Power-on methods and devices for equipment, storage media and electronic equipment

Abstract

This application provides a device power-on method and apparatus, a storage medium, and an electronic device. The device power-on method includes: obtaining an initial power-on strategy corresponding to a cluster of devices to be powered on; determining a target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy, and determining the current cluster load of the cluster of devices to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the cluster of devices to be powered on; if, based on the current cluster load, it is determined that powering the target device according to the initial power-on strategy would result in a power-on anomaly, adjusting the initial power-on strategy to obtain a target power-on strategy; and powering on the target device based on the target power-on strategy. This addresses the problem in related technologies where device power-on often remains at a basic level, leading to potential power fluctuations and uneven load during device startup, affecting the stability and reliability of the data center.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a power-on method and apparatus for a device, a storage medium, and an electronic device. Background Technology

[0002] With the development of computer technology, the scale of data centers and server clusters continues to expand, leading to an increasing demand for power management and equipment power-on strategies. Among these, the optimized management of the startup process for computer equipment, as an indispensable component of data centers, is receiving increasing attention.

[0003] Traditional BIOS (Basic Input / Output System) power-on strategies mostly remain at the basic level, providing only simple power-on, power-off, and restart functions. While these functions can meet basic startup requirements, they can easily lead to problems such as power fluctuations and uneven loads during startup of data center equipment when facing large-scale data centers, thereby affecting the stability and reliability of the data center.

[0004] Therefore, developing a power-on method that can improve the stability and reliability of data centers has become an important research direction. Summary of the Invention

[0005] This application provides a power-on method and apparatus for a device, a storage medium, and an electronic device, to at least solve the problem in the related art where, when a device is powered on, it often remains at a basic level, which may lead to power fluctuations and uneven loads during device startup, affecting the stability and reliability of the data center.

[0006] According to one embodiment of this application, a method for powering on a device is provided, comprising: obtaining an initial power-on strategy corresponding to a cluster of devices to be powered on; determining a target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy, and determining the current cluster load of the cluster of devices to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the cluster of devices to be powered on; if, based on the current cluster load, it is determined that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, adjusting the initial power-on strategy to obtain a target power-on strategy; and powering on the target device based on the target power-on strategy.

[0007] In one exemplary embodiment, determining the initial power-on strategy includes: determining device attribute parameters of each device in the device cluster to be powered on; determining the power-on priority of each device based on the device attribute parameters of each device; and determining the initial power-on strategy according to the power-on priority of each device.

[0008] In an exemplary embodiment, determining the initial power-on strategy according to the power-on priority of each device includes: determining the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load in the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point at which a power-on instruction for the device cluster to be powered on is obtained, the power-on instruction being an instruction to power on each device in the device cluster to be powered on; determining the delay duration of each device in the device cluster to be powered on based on the cluster load in the historical time period; wherein the delay duration characterizes the duration between obtaining the first time point and a second time point at which each device begins powering on; and determining the initial power-on strategy according to the power-on priority of each device and the delay duration.

[0009] In an exemplary embodiment, the step of adjusting the initial power-on strategy to obtain a target power-on strategy when it is determined that the target device has a power-on anomaly when powered on according to the initial power-on strategy based on the current cluster load includes: comparing the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result shows that the current cluster load is less than the rated load, obtaining the cluster load of the device cluster to be powered on at multiple preset times; selecting a first preset time and a second preset time from the multiple preset times of the device cluster to be powered on, and determining the cluster load at the first preset time as the first cluster load, and determining the cluster load at the second preset time as the second cluster load; wherein, the first preset time is the cluster load among the multiple preset times. The first preset time is the moment with the largest load value; the second preset time is the moment with the shortest interval between the first preset time and the first preset time; based on the difference between the load of the first cluster and the load of the second cluster, the load change of the device cluster to be powered on is determined; the load change is multiplied by a preset base delay duration to obtain the product of the load change and the base delay duration, and the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein, the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the base delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain the target delay duration; the target power-on strategy is obtained based on the target delay duration.

[0010] In an exemplary embodiment, powering on the target device based on the target power-on strategy includes: determining a target delay duration for powering on the target device based on the target power-on strategy; and, if the duration of the power-on command reaches the target delay duration, controlling the target device to perform initialization processing to complete the power-on of the target device.

[0011] In an exemplary embodiment, determining the target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy includes: determining the device with the highest power-on priority in the cluster of devices to be powered on as the target device to be powered on based on the power-on priority specified in the initial power-on strategy.

[0012] In one exemplary embodiment, the method further includes: determining a status parameter associated with the target device; wherein the status parameter is used to characterize the current status of the target device; if it is determined that the target device has a fault based on the device status parameter, ending the power-on of the target device, and determining a new target device from the cluster of devices to be powered on based on the initial power-on strategy; based on the new target device, returning to the step of determining the current cluster load of the cluster of devices to be powered on, until a preset stop condition is met.

