment operation interruption and even data loss, which seriously affects the safety and stability of the equipment system.

[0054] In order to overcome the above-mentioned technical problems, the present application discloses a power supply warning method, device, equipment and storage medium, which can perform warning analysis based on data collected in real time during the power supply mode switching process, effectively improving the accuracy of the power supply warning, and thus avoiding accidents caused by power supply operations due to the unstable current power supply state.

[0055] The terms "including" and "having" in the specification of the present invention and the above-mentioned drawings, as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may include steps or units that are not listed.

[0056] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0057] In this application, power warning is performed through deep learning and early warning system of server power life, wherein the deep learning and early warning system of server power life includes intelligent control module for switching between active and standby modes of server power, deep learning module for server power life model, and monitoring and early warning module for server power status. The deep learning and early warning system of server power life is arranged on the control machine of the computer room, and the front-end visual interface software is installed on the operation and maintenance mobile terminal and the control machine of the computer room.

[0058] See also Figure 1 As shown, the embodiment of the present application discloses a power supply early warning method, including:

[0059] Step S11: Filter out a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device.

[0060] In this embodiment, after the server device is powered on successfully and connected to the server power life deep learning and early warning system, the server power main and standby mode switching intelligent control module, the server power life model deep learning module and the server power state monitoring and early warning module are automatically installed on the server device, and then the input power consumption of several local devices needs to be counted to determine the target device with the highest current power consumption among the several devices based on the input power consumption, and then a power mode switching instruction is issued to switch the power mode of each power supply of the target device, and read the input power and output power of the current working power supply of the target device. Specifically, the server power life deep learning and early warning system will issue a work instruction to the server power life model deep learning module. After receiving the work instruction, the server power life model deep learning module will count the devices with high power consumption in the current system as target devices, and then the server power life model deep learning module will issue a power mode switching instruction to the server power main and standby mode switching intelligent control module through the server power state monitoring and early warning module, and then execute the corresponding power switching plan, and intelligently switch the power mode of the target device power supply to the main and standby mode according to the power switching plan, and read the input power and output power of the target device power supply during the switching process.

[0061] It should be noted that, taking the example of a server device being redundantly powered by two power supplies, a first power supply PSU0, and a second power supply PSU1, the process of issuing a power mode switching instruction to switch the power modes of the various power supplies of the target device is as follows, including: based on the first power mode switching instruction, the second power mode switching instruction, the third power mode switching instruction, and the fourth power mode switching instruction issued in sequence, executing the corresponding power switching plan in sequence to switch the power modes of the various power supplies of the target device; wherein the first power mode switching instruction is to issue a first power mode switching to an Active working state and a second power mode switching to a Standby standby state, and then respectively record the first power mode switching instruction and the second power mode switching instruction. The first input power and the first output power instructions of the power supply are respectively recorded; the second power mode switching instruction is to switch the first power supply and the second power supply to the normal working state, and then record the second input power and the second output power instructions of the first power supply and the second power supply respectively; the third power mode is to switch the first power supply to the Standby standby state and the second power supply to the Active working state, and record the third input power and the third output power instructions of the first power supply and the second power supply respectively; the fourth power mode switching instruction is to switch the first power supply and the second power supply to the normal working state again, and record the fourth input power and the fourth output power instructions of the first power supply and the second power supply respectively. And the above power mode switching instructions are all issued through the ipmitool instruction of the BMC (baseboard management controller).

[0062] Furthermore, when the server power supply master-slave mode switching intelligent control module issues Active and Standby commands through the BMC's ipmitool command, the server power supply status monitoring and early warning module will read the input power and output power values ​​of the power supply in real time. If the current working power supply is in standby mode, and the output power is greater than the preset output power threshold, for example, exceeding the 20W limit, the power supply mode of the current working power supply will be switched to the working state, and then the Active and Standby commands will be re-issued through the ipmitool command after the reset mode is started, until the server power supply status monitoring and early warning module feedbacks that the actual output power difference of the Standby mode power supply does not exceed the 20W limit, and then the apparent input power of the Standby mode power supply is forced to zero again. It should be noted that since the server power supply in the computer room may use models from different manufacturers, when the mode is switched, the adjustment method for switching the load of the standby mode power supply to the working mode power supply will be different, and the time required will also be different. Because the standby mode power supply is actually in standby state and has the characteristics of being awakened at any time, it has a small standby power consumption. In order to ensure the uniformity of the apparent input power, if the power supply does not complete the load switching within the specified time, the apparent input power of the standby mode power supply will be forced to zero. In this way, it can be ensured that the load of the Standby power supply is fully switched to the Active power supply, and then the load of the terminal line of the computer room powered by the Active power supply can reach the expected maximum training value through the server power supply main and standby mode switching action, thereby avoiding the deviation between the actual value of the power load jump during the switching process and the monitored theoretical value due to the fact that the power load in the Standby state is not fully switched to the Active power supply, resulting in a large deviation between the actual state of the server power supply and the evaluation result of the life assessment curve, resulting in the working state not meeting the specification requirements. The power supply cannot be accurately and automatically monitored and warned, and the subsequent server is prone to power failure and shutdown due to power aging in the single power supply mode, causing server work interruption and even data loss.

