Temperature management method and device, electronic equipment and medium

Abstract

The invention provides a temperature management method and device, electronic equipment and a medium, belongs to the technical field of temperature management, and aims to solve the problem that a power supply management method in the related technology can cause server power supply explosion. The method comprises the following steps: collecting a target power supply temperature of a target server power supply; performing temperature anomaly prediction on the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the abnormal prediction result at least comprises the temperature rise rate of the target power supply temperature in the target unit time; and under the condition that the abnormal prediction result triggers an advanced protection condition, executing a protection strategy.

Description

Technical Field

[0001] The present disclosure relates to the field of temperature management technology, and in particular to a temperature management method, device, electronic equipment and medium. Background Art

[0002] Server systems have increasingly higher requirements for the power density of server power supplies. As the power density increases, the internal heat of the server power supply will become more serious. In related technologies, when the ambient temperature or hot spot temperature is too high, the server power supply will trigger OTP (Over-Temperature Protection), which will shut down the server power supply.

[0003] However, in the related art, the server power supply will only perform protection operations when the OTP is triggered, such as the system switching the power supply, without any early warning and intervention mechanism. Therefore, when the server power supply works abnormally and the temperature rises abnormally and rapidly, once the OTP delay time is too long, the server power supply is at risk of exploding. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a temperature management method, device, electronic device and medium. The technical solution of the present disclosure is as follows: According to a first aspect of an embodiment of the present disclosure, there is provided a temperature management method, including: Collect target power supply temperature of target server power supply; Performing temperature anomaly prediction on the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the anomaly prediction result at least includes a temperature rise rate of the target power supply temperature in a target unit time; When the abnormal prediction result triggers an advance protection condition, a protection strategy is executed.

[0005] Optionally, the temperature rise rate of the target power supply temperature in a target unit time is determined according to the following steps, including: Obtaining the preset target unit time; Determine a first acquisition timestamp; the first acquisition timestamp represents a timestamp corresponding to the most recent acquisition of the target power supply temperature; determine the target power supply temperature corresponding to the first acquisition timestamp as a first target power supply temperature; Determine a second acquisition timestamp that is separated from the first acquisition timestamp by the target unit time; the second acquisition timestamp is earlier than the first acquisition timestamp; determine the target power supply temperature corresponding to the second acquisition timestamp as the second target power supply temperature; determining a target difference between the first target power supply temperature and the second target power supply temperature; The temperature rise rate of the target power supply temperature in a target unit time is determined according to the target difference.

[0006] Optionally, the abnormal prediction result further includes a current sharing working condition of the target server power supply; and when the abnormal prediction result triggers an advance protection condition, executing a protection strategy includes: When it is determined that the temperature of the target server power supply rises abnormally through the temperature rise rate of the target power supply temperature in the target unit time, executing a protection strategy; and / or, When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not working in current sharing, a protection strategy is executed.

[0007] Optionally, when it is determined that the temperature of the target server power supply rises abnormally through the temperature rise rate of the target power supply temperature in a target unit time, executing the protection strategy includes: Determining, according to the target power supply temperature, a temperature rise rate of the target power supply temperature corresponding to the target server power supply in a target unit time; When the temperature increase rate is positive and the temperature increase rate is greater than or equal to the change rate threshold, determining that the temperature of the target server power supply has increased abnormally, and shutting down the target server power supply; The power supply system includes a plurality of server power supplies. When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not in current sharing working condition, a protection strategy is executed, including: Determine a real-time temperature difference between the target power supply temperature and the average temperature of each server power supply in the power supply system; the real-time temperature difference represents the current sharing working condition of the target server power supply; Obtain one or more alarm temperature difference thresholds and a fault temperature difference threshold; the value corresponding to the fault temperature difference threshold is greater than any of the alarm temperature difference thresholds; When the real-time temperature difference is greater than or equal to any of the alarm temperature difference thresholds, and the real-time temperature difference is less than the fault temperature difference threshold, the current sharing working condition of the target server power supply is reported to the system, and a current sharing alarm is issued; When the real-time temperature difference is greater than or equal to the fault temperature difference threshold, it is determined that the target server power supply is not in current sharing operation, and it is determined that the target server power supply is abnormal, and the target server power supply is turned off.

[0008] Optionally, it also includes: adjusting the fan speed of the fan corresponding to the server power supply according to the target power supply temperature; or, When the target power supply temperature triggers over-temperature protection, the target server power supply is turned off.

[0009] Optionally, the power supply system includes one or more running server power supplies and a standby power supply in a standby state, and after shutting down the target server power supply, further includes: Enable the backup power supply, and replace and troubleshoot the target server power supply.

[0010] Optionally, the temperature target power source includes: any one of: a primary side ambient temperature, a primary side hotspot temperature, a secondary side ambient temperature, and a secondary side hotspot temperature; The collecting of the target power supply temperature corresponding to the target server power supply includes: The primary side ambient temperature and the primary side hot spot temperature of the target server power supply are collected from the input side of the target server power supply; the primary side ambient temperature is the ambient temperature collected from the input side of the target server power supply, and the primary side hot spot temperature is the heating temperature collected from the most seriously heated position on the input side; The secondary side ambient temperature and the secondary side hot spot temperature of the target server power supply are collected from the output side of the target server power supply; the secondary side ambient temperature is the ambient temperature collected from the output side of the target server power supply, and the secondary side hot spot temperature is the heating temperature collected from the most seriously heated position on the output side.

