Power supply control method, power supply device, electronic device and computer program product

Abstract

The embodiment of the invention provides a power supply control method, power supply equipment, electronic equipment and a computer program product, and relates to the field of computers, and the method comprises the steps: detecting the actual total load of the power supply equipment; a target total load interval where the actual total load is located is determined, different total load intervals are associated with different power supply total loss curves, and each power supply total loss curve comprises at least one power supply total loss curve segment; according to a target power supply total loss curve associated with the target total load interval, determining the target number of the active power supply units when the actual power supply total loss is minimum under the actual total load; and controlling the target number of power supply units to be in an active state. Through the method and the device, the problem of resource waste caused by determining the corresponding load rate when the efficiency of the active power supply units is relatively high according to the empirical value, then determining the number of the active power supply units according to the total power supply load and the load rate and controlling the corresponding number of power supply units to work is solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the computer field, and in particular, to a power supply control method, a power supply device, an electronic device, and a computer program product. Background Art

[0002] In the whole cabinet server, centralized power supply technology can be used to power the server nodes. That is, a Powershelf is set up in the cabinet to output power to the copper busbars at the back of the cabinet, and the server nodes connected to each copper busbar obtain power from the copper busbars. Multiple PSUs (Power Supply Units) are set up inside the Powershelf. The AC power input of the PSU is converted into DC power after power conversion and output to the copper busbars.

[0003] Multiple PSUs in the Powershelf support two modes: Active (active, outputting power) and Standby (sleeping, not outputting power). In the related art, the load rate corresponding to the higher efficiency of the active PSU is determined based on empirical values, and then the number of active PSUs is determined based on the total load and load rate, and the remaining PSUs are set to sleep mode. However, the total power loss of this power supply control method in the related art is not the minimum value, and there is a certain waste of resources. Summary of the invention

[0004] The embodiments of the present application provide a power supply control method, a power supply device, an electronic device, and a computer program product to at least solve the problem of waste of resources in the related art of determining the load rate corresponding to a higher efficiency of an active power supply unit based on empirical values, and then determining the number of active power supply units based on the total power supply load and the load rate of the active power supply unit, and controlling the operation of the corresponding number of power supply units.

[0005] According to an embodiment of the present application, a power supply control method is provided, comprising: detecting an actual total load of a power supply device, wherein the power supply device comprises a plurality of power supply units; determining a target total load interval in which the actual total load is located, wherein different total load intervals are associated with different total power loss curves, each total power loss curve characterizing the relationship between the total power loss and the number of active power supply units, each total power loss curve comprising at least one total power loss curve segment, and different total power loss curve segments characterizing the relationship between the total power loss of the active power supply unit and the number of active power supply units under different load rate intervals, wherein the load rate is a ratio of the total load to the number of active power supply units; determining a target number of active power supply units when the actual total power loss under the actual total load is minimized according to the target total power loss curve associated with the target total load interval, wherein the actual total power loss comprises the actual dynamic power loss of the active power supply unit and the actual static power loss of the dormant power supply unit, and the target number is the number of active power supply units that need to be set; and controlling the target number of power supply units to be in an active state.

[0006] In an exemplary embodiment, the relationship between the total power supply loss and the number of active power supply units in different load rate intervals of the active power supply unit is determined in the following manner: for a target load rate interval in different load rate intervals, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval; based on the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval, and the relationship between the load rate of the active power supply unit and the number of active power supply units, determining the relationship between the total power supply loss and the number of active power supply units in the target load rate interval.

[0007] In an exemplary embodiment, the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval is determined in the following manner: determining the relationship between the dynamic power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a dynamic loss relationship; determining the relationship between the static power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a static loss relationship; based on the static loss relationship and the dynamic loss relationship, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval.

[0008] In an exemplary embodiment, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized based on the target total power loss curve associated with the target total load interval includes: when the actual total load is in the target total load interval, if the total power loss and the number of active power supply units are anti-correlated when the number of active power supply units is different, then the total number of power supply units of the power supply device is determined as the target number.

[0009] In an exemplary embodiment, different total load intervals include a first total load interval, a second total load interval, a third total load interval and a fourth total load interval, wherein the upper limit of the fourth total load interval is equal to the lower limit of the third total load interval, the upper limit of the third total load interval is equal to the lower limit of the second total load interval, the upper limit of the second total load interval is equal to the lower limit of the first total load interval, the lower limit of the first total load interval is equal to half of the maximum total load of the power supply equipment, the lower limit of the second total load interval is the total load value corresponding to the rising inflection point of the total power supply loss when the total load is less than the lower limit of the first total load interval, and the lower limit of the third total load interval is the total load value corresponding to the falling inflection point of the total power supply loss when the total load is less than the lower limit of the second total load interval.

[0010] In an exemplary embodiment, under a first total load interval, the load rate of the active power supply unit is in a first load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, and according to a target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: when the target total load interval is the first total load interval, obtaining a first relationship associated with when the load rate of the active power supply unit under the first total load interval is in the first load rate interval, wherein the first relationship indicates that the total power supply loss and the number of active power supply units are inversely correlated; and determining the total number of power supply units of the power supply device as the target number according to the first relationship.

[0011] In an exemplary embodiment, in the second total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, and the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, and according to the target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: when the target total load interval is the second total load interval, obtaining a first relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the first load rate interval, and a second relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the second load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated; and determining the total number of power supply units of the power supply device as the target number according to the first relationship and the second relationship.

[0012] In an exemplary embodiment, in the case of a third total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, or the third load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, and the actual power supply total loss under the actual total load is determined according to the target total power supply loss curve associated with the target total load interval. The target number of active power supply units when the loss is minimized includes: when the target total load interval is the third total load interval, obtaining a first relationship associated with the load rate of the active power supply units in the third total load interval when they are in the first load rate interval, a second relationship associated with the load rate in the second load rate interval, and a third relationship associated with the load rate in the third load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; determining that the actual total power supply loss is minimized when the actual total load is at the lower limit of the second load rate interval according to the first relationship, the second relationship, and the third relationship, and determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval.

[0013] In an exemplary embodiment, determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval includes: calculating the product of the rated power of the power supply unit and the lower limit of the second load rate interval to obtain the set load of each active power supply unit; determining the target number based on the ratio of the actual total load and the set load of each active power supply unit.

[0014] In an exemplary embodiment, in the fourth total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval or the third load rate interval or the fourth load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, the upper limit of the fourth load rate interval is equal to the lower limit of the fourth total load interval, and the target power supply total load interval is associated with the target power supply total load interval. Loss curve, determining the target number of active power supply units when the actual total power loss under the actual total load is the smallest includes: when the target total load is the fourth total load interval, obtaining the first relationship associated when the load rate of the active power supply unit under the fourth total load interval is in the first load rate interval, the second relationship associated when it is in the second load rate interval, the third relationship associated when it is in the third load rate interval, and the fourth relationship associated when it is in the fourth load rate interval, wherein the first relationship, the second relationship, and the fourth relationship respectively indicate that the total power loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power loss and the number of active power supply units are positively correlated; according to the first relationship, the second relationship, the third relationship, and the fourth relationship, determining the target number of active power supply units when the actual total power loss under the actual total load is the smallest.

[0015] In an exemplary embodiment, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized according to the first relationship, the second relationship, the third relationship and the fourth relationship includes: determining the set number of active power supply units when the actual total power loss is minimized based on the actual total load and the lower limit of the second load rate interval, controlling the load rates of the active power supply units of the set number of power supply units of the power supply device to be within the lower limit of the second load rate interval, and recording the input power of the power supply device to obtain a first input power; controlling the load rates of the active power supply units of all power supply units of the power supply device to be in an active state, and recording the input power of the power supply device to obtain a second input power; when the first input power is less than the second input power, determining the target number by the set number; and when the first input power is greater than or equal to the second input power, determining the total number of power supply units of the power supply device as the target number.

