Power supply control method, device and electronic equipment for server

Abstract

The present application discloses a power supply control method, device and electronic equipment for a server, which relate to the field of computer technology. The power supply modes of a group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. The method comprises: acquiring power consumption data of a group of power supplies in a specified historical period to obtain historical power consumption data; predicting a load trend of a group of power supplies in a specified future period based on the historical power consumption data to obtain a predicted load trend of a group of power supplies, wherein the specified future period is a future period with the current moment or a future moment after the current moment as the starting moment; dynamically switching the power supply mode of a group of power supplies according to the predicted load trend and the specified mode switching condition, thereby solving the technical problems of low power supply efficiency and serious energy waste in the power supply control method in the related art, and achieving the technical effect of improving the efficiency of the power supply and reducing energy waste.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a power supply control method, device, and electronic device for a server. Background Art

[0002] In related technologies, servers typically use a 1+1 or N+1 redundant power supply design to ensure power supply reliability. The redundant power supplies will be in standby mode at full power, resulting in unnecessary energy waste. In addition, server power supplies are typically configured according to peak load and maintain high power supply during actual low-load business operation.

[0003] Furthermore, the redundant power supply design described above often results in some power supplies operating at low or no load for extended periods of time. Power supply efficiency typically drops significantly below 30% of their operating load, resulting in low power supply efficiency. This demonstrates that the power supply control methods used in related technologies suffer from low power supply efficiency and significant energy waste. Summary of the Invention

[0004] The present application provides a power supply control method, device and electronic device for a server, so as to at least solve the technical problems of low power supply efficiency and serious energy waste in the power supply control method in the related art.

[0005] The present application provides a power supply control method for a server, wherein the server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a shutdown state. The method comprises: obtaining power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as an end time; predicting a load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period with a future moment after the current moment as a start time; and dynamically switching the power supply mode of the group of power supplies according to the predicted load trend and a specified mode switching condition.

[0006] The present application also provides a power supply control device for a server, wherein the server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode, wherein in the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a shutdown state; the device includes: an acquisition unit, configured to acquire power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as an end time; a prediction unit, configured to predict a load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period with a current moment or a future moment after the current moment as a start time; and a switching unit, configured to dynamically switch the power supply mode of the group of power supplies according to the predicted load trend and a specified mode switching condition.

[0007] The present application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of any of the above-mentioned server power supply control methods when executing the computer program.

[0008] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned power supply control methods for the server are implemented.

[0009] The present application also provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned power supply control methods for the server when the computer program is executed by a processor.

[0010] Through the present application, a group of power supplies has a static redundant power supply mode and a dynamic redundant power supply mode. The static redundant power supply mode always keeps the redundant power supplies in standby state, which is suitable for high-load scenarios. The dynamic redundant power supply module can adjust the number of power supplies in working state according to the actual load, which is suitable for low-load scenarios. Since the future load trend of the power supply can be predicted and the power supply mode of a group of power supplies can be dynamically switched based on the load trend, the redundant power supplies can be reduced in the low-load scenario and the power loss can be reduced. Therefore, the technical problems of low power supply efficiency and serious power waste in the power supply control method in the related technology can be solved, and the technical effect of improving the efficiency of the power supply and reducing power waste can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0012] Figure 1 This is a schematic diagram of an application scenario of a power supply control method for a server according to an embodiment of the present application.

[0013] Figure 2 This is a flow chart of an optional method for controlling power supply of a server according to an embodiment of the present application.

[0014] Figure 3 This is a schematic diagram of an optional server power supply control method according to an embodiment of the present application.

[0015] Figure 4 This is a schematic structural diagram of an optional server power supply control system according to an embodiment of the present application.

[0016] Figure 5 This is a structural block diagram of an optional server power supply control device according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] It should be noted that, in the description of this application, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. The terms "first," "second," etc., in this application are used to distinguish similar objects, and are not used to describe a particular order or sequence.

[0019] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0020] According to one aspect of an embodiment of the present application, a method for controlling power supply of a server is provided. Optionally, in this embodiment, the method for controlling power supply of the server can be applied to, but is not limited to, Figure 1 The hardware environment shown includes a power supply 102 and a server device 104. The power supply 102 can be connected to the server device 104 through a power supply interface and can be used to provide power to the server device 104.

[0021] The power supply interface may include, but is not limited to, at least one of the following: a direct power line connection or an internal hardware interface connection. The power supply 102 may be, but is not limited to, a high-voltage DC power supply or a multi-phase power supply. The server device 104 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), storage devices, and random access memory (RAM).

[0022] The power supply control method of the server according to the embodiment of the present application can be executed by the server. Figure 2 FIG. 1 is a flow chart of an optional method for controlling power supply of a server according to an embodiment of the present application, as shown in FIG. Figure 2 As shown, the process of the method may include the following steps:

[0023] Step S202 , acquiring power consumption data of a group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period with the current moment or a historical moment before the current moment as an end moment.

[0024] Step S204, predicting the load trend of a group of power supplies in a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period starting at the current moment or a future moment after the current moment.

[0025] In step S206 , the power supply modes of a group of power supplies are dynamically switched according to the predicted load trend and the specified mode switching condition.

[0026] In which, the server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In which, in the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a closed state.

[0027] The server power supply control method of this embodiment can be applied in the computer field, specifically to scenarios involving the management and control of power supplies for servers (e.g., high-efficiency data centers, cloud computing platforms, or edge computing nodes). A power supply unit (PSU) is a type of power supply that converts electrical energy (as opposed to battery-powered power supplies) into low-voltage, stable DC power for use by other components requiring power.

[0028] In related technologies, servers typically use a 1+1 or N+1 redundant power supply design to ensure power supply reliability. This means that an additional redundant power supply is retained in addition to the power supply required for regular power supply to ensure that the system can continue to operate normally in the event of a failure of any power supply. However, this redundant structure will cause some power supplies to operate at low load or no load for a long time most of the time, resulting in low efficiency and increased energy consumption. In addition, the server's power supply is usually configured according to peak load, maintaining high power supply during actual low-load operation, further exacerbating the problem of energy waste.