[0011] According to a second aspect of an embodiment of the present disclosure, there is provided a temperature management device, comprising: A collection module, used for collecting a target power supply temperature of a target server power supply; A determination module, configured to predict temperature anomalies of the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the anomaly prediction result at least includes a temperature rise rate of the target power supply temperature in a target unit time; The execution module is used to execute the protection strategy when the abnormal prediction result triggers the advance protection condition.

[0012] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the temperature management method described in the first aspect are implemented.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the temperature management method described in the first aspect are implemented.

[0014] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the temperature management method described in the first aspect are implemented.

[0015] The present disclosure collects temperature data of the target server power supply in real time and performs abnormal prediction, which can identify potential overheating risks before the actual temperature reaches a dangerous level, and enable the system to take action before the problem becomes serious, thereby reducing the risk of server power supply explosion. By predicting temperature anomalies in advance and executing protection strategies before expected problems occur, the response delay of OTP can be effectively reduced, thereby preventing hardware damage caused by overheating. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the description of the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 is a schematic diagram of steps of a temperature management method shown in an embodiment of the present disclosure; Figure 2 is a schematic diagram of temperature collection shown in an embodiment of the present disclosure; Figure 3 is a temperature management flow chart shown in an embodiment of the present disclosure; Figure 4 is a temperature management flow chart shown in an embodiment of the present disclosure; Figure 5 is a schematic diagram of temperature management shown in an embodiment of the present disclosure; Figure 6 is a block diagram of a temperature management device shown in an embodiment of the present disclosure; Figure 7 It is a schematic diagram of an electronic device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0019] The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0020] With the rapid development of data centers, the demand for servers in data centers is also increasing. Server systems are also requiring higher power density from server power supplies. As power density increases, the heat inside the server power supply will become more serious.

[0021] In the related technology, the ambient temperature and hotspot temperature of the PFC side and DCDC side of the server power supply are detected. Once the ambient temperature or hotspot temperature changes, the server power supply system will control the fan speed in combination with the load conditions; when the ambient temperature or hotspot temperature is too high, the server power supply will have OTP. OTP is a safety mechanism that automatically cuts off the power supply when the temperature of the power supply or other components exceeds the safety threshold to prevent further damage or more serious consequences. This mechanism is usually used as a last resort protection measure rather than a preventive measure.

[0022] There is no mechanism for early warning and intervention of power supply temperature anomalies in the relevant technology. The system will only respond when the temperature anomaly reaches the threshold that triggers OTP, but this response is passive and often catastrophic, that is, the power supply is cut off.

[0023] However, when the server power supply works abnormally and the temperature rises abnormally and rapidly, if the delay time of OTP is too long, the server power supply is at risk of explosion. For example: in a server system with N+1 redundant power supply design, when the temperature of a server power supply rises abnormally, in the existing design, unless OTP occurs, the system will switch the power supply, otherwise the system will not take any pre-predictive action.

[0024] In order to solve the above technical problems, the present disclosure proposes a temperature management method, which can execute a corresponding protection strategy when an abnormal temperature rise is found before OTP.

[0025] Figure 1 Schematic diagram of a temperature management method according to an embodiment of the present disclosure. Figure 1 As shown, the temperature management method may include the following steps: Step S11: collecting the target power supply temperature of the target server power supply; Temperature sensors can be installed at key locations of the server power supply to monitor the temperature inside the power supply in real time. Temperature data can be collected regularly or continuously and transmitted to the monitoring system. The collected data can be cleaned to remove noise and outliers to ensure data accuracy.

[0026] Step S12: performing temperature anomaly prediction on the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the anomaly prediction result at least includes a temperature rise rate of the target power supply temperature in a target unit time; You can use machine learning or statistical models to analyze temperature data to predict future temperature trends and possible anomalies. The model may be time series analysis, regression analysis, etc. Set temperature thresholds based on the prediction model to identify possible abnormal conditions, such as the rate of temperature increase or abnormal fluctuations in historical data.

[0027] The abnormal prediction result at least includes the temperature rise rate of the target power supply temperature in the target unit time, and whether the target server has an abnormal temperature rise phenomenon can be determined by the temperature rise rate of the target power supply temperature in the target unit time.

[0028] Step S13: When the abnormal prediction result triggers an advance protection condition, a protection strategy is executed.

[0029] Monitor the prediction results in real time, and automatically start the protection measures when the prediction data triggers the advance protection conditions. The protection measures can include cooling measures, load adjustment, alarms, and shutdowns. Cooling measures can reduce the temperature by adjusting the system fan speed or starting additional cooling devices. Load adjustment can reduce power consumption to reduce heat by reducing the power load, shutting down certain non-critical services, and reducing power consumption. Alarms can send alerts or notifications to system administrators for manual intervention or further investigation. Shutdown can turn off the server power supply in extreme cases to prevent damage to the server power supply.