[0013] According to another embodiment of this application, a device power-on apparatus is provided, comprising: an acquisition module, configured to acquire an initial power-on strategy corresponding to a cluster of devices to be powered on; a determination module, configured to determine a target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy, and determine the current cluster load of the cluster of devices to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the cluster of devices to be powered on; an adjustment module, configured to adjust the initial power-on strategy to obtain a target power-on strategy when it is determined, based on the current cluster load, that the target device has a power-on anomaly when powered on according to the initial power-on strategy; and a power-on module, configured to power on the target device based on the target power-on strategy.

[0014] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0015] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0016] According to yet another embodiment of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0017] This application obtains an initial power-on strategy corresponding to a cluster of devices to be powered on; based on the initial power-on strategy, it identifies target devices to be powered on from the cluster, avoiding simultaneous power-on of all devices, which could lead to current surges and insufficient power supply, thereby reducing the risk of startup failure. Furthermore, it determines the current cluster load of the cluster of devices to be powered on; wherein the current cluster load characterizes the real-time power capacity of the cluster; if, based on the current cluster load, it is determined that powering on the target device according to the initial power-on strategy would result in a power-on anomaly, the initial power-on strategy is adjusted to obtain a target power-on strategy; and the target device is powered on based on the target power-on strategy. In other words, when a power-on anomaly is determined to occur according to the initial power-on strategy, the power-on strategy can be adjusted in a timely manner to obtain the target power-on strategy, and powering on the target power-on strategy is performed according to the target power-on strategy, avoiding negative impacts of abnormal power-on on the overall operation of the cluster and ensuring the stable startup of the entire cluster. Attached Figure Description

[0018] Figure 1 This is a hardware structure block diagram of a baseboard management controller for a device power-on method according to an embodiment of this application;

[0019] Figure 2 This is a flowchart of a power-on method for a device according to an embodiment of this application;

[0020] Figure 3 This is another flowchart of a power-on method for a device according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of the interface of the power-on method of the device according to an embodiment of this application;

[0022] Figure 5 This is a structural block diagram of the power-on device of the device according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0025] The methods and embodiments provided in this application can be executed in a BMC (Baseboard Management Controller) or a similar computing device, wherein the BMC can be deployed in a computer device or independent of a computer device. Taking running on a BMC as an example, Figure 1 This is a hardware structure block diagram of the BMC for a device power-on method according to an embodiment of this application. For example... Figure 1 As shown, a BMC may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The BMC may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the BMC described above. For example, the BMC may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0026] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the load resource allocation method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a server via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by BMC's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0028] Figure 2This is a flowchart of a power-on method for a device according to an embodiment of this application. The method is illustrated using an example of its application in a BMC (Browser Control Center). Figure 2 As shown, the process includes the following steps:

[0029] Step S202: Obtain the initial power-on strategy corresponding to the cluster of devices to be powered on;

[0030] It should be noted that the initial power-on strategy refers to the preset power-on sequence and parameters of devices before any intelligent optimization or adjustment is performed. It can include key parameters such as device power-on priority, grouping information, power-on priority of each group of devices, device power-on delay time, or device power-on sequence, which are used to guide the initial startup of devices or the startup sequence after power is restored.

[0031] A device cluster refers to a data center consisting of multiple servers or multiple computer terminals.

[0032] In some embodiments, the initial power-on policy can be obtained by accessing non-volatile memory (such as NVRAM or EEPROM), which ensures that data is retained after the server or computer terminal restarts or is powered off. Alternatively, the initial power-on policy can be stored in a system database as part of power management, and then queried and obtained through a software interface.

[0033] In some embodiments, in addition to setting a power-on priority for each device to be powered on, the devices can be divided into different groups based on factors such as service type, hardware configuration, or geographical location, facilitating power-on control in a specific order. Setting a power-on priority for each device group ensures that higher-priority groups receive startup resources first during the power-on process, guaranteeing rapid startup for critical business devices. A power-on delay time can be set for each device group or individual device; this time refers to the time interval from when the main power switch is turned on until the device group or device begins its startup attempt. Setting a power-on delay helps prevent the data center from experiencing excessive startup current in a short period, reducing power load pressure.

[0034] Step S204: Based on the initial power-on strategy, determine the target device to be powered on from the cluster of devices to be powered on, and determine the current cluster load of the cluster of devices to be powered on; wherein, the current cluster load is used to characterize the real-time power capacity of the cluster of devices to be powered on.

[0035] It should be noted that the target device to be powered on can be determined based on the initial power-on strategy read from the database. The determination process can be based on the power-on priority and device grouping in the initial power-on strategy, that is, selecting the target device from the current device cluster for power-on in descending order of priority.

[0036] The current cluster load can refer to the remaining power capacity after deducting the total power consumed by currently running devices and non-powered devices. The BMC can obtain the current and voltage data of the PDU (Power Distribution Unit) to calculate the real-time power consumption of the device cluster, thereby obtaining the current cluster load. When calculating the cluster load, the instantaneous high current demand at the moment the device powers on can also be considered, but this embodiment of the application does not impose any limitations.