[0029] Taking data centers (typically housing server clusters) as an example, power consumption primarily comes from information technology (IT) equipment and air conditioning for cooling and dissipating heat. Addressing energy waste requires comprehensive consideration of the heat and power consumption generated by these devices. While some servers already support dynamic fan speed regulation or load-aware fan speed control, this technology lacks comprehensive consideration of real-time load, historical operating trends, and business model forecasts on the power supply side.

[0030] In order to at least partially solve the above technical problems, in this embodiment, the power supply has at least two power supply modes, and the power supply mode can be flexibly adjusted according to the predicted load trend, thereby reducing energy waste.

[0031] The two power supply modes mentioned above include static redundant power supply mode and dynamic redundant power supply mode. The static redundant power supply mode is similar to the 1+1 or N+1 redundant power supply modes in related technologies. In addition to the N actual load power supplies, at least one redundant backup power supply is reserved. The redundant power supply is in standby mode before being activated. For example, if the system requires three PSUs for normal operation, four PSUs can be deployed, one of which is a redundant standby PSU. The dynamic redundant power supply mode dynamically determines the number of redundant power supplies based on real-time load. For example, if the load remains below a certain threshold for a long period of time, the redundant PSU can be shut down to reduce energy consumption. The static redundant power supply mode is characterized by redundant resources being always powered on and in standby mode, ensuring that the system does not shut down if any power supply fails. However, this mode consumes more energy, as the redundant power supplies continue to consume energy even when they are not under load. The dynamic redundant power supply mode is characterized by the ability to dynamically shut down and enable power supplies (for example, switching from four PSUs to three or two online), which can save unnecessary redundant standby power consumption. However, ensuring stable operation of the power supply requires accurate prediction and rapid response capabilities.

[0032] In order to achieve flexible and accurate switching between the two modes, in this embodiment, it is necessary to obtain historical power consumption data and predict future load trends based on it. Here, obtaining historical power consumption data means obtaining power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data.

[0033] Optionally, a baseboard management controller (BMC) or a power management bus (PMBus) can be used to obtain historical power consumption data. The historical power consumption data may include power input current, voltage, power, etc. Furthermore, historical power consumption data may be collected according to a specified sampling period. The specified sampling period can be set based on experience, for example, 1 second, 1.5 seconds, or other values, and is not limited in this embodiment.

[0034] After acquiring the historical power consumption data, the load trends of a group of power supplies within a specified future time period can be predicted based on the historical power consumption data to obtain a predicted load trend for the group of power supplies. Here, the specified future time period is a future time period starting at or after the current moment. For example, the specified future time period can be five minutes after the current moment. Alternatively, the load trend can be predicted based on a certain period, and this period must be less than the range of the specified future time period. For example, the load trend for the next five minutes can be predicted every three minutes.

[0035] Alternatively, load trends can be predicted using pre-trained deep learning-based load trend prediction models, such as Long Short-Term Memory (LSTM) networks, Gated Recurrent Unit (GRU) networks, or Transformer models. The input to these models is historical power consumption data. To improve the accuracy of load trend predictions, a sensor gateway can be connected to normalize the power consumption of server devices such as the CPU, memory, and GPU, and use this as input to the model.

[0036] After obtaining the predicted load trend, the power supply mode of a group of power supplies can be dynamically switched based on the predicted load trend and specified mode switching conditions. For example, if a high load is predicted for a specified future period, the system can switch to static redundant power supply mode to ensure stable power supply. If a low load is predicted for a specified future period, the system can switch to dynamic redundant power supply mode to improve energy efficiency and reduce waste.

[0037] It should be noted that the power supply efficiency of the power supply usually drops significantly when its workload is below 30%. Keeping the power supply at a higher load can reduce waste. In this embodiment, when the load is low, such as when the traffic is low at night, it is possible to switch to a dynamic redundant power supply mode, which can reduce the number of power supplies being supplied, thereby increasing the load of each power supply being supplied and improving the power supply efficiency. If static redundant power supply is still used during the night when the traffic is low, not only will the redundant power supplies be in full power standby mode, but the load of each power supply being supplied will also be low, which will result in a large amount of unnecessary energy waste. Therefore, dynamically adjusting the power supply mode can effectively reduce energy waste and improve the efficiency of the power supply.

[0038] According to an embodiment provided by the present application, a server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a closed state. The method includes: obtaining power consumption data of the group of power supplies within a specified historical period to obtain the historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as the end time; predicting the load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period with a future moment after the current moment as the start time; and dynamically switching the power supply mode of the group of power supplies according to the predicted load trend and a specified mode switching condition. This solves the technical problems of low power supply efficiency and serious energy waste in power supply control methods in related technologies, thereby improving the efficiency of the power supplies and reducing energy waste.

[0039] In an exemplary embodiment, the specified mode switching condition includes a first switching condition for switching from a static redundant power supply mode to a dynamic redundant power supply mode, the first switching condition including that the load of a group of power supplies is less than a first load threshold for a duration greater than or equal to a specified time threshold; dynamically switching the power supply mode of a group of power supplies according to the predicted load trend and the specified mode switching condition, including: when the power supply mode of a group of power supplies is a static redundant power supply mode, and the predicted load trend indicates that the predicted load of a group of power supplies in a specified future time period is less than a first load threshold for a duration greater than or equal to the specified time threshold, switching the power supply mode of a group of power supplies to a dynamic redundant power supply mode.

[0040] In static redundant power supply mode, even when the server is under low load or even idle, such as during low load operation at night or during off-peak hours, the redundant power supplies remain on standby and continue to consume power. To address the issue of excessive power consumption by redundant power supplies under low load, the power supply mode can be switched to dynamic redundant power supply mode when the first switching condition is met. This avoids unnecessary power consumption by the redundant power supplies and increases the load of each active power supply, thereby improving the power supply efficiency.