[0030] The server power supply corresponds to four temperature types, including primary side ambient temperature, primary side hot spot temperature, secondary side ambient temperature, and secondary side hot spot temperature. The four temperature types are managed separately. When any temperature type is predicted to be abnormal, the protection strategy is executed.

[0031] By adopting the embodiments of the present disclosure, by predicting future temperature anomalies, measures can be taken before overheat protection occurs, reducing the impact on system stability. Through real-time monitoring and prediction, power failure due to overheating can be more effectively prevented, thereby improving the reliability of the system. The dynamic adjustment of the protection strategy enables the system to respond adaptively according to real-time data, improving the accuracy and efficiency of protection measures. By predicting temperature anomalies in advance, the response delay of OTP can be effectively reduced, thereby preventing hardware damage caused by overheating.

[0032] Among them, in an optional embodiment, the temperature target power supply includes: any one of the primary side ambient temperature, the primary side hotspot temperature, the secondary side ambient temperature and the secondary side hotspot temperature; the target power supply temperature corresponding to the target server power supply is collected, including: collecting the primary side ambient temperature and the primary side hotspot temperature of the target server power supply from the input side of the target server power supply; the primary side ambient temperature is the ambient temperature collected from the input side of the target server power supply, and the primary side hotspot temperature is the heating temperature collected from the most seriously heated position on the input side; the secondary side ambient temperature and the secondary side hotspot temperature of the target server power supply are collected from the output side of the target server power supply; the secondary side ambient temperature is the ambient temperature collected from the output side of the target server power supply, and the secondary side hotspot temperature is the heating temperature collected from the most seriously heated position on the output side.

[0033] Figure 2 This is a schematic diagram of temperature collection shown in an embodiment of the present disclosure. Figure 2 As shown, in the existing server power system design, it is an important safety measure to detect the ambient temperature and hot spot temperature of the PFC side (Power Factor Correction Side) and the DCDC side (Direct Current-to-Direct Current Converter Side). The primary side ambient temperature and the primary side hot spot temperature are collected from the PFC side; the secondary side ambient temperature and the secondary side hot spot temperature are collected from the DCDC side. The control signals of the PFC side and the DCDC side are controlled by DSP (Digital Signal Processor) 1 and DSP2 respectively. Once a fault such as OTP occurs on one side and the entire server power supply needs to be controlled to stop working, DSP1 and DSP2 communicate through UART (Universal Asynchronous Receiver / Transmitter) to achieve synchronous shutdown control of the PFC side and the DCDC side.

[0034] The temperature management method is for a target power supply temperature of any temperature type, including a primary side ambient temperature, a primary side hot spot temperature, a secondary side ambient temperature, and a secondary side hot spot temperature.

[0035] Use a temperature sensor installed in the environment area on the power input side of the target server. Read the temperature sensor data regularly or in real time and record it as the primary side environment temperature.

[0036] Identify the location where the input side heats the most, which can be determined by thermal imaging or empirical judgment. Read the data of this sensor in real time or regularly and record it as the primary side hot spot temperature. Read the data of this sensor in real time or regularly and record it as the primary side hot spot temperature.

[0037] Install a temperature sensor in the environment area on the output side of the target server power supply. Read the data from the temperature sensor in real time or periodically and record it as the secondary side environment temperature.

[0038] Identify the location where the output side is most heated. Install a high-precision temperature sensor at this location. Read the temperature sensor data in real time or periodically and record it as the secondary side hot spot temperature.

[0039] By adopting the embodiments of the present disclosure, comprehensive and accurate monitoring of the target server power supply temperature can be achieved by collecting data at different positions (input side and output side) and different types of temperatures (ambient temperature and hot spot temperature) of the power supply. The collection of hot spot temperature helps to timely discover local overheating problems inside the power supply and provide early warning to prevent equipment damage. Real-time monitoring of the power supply temperature and taking measures such as adjusting the fan speed and shutting down the overheated power supply when necessary can effectively reduce the risk of system instability caused by overheating of the power supply. By analyzing the temperature data at different positions, the effectiveness of the current heat dissipation design can be evaluated and data support can be provided for subsequent optimization.

[0040] Among them, in an optional embodiment, the temperature rise rate of the target power supply temperature in the target unit time is determined according to the following steps, including: obtaining the preset target unit time; determining a first acquisition timestamp; the first acquisition timestamp represents the timestamp corresponding to the most recent acquisition of the target power supply temperature; determining the target power supply temperature corresponding to the first acquisition timestamp as the first target power supply temperature; determining a second acquisition timestamp that is separated from the first acquisition timestamp by the target unit time; the second acquisition timestamp is earlier than the first acquisition timestamp; determining the target power supply temperature corresponding to the second acquisition timestamp as the second target power supply temperature; determining a target difference between the first target power supply temperature and the second target power supply temperature; and determining the temperature rise rate of the target power supply temperature in the target unit time through the target difference.

[0041] The target unit time can be pre-configured, such as every minute or every hour. Query the log or real-time data of the temperature acquisition system to find the timestamp of the most recent target power supply temperature acquisition, and ensure that the latest temperature data is used as the calculation basis. According to the first acquisition timestamp, retrieve the corresponding temperature value from the temperature database as the first target power supply temperature. Trace back the target unit time from the first acquisition timestamp to calculate the second acquisition timestamp. Use the second acquisition timestamp to retrieve the corresponding temperature value from the temperature database as the second target power supply temperature. Calculate the difference between the first target power supply temperature and the second target power supply temperature, which directly reflects the change in the target power supply temperature between the two time points. The target difference can then be divided by the target unit time to obtain the temperature rise rate, which can quantify the rate of temperature change per unit time.