[0037] Understandably, the current cluster load can be used to assess the remaining power capacity of the device cluster and whether it can safely and efficiently start the next wave of target devices. If the current cluster load is low, the initial power-on strategy can be adjusted to extend the power-on delay of the target devices to avoid power spikes and ensure the stable operation of the entire device cluster. Conversely, if the current cluster load is close to the data center's maximum capacity, the delay can be appropriately shortened to speed up device startup and improve the data center's responsiveness and efficiency. After determining the target devices and the current cluster load, the power-on strategy is dynamically adjusted based on real-time data and preset optimization algorithms. Possible adjustments include changing the delay time of the target devices, rearranging the startup order of devices, and even adjusting the data center's output power to adapt to current power demands.

[0038] In an exemplary embodiment, determining the target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy includes: determining the device with the highest power-on priority in the cluster of devices to be powered on as the target device to be powered on based on the power-on priority specified in the initial power-on strategy.

[0039] Understandably, the initial power-on strategy assigns a power-on priority to each device or group of devices. This priority can be determined based on factors such as the urgency of the business, the device's hardware configuration, geographical location, or power demand. For example, critical business servers, storage devices, or network core switches may be set to high priority to ensure rapid startup upon power restoration, meeting business continuity and data security requirements.

[0040] When it is determined that a device cluster needs to be powered on, the BMC can first parse the power-on priority information in the initial power-on strategy and sort the devices in the cluster according to their priority. The device with the highest priority will be placed at the beginning of the sequence, meaning that it will receive power resources first during the power-on process. Based on the power-on priority sorting result, the device with the highest priority can be selected as the target device to be powered on.

[0041] In some embodiments, when identifying the target device, the available resources and current load of the device cluster can also be assessed. If the power system has sufficient remaining capacity, the target device will be powered on according to the settings in the initial power-on strategy. Conversely, if the current power system is close to full load, the initial power-on strategy can be dynamically adjusted to extend the power-on delay of the target device, thereby avoiding power peaks and ensuring the stable operation of the data center.

[0042] In other implementations, when power resources are scarce in the equipment cluster, in addition to prioritizing target equipment for power-on, the power-on sequence can be adjusted based on the equipment's power demand. For example, equipment with lower power demand can be started first to ensure a smooth power system transition. When power demand is low, high-priority equipment can be started up more quickly to improve service response speed.

[0043] In a specific application, the target device to be powered on can also be determined according to the device group. If the highest priority device group in the initial power-on strategy is the "critical business server group", then the device can be selected from the critical business server group as the target device to be powered on.

[0044] Step S206: If, based on the current cluster load, it is determined that the target device has a power-on abnormality when powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain the target power-on strategy.

[0045] It should be noted that BMC determines, based on the current cluster load, whether it is close to or exceeds the preset safety threshold. This means that the data center may not be able to withstand the instantaneous high current demand when the target device starts up. It will then determine that there is an abnormal power load, i.e., a power-on abnormality. BMC will intelligently adjust the initial power-on strategy based on the real-time cluster load and device status.

[0046] When adjusting the initial power-on strategy, adjustments can be made to the power-on delay time of the target device. If the current cluster load is close to full load, the power-on delay time of the target device can be extended to avoid power peaks and ensure the stable operation of the power system.

[0047] Step S208: Power on the target device based on the target power-on strategy.

[0048] In an exemplary embodiment, powering on the target device based on the target power-on strategy includes: determining a target delay duration for powering on the target device based on the target power-on strategy; and, if the duration of the power-on command reaches the target delay duration, controlling the target device to perform initialization processing to complete the power-on of the target device.

[0049] It's important to note that upon receiving a power-on command, the BMC begins timing, monitoring the duration from the command's issuance to the current moment. This monitoring ensures the power system accurately controls the power-on timing of devices when executing its power-on strategy, preventing premature or delayed power-on. Once the duration reaches the target delay, the BMC sends an initialization command to the target device, initiating the power-on process. Initialization typically includes hardware detection, system software loading, and device status checks to ensure safe and orderly startup. The initialization process can also run a pre-startup check procedure to ensure the device's hardware and software meet startup requirements, preventing startup failures or post-startup anomalies.

[0050] In the above embodiments, the BMC can precisely control the power-on time of the target device based on the target power-on strategy, and complete the safe and orderly startup of the target device while ensuring the stable operation of the device cluster. This process avoids the negative impact of abnormal power-on on the operation of the overall cluster and ensures the stable startup of the entire device cluster.