[0016] In an exemplary embodiment, the lower limit of the second total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the first total load interval, keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to decrease and an upward inflection point appears, and determining the load corresponding to the rising inflection point as the lower limit of the second total load interval; the lower limit of the third total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the second total load interval, and keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to increase and a downward inflection point appears, and determining the load corresponding to the downward inflection point as the lower limit of the third total load interval.

[0017] According to another embodiment of the present application, a power supply device is provided, including: a plurality of power supply units; and a controller, wherein a power supply control method of the controller controls a target number of power supply units among the plurality of power supply units to be in an active state.

[0018] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0019] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0020] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0021] Through the present application, the actual total load of the power supply equipment is monitored in real time, and then the monitored total load is positioned within the target total load interval in multiple total load intervals, and the total power loss curve matching the target total load interval is obtained, each total power loss curve includes at least one total power loss curve segment, which characterizes the relationship between the total power loss and the number of active power supply units under the corresponding load rate interval. Since the total power loss in the target total power loss curve includes the dynamic power loss of the active power supply unit and the static power loss of the dormant power supply unit, the target number of active power supply units when the total power loss is minimized is determined according to the target total power loss curve, and the target number of power supply units is controlled to be in an active state, and the remaining power supply units are controlled to be in a dormant state, so that the power supply equipment can not only meet the power demand of the server, but also reduce the dynamic loss and static loss of unnecessary power supply units. Thus, the problem of resource waste in the related art is solved, in which the load rate corresponding to the high efficiency of the active power supply unit is determined according to the empirical value, and then the number of active power supply units is determined according to the total power load and the load rate of the active power supply unit, and the corresponding number of power supply units are controlled to work, and the power efficiency of the entire power supply equipment is optimized and the operating cost is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 paying any creative work.

[0023] Figure 1 is a schematic diagram of the front of a cabinet of an AI super-node whole-cabinet server according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of the back of a cabinet of an AI super-node whole-cabinet server according to an embodiment of the present application;

[0025] Figure 3 Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 1 ;

[0026] Figure 4Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 2 ;

[0027] Figure 5 Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 3 ;

[0028] Figure 6 is a flow chart of a power supply control method according to an embodiment of the present application;

[0029] Figure 7 is a curve showing the relationship between the efficiency and the load rate of the active power supply unit according to an embodiment of the present application;

[0030] Figure 8 is a total power supply loss curve associated with the first total load interval according to an embodiment of the present application;

[0031] Fig. 9 is a total power supply loss curve associated with a second total load interval according to an embodiment of the present application;

[0032] Fig.10 is a total power supply loss curve associated with a third total load interval according to an embodiment of the present application;

[0033] Fig.11 is a total power supply loss curve associated with a fourth total load interval according to an embodiment of the present application;

[0034] Fig.12 It is a structural block diagram of a power supply control device according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0037] With the continuous development of artificial intelligence technology, AI (Artificial Intelligence) model training and reasoning have attracted more and more attention. As the key infrastructure supporting AI model training and reasoning, the new generation of computing cluster architecture is facing severe performance challenges. The marginal benefits of single server processor performance are decreasing, approaching the physical limit, and it is difficult to meet the continuous growth demand for computing power of large AI models. At the same time, the horizontal expansion strategy of computing clusters by simply increasing the number of servers has also encountered bottlenecks in efficiency and scalability, and faces challenges including cost, data synchronization and energy consumption, which hinders the efficient execution of large-scale parallel computing. In this context, the AI ​​super-node whole cabinet system came into being. It systematically integrates multiple groups of GPU (Graphics Processing Unit) computing units and switching units through an innovative topological architecture, and comprehensively optimizes the integration of multiple computing power, high-speed advanced interconnection, heat dissipation, high power density power supply, and whole cabinet management. It provides a scalable high-bandwidth domain (HBD) super node system with 32 cards or more to meet the cutting-edge large model training and reasoning needs.

[0038] Figure 1 is a schematic diagram of the front of a cabinet of an AI super node whole cabinet server according to an embodiment of the present application. Figure 1 As shown, the number of Us represents the number of layers of the whole cabinet server cabinet. The height of each U position can be adjusted. Generally, the square hole bar of each node of the cabinet can be set to OU (48mm), RU (44.45mm) or SU (46.5mm) in three specifications, but not limited to. The various components of the server can be deployed in each layer of the whole server cabinet in a dispersed manner, for example, the management switch can be deployed at the 44OU and 42OU positions, the cable tray can be deployed at the 43OU position, the Powershelf (power rack, used to provide centralized power management for devices in the server rack) node can be deployed at the 37~38OU position and the 5~6OU position, the Rack Stiffener (rack reinforcement, used to increase the structural strength and stability of the server rack) node can be deployed at the 36OU position and the 7OU position, and the CDU (Cooling Distribution Unit, a cooling distribution unit used to manage and distribute cooling liquid or cold air) node can be deployed at the 1~4OU position. Figure 1 In the distribution shown, the 39~41OU positions have not yet been considered for deployment of any components, so they are marked as NA (Not Applicable) layers. In actual applications, specific functional components can be deployed in the NA layer according to the functional requirements of the server. The computing nodes are placed on the upper and lower sides of the cabinet (for example Figure 1The 28OU~35OU and 8OU~15OU shown in the figure are used to deploy computing nodes, and the switching nodes are placed in the middle of the cabinet (for example Figure 1 The 16OU~27OU shown in the figure are deployed with switching nodes). This design can make the deployment of power cables and communication cables more balanced. Figure 1 The configuration shown in FIG. 1 is only a typical configuration, and the number of switching nodes and the number of computing nodes can be adjusted according to actual conditions.

[0039] Figure 2 Schematic diagram of the back of a cabinet of an AI super node whole cabinet server according to an embodiment of the present application. Figure 2 As shown, the back of the whole cabinet server mainly includes three components: Busbar (bus duct), Manifold (manifold) and Cable Tray (cable tray). The Busbar is located in the middle (or one side), and the Powershelf node is connected to the Busbar to power the entire cabinet. The Cable Tray is located on the left and right sides of the Busbar. The Cable Tray is used to connect the high-speed signals of the computing nodes and the switching nodes according to the designed topological interconnection relationship. The Manifold is located on the left and right sides of the rear of the cabinet, providing water inlet and outlet, and providing a liquid path for liquid cooling for the entire cabinet. These components work together to ensure that the power supply and cooling system of the whole cabinet server operate efficiently and safely.

[0040] Figure 3 Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 1 .like Figure 3As shown, #1~#N are N computing nodes, and one CPU (Central Processing Unit) can be deployed on each computing node, but is not limited to, and four GPUs can be connected to the CPU through a PCIe (Peripheral Component Interconnect Express, a high-speed serial computer expansion bus standard) switching chip. Taking 16 computing nodes deployed in an AI whole cabinet server as an example, there are 16×4=64 GPUs in this AI whole cabinet server. If N computing nodes are deployed in an AI whole cabinet server, there are 4×N GPUs in this AI whole cabinet server. DPU (Data Processing Unit) network cards, storage devices, and BMC (Baseboard Management Controller) management modules can be deployed on computing nodes, but are not limited to. The storage device can be, but is not limited to, an SSD (Solid State Drive). Figure 3 The switching nodes 1 to M shown are M switching nodes, and each switching node may have, but is not limited to, a MAC (Media Access Control) chip. The high-speed signals of the switching nodes and the computing nodes are interconnected through the Cable Tray. In the AI ​​whole-rack server, all the computing nodes and switching nodes are connected to the Rack Cable Tray (cable bridge in or near the rack) through high-density connectors to achieve Serdes (Serializer / Deserializer) high-speed interconnection between all GPUs in the AI ​​whole-rack server. Figure 4 Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 2 , the Serdes high-speed interconnection method between all the aforementioned GPUs is as follows Figure 4 It should be noted that the solution of fully interconnecting computing nodes in the AI ​​whole cabinet server through switching nodes requires that the high-speed signal resources of each GPU in each computing node be evenly distributed to each switching node. This is a scale-up topology. Figure 5 Schematic diagram of the connection between the computing node and the switching node of an AI super node whole cabinet server according to an embodiment of the present application Figure 3 ,like Figure 5As shown in the figure, computing nodes 1-8 are interconnected through switching nodes 1-8. The connector of each computing node in the AI ​​whole cabinet server is connected to 4 GPUs, and the signals at the same position of 8 computing nodes are connected to a switch (i.e., switching node). Figure 5 The computing node signals and switching node signals with the same number shown in FIG. 1 have a connection relationship.