[0042] By adopting the embodiments of the present disclosure, the temperature rise rate is determined by the target unit time, which can ensure that the calculation of the temperature rise rate is based on a clear and adjustable time unit, which is convenient for flexible application in different scenarios. Based on the temperature rise rate data monitored over a long period of time, the temperature condition of the current target server power supply can be evaluated to provide data support for protective measures. The temperature rise rate of the target power supply temperature in the target unit time can provide data support for determining whether the target server power supply has an abnormal temperature rise.

[0043] Among them, in an optional embodiment, the abnormal prediction result also includes the current sharing working condition of the target server power supply; when the abnormal prediction result triggers the advance protection condition, the protection strategy is executed, including: when it is determined that the temperature of the target server power supply rises abnormally through the temperature rise rate of the target power supply temperature in the target unit time, the protection strategy is executed; and / or, when it is determined that the target server power supply is not working in current sharing through the current sharing working condition of the target server power supply, the protection strategy is executed.

[0044] You can select or train a suitable machine learning or deep learning model to predict the temperature trend of the power supply and the current sharing status. You can use historical data to train the model and continuously optimize the model parameters to improve the prediction accuracy.

[0045] Define the standard for abnormal temperature rise, such as setting a threshold or calculating the temperature rise rate exceeding a certain predetermined range. Define the standard for abnormal current sharing, such as detecting that the current output difference of each power module exceeds the preset range, indicating that the load is not balanced. Based on the prediction results, determine whether to trigger the early protection condition.

[0046] If it is predicted that the temperature will rise abnormally, the server load distribution can be automatically adjusted to reduce the load on the target server; or the cooling system can be activated, such as increasing the fan speed; in extreme cases, the server can be safely shut down to avoid hardware damage.

[0047] If abnormal current sharing is detected, try restarting the power module to restore the balanced state.

[0048] The implementation status and effects of protection strategies can be recorded to provide data support for subsequent operation, maintenance and optimization.

[0049] By adopting the embodiments of the present disclosure, hardware failures caused by power overheating or uneven load can be effectively avoided through real-time prediction and early intervention, thereby improving the stability and reliability of the server. Protective measures can be taken before a failure occurs to reduce the risk of data loss and business interruption caused by hardware damage, thereby reducing operation and maintenance costs. Through data analysis, operation and maintenance personnel can better understand the system operation status, optimize resource allocation and operation and maintenance strategies, realize automated monitoring and intelligent decision-making, reduce manual intervention, and improve operation and maintenance efficiency and accuracy.

[0050] Among them, in an optional embodiment, the fan speed of the fan corresponding to the server power supply is adjusted according to the target power supply temperature; or, when the target power supply temperature triggers over-temperature protection, the target server power supply is turned off.

[0051] Figure 3 is a temperature management flow chart shown in an embodiment of the present disclosure. Figure 3 As shown, taking DSP2 as an example, DSP2 performs temperature management on two temperature types based on the hotspot temperature sampling and ambient temperature sampling corresponding to the DCDC side; when it is detected that the hotspot temperature sampling or the ambient temperature sampling is greater than the temperature comparison point, the fan speed is adjusted; the temperature comparison points may include multiple, such as temperature comparison point 1, temperature comparison point 2 and temperature comparison point N, and the fan speed corresponding to the server power supply is adjusted by comparing the temperature of a certain temperature type with the temperature comparison point; at the same time, the hotspot temperature sampling or the ambient temperature sampling is compared with the OTP, and when the OTP is triggered, the machine, that is, the server power supply, is turned off, and if the OTP is not triggered, the operation is not performed.

[0052] The management controller corresponding to the fan determines whether the fan speed needs to be adjusted based on the preset algorithm and temperature data. The preset algorithm can include temperature thresholds, fan speed curves, or adaptive control strategies; they are set based on factors such as the server model, configuration, and heat dissipation requirements. If the temperature is within the normal range but is too high, the fan speed can be gradually increased to enhance heat dissipation.

[0053] When it is determined that the fan speed needs to be adjusted, the management controller sends a command to the fan speed controller. The fan speed controller uses PWM technology or other control methods to adjust the fan speed according to the received command. The adjusted fan speed will take effect immediately and will continue to adjust dynamically according to temperature changes.

[0054] If the target power supply temperature continues to rise and exceeds the preset over-temperature protection temperature threshold, the system will trigger the over-temperature protection mechanism. The over-temperature protection mechanism includes immediately cutting off the power output, shutting down the target server power supply, or initiating other emergency measures to prevent overheating from damaging the server system and the power supply itself. After shutting down the power supply, the system will record the relevant events and issue an alarm to notify the administrator.