[0051] Through the above steps, an initial power-on strategy corresponding to the cluster of devices to be powered on is obtained. Based on the initial power-on strategy, the target devices to be powered on are determined from the cluster, avoiding all devices from being powered on at the same time, which could lead to current surges and insufficient power supply, thereby reducing the risk of startup failure. Furthermore, the current cluster load of the cluster of devices to be powered on is determined; the current cluster load represents the real-time power capacity of the cluster. If, based on the current cluster load, it is determined that powering the target device according to the initial power-on strategy would result in a power-on anomaly, the initial power-on strategy is adjusted to obtain a target power-on strategy. The target device is then powered on based on the target power-on strategy. In other words, if a power-on anomaly is determined to occur when powering on according to the initial power-on strategy, the power-on strategy can be adjusted in a timely manner to obtain the target power-on strategy, and powering on the target power-on strategy is performed according to the target power-on strategy, avoiding negative impacts on the overall operation of the cluster and ensuring the stable startup of the entire cluster.

[0052] In one exemplary embodiment, determining the initial power-on strategy includes: determining device attribute parameters of each device in the device cluster to be powered on; determining the power-on priority of each device based on the device attribute parameters of each device; and determining the initial power-on strategy according to the power-on priority of each device.

[0053] Understandably, for each device, the BMC can collect its device attribute parameters, which may include device type, hardware configuration, power requirements, business importance, geographical location, and health status. For example, a mission-critical server may have high computing and storage capabilities, while also requiring significant power support; and a network switch may be located at the core of the cluster, crucial to the connectivity of the entire network.

[0054] BMC can determine the power-on priority of each device based on its attribute parameters using a preset priority algorithm. This algorithm may comprehensively consider factors such as device hardware configuration, business importance, power demand, geographical location, and health status to determine the most reasonable power-on sequence. Based on the calculated priorities, devices are sorted, with higher-priority devices listed first, meaning they will receive power resources first when power is restored.

[0055] Based on the determined power-up priority, an initial power-up policy is constructed. This policy includes the device startup order, power-up delay time, and possible power resource allocation plan. The constructed initial power-up policy is stored in the BIOS or BMC configuration so that it can be automatically read and applied on the next boot. The BMC can also synchronize the power-up policy to other management components within the data center, such as PDUs, through out-of-band programs such as Redfish (an open standard), to achieve global power resource management and power-up control.

[0056] In the above embodiments, the BMC can intelligently determine the power-on priority based on device attribute parameters and construct an initial power-on strategy accordingly. This strategy not only ensures the priority startup of critical business equipment but also fully considers the rational allocation of power resources and the orderly progress of the power-on process, representing an important manifestation of intelligent power management in data centers.

[0057] In an exemplary embodiment, determining the initial power-on strategy according to the power-on priority of each device includes: determining the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load in the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point at which a power-on instruction for the device cluster to be powered on is obtained, the power-on instruction being an instruction to power on each device in the device cluster to be powered on; determining the delay duration of each device in the device cluster to be powered on based on the cluster load in the historical time period; wherein the delay duration characterizes the duration between obtaining the first time point and a second time point at which each device begins powering on; and determining the initial power-on strategy according to the power-on priority of each device and the delay duration.

[0058] It should be noted that BMC can determine the power consumption data of the equipment cluster over a historical period prior to the issuance of the power-on command. This data reflects the power demand and consumption patterns of the equipment cluster under normal operating conditions. By analyzing historical power consumption data, key indicators such as the average load, peak load, and load change trends of the equipment cluster can be calculated. These indicators provide important references for predicting the power demand of the equipment under the current power-on command.

[0059] Based on historical load data and combined with device attribute parameters (such as power demand), the power-on delay time for each device is calculated. This delay is typically used to avoid power peaks and ensure a smooth transition of the power system.

[0060] An initial power-on strategy is constructed based on the device's power-on priority and the calculated delay duration. This strategy specifies in detail the device startup sequence, delay time, and power resource allocation plan. The initial power-on strategy is stored in the BIOS or BMC configuration. When a power-on command is received, this strategy is loaded and executed to control the device's power-on process.

[0061] In the above embodiments, by combining the cluster load of the devices to be powered on during historical time periods, the initial power-on strategy can be intelligently determined, ensuring that power resources can be rationally allocated during peak power demand periods, while avoiding the impact of power peaks on the power system. This strategy not only considers the business importance and power demand of the devices, but also combines the real-time status of the power system and historical load trends, providing an efficient and stable solution for data center power management.

[0062] In an exemplary embodiment, the step of adjusting the initial power-on strategy to obtain a target power-on strategy when it is determined that the target device has a power-on anomaly when powered on according to the initial power-on strategy based on the current cluster load includes: comparing the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result shows that the current cluster load is less than the rated load, obtaining the cluster load of the device cluster to be powered on at multiple preset times; selecting a first preset time and a second preset time from the multiple preset times of the device cluster to be powered on, and determining the cluster load at the first preset time as the first cluster load, and determining the cluster load at the second preset time as the second cluster load; wherein, the first preset time is the cluster load among the multiple preset times. The first preset time is the moment with the largest load value; the second preset time is the moment with the shortest interval between the first preset time and the first preset time; based on the difference between the load of the first cluster and the load of the second cluster, the load change of the device cluster to be powered on is determined; the load change is multiplied by a preset base delay duration to obtain the product of the load change and the base delay duration, and the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein, the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the base delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain the target delay duration; the target power-on strategy is obtained based on the target delay duration.