[0041] In this embodiment, the specified mode switching condition includes a first switching condition for switching from a static redundant power supply mode to a dynamic redundant power supply mode, and the first switching condition includes a predicted load trend indicating that the predicted load of a group of power supplies in a specified future time period is less than a first load threshold for a duration greater than or equal to a specified time threshold, that is, it is predicted that the load of a group of power supplies will continue to be low. Here, both the first load threshold and the specified time threshold can be set based on experience. For example, the first load threshold can be 50%, 30% or other values, and the specified time threshold needs to be less than the predicted specified future time period. For example, if the specified future time period is 30 minutes in the future, the specified time threshold can be 15 minutes, 20 minutes or other values ​​less than 30 minutes. This is not limited in this embodiment.

[0042] Optionally, a redundancy safety assessment can be performed before switching to dynamic redundant power supply mode. If the redundancy safety assessment fails, the system will not switch to dynamic redundant power supply mode. Here, conditions for passing the redundancy safety assessment may include: the existing power supply can support 150% of the peak load capacity; both the power distribution unit (PDU) and the uninterruptible power supply (UPS) have sufficient capacity; the system is not currently undergoing critical maintenance, upgrades, or switching; and current device temperature, safety voltage, and other indicators are normal. After passing the above redundancy safety assessment, one or more redundant power supplies can be shut down through software power-off or physical power-off.

[0043] Optionally, the power supply mode switching method may include a hardware layer method, for example, through PSU / PDU control, using PMBus, Redfish, Intelligent Platform Management Interface (Intelligent Platform Management Interface, referred to as IPMI) and other protocols to implement power on / off control of the PSU. For example, when using the IPMI protocol, the IPMI command may be "chassis power off<PSU_id> In addition, the PSU's input / output current, voltage, power, etc. can be read in real time through hardware layer methods to determine the power supply path status and achieve continuous monitoring of the PSU status.

[0044] Optionally, the power supply mode switching method may also include software-layer policy scheduling. For example, the corresponding module in the system first proposes a redundancy reduction suggestion, and the central management control unit decides whether to execute the redundancy reduction operation. Before confirming the execution of the redundancy reduction operation, the feasibility of the "minimum redundancy margin" formula must be met. After the power supply mode switching operation is executed, the switching operation record is written to the log. Here, the code for the "minimum redundancy margin" formula calculation can be:

[0045] Ptotal_available≥Ppredicted_peak×safety_marginP_{\text{total\_available}}\geq P_{\text{predicted\_peak}}\times

[0046] \text{safety\_margin}Ptotal_available≥Ppredicted_peak×safety_margin

[0047] Through this embodiment, when it is predicted that the load trend will continue to be low, the dynamic redundant power supply mode is switched to avoid the inefficient operation of the redundant power supply and unnecessary power consumption can be reduced. In addition, reducing the unnecessary operation of the redundant power supply can also extend the service life of the power supply.

[0048] In an exemplary embodiment, the specified mode switching condition includes a second switching condition for switching from a dynamic redundant power supply mode to a static redundant power supply mode, the second switching condition including that the load of a group of power supplies is greater than or equal to a second load threshold, wherein the second load threshold is greater than the first load threshold; dynamically switching the power supply mode of a group of power supplies according to the predicted load trend and the specified mode switching condition, including: when the power supply mode of a group of power supplies is a static redundant power supply mode, and the predicted load trend indicates that there is a future moment within a specified future time period when the predicted load of a group of power supplies is greater than or equal to the second load threshold, switching the power supply mode of a group of power supplies to a static redundant power supply mode.

[0049] In dynamic redundant power supply mode, inactive redundant power supplies are in a shutdown state rather than a standby state. If the server is under high load or a sudden load increase, or if some power supplies fail, the shutdown redundant power supplies will not be able to resume operation in a timely manner, potentially leading to power shortages or power overloads. To address this issue, the power supply mode can be switched to static redundant power supply mode when the second switching condition is met. This maintains a certain number of redundant power supplies in a standby state, ensuring that they can resume operation in a timely manner when needed, thus ensuring the continuity and stability of the power supply.

[0050] In this embodiment, the specified mode switching condition includes a second switching condition for switching from the dynamic redundant power supply mode to the static redundant power supply mode. The second switching condition includes a predicted load trend indicating a future moment in time when a predicted load of a group of power supplies is greater than or equal to a second load threshold within a specified future time period, i.e., a moment when a high load is predicted. Here, the second load threshold can be set based on experience, and the second load threshold needs to be greater than the first load threshold. For example, if the first load threshold is 50%, the second load threshold can be 70%, 75%, or another value greater than the first load threshold. This is not limited in this embodiment.

[0051] Optionally, conditions for switching to static redundant power supply mode may also include: abnormal voltage or current fluctuations in any power supply path; the system entering a high availability or service launch phase; or a device operating temperature exceeding a certain threshold (indicating a decrease in power supply efficiency). If any of these conditions are met, the system can preheat or wake up the redundant power supply and switch to static redundant power supply mode. The method for switching power supply modes here is similar to that in the previous embodiment and will not be further described here.

[0052] Through this embodiment, when a high load trend is predicted, the static redundant power supply mode is switched to, and the redundancy of the power supply is increased in time before the load increases, effectively avoiding insufficient power supply or power overload, thereby ensuring business continuity and stability of server operation.

[0053] In an exemplary embodiment, a load trend of a group of power supplies in a specified future time period is predicted based on historical power consumption data to obtain a predicted load trend of the group of power supplies, including: extracting features from the historical power consumption data to obtain a historical power consumption sequence; inputting the historical power consumption sequence, or the historical power consumption sequence and at least one of the following features into a load prediction model to obtain a predicted load trend output by the load prediction model: a historical power load sequence of a group of power supplies in a specified historical time period, a historical utilization sequence of the server's power load in a specified historical time period, and a task queue feature processed by the server's power load in a specified historical time period, wherein the load prediction model is a time series model for load prediction.