[0041] In this embodiment, a power supply control method is provided for supplying power to the above-mentioned AI whole cabinet server. Figure 6 is a flow chart of a power supply control method according to an embodiment of the present application, such as Figure 6 As shown, the process includes the following steps:

[0042] Step S602 , detecting an actual total load of a power supply device, wherein the power supply device includes a plurality of power supply units.

[0043] The power supply device may be a Powershelf, which is a centralized power management system including multiple power supply units (PSUs). The PSU input may be 220VAC, which may be converted to 54VDC and output to the copper busbar after power conversion. The actual total load of the power supply device refers to the total power obtained from the copper busbar by all current server nodes in the cabinet, that is, the total power being supplied by all active PSUs. The execution subject of the above steps may be a baseboard management controller, but is not limited thereto.

[0044] Step S204, determining the target total load interval in which the actual total load is located, wherein different total load intervals are associated with different total power supply loss curves, each total power supply loss curve characterizes the relationship between the total power supply loss and the number of active power supply units, each total power supply loss curve includes at least one total power supply loss curve segment, different total power supply loss curve segments characterize the relationship between the total power supply loss and the number of active power supply units under different load rate intervals of the active power supply unit, and the load rate is the ratio of the total load to the number of active power supply units.

[0045] Based on the entire load range, the total power supply load is divided into multiple intervals, such as the total load heavy load interval, the total load medium load interval, the total load light load interval, and the total load ultra-light load interval. Since all PSUs can be set to be active and supply power at the same time during normal power supply, and each active PSU shares the load equally, some PSUs can also be set to be active and supply power while others are in a dormant state. Therefore, in different total load intervals, the load rate of the active PSU may fall into different load rate intervals as the number of active PSUs is different.

[0046] Since the active PSU has a higher efficiency in some load rate ranges and a lower load rate in other ranges, the relationship between the total power loss in different load rate ranges of the active PSU and the number of active PSUs is determined based on the efficiency of the active PSU at different load rates and the static power loss of the dormant PSU, and different total power loss curve segments are obtained. Then, the total power loss curve segments associated with the load rate range in which the load rate of the active PSU may fall in a total load range are combined into a total power loss curve associated with the total load range. Different total load ranges have different associated total power loss curves. In order to determine the target total power loss curve that matches the actual total load, the target total load range in which the actual total load is located is first determined.

[0047] Step S606, based on the target total power loss curve associated with the target total load interval, determine the target number of active power supply units when the actual total power loss under the actual total load is minimized, wherein the actual total power loss includes the actual dynamic power loss of the active power supply units and the actual static power loss of the dormant power supply units, and the target number is the number of active power supply units that need to be set.

[0048] The target total power loss curve is used to describe how the total power loss (including the dynamic power loss of the active power supply unit and the static power loss of the dormant power supply unit) changes with the number of active power supply units within the target total load range. The number of active power supply units when the actual total power loss under the actual total load is minimized is determined based on the curve, which is the target number.

[0049] Step S608, controlling the target number of power supply units to be in an active state.

[0050] That is, controlling a target number of power supply units to be in an active state and controlling the remaining power supply units of the power supply equipment to be in a dormant state can ensure that the actual total power loss after adding the actual power supply dynamic loss of the active power supply units of the power supply equipment to the actual power supply static loss of the dormant power supply units can be minimized.

[0051] Through the above steps, the actual total load of the power supply equipment is monitored in real time, and then the monitored total load is positioned within the target total load interval in multiple total load intervals, and the total power loss curve matching the target total load interval is obtained, each total power loss curve includes at least one total power loss curve segment, which characterizes the relationship between the total power loss and the number of active power supply units under the corresponding load rate interval. Since the total power loss in the target total power loss curve includes the dynamic power loss of the active power supply unit and the static power loss of the dormant power supply unit, the target number of active power supply units when the total power loss is minimized is determined according to the target total power loss curve, and the target number of power supply units is controlled to be in an active state, and the remaining power supply units are controlled to be in a dormant state, so that the power supply equipment can not only meet the power demand of the server, but also reduce the dynamic loss and static loss of unnecessary power supply units. Thus, the problem of resource waste in the related art is solved, in which the load rate corresponding to the high efficiency of the active power supply unit is determined according to the empirical value, and then the number of active power supply units is determined according to the total power load and the load rate of the active power supply unit, and the corresponding number of power supply units are controlled to work, and the power efficiency of the entire power supply equipment is optimized and the operating cost is reduced.

[0052] In an exemplary embodiment, the relationship between the total power supply loss and the number of active power supply units in different load rate intervals of the active power supply unit is determined in the following manner: for a target load rate interval in different load rate intervals, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval; based on the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval, and the relationship between the load rate of the active power supply unit and the number of active power supply units, determining the relationship between the total power supply loss and the number of active power supply units in the target load rate interval.

[0053] It should be noted that different load rate intervals can be divided based on the total load interval. For example, the total load interval is divided into: total load heavy load interval, total load medium load interval, total load light load interval and total load ultra-light load interval, and the load rate interval is correspondingly divided into: load rate heavy load interval, load rate medium load interval, load rate light load interval and load rate ultra-light load interval. Among them, the upper and lower limits of each load rate interval are the ratio of the upper and lower limits of the corresponding level of the total load interval to the number of all PSUs of the power supply equipment.

[0054] First of all, the efficiency value of active PSU is different under different load rates, and the efficiency affects the total power supply loss. Figure 7 is a curve showing the relationship between the efficiency and the load rate of the active power supply unit according to an embodiment of the present application, such as Figure 7As shown, in the heavy load range, as the load rate increases, the efficiency decreases slowly (50% is the optimal efficiency point), in the medium load range, as the load rate increases, the efficiency increases slowly, in the light load range, as the load rate increases, the efficiency increases rapidly, and in the ultra-light load range, as the load rate increases, the efficiency increases rapidly. In each load rate range, the relationship between the total power supply loss and the load rate of the active power supply unit is determined by experimental methods.

[0055] Next, determine the relationship between the load rate of the active power supply unit and the number of active power supply units. As the number of active power supply units increases, the load rate of each PSU will decrease accordingly, that is, there is an inverse correlation between the load rate of the active power supply unit and the number of active power supply units. The target load rate interval refers to any one of the multiple load rate intervals. Through the inverse correlation and the relationship between the total power supply loss and the load rate of the active power supply unit within the target load rate interval, the relationship between the total power supply loss and the number of active power supply units under the target load rate interval can be determined.

[0056] This embodiment can determine the relationship between the total power supply loss and the number of active power supply units in the target load rate interval based on the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval, and the inverse correlation between the load rate of the active power supply unit and the number of active power supply units, thereby laying a foundation for determining different total power supply loss curve segments and further determining each total power supply loss curve.