[0063] Understandably, the BMC compares the current cluster load with the rated load of the target device to determine if there is a potential risk of insufficient power resources. If the current cluster load is less than the rated load, it indicates that the remaining load of the device cluster is less than the rated load, power resources are insufficient, and delay measures need to be implemented. If the current cluster load is greater than the rated load, it indicates that the remaining load of the device cluster is greater than the rated load, power resources are sufficient, and delay measures are not required.

[0064] BMC can locate and retrieve cluster load data at multiple preset times, which can be within hours or days prior to the power-on command. From these preset times, the time with the highest cluster load is selected as the first preset time, and the time with the shortest time interval to the first preset time is selected as the second preset time, for analyzing load change trends. The difference between the first cluster load (load at the first preset time) and the second cluster load (load at the second preset time) is calculated, representing the load change.

[0065] The delay adjustment is calculated by multiplying the load change by a pre-set base delay duration and then dividing the product by the rated load of the cluster of devices to be powered on. This delay adjustment reflects the degree to which the load change affects the delay duration adjustment. Based on the calculated delay adjustment, the delay duration of the target devices is adjusted; if the load change leads to an increase in load, the delay is increased, and vice versa. The target delay duration, i.e., the adjusted device power-on delay time, is determined based on the adjusted delay value. The updated delay information is integrated into the initial power-on strategy to form the target power-on strategy, which guides the subsequent device power-on process. When powering on, the target power-on strategy is followed, controlling the device startup sequence and delay duration to ensure the rational allocation of power resources and stable device startup.

[0066] In the above embodiments, changes in power demand are monitored and responded to in real time, and the initial power-on strategy is intelligently adjusted to optimize the allocation of power resources, avoid the occurrence of power peaks, and thus improve the operating efficiency of the data center and the reliability of power management.

[0067] In one exemplary embodiment, the method further includes: determining a status parameter associated with the target device; wherein the status parameter is used to characterize the current status of the target device; if it is determined that the target device has a fault based on the device status parameter, ending the power-on of the target device, and determining a new target device from the cluster of devices to be powered on based on the initial power-on strategy; based on the new target device, returning to the step of determining the current cluster load of the cluster of devices to be powered on, until a preset stop condition is met.

[0068] It should be noted that the BMC (Baseboard Management Controller) can continuously collect status parameters of the target device. These parameters can include the device's hardware status (such as CPU (Central Processing Unit) temperature, memory status, power module failure, etc.), software status (such as operating system status, service operation status, etc.), and environmental parameters (such as data center temperature, humidity, etc.). The collected status parameters are analyzed in real time to determine whether the device is in normal working condition and whether there are any potential fault risks.

[0069] If the status parameter analysis results indicate a fault in the target device, it can be determined whether the device can be safely powered on. If the fault would cause the device to fail to power on or affect the stability of the power system, the power-on operation for the target device will be terminated. The faulty device can be removed from the power-on queue to ensure that it does not affect the power-on process of subsequent devices. Based on the priority order of devices in the initial power-on strategy, the system will determine a new target device from the cluster of devices waiting to be powered on, i.e., the next device that should be started according to the power-on strategy.

[0070] Based on the new target equipment, the current cluster load of the equipment cluster to be powered on is reassessed to determine whether power resources are sufficient and whether the delayed power-on strategy needs adjustment. If the current cluster load still meets the power distribution requirements, the power-on strategy will continue to be executed; if the load situation changes, the delay parameters in the power-on strategy will be adjusted to adapt to changes in power demand. The power-on process is continuously monitored until a preset stop condition is met. The preset stop condition may include, but is not limited to: all equipment to be powered on has completed power-on, power resources have reached a preset threshold, or a manual command to stop power-on has been received.

[0071] In the above embodiments, the system can intelligently monitor and respond to changes in device status, ensuring the safety of the power-on process and the rational allocation of power resources. When a device malfunctions, the system can quickly adjust the power-on strategy, eliminate the faulty device, and select a new target device to continue the power-on process, thereby reducing the impact of device failures on data center operations and improving the flexibility and reliability of power management.

[0072] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they 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 this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0073] To better understand the power-on method of the above-mentioned device, the implementation process of the power-on method of the above-mentioned device will be described below in conjunction with optional embodiments, but this is not intended to limit the technical solution of the embodiments of this application.