[0054] In order to accurately predict the load trend, in this embodiment, the load trend in a specified future period is predicted using a load prediction model, wherein the load prediction model is a time series model used for load prediction.

[0055] Optionally, the load prediction model can adopt a two-layer LSTM neural network structure. The two-layer LSTM neural network structure is a deep learning model composed of two stacked LSTM layers. Each layer contains an independent gating mechanism (forget gate, input gate, output gate) and memory unit. It can be used for prediction and analysis of time series data. It has the advantages of processing long sequence dependencies and capturing complex patterns. In this embodiment, it can be used to accurately predict the load trend of the power supply.

[0056] The inputs to the load prediction model include the historical power consumption sequence of the power supply, the historical power load sequence of the power supply, the historical utilization sequence of the server, and the historical task queue features of the server. The historical power consumption sequence of the power supply is obtained by extracting features from the historical power consumption data of the power supply, and can reflect information such as the average power consumption of the power supply within a specified historical period. The historical power load sequence of the power supply is a set of historical power load sequences of the power supply within a specified historical period, which can reflect information such as the peak and valley load values ​​of the power supply within the specified historical period. The historical utilization sequence of the server is a set of historical utilization sequences of the server's power load within a specified historical period, which can reflect information such as the average utilization, peak utilization, and valley utilization values ​​of the server within the specified historical period. The historical task queue features of the server are the features of the task queue processed by the server's power load within the specified historical period. Based on the length of the task queue, it can reflect the amount of tasks processed by the server within the specified historical period. Based on the above input information, the predicted load trend of a group of power supplies within a specified future period can be predicted based on the regression results of the load prediction model. After testing, the error of the predicted load trend is controlled within ±5%.

[0057] Through this embodiment, the load forecasting model is used to predict the load trend in a specified future period. The input of multi-dimensional features including real-time power consumption, historical load, task queue length, etc. can improve the accuracy of the prediction and provide a good data basis for dynamically adjusting the power supply mode.

[0058] In an exemplary embodiment, after predicting the load trend of a group of power supplies in a specified future time period based on historical power consumption data, the above method also includes: when the power supply mode of a group of power supplies is a dynamic redundant power supply mode, when the predicted load trend of a group of power supplies indicates that the predicted load of a group of power supplies is less than or equal to a third load threshold, starting a designated main power supply in a group of power supplies, wherein other power supplies in a group of power supplies except the main power supply are in a shut-down state as redundant power supplies; when the predicted load trend of a group of power supplies indicates that the predicted load of a group of power supplies gradually increases from less than or equal to a third load threshold, at a specified moment before the predicted load of a group of power supplies reaches a load threshold in a group of load thresholds, starting a number of redundant power supplies corresponding to the load threshold in a group of load thresholds, wherein the time interval between the specified moment and the predicted moment when the predicted load of a group of power supplies reaches the load threshold in a group of load thresholds is the specified time interval.

[0059] In the dynamic redundant power supply mode, the number of redundant power supplies can be dynamically adjusted according to the predicted load trend. When the load is predicted to be low, that is, the predicted load trend of a group of power supplies indicates that the predicted load of a group of power supplies is less than or equal to the third load threshold, only one power supply in the group of power supplies can be retained as the main power supply manager, and the main power supply continues to work and supply power, while the remaining power supplies are all shut down as redundant power supplies. Here, the third load threshold can be set based on experience, for example, it can be 30%, 25% or other values, which is not limited in this embodiment. Optionally, the shut-down redundant power supply can be in standby mode, the fan stops, and the standby power consumption is less than 3 watts.

[0060] If a load increase is predicted, i.e., the predicted load trend of a group of power supplies indicates that the predicted load of the group of power supplies gradually increases from less than or equal to a third load threshold, multiple redundant power supplies can be activated before the load reaches the load threshold. Here, the number of redundant power supplies activated corresponds to a load threshold in the set of load thresholds, and the higher the load threshold, the greater the number of redundant power supplies activated. For example, the set of load thresholds may include 60%, 70%, and 80%, where 60% may correspond to two redundant power supplies, 70% may correspond to three redundant power supplies, and 80% may correspond to four redundant power supplies. If it is predicted that the predicted load will reach any one of the set of load thresholds, the corresponding number of redundant power supplies can be cold-started at a specified time before the load threshold is reached. The time interval between the specified time and the predicted time when the predicted load of the group of power supplies reaches the load threshold in the set of load thresholds is the specified time interval. Here, the specified time interval can be set based on experience, for example, 30 seconds, 40 seconds, or other values. The specified time interval needs to be greater than the startup time of the power supplies to ensure that the power supplies can complete startup before the load reaches the load threshold.

[0061] Alternatively, precise control of power supply shutdown and startup can be achieved through IPMI or the Inter-Integrated Circuit (I2C) bus. These two communication protocols provide an efficient and reliable approach to power supply management, enabling servers to intelligently adjust the operating status of each power supply based on load prediction and redundancy strategies.

[0062] Through this embodiment, the redundant power supply is turned off under low load conditions and started in advance under high load conditions, which can achieve a rapid response to load conditions, reduce power consumption, and ensure power supply stability under high load conditions.

[0063] In an exemplary embodiment, the above method also includes: determining a specified load ratio of a power supply in a group of power supplies based on a specified power supply efficiency curve, wherein the specified power supply efficiency curve is used to indicate the energy conversion efficiency of the power supply in the power supply under a load ratio in a group of load ratios, the specified load ratio and the highest energy conversion efficiency in the specified power supply efficiency curve; controlling the power supplies in a working state in a group of power supplies to supply power according to the specified load ratio.

[0064] The energy conversion efficiency of a power supply will decrease when the load is too high or too low. In order to improve the energy conversion efficiency of the power supply, a specified load ratio of the power supplies in a group of power supplies can be determined based on a specified power supply efficiency curve, and the power supplies in the working state can be controlled to supply power according to the specified load ratio.