[0057] In an exemplary embodiment, the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval is determined in the following manner: determining the relationship between the dynamic power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a dynamic loss relationship; determining the relationship between the static power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a static loss relationship; based on the static loss relationship and the dynamic loss relationship, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval.

[0058] It should be noted that the related art believes that the dormant PSU has no loss, and only the active PSU is considered when determining the total power supply loss. However, this embodiment takes into account that the dormant PSU also has certain static losses, and the number of dormant PSUs will also affect the total loss. Under different total loads and different numbers of active PSUs, the changing trends of these two loss curves are different. The total power supply loss is non-monotonic and changes differently under different loads.

[0059] Therefore, in this embodiment, the total power supply loss is set as the superposition of the dynamic loss of the active PSU and the static loss of the inactive PSU. The total load in the obtained total power supply loss curve includes the dynamic power loss of the active power supply unit and the static power loss of the dormant power supply unit. When the number of active power supply units to be set is determined according to the target total power supply loss curve associated with the target total load interval, it is avoided that the total power supply loss in the related technology only considers the dynamic loss of the active PSU, determines the number of active PSUs according to the dynamic loss, and controls the operation of the corresponding number of power supply units, which results in a waste of resources.

[0060] In an exemplary embodiment, different total load intervals include a first total load interval, a second total load interval, a third total load interval and a fourth total load interval, wherein the upper limit of the fourth total load interval is equal to the lower limit of the third total load interval, the upper limit of the third total load interval is equal to the lower limit of the second total load interval, the upper limit of the second total load interval is equal to the lower limit of the first total load interval, the lower limit of the first total load interval is equal to half of the maximum total load of the power supply equipment, the lower limit of the second total load interval is the total load value corresponding to the rising inflection point of the total power supply loss when the total load is less than the lower limit of the first total load interval, and the lower limit of the third total load interval is the total load value corresponding to the falling inflection point of the total power supply loss when the total load is less than the lower limit of the second total load interval.

[0061] Among them, the first total load interval, the second total load interval, the third total load interval and the fourth total load interval are respectively the total load heavy load interval, the total load medium load interval, the total load light load interval and the total load ultra-light load interval. It should be noted that the division method of the total load interval is related to the load rate of the active PSU. Considering that the efficiency of an active PSU is the highest when the active PSU is at a load rate of 50%, all PSUs of the power supply equipment are set to be active and have a load rate greater than or equal to 50%, and the total power supply load at this time is determined as the lower limit of the first total load interval (total load heavy load critical value), that is, the lower limit of the first total load interval is equal to half of the maximum total load of the power supply equipment. Considering that the total power loss will first continue to decrease when the total load is less than the lower limit of the first total load interval, and then increase, and an increasing inflection point will appear, the lower limit of the second total load interval is set to the total load value corresponding to the increasing inflection point of the total power loss. Considering that the total load will first continue to increase when it is less than the lower limit of the second total load interval, and then decrease, and a decreasing inflection point will appear, the lower limit of the third total load interval is set to the total load value corresponding to the decreasing inflection point.

[0062] In an exemplary embodiment, the lower limit of the second total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the first total load interval, keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to decrease and an upward inflection point appears, and determining the load corresponding to the rising inflection point as the lower limit of the second total load interval; the lower limit of the third total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the second total load interval, and keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to increase and a downward inflection point appears, and determining the load corresponding to the downward inflection point as the lower limit of the third total load interval.

[0063] That is, after the lower limit of the first total load interval, the load is continuously reduced, and all PSUs are kept active, and the difference between the input power and the output power is continuously recorded, which is the total power supply loss. The loss should continue to decrease until an increasing inflection point appears, at which point the total load is the lower limit of the second total load interval (the total load medium load critical value). After the lower limit of the second total load interval, the load is continuously reduced, and all PSUs are kept active, and the difference between the input power and the output power is continuously recorded, which is the total power supply loss. The loss should continue to increase until a decreasing inflection point appears, at which point the load is the lower limit of the third total load interval (the total load light load critical value).

[0064] This embodiment takes into account that the load rate of the active PSU may be different depending on the number of active PSUs in different total load intervals, and different load rate curves can be drawn. According to the relationship between the total power supply loss and the number of active PSUs, the first total load interval, the second total load interval, the third total load interval and the fourth total load interval are determined, which lays a foundation for determining the number of active PSUs under the actual total load when the total power supply loss is minimized.

[0065] In an exemplary embodiment, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized based on the target total power loss curve associated with the target total load interval includes: when the actual total load is in the target total load interval, if the total power loss and the number of active power supply units are anti-correlated when the number of active power supply units is different, then the total number of power supply units of the power supply device is determined as the target number.

[0066] It should be noted that if the number of active power supply units is different, the total power supply loss and the number of active power supply units are inversely correlated, which means that the total dynamic loss of the active PSUs and the total static loss of the dormant PSUs under the same number of active PSUs are superimposed. As the number of active PSUs increases, the total power supply loss decreases. Therefore, all PSUs are set to be active, and the number of all PSUs is determined as the target number of active PSUs, which lays the foundation for optimizing the power efficiency of power supply equipment and reducing operating costs.

[0067] In an exemplary embodiment, under a first total load interval, the load rate of the active power supply unit is in a first load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, and according to a target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: when the target total load interval is the first total load interval, obtaining a first relationship associated with when the load rate of the active power supply unit under the first total load interval is in the first load rate interval, wherein the first relationship indicates that the total power supply loss and the number of active power supply units are inversely correlated; and determining the total number of power supply units of the power supply device as the target number according to the first relationship.

[0068] Figure 8 is a total power supply loss curve associated with the first total load interval according to an embodiment of the present application, such as Figure 8 As shown, the total power supply loss curve includes a curve segment corresponding to the first relationship associated with the first load rate interval, and the first relationship associated with the first load rate interval is determined as follows:

[0069] The loss of a single dormant PSU is a fixed value. There are multiple PSUs in the power supply equipment. As the number of active PSUs increases, the number of dormant PSUs decreases. Therefore, the static loss curve of the total dormant PSU is a straight line, and its slope is the static loss value of a single dormant PSU. Therefore, the total static loss function of the dormant PSU can be expressed as: total static loss of dormant PSU = k1*(12-N), k1 is a constant, that is, the static loss of each dormant PSU, N is the number of active PSUs, and 12 is the number of all PSUs.

[0070] The efficiency of a single PSU is highest when the load rate is 50%. When the load rate is higher than 50% or lower than 50%, the efficiency will decrease, and the efficiency loss will increase. When the total load is fixed, the fewer the number of active PSUs, the greater the PSU load rate; when the load rate of each PSU is >50%, the lower the PSU load rate, the smaller the loss factor; when the load rate of each PSU is <50%, the higher the PSU load rate, the smaller the loss factor. Therefore, the relationship between the total loss of active PSU and the PSU load rate (efficiency) is: total loss of active PSU = n*(load rate*3.3kw)*(1 / Ƞ-1)=load rate*(1 / Ƞ-1), where 3.3kw is the rated power of a single PSU, Ƞ is the efficiency value of the PSU, and (1 / Ƞ-1) is the loss factor of a single PSU. Therefore, the total dynamic loss of active PSU is only related to the load rate (efficiency) of the active PSU, and has nothing to do with the number of active PSUs.

[0071] It should be noted that when all PSUs are active, the load rate of each PSU is 50%. When the load rate of each active PSU changes within a range greater than 50% (the first load rate range), the number of active PSUs also changes. In this range, as the number of active PSUs increases, the load rate of each active PSU decreases. According to the efficiency curve of the active PSU, the efficiency of the PSU increases and the loss decreases. That is, the total dynamic loss of the active PSU decreases as the number of active PSUs increases.