[0063] Furthermore, a reset mode can be set. If a mode switching failure occurs during the power mode switching process corresponding to the power mode switching instruction, the process can jump to the step of issuing the power mode switching instruction to switch the power modes of each power supply of the target device, and read the input power and output power of the current working power supply of the target device, so as to re-issue the mode switching instruction.

[0064] Step S12: collecting current power state information corresponding to the target device during the power mode switching process, and performing deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device.

[0065] In this embodiment, the current power status information corresponding to the target device during the power mode switching process can be collected so as to construct a current power life model curve corresponding to the target device based on the collected information. Specifically, the server power status monitoring and early warning module can be used to monitor the current power status information of the target device through the server CPLD communication bus, that is, the front power temperature information, the current output voltage information, and the current output current information, and generate a timestamp verification code, and then add the timestamp verification code to the timeline of the current power status information as verification information, and then input the current power status information and the verification information into the deep learning module, that is, the server power life model deep learning module.

[0066] After receiving the current power status information and the verification information, the server power life model deep learning module will verify the current power status information according to the verification information, and generate the current power life model curve corresponding to the target device based on the current power status information after the verification is passed. Specifically, it is necessary to determine the output voltage during the power mode switching process according to the current output voltage information in the current power status information. It should be noted that the process of power mode switching of the server device is similar to the process of 50% load jump. The lower limit specification value of the output voltage of the server power supply during the mode switching process is set to 11.6V and the upper limit specification value is set to 12.8V. Furthermore, it is necessary to determine the average current sharing and instantaneous current sharing during the power mode switching process according to the current output current information in the target power status information, wherein the average current sharing of the power supply should be less than 5%, and the instantaneous current sharing should be less than 50%, and the calculation formula is as follows: current sharing = (PSU0 output current - average value of PSU0 and PSU1 output currents) / average value of PSU0 and PSU1 output currents. Then, the current power life model curve corresponding to the target device can be generated according to the current power status information. In this way, the power supply life model curve can be constructed based on the data collected in real time, thereby improving the accuracy of power supply early warning.

[0067] Step S13: Analyze the current power state information based on the current power life model curve to determine a power life evaluation value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life evaluation value.

[0068] In this embodiment, it is necessary to analyze the current power state information according to the current power life model curve to determine the power life evaluation value corresponding to the target device. Specifically, it is necessary to determine the power life limit interval of the target device based on the current power life model curve, and then calculate the sum of the output voltage at each moment in the output voltage and the product of the preset influencing parameter to obtain the output voltage life impact value. Specifically, according to the previous power life model curve, the power life evaluation value of the server device power supply can be within the range of 0 to 1, and the power life evaluation value is specified. The power supply within the range of 0 to 0.9 can be used normally, and the power supply with a power supply life assessment value within the range of 0.9 to 1 requires early warning processing. In addition, the rated design output of the server power supply is 12.2V. Taking 12.2V as the midpoint, 11.6V and 12.2V are divided into 100 parts as the lower limit range, and the preset impact parameter of each part is 0.01. The preset impact parameter corresponding to 11.6V is 1; 12.2V and 12.8V are divided into 100 parts as the upper limit range, and the preset impact parameter of each part is 0.01. The preset impact parameter corresponding to 12.8V is 1.

[0069] Furthermore, it is necessary to calculate the sum of the products of the average average current at each moment in the average average current and the preset influencing parameter to obtain the average average current life impact value, where the average average current of the server power supply is 0% and 5% as the judgment interval and is divided into 100 parts. The preset influencing parameter of each part is 0.01, and the preset influencing parameter corresponding to the average average current of 5% is 1.