[0065] Here, the specified power supply efficiency curve is used to indicate the energy conversion efficiency of the power supply in the power supply under a load ratio in a set of load ratios, and the specified load ratio is the highest energy conversion efficiency in the specified power supply efficiency curve. Energy conversion efficiency refers to the energy conversion efficiency of the power supply when converting AC power into DC power for use by server equipment, that is, the ratio of output power to input power. Optionally, the specified power supply efficiency curve can be an 80 PLUS efficiency curve. The 80 PLUS power supply standard defines the efficiency index of the power supply under 20%, 50% and 100% load. The efficiency is highest at around 50% load, that is, 50% is the specified load ratio, and the energy conversion efficiency at 50% load is the highest energy conversion efficiency in the specified power supply efficiency curve. In this embodiment, the power supply in a working state can be controlled to maintain operation at a load close to 50%, ensuring the high energy conversion efficiency of the power supply.

[0066] Through this embodiment, the power supply is precisely controlled to operate under a load with the highest energy conversion efficiency, so that the power supply is located in a high efficiency zone, which can improve the energy conversion efficiency of the power supply in the working state, thereby reducing energy waste.

[0067] In an exemplary embodiment, after inputting the historical power consumption sequence, or the historical power consumption sequence and at least one of the following features into the load prediction model, the above method also includes: calculating a set of energy efficiency indicators of the server based on the historical power consumption data, wherein the set of energy efficiency indicators includes at least one of the following: power utilization efficiency, cooling energy efficiency ratio; generating a set of candidate operating modes based on the set of energy efficiency indicators of the server, wherein one candidate operating mode in the set of candidate operating modes is used to indicate the redundant configuration method of a group of power supplies, the number of power supplies in working state in a group of power supplies, and the load distribution method of power supplies in working state in a group of power supplies; based on the predicted load trend, determining the target operating mode from the set of candidate operating modes, and controlling the operation of a group of power supplies according to the target operating mode.

[0068] A set of energy efficiency indicators can include Power Usage Effectiveness (PUE) and Energy Efficiency Ratio (EER). PUE refers to the ratio of a data center's total energy consumption to the energy consumption of IT equipment. Its value should be ≥ 1, and the closer it is to 1, the lower the energy consumption of non-IT equipment (such as cooling and power supply), indicating higher data center energy efficiency. EER refers to the ratio of the cooling capacity of the refrigeration system to its input power. The higher the value, the higher the cooling efficiency. To reduce energy waste, it is necessary to lower PUE and increase EER, thereby improving energy utilization efficiency. In this embodiment, based on the PUE and EER of the server, a suitable target operating mode can be selected from a set of candidate operating modes, and a set of power supplies can be controlled according to the target operating mode to optimize the set of energy efficiency indicators.

[0069] In this embodiment, a candidate operating mode can be used to indicate the redundancy configuration mode of a group of power supplies, the number of power supplies in working state in a group of power supplies, and the load distribution mode of the power supplies in working state in a group of power supplies, wherein the redundancy configuration mode may include N, N+1 or N+N redundancy levels, i.e., not starting the redundant power supply, starting one redundant power supply, or starting multiple redundant power supplies; the number of power supplies in working state in a group of power supplies indicates the number of power supplies in working state and participating in power supply; the load distribution mode may indicate whether the power supplies in working state adopt uniform distribution or priority power supply mode for power supply. Optionally, in addition to the above three dimensions, a candidate operating mode may also include a dynamic adjustment strategy, which is used to indicate whether the power supply automatically switches the operating mode according to the predicted load and real-time PUE / EER. A candidate operating mode is a combination of the above four dimensions.

[0070] For example, a set of candidate operating modes may include the following three candidate operating modes: Mode A, a high-redundancy and high-energy consumption mode, in which the redundancy configuration is 1+1, the number of power supplies in operation is 4, and the load ratio of each power supply is 37.5%. This mode has low efficiency and a relatively high PUE; Mode B, an optimal efficiency mode, in which the redundancy configuration is N (the redundant power supply is not started), the number of power supplies in operation is 2, and the load ratio of each power supply is 75%. This mode has high conversion efficiency, minimizes system energy consumption, and can maximize EER; Mode C, a critical balanced redundancy mode, in which the redundancy configuration is N+1, the number of power supplies in operation is 3, and the load ratio of each power supply is 50%. This mode balances redundancy and efficiency.

[0071] After obtaining a set of candidate operating modes, the most appropriate target operating mode can be selected and executed based on the predicted load trend, ensuring that the power supply can operate in the most efficient manner while meeting business needs.

[0072] Through this embodiment, the current energy efficiency index is calculated in real time, and the target operation mode is determined based on PUE and EER as well as the predicted load trend, which can reduce energy waste while ensuring that business needs are met and maintain a good cooling effect.

[0073] In an exemplary embodiment, based on configuration information, a set of service level agreement rules and a set of alarm levels are determined, wherein a set of service level agreement rules corresponds to a plurality of nodes powered by a set of power supplies, indicating the minimum number of power supplies in standby state, the minimum number of reserved power supplies and alarm thresholds corresponding to the plurality of nodes, and a set of alarm levels includes a plurality of alarm triggering mechanisms and alarm handling methods corresponding to the plurality of alarm triggering mechanisms; when one of the alarm triggering mechanisms in a set of alarm levels is satisfied, the alarm handling method corresponding to the alarm triggering mechanism is executed.