[0072] Since the total dynamic loss of active PSUs decreases as the number of active PSUs increases, the total static loss of dormant PSUs decreases monotonically. When the load rate of active PSUs changes within a range greater than 50% (for example, 90%-50%), the total dynamic loss of active PSUs and the total static loss of dormant PSUs under the same number of active PSUs are superimposed. Combined with the active PSU efficiency curve, it can be seen that within this range, as the number of active PSUs increases, the load rate of each active PSU decreases and the efficiency of a single PSU increases. That is, the active PSU loss reduction curve is superimposed on the dormant PSU loss reduction curve, and the total power supply loss curve is a decreasing curve.

[0073] Therefore, when the total load is overloaded: depending on the number of active PSUs, the load rate of each active PSU is greater than 50%, and there is only one overload situation. The more active PSUs there are, the lower the total loss. Therefore, all PSUs are set to be active. Overload critical value = (3.3kw*12*50%) = 19.8kw. Therefore, when the total load is detected to be greater than or equal to 19.8kw, the active PSU = 12, at which time the total loss is the lowest. Therefore, 50% is the overload critical point of the PSU load rate (the lower limit of the first load rate interval).

[0074] This embodiment takes into account that within the power supply loss curve associated with the first total load interval, the total PSU loss varies monotonically with the number of active PSUs, and determines the number of all PSUs as the target number of active PSUs, laying a foundation for optimizing the power efficiency of the power supply equipment and reducing operating costs.

[0075] In an exemplary embodiment, in the second total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, and the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, and according to the target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: when the target total load interval is the second total load interval, obtaining a first relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the first load rate interval, and a second relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the second load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated; and determining the total number of power supply units of the power supply device as the target number according to the first relationship and the second relationship.

[0076] Fig. 9 is a total power supply loss curve associated with the second total load interval according to an embodiment of the present application, such as Fig. 9 As shown: the total power loss curve includes a curve segment corresponding to the first relationship associated with the first load rate interval, and a curve segment corresponding to the second relationship associated with the second load rate interval. The first relationship associated with the first load rate interval is not repeated here. The second relationship associated with the second load rate interval is determined as follows:

[0077] The second total load interval is when the total load is medium load. When the total load is medium load, when all PSUs are active, the load factor of each PSU is lower than that of heavy load, so the loss factor curve of the single active PSU and the total dynamic loss curve of the active PSU are both shifted to the left. When all PSUs are active, the load factor of each active PSU is reduced from 50% to X%, and the interval of 50%-X% is the second load factor interval.

[0078] When the load factor of each active PSU changes within the range of 50%-X%, the number of active PSUs also changes. In this range, as the number of active PSUs increases, the load factor of each active PSU decreases. According to the efficiency curve of the active PSU, the efficiency of the active PSU decreases and the loss increases. That is, the total dynamic loss of the active PSU increases as the number of active PSUs increases.

[0079] The total dynamic loss of active PSUs increases with the number of active PSUs, while the total static loss of dormant PSUs decreases monotonically with the number of active PSUs. Therefore, when the load rate of active PSUs changes in the range of 50%-X%, the total dynamic loss of active PSUs and the total static loss of dormant PSUs under the same number of active PSUs are superimposed. Combined with the efficiency curve of active PSUs, it can be seen that the slope of the efficiency curve of a single active PSU is extremely low. As the number of active PSUs increases and the load rate of each active PSU changes, the efficiency of a single active PSU does not change much. Therefore, the total dynamic loss of active PSUs does not increase much, and the static loss of dormant PSUs accounts for the main trend, so the total power supply loss is on a downward trend.

[0080] Therefore, when the total load is medium load: depending on the number of active PSUs, the load rate of each active PSU is 90%-50% (heavy load) and 50%-X% (medium load). As the number of active PSUs increases, the total PSU loss curves for heavy load and medium load of each active PSU are both decreasing, that is, the first relationship and the second relationship indicate that the total power supply loss is inversely correlated with the number of active power supply units, and the total PSU loss curve is monotonically decreasing. The more active PSUs there are, the lower the total loss. Therefore, all PSUs are set active, and the total loss is the lowest at this time. It should be noted that the medium load critical value = 12*3.3kw*X%, so X% (approximately 20%) can be calculated, 12 is the number of all PSUs, and this X% is the medium load critical point of the PSU load rate (the lower limit of the second load rate range).

[0081] The lower limit of the second load rate interval is determined as follows: after the lower limit of the first total load interval, the load is continuously reduced, and all PSUs are kept active, and the difference between the input power and the output power is continuously recorded, that is, the total power loss. The loss should continue to decrease until an upward inflection point appears, at which time the total load is the lower limit of the second total load interval (the total load mid-load critical value).

[0082] This embodiment takes into account that within the power supply loss curve associated with the second total load interval, the total PSU loss varies monotonically with the number of active PSUs, and determines the number of all PSUs as the target number of active PSUs, laying a foundation for optimizing the power efficiency of the power supply equipment and reducing operating costs.

[0083] In an exemplary embodiment, in the case of a third total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, or the third load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, and the actual power supply total loss under the actual total load is determined according to the target total power supply loss curve associated with the target total load interval. The target number of active power supply units when the loss is minimized includes: when the target total load interval is the third total load interval, obtaining a first relationship associated with the load rate of the active power supply units in the third total load interval when they are in the first load rate interval, a second relationship associated with the load rate in the second load rate interval, and a third relationship associated with the load rate in the third load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; determining that the actual total power supply loss is minimized when the actual total load is at the lower limit of the second load rate interval according to the first relationship, the second relationship, and the third relationship, and determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval.

[0084] Fig.10 is a total power supply loss curve associated with the third total load interval according to an embodiment of the present application, such as Fig.10 As shown: the total power supply loss curve includes a curve segment corresponding to the first relationship associated with the first load rate interval, a curve segment corresponding to the second relationship associated with the second load rate interval, and a curve segment corresponding to the third relationship associated with the third load rate interval. The determination method of the first relationship associated with the first load rate interval and the second relationship associated with the second load rate interval will not be repeated. The determination method of the third relationship associated with the third load rate interval is as follows:

[0085] The third total load interval is when the total load is light. When the total load is light, when all PSUs are active, the load factor of each PSU is lower than that of medium load, so the loss factor curve of the single active PSU and the total dynamic loss curve of the active PSU are both shifted to the left. When all PSUs are active, the load factor of each active PSU continues to decrease from X% to Y%, and the interval of X%-Y% is the third load factor interval.

[0086] When the load factor of each active PSU changes within the range of X%-Y%, the number of active PSUs also changes. In this range, as the number of active PSUs increases, the load factor of each active PSU decreases. According to the efficiency curve of the active PSU, the efficiency of the active PSU decreases and the loss increases. That is, the total dynamic loss of the active PSU increases as the number of active PSUs increases.

[0087] Since the total dynamic loss of active PSUs increases with the number of active PSUs, while the total static loss of dormant PSUs decreases monotonically with the number of active PSUs, when the load rate of active PSUs changes within the range of X%-Y%, the total dynamic loss of active PSUs and the total static loss of dormant PSUs under the same number of active PSUs are superimposed, and combined with the efficiency curve of active PSUs, it can be seen that the slope of the efficiency curve of a single active PSU is higher. As the number of active PSUs increases and the load rate of each active PSU changes, the efficiency of a single active PSU changes significantly, and the increase in the total dynamic loss of active PSUs is the main trend, so the total power supply loss increases.