[0074] Existing power-on policies are mostly basic, offering only simple functions like power on, power off, and restart. They lack intelligent management and decision-making capabilities, failing to dynamically adjust power-on policies based on the server's actual operating status or power load. This low level of intelligence limits the efficient operation and stability of data centers, especially in large-scale server clusters, potentially leading to inefficient startup and energy waste. They typically lack flexible configuration options and cannot be customized to specific needs. For example, they cannot set server startup priorities, latency times, or group management based on server type. This lack of flexibility makes it difficult to respond flexibly to complex and changing operating environments, increasing the complexity and difficulty of maintenance. Furthermore, existing power-on policies often lack real-time monitoring and dynamic adjustment capabilities. They cannot automatically adjust power-on policies based on real-time data such as power load and server status. This static power-on policy may lead to power fluctuations and uneven loads during server startup, affecting system stability and reliability. Moreover, many traditional configuration interfaces in existing technologies are complex and difficult to operate, making power-on policy configuration a daunting task for non-professionals. This not only increases the error rate of configuration, but may also lead to system startup failure or performance degradation.

[0075] This application aims to address a series of core problems existing in the current technical field, which mainly stem from the limitations of existing technical solutions and their inability to meet the growing market demands and technological advancements. Specifically, this application is committed to solving the following comprehensive technical problems: First, this application focuses on improving the level of intelligence. Existing technical solutions often lack intelligent decision-making and management capabilities, and cannot dynamically adjust based on real-time data and system status. This leads to problems such as low system efficiency, resource waste, and inability to respond promptly to environmental changes. This application can automatically optimize the system status based on real-time data, improving overall performance and efficiency. Second, in terms of control strategies, while some existing advanced BIOS functions have begun to introduce intelligent elements, they are often limited to the optimization of single hardware components, such as CPU frequency adjustment, lacking systematic power-on strategy management. This application, however, adopts a more refined control strategy, achieving comprehensive and multi-level management of the power-on process through server grouping, priority settings, and delay time adjustments. This refined control not only ensures priority power-on for critical business servers but also effectively reduces power supply load pressure through staggered power-on, avoiding the potential threat of current surges to system stability.

[0076] refer to Figure 3The diagram shows a flowchart of the power-on method for the device described in this application. For a data center consisting of multiple servers, firstly, in the setup phase 302, the BIOS interface can be accessed through the BIOS setup interface or a remote management interface (such as IPMI, KVM, etc.). This is typically done during the server startup process of a server cluster, by using a specific key combination (such as the Del key, F2 key, etc.) to enter the BIOS setup menu and navigate to the configuration section related to the power-on strategy.

[0077] refer to Figure 4 The image shows a schematic of the BIOS settings interface. This interface includes several modules such as AC (Alternating Current) control policy, power-on delay policy, device grouping, rack number, and power-on delay time. Users can access the desired module to view and configure settings. Each module allows for the definition of parameters. For example, a user can view the power-on delay module, set the delay time to 5 minutes, identify the server's rack number as 001, determine the device group as Grub1, and set the power-on delay policy to Auto (Automatic).

[0078] In the BIOS, you can find one or more server grouping options. Servers can be divided into different groups based on their actual usage, such as business type, geographical location, and hardware configuration. For each group, users can set its startup priority, typically by dragging, selecting, or entering numbers. Higher-priority groups will have priority access to startup resources during power-on. After setting the groups and priorities, users need to set a boot delay time for each group or individual server. This delay time refers to the time interval between the main power switch being turned on and the group or server attempting to start. Users can set different delay times for different groups or servers according to actual needs and power load conditions to achieve staggered power-on.

[0079] After all settings are completed, the initial power-on policy is obtained, and then the process enters step 304, which means that the initial power-on policy is written to the memory unit. Typically, the initial power-on policy can be stored in non-volatile memory (such as NVRAM) so that these settings can be automatically loaded and applied on the next boot.

[0080] Further, the process proceeds to machine power-on step 306, specifically referring to the main power-on. When the data center's main power switch is turned on, the BMC begins executing the preset initial power-on strategy. At this point, the BMC enters the initial power-on strategy reading step 308, first checking and loading the initial power-on strategy stored in NVRAM. Based on the loaded configuration information, and according to the preset priority and delay time order, the server with the highest priority is selected as the target device to be powered on.

[0081] After identifying the target device to be powered on, the system enters the dynamic adjustment phase 310. The BMC monitors power data and provides functional support, determining if any abnormalities exist during the power-on process based on real-time monitoring information. These abnormalities may include excessive power load, server failure to start, or network latency causing startup timeouts. The BMC automatically analyzes and adjusts the power-on strategy based on these abnormalities. For example, if the power load is too high, the management module will modify the BIOS settings out-of-band to increase the latency of subsequent server groups, reducing the number of servers powered on simultaneously. If a server fails to start, the BMC may skip that server and continue starting other servers. The adjusted power-on strategy takes effect immediately, and the BMC modifies BIOS options out-of-band via Redfish and continues to control the server power-on process according to the new strategy.

[0082] Delay settings are displayed and configured in the BIOS, but actual control relies on the BMC for delay. When the power-on policy is set to manual, the relevant power-on policy is transmitted to the BMC via Redfish (an open standard). When an administrator performs a power-on operation (starting or turning on electronic devices) through the BMC, the BMC will perform a delay before executing the power-on command. Furthermore, for server security reasons, the physical power-on button's power-on policy remains the highest priority; powering on via an external power button ignores the BIOS's power-on delay policy. When the power-on delay policy is set to Auto, the BMC performs a delay based on the intelligent control system's allocation before executing the power-on command.