[0074] Here, a Service Level Agreement (SLA) rule refers to a mutually agreed agreement or contract between the service provider and the customer regarding the quality, level, and performance of the service. Server operation must comply with the SLA rules. The SLA rules can correspond to multiple nodes powered by a group of power supplies, indicating the minimum number of power supplies in standby state, the minimum number of reserved power supplies, and the alarm threshold for the multiple nodes. For example, Figure 3As shown, node types can include GPU nodes, storage nodes, web server nodes, and management control nodes. The SLA level for GPU nodes is 1, with a redundancy requirement of permanent 1+1, an alarm threshold of a power drop >5%, dynamic redundant power supply mode prohibited, and a minimum number of PSUs to be retained of 2. The SLA level for storage nodes is 2, with a redundancy requirement of minimum N, an alarm threshold of a power drop >10%, dynamic redundant power supply mode permitted, and a minimum number of PSUs to be retained of 1. The SLA level for web server nodes is 2, with a redundancy requirement of N+1 and elastic adjustment permitted, an alarm threshold of a power drop >7%, dynamic redundant power supply mode permitted within ten minutes, and a minimum number of PSUs to be retained of 1. The SLA level for management control nodes is 1, with a redundancy requirement of permanent 1+1, an alarm threshold of a power drop >3%, dynamic redundant power supply mode prohibited, and a minimum number of PSUs to be retained of 2. It should be noted that the switching between the aforementioned static redundant power supply mode and the dynamic redundant power supply mode also needs to be based on the aforementioned SLA rules, and the switching can only be performed if the SLA rules are met.

[0075] When an alarm trigger mechanism is met in a set of alarm levels, the alarm handling method corresponding to the alarm trigger mechanism can be executed to achieve intelligent response and alarm processing. Optionally, the alarm handling method may include activating additional redundant power supplies, notifying relevant personnel, etc.

[0076] Through this embodiment, different energy strategies can be formulated according to different business types to ensure business needs while optimizing overall energy efficiency. In addition, the automatic execution of alarm processing methods can intelligently handle failures that occur during work, improve the response speed and processing efficiency of abnormal events, and effectively prevent business interruptions.

[0077] The power supply control method of the server in the embodiment of the present application is explained below with reference to an optional example. In this optional example, the above method is executed by the power supply control system of the server, and the power supply control system of the server can be used for a 2U server.

[0078] Figure 4 This is a schematic diagram of the power supply control system of the server in this optional example. Figure 4 As shown, the power supply control system of the server can include six functional modules: power consumption data acquisition module, load prediction engine, dynamic power distribution module, redundancy strategy adaptive adjustment module, energy efficiency optimization scheduler and central management control unit, as well as multiple power modules under the control of the system.

[0079] Optionally, the load prediction engine can output load trends for the next 30 minutes every 5 minutes. The central management and control unit can receive the prediction results and call the energy efficiency optimization scheduler to analyze the power supply strategy. The energy efficiency optimization scheduler can then work with the redundancy strategy adaptive adjustment module to determine whether to downgrade PSU redundancy. After this, the central management and control unit can send the results to the power control interface layer for actual power scheduling. In addition, during system operation, a monitoring module can continuously report power consumption and prediction errors back to the central management and control unit, and the load prediction engine and energy efficiency optimization scheduler can automatically adjust to optimize control results.

[0080] Optionally, the dynamic power distribution module can also support hot-plugging and automatic switching of PSUs; the redundant policy adaptive adjustment module can also provide log auditing and policy rollback capabilities; the central management control unit can be deployed on a BMC chip, running a lightweight Linux system, and supporting docking with the data center's Data Center Infrastructure Management (DCIM) / Energy Management System (EMS), and can also provide a Web interface / Application Programming Interface (API) to facilitate remote policy configuration and alarm processing.

[0081] For example, this system controls the power supply of a 2U dual-power server. Three 1.6kW PSUs (typically in an N+1 configuration) can be configured. When the predicted load drops below 20% at night, the system automatically shuts down two PSUs, leaving the primary PSU to operate independently. Five minutes before a daytime traffic increase (when a trend is predicted), the backup PSU can be activated. Testing has shown an overall efficiency increase from approximately 82% to approximately 91%, saving approximately 120 kWh of electricity per server annually.

[0082] This system incorporates load prediction algorithms, dynamically starts and stops redundant power modules, and an intelligently switched power distribution architecture. It also supports automatic switching between multiple redundancy modes. These modules collaborate to dynamically start and stop power modules and adjust redundancy strategies, automatically balancing redundancy and energy efficiency. The central management and control unit utilizes embedded BMC control and supports remote control via Redfish / IPMI interfaces. Integration with data center DCIM systems / EMS platforms enables both centralized and distributed control, improving system compatibility.

[0083] Through this optional example, by predicting the load and dynamically starting and stopping redundant power supply modules, the PSU can always operate in the optimal efficiency zone, reducing the time the PSU runs in the no-load or low-efficiency range, which can reduce energy waste and improve the overall operating efficiency of the PSU; the system can automatically switch between static redundant power supply mode and dynamic redundant power supply mode according to the business SLA level, load trend, and alarm status, which can reduce resource waste caused by excessive redundancy while ensuring safety; combined with deep learning models, high-precision load prediction can achieve early wake-up / sleep PSU to avoid power supply jitter caused by delays; in addition, in terms of economic effects, it can save electricity costs and reduce equipment aging and maintenance costs; in terms of operation and management benefits, the intelligent energy-saving strategy is transparent and controllable, and can also be seamlessly connected with the data center platform in related technologies to reduce operation and maintenance pressure.

[0084] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0086] According to another aspect of the embodiments of the present application, a power supply control device for a server is also provided, which can be used to implement the power supply control method for the server provided in the above embodiments, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0087] Figure 5 This is a structural block diagram of an optional server power supply control device according to an embodiment of the present application, such as Figure 5 As shown in , the power supply control device of the server includes:

[0088] An acquiring unit 502 is configured to acquire power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period starting at or before the current moment and ending at the current moment;

[0089] a prediction unit 504 configured to predict a load trend of the group of power supplies within a specified future period based on the historical power consumption data, thereby obtaining a predicted load trend of the group of power supplies, wherein the specified future period is a future period starting at the current moment or a future moment after the current moment;

[0090] The switching unit 506 is configured to dynamically switch the power supply modes of the group of power supplies according to the predicted load trend and the specified mode switching condition.