[0088] Therefore, when the total load is light, depending on the number of active PSUs, the load rate of each active PSU is 90%-50% (heavy load), 50%-X% (medium load), and X%-Y% (light load). As the number of active PSUs increases, the total PSU loss curves for heavy and medium loads of each active PSU are both decreasing, that is, the first relationship and the second relationship indicate that the total power loss is inversely correlated with the number of active power supply units; the total PSU loss curve for light loads of each active PSU increases, that is, the third relationship indicates that the total power loss is positively correlated with the number of active power supply units.

[0089] Therefore, the intersection of medium load and light load of the active PSU load rate (the lower limit of the second load rate interval) is the lowest value of the total PSU loss. At this time, the load rate of the PSU is X%. Therefore, when it is detected that the total load is in the range from the medium load critical value to the light load critical value, the load rate of each PSU is at X%, and the loss is lowest at this time. It should be noted that the light load critical value = 12*3.3kw*Y%, so Y% can be calculated (somewhere between 20%-10%), 12 is the number of all PSUs, and Y% is the light load critical point of the PSU load rate (the lower limit of the third load rate interval).

[0090] The lower limit of the third total load interval is determined in the following way: after the lower limit of the second total load interval, the load is continuously reduced, and all PSUs are kept active, and the difference between the input power and the output power is continuously recorded, that is, the total power supply loss. The loss should continue to increase until a downward inflection point appears, at which time the load is the lower limit of the third total load interval (the total load light load critical value).

[0091] In an exemplary embodiment, determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval includes: calculating the product of the rated power of the power supply unit and the lower limit of the second load rate interval to obtain the set load of each active power supply unit; determining the target number based on the ratio of the actual total load and the set load of each active power supply unit.

[0092] Exemplarily, the load of each active PSU is set to X% (the lower limit of the second load rate interval, i.e., the medium load critical point). At this time, the number of active PSUs = actual load / (3.3kw*X%), and the result is rounded to the set number, where 3.3kw is the rated power of the PSU.

[0093] This embodiment takes into account that within the power supply loss curve associated with the third total load interval, the total PSU loss does not change monotonically with the number of active PSUs, and there is a point where the total PSU loss is extremely low. The number of active PSUs corresponding to the point where the total PSU loss is extremely low is determined as the target number of active PSUs, which lays a foundation for optimizing the power efficiency of the power supply equipment and reducing operating costs.

[0094] In an exemplary embodiment, in the fourth total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval or the third load rate interval or the fourth load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, the upper limit of the fourth load rate interval is equal to the lower limit of the fourth total load interval, and the target power supply total load interval is associated with the target power supply total load interval. Loss curve, determining the target number of active power supply units when the actual total power loss under the actual total load is the smallest includes: when the target total load is the fourth total load interval, obtaining the first relationship associated when the load rate of the active power supply unit under the fourth total load interval is in the first load rate interval, the second relationship associated when it is in the second load rate interval, the third relationship associated when it is in the third load rate interval, and the fourth relationship associated when it is in the fourth load rate interval, wherein the first relationship, the second relationship, and the fourth relationship respectively indicate that the total power loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power loss and the number of active power supply units are positively correlated; according to the first relationship, the second relationship, the third relationship, and the fourth relationship, determining the target number of active power supply units when the actual total power loss under the actual total load is the smallest.

[0095] Fig.11 is a total power supply loss curve associated with the fourth total load interval according to an embodiment of the present application, such as Fig.11 As shown: the total power supply loss curve includes a curve segment corresponding to the first relationship associated with the first load rate interval, a curve segment corresponding to the second relationship associated with the second load rate interval, a curve segment corresponding to the third relationship associated with the third load rate interval, and a curve segment corresponding to the fourth relationship associated with the fourth load rate interval. The first relationship associated with the first load rate interval, the second relationship associated with the second load rate interval, and the third relationship associated with the third load rate interval are determined in a manner that is not repeated. The fourth relationship associated with the fourth load rate interval is determined as follows:

[0096] The fourth total load interval is when the total load is ultra-light load. When the total load is ultra-light load, when all PSUs are active, the load factor of each PSU is lower than that of light load, so the single active PSU loss factor curve and the total dynamic loss curve of the active PSU are both shifted to the left. When all PSUs are active, the load factor of each active PSU continues to decrease from Y% to Z%, and the interval of Y%-Z% is the fourth load rate interval. When the load factor of each active PSU changes within the interval of Y%-Z%, the number of active PSUs also changes. In this interval, as the number of active PSUs increases, the load factor of each active PSU decreases. According to the efficiency curve of the active PSU, the efficiency of the active PSU decreases and the loss increases. That is, the total dynamic loss of the active PSU increases with the increase in the number of active PSUs.

[0097] Since the total dynamic loss of active PSUs increases with the number of active PSUs, while the total static loss of dormant PSUs decreases monotonically with the number of active PSUs. Therefore, when the load rate of active PSUs changes in the range of Y%-Z%, the total dynamic loss of active PSUs and the total static loss of dormant PSUs under the same number of active PSUs are superimposed. Combined with the efficiency curve of active PSUs, it can be seen that the slope of the efficiency curve of a single active PSU is higher, but because the total load is too light, after the number of active PSUs increases, the load rate of each active PSU changes too little, resulting in an insignificant change in the actual efficiency of a single active PSU. Therefore, the loss of active PSUs does not change significantly, and the decline in the loss of dormant PSUs is the main trend, so the total power supply loss decreases.

[0098] Therefore, when the total load is ultra-light load, depending on the number of active PSUs, the load rate of each active PSU is 90%-50% (heavy load), 50%-X% (medium load), X%-Y% (light load), and Y%-Z% (ultra-light load).

[0099] As the number of active PSUs increases, the total PSU loss curves of heavy load and medium load of each active PSU decrease, that is, the first relationship and the second relationship indicate that the total power supply loss is inversely correlated with the number of active power supply units; the total PSU loss curve when the load rate is light load increases, that is, the third relationship indicates that the total power supply loss is positively correlated with the number of active power supply units; the total PSU loss curve when the load rate is ultra-light load decreases, that is, the fourth relationship indicates that the total power supply loss is inversely correlated with the number of active power supply units.

[0100] Therefore, within the entire loss curve, there are two points where the total PSU loss is extremely low: one is when the number of active PSUs makes the load rate of the active PSUs at the critical point of medium load (the lower limit of the second load rate interval), and the other is when the number of active PSUs is the maximum. Therefore, it is necessary to determine the target number of active power supply units when the actual total power loss under the actual total load is minimized based on the first relationship, the second relationship, the third relationship, and the fourth relationship.

[0101] In an exemplary embodiment, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized according to the first relationship, the second relationship, the third relationship and the fourth relationship includes: determining the set number of active power supply units when the actual total power loss is minimized based on the actual total load and the lower limit of the second load rate interval, controlling the load rates of the active power supply units of the set number of power supply units of the power supply device to be within the lower limit of the second load rate interval, and recording the input power of the power supply device to obtain a first input power; controlling the load rates of the active power supply units of all power supply units of the power supply device to be in an active state, and recording the input power of the power supply device to obtain a second input power; when the first input power is less than the second input power, determining the target number by the set number; and when the first input power is greater than or equal to the second input power, determining the total number of power supply units of the power supply device as the target number.

[0102] Exemplarily, the load of each active PSU is set to X% (the lower limit of the second load rate interval, i.e., the medium load critical point). At this time, the number of active PSUs = actual load / (3.3kw*X%), and the result is rounded to the set number, where 3.3kw is the rated power of the PSU. At this time, the recorded input power is P1 (i.e., the first input power).

[0103] Alternatively, set the number of active PSUs to the total number of all active PSUs, and record the input power to get P2 (i.e., the second input power). Take the number of active PSUs corresponding to the smaller value of P1 and P2 as the target number, that is, set the number of PSUs as active, and also output the lowest total power loss under total load.