[0083] After receiving the group information from the server, the BMC reads the PDU information of the group containing the server and obtains the current load occupancy of the PDU. When the current remaining load power is less than the server's rated power, the BMC executes a delayed power-on measure. The BMC reads the power information three times within one minute and predicts the power load of the subsequent PDUs based on the current power change trend. The greater the power decrease trend, the shorter the delay time. Conversely, if the power increases, the power-on delay time is appropriately extended according to the power increase. The extension time is (power increase * 60 / PDU rated power percentage) seconds.

[0084] The power-on method of the device described in this application, through intelligent management and dynamic adjustment mechanisms, brings significant benefits to data centers, including improved system stability and reliability, reduced operation and maintenance costs and difficulty, enhanced system flexibility and adaptability, improved resource utilization efficiency, and improved user experience and satisfaction. These effects collectively contribute to the overall performance and management level of the data center, providing users with a more efficient, stable, and reliable server operating environment.

[0085] This embodiment also provides a power-on device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0086] Figure 5 This is a structural block diagram of the power-on device of the device according to an embodiment of this application, such as... Figure 5 As shown, the device includes:

[0087] The acquisition module 52 is used to acquire the initial power-on strategy corresponding to the cluster of devices to be powered on;

[0088] The determination module 54 is used to determine the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and to determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on.

[0089] Adjustment module 56 is used to adjust the initial power-on strategy to obtain the target power-on strategy when it is determined that the target device has a power-on abnormality when powering on according to the initial power-on strategy based on the current cluster load.

[0090] The power-on module 58 is used to power on the target device based on the target power-on strategy.

[0091] The aforementioned device acquires an initial power-on strategy corresponding to the cluster of devices to be powered on. Based on this initial power-on strategy, it identifies the target devices to be powered on from the cluster, preventing all devices from powering on simultaneously, which could lead to current surges and insufficient power supply, thus reducing the risk of startup failure. Furthermore, it determines the current cluster load of the cluster of devices to be powered on; the current cluster load characterizes the real-time power capacity of the cluster. If, based on the current cluster load, it is determined that powering the target device according to the initial power-on strategy would result in a power-on anomaly, the initial power-on strategy is adjusted to obtain a target power-on strategy. The target device is then powered on based on this target power-on strategy. In other words, when a power-on anomaly is determined to occur according to the initial power-on strategy, the power-on strategy can be adjusted promptly to obtain the target power-on strategy, and powering on the target power-on strategy is performed accordingly, avoiding negative impacts on the overall operation of the cluster and ensuring a stable startup of the entire cluster.

[0092] In an exemplary embodiment, the acquisition module 52 is further configured to determine the device attribute parameters of each device in the device cluster to be powered on; determine the power-on priority of each device based on the device attribute parameters of each device; and determine the initial power-on strategy according to the power-on priority of each device.

[0093] In an exemplary embodiment, the acquisition module 52 is further configured to determine the cluster load of the device cluster to be powered on during a historical time period; wherein the cluster load during the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point at which a power-on instruction for the device cluster to be powered on is obtained, the power-on instruction being an instruction to power on each device in the device cluster to be powered on; based on the cluster load during the historical time period, the delay duration of each device in the device cluster to be powered on is determined; wherein the delay duration characterizes the duration between obtaining the first time point and the second time point at which each device begins to power on; and the initial power-on strategy is determined according to the power-on priority of each device and the delay duration.

[0094] In an exemplary embodiment, the adjustment module 56 is further configured to compare the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result indicates that the current cluster load is less than the rated load, to obtain the cluster load of the device cluster to be powered on at multiple preset times; to select a first preset time and a second preset time from the multiple preset times of the device cluster to be powered on, and to determine the cluster load at the first preset time as the first cluster load, and the cluster load at the second preset time as the second cluster load; wherein, the first preset time is the time when the cluster load value is the largest among the multiple preset times; the second preset time is the interval between the first preset time and the first preset time. The shortest time interval is determined; based on the difference between the load of the first cluster and the load of the second cluster, the load change of the device cluster to be powered on is determined; the load change is multiplied by a pre-set base delay duration to obtain the product of the load change and the base delay duration, and the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein, the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the base delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain the target delay duration; the target power-on strategy is obtained based on the target delay duration.

[0095] In an exemplary embodiment, the power-on module 58 is further configured to determine a target delay duration for powering on the target device based on the target power-on strategy; and, if the duration of the power-on command reaches the target delay duration, control the initialization process of the target device to complete the power-on of the target device.

[0096] In one exemplary embodiment, the determining module 54 is further configured to determine the device with the highest power-on priority in the cluster of devices to be powered on as the target device to be powered on, based on the power-on priority specified in the initial power-on strategy.