[0091] It should be noted that the acquisition unit 502 in this embodiment can be used to perform the above step S202, the prediction unit 504 in this embodiment can be used to perform the above step S204, and the switching unit 506 in this embodiment can be used to perform the above step S206.

[0092] According to an embodiment provided by the present application, a server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a closed state. The method includes: obtaining power consumption data of the group of power supplies within a specified historical period to obtain the historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as the end time; predicting the load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period with a future moment after the current moment as the start time; and dynamically switching the power supply mode of the group of power supplies according to the predicted load trend and a specified mode switching condition. This solves the technical problems of low power supply efficiency and serious energy waste in power supply control methods in related technologies, thereby improving the efficiency of the power supplies and reducing energy waste.

[0093] In an exemplary embodiment, the specified mode switching condition includes a first switching condition for switching from a static redundant power supply mode to a dynamic redundant power supply mode, and the first switching condition includes that the load of a group of power supplies is less than a first load threshold for a duration greater than or equal to a specified time threshold; the switching unit includes: a first switching module, used to switch the power supply mode of a group of power supplies to a dynamic redundant power supply mode when the power supply mode of the group of power supplies is a static redundant power supply mode and the predicted load trend indicates that the predicted load of a group of power supplies in a specified future time period is less than the first load threshold for a duration greater than or equal to the specified time threshold.

[0094] In an exemplary embodiment, the specified mode switching condition includes a second switching condition for switching from a dynamic redundant power supply mode to a static redundant power supply mode, and the second switching condition includes that the load of a group of power supplies is greater than or equal to a second load threshold, wherein the second load threshold is greater than the first load threshold; the switching unit includes: a second switching module, which is used to switch the power supply mode of a group of power supplies to a static redundant power supply mode when the power supply mode of the group of power supplies is a static redundant power supply mode and the predicted load trend indicates that there is a future moment in a specified future time period when the predicted load of a group of power supplies is greater than or equal to the second load threshold.

[0095] In an exemplary embodiment, the prediction unit includes: an extraction module for extracting features from historical power consumption data to obtain a historical power consumption sequence; an input module for inputting the historical power consumption sequence, or the historical power consumption sequence and at least one of the following features into a load prediction model to obtain a predicted load trend output by the load prediction model: a historical power load sequence of a group of power supplies in a specified historical period, a historical utilization sequence of the server's power load in a specified historical period, and a task queue feature processed by the server's power load in a specified historical period, wherein the load prediction model is a time series model for load prediction.

[0096] In an exemplary embodiment, after predicting the load trend of a group of power supplies in a specified future time period based on historical power consumption data, the above-mentioned device also includes: a first starting unit, which is used to start a specified main power supply in a group of power supplies when the power supply mode of the group of power supplies is a dynamic redundant power supply mode, when the predicted load trend of a group of power supplies indicates that the predicted load of the group of power supplies is less than or equal to a third load threshold, wherein other power supplies in the group of power supplies except the main power supply are in a shut-down state as redundant power supplies; a second starting unit, which is used to start a number of redundant power supplies corresponding to the load threshold in a group of load thresholds at a specified time before the predicted load of a group of power supplies reaches the load threshold in a group of load thresholds when the predicted load trend of a group of power supplies indicates that the predicted load of a group of power supplies gradually increases from less than or equal to the third load threshold, wherein the time interval between the specified time and the predicted time when the predicted load of a group of power supplies reaches the load threshold in a group of load thresholds is the specified time interval.

[0097] In an exemplary embodiment, the above-mentioned device also includes: a first determination unit, used to determine a specified load ratio of a power supply in a group of power supplies based on a specified power supply efficiency curve, wherein the specified power supply efficiency curve is used to indicate the energy conversion efficiency of the power supply in the power supply under a load ratio in a group of load ratios, and the specified load ratio is the highest energy conversion efficiency in the specified power supply efficiency curve; a control unit, used to control the power supply in a working state in a group of power supplies to supply power according to the specified load ratio.

[0098] In an exemplary embodiment, after inputting the historical power consumption sequence, or the historical power consumption sequence and at least one of the following features into the load prediction model, the above-mentioned device also includes: a calculation unit for calculating a set of energy efficiency indicators of the server based on the historical power consumption data, wherein the set of energy efficiency indicators includes at least one of the following: power utilization efficiency, cooling energy efficiency ratio; a generation unit for generating a set of candidate operating modes based on the set of energy efficiency indicators of the server, wherein one candidate operating mode in the set of candidate operating modes is used to indicate the redundant configuration method of a group of power supplies, the number of power supplies in working state in a group of power supplies, and the load distribution method of power supplies in working state in a group of power supplies; a first execution unit for determining a target operating mode from a group of candidate operating modes based on the predicted load trend, and controlling the operation of a group of power supplies according to the target operating mode.

[0099] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the above-mentioned server power supply control method embodiments.

[0100] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above-mentioned server power supply control method embodiments when running.

[0101] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0102] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned server power supply control method embodiments are implemented.

[0103] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above-mentioned server power supply control method embodiments are implemented.

[0104] 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 above description has generally described the components and steps of each example according to their functions. 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 beyond the scope of this application.

[0105] The above is a detailed introduction to the power supply control method, device and electronic device of a server provided by this application. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method of this application and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A method for controlling power supply of a server, characterized in that: The server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a shutdown state. The method includes: Obtaining power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as an end moment; Predicting a load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period starting at the current moment or a future moment after the current moment; Dynamically switch the power supply mode of the group of power supplies according to the predicted load trend and the specified mode switching condition, wherein the specified mode switching condition includes a first switching condition for switching from the static redundant power supply mode to the dynamic redundant power supply mode and a second switching condition for switching from the dynamic redundant power supply mode to the static redundant power supply mode, the first switching condition includes that the load of the group of power supplies is less than a first load threshold for a duration greater than or equal to a specified time threshold, the second switching condition includes that the load of the group of power supplies is greater than or equal to a second load threshold, and the second load threshold is greater than the first load threshold.