[0055] By adopting the embodiments of the present disclosure, by dynamically adjusting the fan speed according to the temperature, it is possible to ensure that the server can efficiently dissipate heat while reducing energy consumption and noise. This helps to maintain the stable operation of the server and extend the life of the hardware. The over-temperature protection mechanism can quickly cut off the power supply or shut down the server when the power supply temperature rises abnormally, thereby preventing hardware damage and data loss caused by overheating. By finely controlling the fan speed and shutting down the overheated power supply in time, unnecessary energy waste and hardware loss can be avoided.

[0056] Among them, in an optional embodiment, when it is determined that the temperature of the target server power supply has risen abnormally through the temperature rise rate of the target power supply temperature in the target unit time, a protection strategy is executed, including: determining the temperature rise rate of the target power supply temperature corresponding to the target server power supply in the target unit time according to the target power supply temperature; when the temperature rise rate is positive and the temperature rise rate is greater than or equal to the change rate threshold, it is determined that the temperature of the target server power supply has risen abnormally, and the target server power supply is turned off.

[0057] Read the current temperature value from the temperature sensor of the target server power supply in real time and record the timestamp. Update the temperature data regularly (such as every second, every minute, etc.) to form time series data. Based on the time series data, you can calculate the difference between two consecutive temperature readings; you can also set a target unit time to determine the difference between the most recently collected temperature data and the temperature data collected at the target unit time interval. Calculate the temperature change within the corresponding time difference, that is, the next reading minus the previous reading; calculate the temperature change rate.

[0058] A change rate threshold is set based on the normal operating temperature of the server power supply and the maximum allowable temperature change rate, and the calculated temperature change rate is compared with the change rate threshold.

[0059] If the temperature change rate is greater than or equal to the change rate threshold, and the target power supply temperature shows an increasing trend, it is determined that the temperature of the target server power supply increases abnormally.

[0060] Before turning off the power, the data backup mechanism can be triggered to ensure the security and integrity of critical data.

[0061] By adopting the embodiments of the present disclosure, by real-time monitoring and calculating the temperature change rate, intervention can be carried out at the early stage of abnormal temperature rise to avoid hardware damage caused by continued temperature rise. Shutting down the power supply of the server with abnormal temperature rise in advance can prevent hardware failure caused by overheating and reduce the risk of data loss and business interruption. Through automated protection strategies, the need for manual intervention is reduced, and the overall reliability and stability of the server system is improved.

[0062] Among them, in an optional embodiment, the power supply system includes multiple server power supplies. When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not working in current sharing, a protection strategy is executed, including: determining the real-time temperature difference between the target power supply temperature and the average temperature of each server power supply in the power supply system; the real-time temperature difference represents the current sharing working condition of the target server power supply; obtaining one or more alarm temperature difference thresholds and a fault temperature difference threshold; the numerical value corresponding to the fault temperature difference threshold is greater than any of the alarm temperature difference thresholds; when the real-time temperature difference is greater than or equal to any of the alarm temperature difference thresholds, and the real-time temperature difference is less than the fault temperature difference threshold, the current sharing working condition of the target server power supply is reported to the system, and a current sharing alarm is issued; when the real-time temperature difference is greater than or equal to the fault temperature difference threshold, it is determined that the target server power supply is not working in current sharing, and it is determined that the target server power supply has an abnormality, and the target server power supply is turned off.

[0063] A power supply system usually has multiple running server power supplies. In theory, each server power supply works with equal current, that is, each server power supply shares an equal or similar load. If each server power supply shares an equal or similar load, the temperature generated by each server power supply is also equal or similar. Therefore, it is possible to compare the average temperature of each server power supply with the temperature of the target server power supply to determine whether the target server power supply is current-balanced.

[0064] The average temperature of all server power supplies is calculated in real time as a reference. The target power supply temperature of the target server obtained at each moment is compared with the average temperature in real time to determine the real-time temperature difference between the target power supply temperature and the average temperature. The real-time temperature difference reflects the degree of deviation between the working state of the target power supply and its ideal current sharing state, and can be used to indicate whether the target server power supply is in the current sharing working state.

[0065] A series of warning temperature difference thresholds and at least one fault temperature difference threshold can be preset. The thresholds are customized according to system specifications, environmental conditions and design redundancy.

[0066] Compare the real-time temperature difference with each temperature difference threshold. When the real-time temperature difference exceeds any alarm temperature difference threshold but does not reach the fault temperature difference threshold, the current sharing alarm is triggered and the relevant information is reported to the system management interface or log to prompt the administrator to pay attention and make corresponding adjustments. If the real-time temperature difference reaches or exceeds the fault temperature difference threshold, the system determines that the target server power supply is not only not working in current sharing, but also has a potential fault or serious overheating risk, and automatically executes protection measures, such as shutting down the power supply, to prevent further damage or affect the stability of the entire power supply system.

[0067] By adopting the embodiments of the present disclosure, through real-time monitoring and timely adjustment, it is ensured that the power supplies of each server in the power supply system are in a better load distribution state, reducing hardware failures caused by overheating or overloading. Through early warning, administrators can discover and deal with potential problems in a timely manner to avoid the expansion of failures, thereby reducing downtime and maintenance costs. This strategy allows for flexible adaptation to system requirements of different scales and configurations by adjusting thresholds and current sharing strategies when increasing or decreasing server power. Automated alarm and protection mechanisms reduce the burden on administrators, allowing them to focus more on high-level management and strategic planning of the system.