[0070] Next, it is necessary to calculate the sum of the products of the instantaneous average current and the preset influencing parameter at each moment in the instantaneous average current to obtain the instantaneous average current life impact value. The instantaneous average current of the server power supply is 0% and 50% as the judgment interval and divided into 100 parts. The preset influencing parameter of each part is 0.01, and the preset influencing parameter corresponding to the average average current of 50% is 1.

[0071] Finally, it is necessary to calculate the power supply life assessment value corresponding to the power supply of the target device based on the calculated output voltage life impact value, average average current life impact value and instantaneous average current life impact value. Specifically, it is necessary to assign corresponding weights to the output voltage life impact value, average average current life impact value and instantaneous average current life impact value respectively. The weight corresponding to the output voltage life impact value is 0.4, the weight corresponding to the average average current life impact value is 0.3, and the weight corresponding to the instantaneous average current life impact value is 0.3. Then calculate the power supply life assessment value according to the power supply life assessment value calculation formula, and the formula is as follows: Power supply life assessment value = voltage life impact value * 0.4 + average average current life impact value * 0.3 + instantaneous average current life impact value * 0.3. If the power supply life assessment value is in the range of 0.9 to 1, a warning process is performed.

[0072] It should be noted that if it is confirmed that early warning processing is needed, power warning information is generated and transmitted to the front-end visualization page of the power warning system so that the early warning can be displayed through the front-end visualization page. In addition, since the power life model curve is constructed based on the power information collected in real time, the accuracy and reliability of the power warning are effectively improved, and the problem of deviation in the data displayed on the front-end visualization interface is also effectively solved.

[0073] In this embodiment, it is first necessary to filter out the target device with the highest power consumption among several local devices, switch the power mode of the target device, and then collect the real-time power status information of the target device during the power mode switching process, and build a power life model curve based on the collected power status information, and finally determine the current power life evaluation value of the target device according to the power model life curve, and perform a power warning based on the power life evaluation value. In this way, the power status information during the power mode switching process can be collected, and a power life model curve can be built according to the collected power status information, and then the power life evaluation value can be determined according to the constructed power life model curve, and then it is determined whether to perform a power warning based on the obtained power life evaluation value. Since the warning analysis is performed based on the data collected in real time during the power mode switching process, the accuracy of the power warning is effectively improved, thereby avoiding the situation where power operations are performed due to the instability of the current power state, thereby causing accidents.

[0074] See also Figure 2 As shown, the present application discloses a power supply early warning system, comprising:

[0075] like Figure 2 As shown, after the server node, that is, the server equipment is powered on, the server power life deep learning and early warning system configured on the computer room control machine receives and passes the networking request of the server equipment, and the server power life deep learning and early warning system are respectively interconnected with the server power state monitoring and early warning module and the server power life model deep learning module configured on the server equipment, and the server power state monitoring and early warning module configured on the server equipment is interconnected with the server power main and standby mode switching intelligent control module. After the server power life deep learning and early warning system is successfully interconnected with each module, the server power life deep learning and early warning system starts to work.

[0076] During the debugging phase after the server is installed on the shelf in the computer room, the operation and maintenance personnel need to issue the server power life deep learning and early warning system startup command in the visual interface. After the server power life deep learning and early warning system is started, the server power status monitoring and early warning module is used to monitor the power status of the server equipment in real time and prepare for early warning. Before the server power life model deep learning module performs power life curve training and learning, the server power status monitoring and early warning module first issues a power mode switching command to the server power status monitoring and early warning module. The server power status monitoring and early warning module receives the command and issues a power master-slave mode switching command to the server power master-slave mode switching intelligent control module. The server power master-slave mode switching intelligent control module switches the server according to the power life model training plan conveyed by the server power life model deep learning module through the server power status monitoring and early warning module. The power supply of the server equipment performs intelligent switching of the active and standby modes; during the intelligent switching of the server power active and standby modes according to the power life model training plan, the server power status monitoring and early warning module obtains the power status information in real time during the intelligent switching of the server power active and standby modes, and promptly transmits it to the server power life model deep learning module through the CPLD communication bus; the server power life model deep learning module receives the power status information of the active and standby mode intelligent switching process fed back by the server power status monitoring and early warning module in real time, automatically trains and deeply learns the power life of the server equipment during the switching of its power active and standby modes, automatically fits the server power life model curve, and uploads it to the server power life deep learning, early warning system visualization interface repository and the server power status monitoring and early warning module repository for archiving and backup. In addition, when the server power mode is switched, the server power life deep learning and early warning system monitors the power supply in the active-standby mode switching in real time through the server power status monitoring and early warning module, and brings the monitored power status information into the server power life model curve fitted by the server power life model deep learning module during the server on-shelf debugging phase in the computer room for calculation and analysis. The server power status monitoring and early warning module identifies and locates the power supply that exceeds the limit of the server power life model curve and conveys the power life limit warning information to the server power life deep learning and early warning system. The computer room operation and maintenance personnel can view the server power warning information in real time during the active-standby switching process of the server power in the computer room through the mobile terminal visualization interface, so as to quickly locate the warning power supply problem and deal with it in time.