2. The method according to claim 1, characterized in that The dynamically switching the power supply modes of the group of power supplies according to the predicted load trend and the specified mode switching condition includes: When the power supply mode of the group of power supplies is the static redundant power supply mode and the predicted load trend indicates that the predicted load of the group of power supplies in the specified future time period is less than the first load threshold for a duration greater than or equal to the specified time threshold, the power supply mode of the group of power supplies is switched to the dynamic redundant power supply mode.

3. The method according to claim 2, characterized in that The dynamically switching the power supply modes of the group of power supplies according to the predicted load trend and the specified mode switching condition includes: When the power supply mode of the group of power supplies is the static redundant power supply mode and the predicted load trend indicates a future moment when the predicted load of the group of power supplies is greater than or equal to the second load threshold within the specified future time period, the power supply mode of the group of power supplies is switched to the static redundant power supply mode.

4. The method according to claim 1, wherein The step of predicting a load trend of the group of power supplies within a specified future period based on the historical power consumption data to obtain a predicted load trend of the group of power supplies includes: Extracting features from the historical power consumption data to obtain a historical power consumption sequence; The historical power consumption sequence, or the historical power consumption sequence and at least one of the following features are input into a load prediction model to obtain the predicted load trend output by the load prediction model: the historical power load sequence of the group of power supplies in the specified historical period, the historical utilization sequence of the power load of the server in the specified historical period, and the task queue feature processed by the power load of the server in the specified historical period, wherein the load prediction model is a time series model for load prediction.

5. The method according to claim 1, wherein After predicting the load trend of the group of power supplies within a specified future period based on the historical power consumption data, the method further includes: When the power supply mode of the group of power supplies is the dynamic redundant power supply mode, when the predicted load trend of the group of power supplies indicates that the predicted load of the group of power supplies is less than or equal to a third load threshold, starting a designated active power supply in the group of power supplies, wherein the other power supplies in the group of power supplies except the active power supply are in a shutdown state as the redundant power supplies; When the predicted load trend of the group of power supplies indicates that the predicted load of the group of power supplies gradually increases from less than or equal to the third load threshold, at a specified moment before the predicted load of the group of power supplies reaches a load threshold in a set of load thresholds, the redundant power supplies corresponding to a number of the load thresholds in the set of load thresholds are started, wherein the time interval between the specified moment and the predicted moment when the predicted load of the group of power supplies reaches the load threshold in the set of load thresholds is the specified time interval.

6. The method according to claim 1, characterized in that The method further comprises: determining a specified load ratio of a power supply in the group of power supplies based on a specified power supply efficiency curve, wherein the specified power supply efficiency curve is used to indicate the energy conversion efficiency of the power supply in the group of power supplies at a load ratio in a group of load ratios, and the specified load ratio corresponds to the highest energy conversion efficiency in the specified power supply efficiency curve; The power supplies in the group of power supplies that are in working state are controlled to supply power according to the specified load ratio.

7. The method according to claim 4, characterized in that After inputting the historical power consumption sequence, or the historical power consumption sequence and at least one of the following features into the load prediction model, the method further includes: Based on the historical power consumption data, a set of energy efficiency indicators of the server is calculated, wherein the set of energy efficiency indicators includes at least one of the following: power utilization efficiency, cooling energy efficiency ratio; generating a set of candidate operating modes based on the set of energy efficiency indicators of the server, wherein one candidate operating mode in the set of candidate operating modes is used to indicate a redundancy configuration of the set of power supplies, a number of working power supplies in the set of power supplies, and a load distribution method of the working power supplies in the set of power supplies; Based on the predicted load trend, a target operating mode is determined from the set of candidate operating modes, and the operation of the set of power supplies is controlled according to the target operating mode.

8. The method according to claim 1, characterized in that The method further comprises: Determining, based on the configuration information, a set of service level agreement rules and a set of alarm levels, wherein the set of service level agreement rules corresponds to a plurality of nodes powered by the set of power supplies, and indicates a minimum number of the power supplies in standby state, a minimum number of reserved power supplies, and an alarm threshold corresponding to the plurality of nodes, and the set of alarm levels includes a plurality of alarm triggering mechanisms and alarm handling methods corresponding to the plurality of alarm triggering mechanisms; When one alarm triggering mechanism in the set of alarm levels is satisfied, the alarm processing method corresponding to the alarm triggering mechanism is executed.

9. A power supply control device for a server, characterized in that: The server has a group of power supplies, and the power supply modes of the group of power supplies include a static redundant power supply mode and a dynamic redundant power supply mode. In the static redundant power supply mode, the number of redundant power supplies in the group of power supplies is fixed, and when not enabled, the redundant power supplies are in a standby state; in the dynamic redundant power supply mode, the number of redundant power supplies in the group of power supplies is dynamically adjusted according to the load of the group of power supplies, and when not enabled, the redundant power supplies are in a closed state. The device includes: an acquiring unit, configured to acquire power consumption data of the group of power supplies within a specified historical period to obtain historical power consumption data, wherein the specified historical period is a historical period with a current moment or a historical moment before the current moment as an end moment; a prediction unit, configured to predict a load trend of the group of power supplies within a specified future period based on the historical power consumption data, to obtain a predicted load trend of the group of power supplies, wherein the specified future period is a future period starting at the current moment or a future moment after the current moment; A switching unit is used to dynamically switch the power supply mode of the group of power supplies according to the predicted load trend and the specified mode switching condition, wherein the specified mode switching condition includes a first switching condition for switching from the static redundant power supply mode to the dynamic redundant power supply mode and a second switching condition for switching from the dynamic redundant power supply mode to the static redundant power supply mode, the first switching condition includes that the load of the group of power supplies is less than a first load threshold for a duration greater than or equal to a specified time threshold, and the second switching condition includes that the load of the group of power supplies is greater than or equal to a second load threshold, and the second load threshold is greater than the first load threshold.

10. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the power supply control method for a server according to any one of claims 1 to 8 when executing the computer program.

Images