[0068] Figure 4 is a temperature management flow chart shown in an embodiment of the present disclosure. Figure 4 As shown, taking DSP2 corresponding to the target server power supply as an example, for the hotspot temperature sampling or ambient temperature sampling corresponding to DSP2, a prediction strategy is set to manage the server power supply. The following temperature management solution is applied to hotspot temperature sampling or ambient temperature sampling to obtain the temperature of the target server power supply in real time.

[0069] according to Figure 4 As shown, it can be determined whether the temperature of the target server power supply rises sharply. It can continuously determine whether the temperature rises sharply; if the temperature rises sharply, report to the system, shut down the faulty power supply and enable the backup power supply; if the temperature does not rise sharply, no operation is performed.

[0070] according to Figure 4 As shown, it can be determined whether the target server power supply is working in current sharing. Determine whether the average temperature difference between the target server power supply and each server power supply in the power supply system is greater than comparison point 1; if the average temperature difference between the target server power supply and each server power supply in the power supply system is not greater than comparison point 1, do not perform any operation; if the average temperature difference between the target server power supply and each server power supply in the power supply system is greater than comparison point 1, report a system alarm; further determine whether the average temperature difference between the target server power supply and each server power supply in the power supply system is greater than comparison point 2; if the average temperature difference between the target server power supply and each server power supply in the power supply system is not greater than comparison point 2, do not perform any operation; if the average temperature difference between the target server power supply and each server power supply in the power supply system is greater than comparison point 2, report to the system, shut down the faulty power supply and enable the backup power supply.

[0071] according to Figure 4 As shown, the fan speed can also be adjusted and the target server power supply can be judged whether OTP is triggered. The temperature of the target server power supply obtained in real time is compared with the temperature comparison point, and the fan speed is adjusted. The temperature comparison point can include multiple, such as temperature comparison point 1, temperature comparison point 2, etc. Determine whether the temperature is greater than temperature comparison point 1; when the temperature is not greater than temperature comparison point 1, the fan maintains the lowest speed; when the temperature is greater than temperature comparison point 1, continue to judge whether the temperature is greater than temperature comparison point 2; when the temperature is not greater than temperature comparison point 2, adjust the fan speed to speed 1; when the temperature is greater than temperature comparison point 2, continue to judge whether the temperature is greater than the next temperature comparison point, until it is judged whether the temperature is greater than temperature comparison point N; when the temperature is greater than temperature comparison point N, adjust the fan to the highest speed. Detect whether the temperature triggers OTP, and when OTP is triggered, turn off the target server power supply. Among them, when the corresponding operation is triggered by any temperature of hot spot temperature sampling or ambient temperature sampling, the corresponding strategy is executed.

[0072] Among them, in an optional embodiment, the power supply system includes one or more running server power supplies and a backup power supply in a standby state. After shutting down the target server power supply, it also includes: enabling the backup power supply, and replacing and troubleshooting the target server power supply.

[0073] In server systems, the power supply system is usually designed with redundancy. In this design, the system is equipped with more power supply units than are actually required for operation, that is, N+1 power supplies, where N is the number of power supplies required for normal operation and +1 is an additional backup power supply. When a power supply unit in the system fails, the backup power supply can take over seamlessly to ensure that the system continues to operate without being affected.

[0074] After all critical data and business operations have been saved and are in a safe state, turn off the power supply of the target server. After turning off the power supply of the target server, immediately enable the backup power supply to take over the power supply task. The backup power supply automatically takes over the power supply when a main power failure or power outage is detected. Confirm that the backup power supply is supplying power normally, and observe whether the server has smoothly transitioned to the backup power supply state.

[0075] After confirming that the backup power supply is supplying power normally and the server is running stably, start replacing the target server power supply. After replacing the power supply, check the faulty power supply to determine the cause of the fault, including checking whether the power module itself is damaged, whether the power line is short-circuited or broken, and whether the power plug and socket are in good contact.

[0076] By adopting the embodiments of the present disclosure, by setting up a backup power supply, the power supply task can be quickly taken over when the main power supply fails, ensuring that the server system can continue to operate stably. Timely discovery and replacement of the faulty power supply can avoid more serious consequences such as server hardware damage or data loss caused by power problems. By setting up a backup power supply and a replaceable power supply module, the power supply configuration of the server can be flexibly adjusted according to actual needs.

[0077] Figure 5 This is a temperature management schematic diagram shown in an embodiment of the present disclosure. In a redundant power supply system, under normal working conditions, there are three server power supplies in a current-balanced power supply state, referred to as PSU (Power Supply Unit, server power supply) 1, PSU2, and PSU3, and one of the server power supplies is in a standby "sleeping" state, referred to as PSU4. The three working server power supplies are monitored separately; for any server power supply, the hot spot temperature intelligent management of DSP2 of the server power supply is taken as an example.