[0077] See also Figure 3 As shown, the embodiment of the present application discloses a power supply early warning device, including:

[0078] A mode switching module 11 is used to select a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device;

[0079] A curve construction module 12 is used to collect current power state information corresponding to the target device during the power mode switching process, and perform deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device;

[0080] The life warning module 13 is used to analyze the current power state information based on the current power life model curve to determine the power life evaluation value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life evaluation value.

[0081] In this embodiment, it is first necessary to screen out the target device with the highest current power consumption among several local devices, and switch the power mode of the target device; then collect the current power status information corresponding to the target device during the power mode switching process, and perform deep learning based on the current power status information to obtain the current power life model curve corresponding to the target device; finally, analyze the current power status information based on the current power life model curve to determine the power life evaluation value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life evaluation value. It can be seen that the method of this application needs to switch the power mode of the target device after screening out the target device with the highest current power consumption among several local devices, and then collect the real-time power status information of the target device during the power mode switching process, and construct a power life model curve based on the collected power status information, and finally determine the current power life evaluation value of the target device according to the power model life curve, and perform a power warning based on the power life evaluation value. In this way, the power status information during the power mode switching process can be collected, and a power life model curve can be constructed based on the collected power status information. Then, the power life assessment value can be determined based on the constructed power life model curve, and then whether to issue a power warning can be determined based on the obtained power life assessment value. Since the warning analysis is performed based on the data collected in real time during the power mode switching process, the accuracy of the power warning is effectively improved, thereby avoiding power operations due to unstable current power status, which may lead to accidents.

[0082] In some embodiments, the mode switching module 11 may specifically include:

[0083] A device determination submodule, configured to count the input power consumption of a plurality of local devices, so as to determine a target device with the highest current power consumption among the plurality of devices based on the input power consumption;

[0084] A first mode switching submodule, used for issuing a power mode switching instruction to switch the power mode of each power supply of the target device, and reading the input power and output power of the current working power supply of the target device;

[0085] A second mode switching submodule, configured to switch the power mode of the current working power supply to the working state, enable each power supply corresponding to the target device, and then set the input power to zero if the current working power supply is in the standby state and the output power is greater than a preset output power threshold;

[0086] The step jump submodule is used to jump to the step of issuing the power mode switching instruction to switch the power mode of each power supply of the target device, and read the input power and output power of the current working power supply of the target device if a mode switching failure occurs during the power mode switching process corresponding to the power mode switching instruction.

[0087] In some embodiments, the first mode switching submodule may specifically include:

[0088] a switching plan execution unit, configured to sequentially execute corresponding power switching plans based on the first power mode switching instruction, the second power mode switching instruction, the third power mode switching instruction, and the fourth power mode switching instruction issued sequentially, so as to switch the power modes of the respective power supplies of the target device;

[0089] The first power mode switching instruction is used to switch the first power supply of the target device to a working state and the second power supply to a standby state, and to record the first input power and the first output power of the first power supply and the second power supply respectively;

[0090] The second power mode switching instruction is used to switch both the first power supply and the second power supply to a working state, and to record the second input power and the second output power of the first power supply and the second power supply respectively;

[0091] The third power mode switching instruction is used to switch the first power supply to a standby state and the second power supply to a working state, and to record a third input power and a third output power of the first power supply and the second power supply respectively;

[0092] The fourth power mode switching instruction is used to switch the first power supply and the second power supply to the working state again, and respectively record the fourth input power and the fourth output power of the first power supply and the second power supply.