[0097] In one exemplary embodiment, the apparatus further includes a processing module; the processing module is configured to determine a status parameter associated with the target device; wherein the status parameter is used to characterize the current status of the target device; if it is determined that the target device has a fault based on the device status parameter, the power-on process for the target device is terminated, and a new target device is determined from the cluster of devices to be powered on based on the initial power-on strategy; based on the new target device, the process returns to the step of determining the current cluster load of the cluster of devices to be powered on, until a preset stop condition is met.

[0098] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0099] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0100] Embodiments of this application also provide 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 perform the steps in any of the above method embodiments.

[0101] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0102] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0103] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0104] Embodiments of this application also provide a computer program that includes computer instructions stored in a computer-readable storage medium; a processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the steps in any of the above method embodiments.

[0105] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0106] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0107] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for powering on a device, characterized in that, include: Obtain the initial power-on policy corresponding to the cluster of devices to be powered on; Based on the initial power-on strategy, the target device to be powered on is determined from the cluster of devices to be powered on, and the current cluster load of the cluster of devices to be powered on is determined; wherein, the current cluster load is used to characterize the real-time power capacity of the cluster of devices to be powered on. The current cluster load is compared with the rated load of the target device to obtain a load comparison result. If the load comparison result indicates that the current cluster load is less than the rated load, the cluster load of the device cluster to be powered on is obtained at multiple preset times. A first preset time and a second preset time are selected from the multiple preset times of the device cluster to be powered on, and the cluster load at the first preset time is determined as the first cluster load, and the cluster load at the second preset time is determined as the second cluster load. Wherein, the first preset time is the time with the largest cluster load value among the multiple preset times; the second preset time is the time with the shortest interval from the first preset time. Based on the... The load difference between the first cluster load and the second cluster load is used to determine the load change of the device cluster to be powered on; the load change is multiplied by a pre-set base delay duration to obtain the product of the load change and the base delay duration; the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein, the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the base delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain a target delay duration; a target power-on strategy is obtained based on the target delay duration; The target device is powered on based on the target power-on strategy.

2. The method according to claim 1, characterized in that, Determining the initial power-on strategy includes: Determine the device attribute parameters of each device in the cluster of devices to be powered on; Based on the device attribute parameters of each device, the power-on priority of each device is determined; The initial power-on strategy is determined according to the power-on priority of each device.

3. The method according to claim 2, characterized in that, Determining the initial power-on strategy according to the power-on priority of each device includes: Determine the cluster load of the device cluster to be powered on in a historical time period; wherein, the cluster load in the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point at which the power-on instruction for the device cluster to be powered on is obtained, and the power-on instruction is an instruction used to instruct each device in the device cluster to be powered on to be powered on. Based on the cluster load during the historical time period, the delay duration of each device in the device cluster to be powered on is determined; wherein, the delay duration represents the duration between the first time point of acquisition and the second time point at which each device begins to power on; The initial power-on strategy is determined according to the power-on priority of each device and the delay duration.

4. The method according to claim 1, characterized in that, The step of powering on the target device based on the target power-on strategy includes: Based on the target power-on strategy, the target delay duration for powering on the target device is determined; If the duration of the power-on command reaches the target delay duration, the system controls the initialization process of the target device to complete the power-on of the target device.

5. The method according to claim 1, characterized in that, The step of determining the target device to be powered on from the cluster of devices to be powered on based on the initial power-on strategy includes: Based on the power-on priority specified in the initial power-on strategy, the device with the highest power-on priority in the cluster of devices to be powered on is determined as the target device to be powered on.

6. The method according to claim 1, characterized in that, The method further includes: Determine the state parameters associated with the target device; wherein the state parameters are used to characterize the current state of the target device; If the target device is determined to be faulty based on the device status parameters, the power-on process for the target device is terminated, and a new target device is determined from the cluster of devices to be powered on based on the initial power-on strategy. Based on the new target device, return to the step of determining the current cluster load of the device cluster to be powered on, until the preset stop condition is met.

7. A power-on device for an apparatus, characterized in that, include: The acquisition module is used to acquire the initial power-on strategy corresponding to the cluster of devices to be powered on. The determination module is used to determine the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and to determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on. An adjustment module is used to compare the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result shows that the current cluster load is less than the rated load, the module obtains the cluster load of the device cluster to be powered on at multiple preset times; selects a first preset time and a second preset time from the multiple preset times of the device cluster to be powered on, and determines the cluster load at the first preset time as the first cluster load, and the cluster load at the second preset time as the second cluster load; wherein, the first preset time is the time with the largest cluster load value among the multiple preset times; the second preset time is the time with the shortest interval from the first preset time; Based on the difference between the load of the first cluster and the load of the second cluster, the load change of the device cluster to be powered on is determined; the load change is multiplied by a pre-set base delay duration to obtain the product of the load change and the base delay duration; the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein, the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the base delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain a target delay duration; a target power-on strategy is obtained based on the target delay duration; The power-on module is used to power on the target device based on the target power-on strategy.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 6.

Images