[0078] Determine PSU2 as the current local unit, and follow Figure 5As shown, OTP is preset to 120℃; there are 3 hot spot temperature comparison points for fan speed control, which are: 75℃, 85℃, 100℃; fan maximum speed: 24000r / min; hot spot temperature rise slope comparison point: 7℃ / ms; there are 2 temperature difference comparison points between the hot spot temperature and the average hot spot temperature of the three working machines, which are: ±10℃, ±15℃. When PSU2 fails and the hot spot temperature on the secondary side rises rapidly, and the temperature rise per millisecond is greater than 7℃, the server power supply system can timely monitor the sharp rise in the hot spot temperature on the secondary side, and will promptly cut off the faulty power supply PSU2, enable the backup power supply PSU4, and report to the system. When the hot spot temperature T2 of PSU2 is higher than the average hot spot temperature of PSU1, PSU2, and PSU3 (T1+T2+T3) / 3, and the difference is greater than 10℃, it means that there is a significantly high heating condition in PSU2, and it is highly likely that a fault has occurred inside the machine or the device is damaged. When the temperature difference is greater than ±10℃, the PSU will promptly report to the server system and issue an alarm; when the temperature difference is greater than ±15℃, the PSU will quickly shut down the faulty power supply PSU2, enable the backup power supply PSU4, and report to the system; promptly replace and troubleshoot PSU2 to improve the power supply stability of the server system.

[0079] Among them, in an optional embodiment, a corresponding intelligent management method can be proposed in other voltage and current designs of the server through the temperature management method proposed in the present disclosure.

[0080] Figure 6 is a block diagram of a temperature management device shown in an embodiment of the present disclosure. Figure 6 As shown, the temperature management device includes: A collection module 610 is used to collect a target power supply temperature of a target server power supply; The determination module 620 is used to predict the temperature anomaly of the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the anomaly prediction result at least includes the temperature rise rate of the target power supply temperature in a target unit time; The execution module 630 is used to execute the protection strategy when the abnormal prediction result triggers the advance protection condition.

[0081] Optionally, the abnormal prediction result includes a temperature rise condition of the target server power supply and a current sharing working condition of the target server power supply, and the execution module is specifically used to execute: When it is determined through the temperature rise rate of the target server power supply that the temperature of the target server power supply rises abnormally, executing a protection strategy; and / or, When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not working in current sharing, a protection strategy is executed.

[0082] Optionally, the execution module is specifically used to execute: Determining a temperature change rate corresponding to the target server power supply according to the target power supply temperature; When the target power supply temperature shows an upward trend and the temperature change rate is greater than or equal to the change rate threshold, it is determined that the temperature of the target server power supply has increased abnormally, and the target server power supply is turned off.

[0083] Optionally, the power supply system includes a plurality of server power supplies, and the execution module is specifically used to execute: Determine a real-time temperature difference between the target power supply temperature and the average temperature of each server power supply in the power supply system; the real-time temperature difference represents the current sharing working condition of the target server power supply; Obtain one or more alarm temperature difference thresholds and a fault temperature difference threshold; the value corresponding to the fault temperature difference threshold is greater than any of the alarm temperature difference thresholds; When the real-time temperature difference is greater than or equal to any of the alarm temperature difference thresholds, and the real-time temperature difference is less than the fault temperature difference threshold, the current sharing working condition of the target server power supply is reported to the system, and a current sharing alarm is issued; When the real-time temperature difference is greater than or equal to the fault temperature difference threshold, it is determined that the target server power supply is not in current sharing operation, and it is determined that the target server power supply is abnormal, and the target server power supply is turned off.

[0084] Optionally, the temperature management device further includes: A regulating module, used to adjust the fan speed of the fan corresponding to the server power supply according to the target power supply temperature; or The shutdown module is used to shut down the target server power supply when the target power supply temperature triggers over-temperature protection.

[0085] Optionally, the power supply system includes one or more running server power supplies and a standby power supply in a standby state. After shutting down the target server power supply, the temperature management device further includes: The replacement module is used to enable the backup power supply and replace and check the target server power supply.

[0086] Optionally, the temperature target power supply includes: any one of the primary side ambient temperature, the primary side hot spot temperature, the secondary side ambient temperature and the secondary side hot spot temperature; the acquisition module is specifically used to execute: The collecting of the target power supply temperature corresponding to the target server power supply includes: The primary side ambient temperature and the primary side hot spot temperature of the target server power supply are collected from the input side of the target server power supply; the primary side ambient temperature is the ambient temperature collected from the input side of the target server power supply, and the primary side hot spot temperature is the heating temperature collected from the most seriously heated position on the input side; The secondary side ambient temperature and the secondary side hot spot temperature of the target server power supply are collected from the output side of the target server power supply; the secondary side ambient temperature is the ambient temperature collected from the output side of the target server power supply, and the secondary side hot spot temperature is the heating temperature collected from the most seriously heated position on the output side.

[0087] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple, and the relevant parts can be referred to the method embodiment.

[0088] The present disclosure also provides an electronic device, referring to Figure 7 , Figure 7 Schematic diagram of an electronic device shown in an embodiment of the present disclosure. Figure 7 As shown, the electronic device 700 includes: a memory 710 and a processor 720. The memory 710 and the processor 720 are connected via a bus communication. A computer program is stored in the memory 710. The computer program can be run on the processor 720 to implement the steps in the temperature management method disclosed in the embodiment of the present disclosure.

[0089] The embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the temperature management method disclosed in the embodiment of the present disclosure are implemented.