[0093] In some embodiments, the curve construction module 12 may specifically include:

[0094] A data acquisition submodule, used to generate a timestamp check code and collect current power state information corresponding to the target device during the power mode switching process; the current power state information includes current power temperature information, current output voltage information, and current output current information corresponding to the target device;

[0095] A verification information confirmation submodule, used to use the timestamp check code as verification information of the current power state information;

[0096] A curve generation submodule is used to input the current power status information and the verification information into a deep learning module, so that the deep learning module verifies the current power status information based on the verification information, and generates a current power life model curve corresponding to the target device based on the current power status information after the verification is passed.

[0097] In some embodiments, the curve generation submodule may specifically include:

[0098] an information determination unit, configured to determine the output voltage during the power mode switching process according to the current output voltage information in the current power state information, and to determine the average current sharing degree and the instantaneous current sharing degree during the power mode switching process according to the current output current information in the target power state information;

[0099] A curve construction unit is used to construct a current power supply life model curve corresponding to the target device based on the output voltage, the average current distribution and the instantaneous current distribution.

[0100] In some embodiments, the life warning module 13 may specifically include:

[0101] A power life interval determination unit, configured to determine a power life limit interval of the target device based on the current power life model curve;

[0102] A first impact value calculation unit, used for calculating the sum of the output voltage at each moment in the output voltage multiplied by a preset impact parameter, so as to obtain an output voltage life impact value;

[0103] A second influence value calculation unit is used to calculate the sum of the average average flow at each moment in the average average flow and the product of the preset influence parameter to obtain the average average flow life influence value;

[0104] A third influence value calculation unit, used to calculate the sum of the products of the instantaneous average flow at each moment in the instantaneous average flow and a preset influence parameter, so as to obtain the instantaneous average flow life influence value;

[0105] A weight allocation unit, configured to allocate corresponding weight values ​​to the output voltage lifetime impact value, the average average current lifetime impact value, and the instantaneous average current lifetime impact value based on the preset weight corresponding to the target device;

[0106] a power supply life evaluation value calculation unit, configured to perform weighted summation on the output voltage life impact value, the average average current life impact value, and the instantaneous average current life impact value based on the weight value, and determine the weighted summation result as the power supply life evaluation value corresponding to the power supply of the target device;

[0107] The power warning unit is used to determine whether the power life evaluation value is within the power life limit interval, and if the power life evaluation value is within the power life limit interval, generate power warning information to perform power warning.

[0108] In some embodiments, the life warning module 13 may specifically include:

[0109] A warning information display unit is used to determine whether to generate power warning information based on the power life evaluation value, and if so, generate power warning information for the target device, and transmit the power warning information to the front-end visualization page of the power warning system so as to display the warning through the front-end visualization page.

[0110] Furthermore, the present application also discloses an electronic device. Figure 4 It is a structural diagram of an electronic device according to an exemplary embodiment, and the content in the figure cannot be regarded as any limitation on the scope of use of this application. The electronic device may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input and output interface 25 and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the power warning method disclosed in any of the aforementioned embodiments. In addition, the electronic device in this embodiment may specifically be an electronic computer.

[0111] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0112] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0113] The operating system 221 is used to manage and control various hardware devices on the electronic device and the computer program 222, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the power warning method performed by the electronic device disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0114] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the power warning method disclosed above. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, and will not be repeated here.

[0115] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0116] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0118] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0119] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A power supply early warning method, characterized in that: include: Filter out a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device; Collecting current power state information corresponding to the target device during the power mode switching process, and performing deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device; The current power state information is analyzed based on the current power life model curve to determine a power life evaluation value corresponding to the target device, and based on the power life evaluation value, it is determined whether to generate power warning information for power warning.

2. The power supply early warning method according to claim 1, characterized in that: The step of selecting a target device with the highest current power consumption from among a plurality of local devices and switching the power mode of the target device includes: Counting the input power consumption of a plurality of local devices, so as to determine a target device having the highest current power consumption among the plurality of devices based on the input power consumption; Sending a power mode switching instruction to switch the power mode of each power supply of the target device, and reading the input power and output power of the current working power supply of the target device; If the current working power supply is in a standby state and the output power is greater than a preset output power threshold, the power mode of the current working power supply is switched to a working state, and each power supply corresponding to the target device is enabled, and then the input power is set to zero; If a mode switching failure occurs during the power mode switching process corresponding to the power mode switching instruction, jump to the step of issuing the power mode switching instruction to switch the power modes of each power supply of the target device, and read the input power and output power of the current working power supply of the target device.