[0104] This embodiment takes into account that within the power supply loss curve associated with the fourth total load interval, there are two points with extremely low total PSU loss, compares the input power under different numbers of active PSUs corresponding to the two points with extremely low total PSU loss, and determines the number of active PSUs corresponding to the low input power condition as the target number of active PSUs, laying a foundation for optimizing the power efficiency of the power supply equipment and reducing operating costs.

[0105] 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 a 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 prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for 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.

[0106] In this embodiment, a power supply device is further provided, including: a plurality of power supply units; and a controller, wherein a power supply control method of the controller controls a target number of power supply units among the plurality of power supply units to be in an active state.

[0107] In this embodiment, a power supply control device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0108] Fig.12 is a structural block diagram of a power supply control device according to an embodiment of the present application, such as Fig.12 As shown, the device comprises:

[0109] A detection unit 1202, configured to detect an actual total load of a power supply device, wherein the power supply device includes a plurality of power supply units;

[0110] A first determining unit 1204 is configured to determine a target total load interval in which the actual total load is located, wherein different total load intervals are associated with different total power loss curves, each total power loss curve represents a relationship between the total power loss and the number of active power supply units, each total power loss curve includes at least one total power loss curve segment, and different total power loss curve segments represent a relationship between the total power loss and the number of active power supply units under different load rate intervals of the active power supply unit, and the load rate is a ratio of the total load to the number of active power supply units;

[0111] A second determining unit 1206 is used to determine the target number of active power supply units when the actual total power loss under the actual total load is the minimum according to the target total power loss curve associated with the target total load interval, wherein the actual total power loss includes the actual dynamic power loss of the active power supply unit and the actual static power loss of the dormant power supply unit, and the target number is the number of active power supply units that need to be set;

[0112] The control unit 1208 is used to control a target number of power supply units to be in an active state.

[0113] In an exemplary embodiment, the relationship between the total power supply loss and the number of active power supply units in different load rate intervals of the active power supply unit is determined in the following manner: for a target load rate interval in different load rate intervals, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval; based on the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval, and the relationship between the load rate of the active power supply unit and the number of active power supply units, determining the relationship between the total power supply loss and the number of active power supply units in the target load rate interval.

[0114] In an exemplary embodiment, the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval is determined in the following manner: determining the relationship between the dynamic power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a dynamic loss relationship; determining the relationship between the static power supply loss and the load rate of the active power supply unit in the target load rate interval to obtain a static loss relationship; based on the static loss relationship and the dynamic loss relationship, determining the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval.

[0115] In an exemplary embodiment, based on a target total power supply loss curve associated with a target total load interval, the second determination unit 1206 is used to: when the actual total load is in the target total load interval, if the number of active power supply units is different, the total power supply loss and the number of active power supply units are inversely correlated, then the total number of power supply units of the power supply device is determined as the target number.

[0116] In an exemplary embodiment, different total load intervals include a first total load interval, a second total load interval, a third total load interval and a fourth total load interval, wherein the upper limit of the fourth total load interval is equal to the lower limit of the third total load interval, the upper limit of the third total load interval is equal to the lower limit of the second total load interval, the upper limit of the second total load interval is equal to the lower limit of the first total load interval, the lower limit of the first total load interval is equal to half of the maximum total load of the power supply equipment, the lower limit of the second total load interval is the total load value corresponding to the rising inflection point of the total power supply loss when the total load is less than the lower limit of the first total load interval, and the lower limit of the third total load interval is the total load value corresponding to the falling inflection point of the total power supply loss when the total load is less than the lower limit of the second total load interval.

[0117] In an exemplary embodiment, in a first total load interval, the load rate of the active power supply unit is in a first load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, and the second determination unit 1206 is used to: when the target total load interval is the first total load interval, obtain a first relationship associated with the load rate of the active power supply unit in the first total load interval being in the first load rate interval, wherein the first relationship indicates that the total power supply loss and the number of active power supply units are inversely correlated; and determine the total number of power supply units of the power supply device as the target number according to the first relationship.

[0118] In an exemplary embodiment, in the second total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, and the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, and the second determination unit 1206 is used to: when the target total load interval is the second total load interval, obtain a first relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the first load rate interval, and a second relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the second load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated; and the total number of power supply units of the power supply device is determined as the target number according to the first relationship and the second relationship.

[0119] In an exemplary embodiment, in the case of the third total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, or the third load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, and the second determination unit 1206 is used to: When the target total load interval is the third total load interval, a first relationship associated with the load rate of the active power supply unit in the third total load interval is obtained when it is in the first load rate interval, a second relationship associated with the load rate in the second load rate interval, and a third relationship associated with the load rate in the third load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; according to the first relationship, the second relationship and the third relationship, it is determined that the actual total power supply loss is minimum when the actual total load is at the lower limit of the second load rate interval, and the target number when the actual total power supply loss is minimum is determined based on the actual total load and the lower limit of the second load rate interval.

[0120] In an exemplary embodiment, determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval includes: calculating the product of the rated power of the power supply unit and the lower limit of the second load rate interval to obtain the set load of each active power supply unit; determining the target number based on the ratio of the actual total load and the set load of each active power supply unit.

[0121] In an exemplary embodiment, in the fourth total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, the third load rate interval, or the fourth load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, and the upper limit of the fourth load rate interval is equal to the fourth total load interval. The lower limit of the interval, the second determining unit 1206 is used to include: when the target total load is a fourth total load interval, obtaining a first relationship associated with the load rate of the active power supply unit in the fourth total load interval when it is in the first load rate interval, a second relationship associated with the load rate in the second load rate interval, a third relationship associated with the load rate in the third load rate interval, and a fourth relationship associated with the load rate in the fourth load rate interval, wherein the first relationship, the second relationship, and the fourth relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; according to the first relationship, the second relationship, the third relationship, and the fourth relationship, determine the target number of active power supply units when the actual total power loss under the actual total load is minimized.

[0122] In an exemplary embodiment, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized according to the first relationship, the second relationship, the third relationship and the fourth relationship includes: determining the set number of active power supply units when the actual total power loss is minimized based on the actual total load and the lower limit of the second load rate interval, controlling the load rates of the active power supply units of the set number of power supply units of the power supply device to be within the lower limit of the second load rate interval, and recording the input power of the power supply device to obtain a first input power; controlling the load rates of the active power supply units of all power supply units of the power supply device to be in an active state, and recording the input power of the power supply device to obtain a second input power; when the first input power is less than the second input power, determining the target number by the set number; and when the first input power is greater than or equal to the second input power, determining the total number of power supply units of the power supply device as the target number.

[0123] In an exemplary embodiment, the lower limit of the second total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the first total load interval, keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to decrease and an upward inflection point appears, and determining the load corresponding to the rising inflection point as the lower limit of the second total load interval; the lower limit of the third total load interval is determined by: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the second total load interval, and keeping all the power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to increase and a downward inflection point appears, and determining the load corresponding to the downward inflection point as the lower limit of the third total load interval.

[0124] It should be noted that the above-mentioned units or modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above-mentioned modules are all located in the same processor; or the above-mentioned modules are located in different processors in any combination.

[0125] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0126] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0127] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0128] In an 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.

[0129] 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 one of the above method embodiments are implemented.

[0130] 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 in any of the above method embodiments are implemented.