[0090] The embodiments of the present disclosure further provide a computer program product, including a computer program. When the computer program is executed by a processor, the steps in the temperature management method disclosed in the embodiments of the present disclosure are implemented.

[0091] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0092] It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, devices or computer program products. Therefore, the embodiments of the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] Although some embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present disclosure.

[0097] The temperature management method, device, electronic device and storage medium provided by the present disclosure are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present disclosure, 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 disclosure.

Claims

1. A temperature management method, characterized in that: include: Collect target power supply temperature of target server power supply; Performing temperature anomaly prediction on the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; The abnormal prediction result at least includes the temperature rise rate of the target power supply temperature in the target unit time; When the abnormal prediction result triggers an advance protection condition, a protection strategy is executed.

2. The method according to claim 1, characterized in that The temperature rise rate of the target power supply temperature in the target unit time is determined according to the following steps, including: Obtaining the preset target unit time; Determine a first acquisition timestamp; the first acquisition timestamp represents a timestamp corresponding to the most recent acquisition of the target power supply temperature; determine the target power supply temperature corresponding to the first acquisition timestamp as a first target power supply temperature; Determine a second acquisition timestamp separated from the first acquisition timestamp by the target unit time; the second acquisition timestamp is earlier than the first acquisition timestamp; determine the target power supply temperature corresponding to the second acquisition timestamp as the second target power supply temperature; determining a target difference between the first target power supply temperature and the second target power supply temperature; The temperature rise rate of the target power supply temperature in a target unit time is determined according to the target difference.

3. The method according to claim 1, characterized in that The abnormal prediction result also includes the current sharing working condition of the target server power supply; when the abnormal prediction result triggers the advance protection condition, executing the protection strategy includes: When it is determined that the temperature of the target server power supply rises abnormally through the temperature rise rate of the target power supply temperature in the target unit time, executing a protection strategy; and / or, When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not working in current sharing, a protection strategy is executed.

4. The method according to claim 3, characterized in that The method of executing a protection strategy when it is determined that the temperature of the target server power supply rises abnormally according to the temperature rise rate of the target power supply temperature in the target unit time includes: Determining, according to the target power supply temperature, a temperature rise rate of the target power supply temperature corresponding to the target server power supply in a target unit time; When the temperature increase rate is positive and the temperature increase rate is greater than or equal to the change rate threshold, determining that the temperature of the target server power supply has increased abnormally, and shutting down the target server power supply; The power supply system includes a plurality of server power supplies. When it is determined through the current sharing working condition of the target server power supply that the target server power supply is not in current sharing working condition, a protection strategy is executed, including: Determine a real-time temperature difference between the target power supply temperature and the average temperature of each server power supply in the power supply system; the real-time temperature difference represents the current sharing working condition of the target server power supply; Obtain one or more alarm temperature difference thresholds and a fault temperature difference threshold; the value corresponding to the fault temperature difference threshold is greater than any of the alarm temperature difference thresholds; When the real-time temperature difference is greater than or equal to any of the alarm temperature difference thresholds, and the real-time temperature difference is less than the fault temperature difference threshold, the current sharing working condition of the target server power supply is reported to the system, and a current sharing alarm is issued; When the real-time temperature difference is greater than or equal to the fault temperature difference threshold, it is determined that the target server power supply is not in current sharing operation, and it is determined that the target server power supply is abnormal, and the target server power supply is turned off.

5. The method according to claim 1, characterized in that Also includes: adjusting the fan speed of the fan corresponding to the server power supply according to the target power supply temperature; or, When the target power supply temperature triggers over-temperature protection, the target server power supply is turned off.

6. The method according to any one of claims 3 to 5, characterized in that: The power supply system includes one or more running server power supplies and a standby power supply in a standby state, and after shutting down the target server power supply, further includes: Enable the backup power supply, and replace and troubleshoot the target server power supply.

7. The method according to claim 1, characterized in that The temperature target power supply includes: any one of the primary side ambient temperature, the primary side hot spot temperature, the secondary side ambient temperature and the secondary side hot spot temperature; The collecting of the target power supply temperature corresponding to the target server power supply includes: The primary side ambient temperature and the primary side hot spot temperature of the target server power supply are collected from the input side of the target server power supply; the primary side ambient temperature is the ambient temperature collected from the input side of the target server power supply, and the primary side hot spot temperature is the heating temperature collected from the most seriously heated position on the input side; The secondary side ambient temperature and the secondary side hot spot temperature of the target server power supply are collected from the output side of the target server power supply; the secondary side ambient temperature is the ambient temperature collected from the output side of the target server power supply, and the secondary side hot spot temperature is the heating temperature collected from the most seriously heated position on the output side.

8. A temperature management device, characterized in that: include: A collection module, used for collecting a target power supply temperature of a target server power supply; A determination module, configured to predict the temperature anomaly of the target server power supply according to the target power supply temperature to obtain an anomaly prediction result; the anomaly prediction result at least includes a temperature rise rate of the target power supply temperature in a target unit time; The execution module is used to execute the protection strategy when the abnormal prediction result triggers the advance protection condition.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the temperature management method according to any one of claims 1 to 7 are implemented.

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 temperature management method according to any one of claims 1 to 7 are implemented.

Images