3. The power supply early warning method according to claim 2, characterized in that: The issuing of a power mode switching instruction to switch the power mode of each power source of the target device includes: Based on the first power mode switching instruction, the second power mode switching instruction, the third power mode switching instruction and the fourth power mode switching instruction issued in sequence, the corresponding power switching plans are executed in sequence to switch the power modes of the respective power supplies of the target device; The first power mode switching instruction is used to switch the first power supply of the target device to a working state and the second power supply to a standby state, and to record the first input power and the first output power of the first power supply and the second power supply respectively; The second power mode switching instruction is used to switch both the first power supply and the second power supply to a working state, and to record the second input power and the second output power of the first power supply and the second power supply respectively; The third power mode switching instruction is used to switch the first power supply to a standby state and the second power supply to a working state, and to record a third input power and a third output power of the first power supply and the second power supply respectively; The fourth power mode switching instruction is used to switch the first power supply and the second power supply to the working state again, and respectively record the fourth input power and the fourth output power of the first power supply and the second power supply.

4. The power supply early warning method according to claim 1, characterized in that: The collecting of current power state information corresponding to the target device during the power mode switching process, and performing deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device, includes: Generate a timestamp check code, and collect current power state information corresponding to the target device during the power mode switching process; the current power state information includes current power temperature information, current output voltage information, and current output current information corresponding to the target device; Using the timestamp check code as verification information of the current power state information; The current power status information and the verification information are input into a deep learning module so that the deep learning module verifies the current power status information based on the verification information, and generates a current power life model curve corresponding to the target device based on the current power status information after the verification is passed.

5. The power supply early warning method according to claim 4, characterized in that: The generating a current power life model curve corresponding to the target device based on the current power state information includes: Determine the output voltage during the power mode switching process according to the current output voltage information in the current power state information, and determine the average current sharing and the instantaneous current sharing during the power mode switching process according to the current output current information in the target power state information; A current power supply life model curve corresponding to the target device is constructed based on the output voltage, the average current sharing and the instantaneous current sharing.

6. The power supply early warning method according to claim 5, characterized in that: The analyzing the current power state information based on the current power life model curve to determine a power life evaluation value corresponding to the target device, and determining whether to generate power warning information for power warning based on the power life evaluation value, includes: Determine a power life limit interval of the target device based on the current power life model curve; Calculating the sum of the output voltage at each moment in the output voltage multiplied by the preset influencing parameter to obtain the output voltage life influencing value; Calculate the sum of the average average flow rate at each moment in the average average flow rate and the product of the preset influencing parameter to obtain the average average flow rate life influence value; Calculating the sum of the product of the instantaneous average flow at each moment in the instantaneous average flow and the preset influence parameter to obtain the instantaneous average flow life influence value; Based on the preset weights corresponding to the target devices, corresponding weight values ​​are respectively assigned to the output voltage lifetime impact value, the average average current lifetime impact value, and the instantaneous average current lifetime impact value; Based on the weight value, weighted sum of the output voltage life impact value, the average average current life impact value and the instantaneous average current life impact value is performed, and the weighted sum result is determined as the power supply life assessment value corresponding to the power supply of the target device; It is determined whether the power life evaluation value is within the power life limit interval. If the power life evaluation value is within the power life limit interval, power warning information is generated to perform a power warning.

7. The power supply early warning method according to any one of claims 1 to 6, characterized in that: The determining whether to generate power warning information to perform power warning based on the power life evaluation value includes: Based on the power life evaluation value, determine whether to generate power warning information. If so, generate power warning information for the target device, and transmit the power warning information to the front-end visualization page of the power warning system so as to display the warning through the front-end visualization page.

8. A power supply early warning device, characterized in that: include: A mode switching module is used to filter out a target device with the highest current power consumption among a number of local devices, and switch the power mode of the target device; A curve construction module, used to collect current power state information corresponding to the target device during the power mode switching process, and perform deep learning based on the current power state information to obtain a current power life model curve corresponding to the target device; The life warning module is used to analyze the current power status information based on the current power life model curve to determine the power life evaluation value corresponding to the target device, and determine whether to generate power warning information for power warning based on the power life evaluation value.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the steps of the power early warning method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power supply early warning method according to any one of claims 1 to 7 are implemented.

Images