[0131] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0132] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0133] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0134] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A power supply control method, characterized in that: include: detecting an actual total load of a power supply device, wherein the power supply device comprises a plurality of power supply units; Determine a target total load interval in which the actual total load is located, wherein different total load intervals are associated with different total power supply loss curves, each total power supply loss curve represents a relationship between the total power supply loss and the number of active power supply units, each total power supply loss curve includes at least one total power supply loss curve segment, different total power supply loss curve segments represent a relationship between the total power supply loss and the number of active power supply units under different load rate intervals of the active power supply unit, and the load rate is a ratio of the total load to the number of active power supply units; Determine, according to the target total power loss curve associated with the target total load interval, the target number of active power supply units when the actual total power loss under the actual total load is minimized, wherein the actual total power loss includes the actual dynamic power loss of the active power supply units and the actual static power loss of the dormant power supply units, and the target number is the number of active power supply units that need to be set; Controlling the target number of power supply units to be in an active state.

2. The method according to claim 1, characterized in that The relationship between the total power loss of the active power supply units at different load rate intervals and the number of active power supply units is determined by: For a target load rate interval in different load rate intervals, determining a relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval; Based on the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval, and the relationship between the load rate of the active power supply unit and the number of active power supply units, the relationship between the total power supply loss and the number of active power supply units in the target load rate interval is determined.

3. The method according to claim 2, characterized in that The relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval is determined by: Determine the relationship between the dynamic power loss and the load rate of the active power supply unit in the target load rate interval to obtain a dynamic loss relationship; Determine the relationship between the power supply static loss and the load rate of the active power supply unit in the target load rate interval to obtain a static loss relationship; According to the static loss relationship and the dynamic loss relationship, the relationship between the total power supply loss and the load rate of the active power supply unit in the target load rate interval is determined.

4. The method according to claim 1, characterized in that Determining, according to the target total power loss curve associated with the target total load interval, the target number of active power supply units at which the actual total power loss under the actual total load is minimized comprises: When the actual total load is within the target total load range, if the number of active power supply units is different, the total power loss and the number of active power supply units are inversely correlated, then the total number of power supply units of the power supply device is determined as the target number.

5. The method according to claim 1, characterized in that Different total load intervals include a first total load interval, a second total load interval, a third total load interval and a fourth total load interval, wherein the upper limit of the fourth total load interval is equal to the lower limit of the third total load interval, the upper limit of the third total load interval is equal to the lower limit of the second total load interval, the upper limit of the second total load interval is equal to the lower limit of the first total load interval, the lower limit of the first total load interval is equal to half of the maximum total load of the power supply device, the lower limit of the second total load interval is the total load value corresponding to the rising inflection point of the total power supply loss when the total load is less than the lower limit of the first total load interval, and the lower limit of the third total load interval is the total load value corresponding to the falling inflection point of the total power supply loss when the total load is less than the lower limit of the second total load interval.

6. The method according to claim 5, characterized in that In the first total load interval, the load rate of the active power supply unit is in the first load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, and according to the target total power loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: When the target total load interval is the first total load interval, obtaining a first relationship associated when the load rate of the active power supply unit in the first total load interval is in the first load rate interval, wherein the first relationship indicates that the total power supply loss is inversely correlated with the number of active power supply units; The total number of power supply units of the power supply device is determined as the target number according to the first relationship.

7. The method according to claim 5, characterized in that In the second total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval or the second load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, and according to the target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power supply loss under the actual total load is minimized includes: When the target total load interval is the second total load interval, obtaining a first relationship associated with the load rate of the active power supply unit in the second total load interval when it is in the first load rate interval and a second relationship associated with the load rate in the second load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated; The total number of power supply units of the power supply device is determined as the target number according to the first relationship and the second relationship.

8. The method according to claim 5, characterized in that In the case of the third total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, or the third load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, and the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units. According to the target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power supply loss under the actual total load is minimized includes: When the target total load interval is the third total load interval, obtaining a first relationship associated when the load rate of the active power supply unit in the third total load interval is in the first load rate interval, a second relationship associated when the load rate is in the second load rate interval, and a third relationship associated when the load rate is in the third load rate interval, wherein the first relationship and the second relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; According to the first relationship, the second relationship and the third relationship, it is determined that the actual total power supply loss is the minimum when the actual total load is at the lower limit of the second load rate interval, and the target number when the actual total power supply loss is the minimum is determined based on the actual total load and the lower limit of the second load rate interval.

9. The method according to claim 8, characterized in that Determining the target number when the actual total power supply loss is minimized based on the actual total load and the lower limit of the second load rate interval includes: Calculating the product of the rated power of the power supply unit and the lower limit of the second load rate interval to obtain a set load of each active power supply unit; The target number is determined according to a ratio of the actual total load to a set load of each active power supply unit.

10. The method according to claim 5, characterized in that In the fourth total load interval, when the number of active power supply units is different, the load rate of the active power supply unit is in the first load rate interval, the second load rate interval, the third load rate interval, or the fourth load rate interval, the lower limit of the first load rate interval is the ratio of the lower limit of the first total load interval to the number of all power supply units, the upper limit of the second load rate interval is equal to the lower limit of the first total load interval, the lower limit of the second load rate interval is the ratio of the lower limit of the second total load interval to the number of all power supply units, the upper limit of the third load rate interval is equal to the lower limit of the second total load interval, the lower limit of the third load rate interval is the ratio of the lower limit of the third total load interval to the number of all power supply units, the upper limit of the fourth load rate interval is equal to the lower limit of the fourth total load interval, and according to the target total power supply loss curve associated with the target total load interval, determining the target number of active power supply units when the actual total power loss under the actual total load is minimized includes: When the target total load is the fourth total load interval, obtaining a first relationship associated with the load rate of the active power supply unit in the fourth total load interval when it is in the first load rate interval, a second relationship associated with the load rate in the second load rate interval, a third relationship associated with the load rate in the third load rate interval, and a fourth relationship associated with the load rate in the fourth load rate interval, wherein the first relationship, the second relationship, and the fourth relationship respectively indicate that the total power supply loss and the number of active power supply units are inversely correlated, and the third relationship indicates that the total power supply loss and the number of active power supply units are positively correlated; According to the first relationship, the second relationship, the third relationship and the fourth relationship, a target number of active power supply units when the actual total power loss under the actual total load is minimized is determined.

11. The method according to claim 10, characterized in that Determining, according to the first relationship, the second relationship, the third relationship, and the fourth relationship, a target number of active power supply units when the actual total power loss under the actual total load is minimized includes: Based on the actual total load and the lower limit of the second load rate interval, determine the set number of active power supply units when the actual total power supply loss is minimum, control the load rates of the active power supply units of the set number of power supply units of the power supply device to be within the lower limit of the second load rate interval, and record the input power of the power supply device to obtain a first input power; Controlling the load rates of active power supply units of all power supply units of the power supply device to be in an active state, and recording the input power of the power supply device to obtain a second input power; In a case where the first input power is less than the second input power, determining the target number by the set number; When the first input power is greater than or equal to the second input power, the total number of power supply units of the power supply device is determined as the target number.

12. The method according to claim 5, characterized in that The lower limit of the second total load interval is determined by: Controlling the actual total load of the power supply device to continuously decrease when it is less than the lower limit of the first total load interval, keeping all power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to decrease and an upward inflection point appears, and determining the load corresponding to the upward inflection point as the lower limit of the second total load interval; The lower limit of the third total load interval is determined in the following manner: controlling the actual total load of the power supply device to continuously decrease while being less than the lower limit of the second total load interval, keeping all power supply units of the power supply device in an active state, and continuously recording the difference between the input power and the output power of the power supply device until the difference continues to rise and a downward inflection point appears, and determining the load corresponding to the downward inflection point as the lower limit of the third total load interval.

13. A power supply device, characterized in that: include: Multiple power supply units; A controller, wherein the controller controls a target number of power supply units among the plurality of power supply units to be in an active state according to the method according to any one of claims 1 to 12.

14. 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, the steps of the method described in any one of claims 1 to 12 are implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.

Images