Heat Dissipation Regulation Method, Device, Computer Equipment, Storage Medium and Program Product

Abstract

The present application discloses a heat dissipation regulation method, device, computer device, storage medium and program product, which relates to the field of computer technologies. Among them, the heat dissipation regulation method can first detect the state changes of each hardware partition in the server to obtain state data, where the hardware partition includes an independently operating host system. Then, based on the state data, a control weight of the heat dissipation device can be assigned to the hardware partition, and based on the control weight, the heat dissipation device can be controlled to dissipate heat from the hardware partition, so that the state of the hardware partition reaches the target state, solving the technical problem of poor heat dissipation system when performing global heat dissipation regulation through the management unit in the server, achieving the technical effect of dynamically allocating the control weight of the heat dissipation device to dynamically optimize the heat dissipation power of the global heat dissipation device and avoid local overheating or power consumption waste of the server.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and particularly to a heat dissipation control method, apparatus, computer device, storage medium, and program product. Background Art

[0002] In recent years, with the rapid development of cloud computing, artificial intelligence, and big data technologies, multi-way and multi-core processors have become the core computing units in data centers. To further improve the utilization rate of hardware resources in the multi-tenant scenario of data centers, multiple virtual machines are virtualized on a single physical server through traditional virtualization technologies to achieve resource sharing. However, the additional overhead of the hypervisor makes it difficult for real-time services to meet the low-latency requirements. For this reason, the hardware partitioning technology has emerged. By physically isolating the computing resources (such as processors, memory, and input / output devices, etc.) of a single server into multiple independently operating "bare metal" host systems, the partitioning of the physical machine performance is thus realized.

[0003] In related heat dissipation control solutions, the management unit in the server often globally manages all heat dissipation devices and adjusts the rotation speed based on the overall temperature threshold of the server. For example, if the server includes multiple hosts, when it is detected that the temperature in the server rises, the management unit can increase the rotation speed of all fans to dissipate heat from the server. However, since there are often differences in each hardware partition in the server, this results in poor heat dissipation coordination for the entire server. For example, if a certain partition has a high temperature and the fan rotation speed is increased to reduce the temperature of this partition, it may cause heat accumulation in adjacent partitions with lower temperatures. Summary of the Invention

[0004] The present application provides a heat dissipation control method, apparatus, computer device, storage medium, and program product to at least solve the problem of poor heat dissipation system when the server performs global heat dissipation control through the management unit in related technologies.

[0005] The present application provides a heat dissipation control method, which includes:

[0006] Detecting the state changes of each hardware partition in the server to obtain state data, where the hardware partition includes an independently operating host system;

[0007] Based on the state data, allocating a control weight of a heat dissipation device to the hardware partition;

[0008] Controlling the heat dissipation device to dissipate heat from the hardware partition based on the control weight, so that the state of the hardware partition reaches the target state.

[0009] The present application also provides a heat dissipation control apparatus, which includes:

[0010] A detection module, configured to detect the status changes of each hardware partition in the server to obtain status data, wherein the hardware partition includes an independently operating host system;

[0011] An allocation module, configured to allocate the control weight of the heat dissipation device to the hardware partition based on the status data;

[0012] A heat dissipation module, configured to control the heat dissipation device to dissipate heat from the hardware partition based on the control weight, so that the status of the hardware partition reaches the target status.

[0013] This application also provides an electronic device, including: a memory, configured to store a computer program; a processor, configured to implement the steps of any of the above heat dissipation control methods when executing the computer program.

[0014] This application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the above heat dissipation control methods are implemented.

[0015] This application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of any of the above heat dissipation control methods are implemented.

[0016] Through this application, first, the status changes of each hardware partition in the server can be detected to obtain status data, wherein the hardware partition includes an independently operating host system, and based on the status data, the control weight of the heat dissipation device is allocated to the hardware partition. Then, the heat dissipation device can be controlled to dissipate heat from the hardware partition based on the control weight, so that the status of the hardware partition reaches the target status. Therefore, the technical problem of poor heat dissipation system when the server performs global heat dissipation control through the management unit can be solved, so as to dynamically allocate the control weight of the heat dissipation device to dynamically optimize the heat dissipation power of the global heat dissipation device and avoid local overheating or power consumption waste of the server. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a heat dissipation control method according to an embodiment of the present invention provided by an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of dynamic heat dissipation management program scheduling;

[0020] Figure 3 Flow chart of another heat dissipation regulation method according to an embodiment of the present invention;

[0021] Figure 4 Schematic diagram of the arrangement of processors and heat dissipation devices in the hardware partition of a four-way server;

[0022] Figure 5 Flow chart of yet another heat dissipation regulation method according to an embodiment of the present invention;

[0023] Figure 6 Block diagram of the structure of a heat dissipation regulation device according to an embodiment of the present invention;

[0024] Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0025] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0026] It should be noted that in the description of the present application, the terms "including", "comprising" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in the present application are used to distinguish similar objects and not to describe a specific order or sequence.

[0027] In order to enable those skilled in the art of the present technology to better understand the solution of the present application, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0028] Combined with the specific application environment architecture or specific hardware architecture on which the execution of the heat dissipation regulation method depends, the specific application environment architecture or specific hardware architecture will be described herein.

[0029] In recent years, with the rapid development of cloud computing, artificial intelligence, and big data technologies, multi-way and multi-core processors have become the core computing units in data centers. To further improve the utilization rate of hardware resources in the multi-tenant scenario of data centers, multiple virtual machines are virtualized on a single physical server through traditional virtualization technology to achieve resource sharing. However, the additional overhead of the hypervisor makes it difficult for real-time services to meet the low-latency requirements. For this reason, the hardware partitioning technology has emerged. By physically isolating the computing resources of a single server (such as processors, memory, and input / output devices, etc.), it is divided into multiple independently running "bare metal" host systems, thus realizing the partitioning of the physical machine performance.

[0030] In related heat dissipation control schemes, the management unit in the server often globally manages all heat dissipation devices and adjusts the rotation speed based on the overall temperature threshold of the server. For example, if the server includes multiple hosts, when it is detected that the temperature in the server rises, the management unit can increase the rotation speed of all fans to dissipate heat from the server. However, since there are often differences in each hardware partition in the server, this results in poor heat dissipation coordination for the entire server.

[0031] For example, if a static allocation scheme is adopted based on the related heat dissipation control scheme and a certain part of the fans are fixedly bound to a specific partition, since the heat dissipation of each hardware partition is jointly determined by multiple fans, this will lead to ambiguous control rights and still result in the problem of poor heat dissipation coordination for the entire server. If the temperature of a certain partition is relatively high and the rotation speed of the fans corresponding to this partition is increased to reduce the temperature of this partition, it may interfere with the air flow distribution in the adjacent partition, causing heat accumulation in the adjacent partition with a lower temperature.

[0032] Embodiments of the present application provide a heat dissipation control method. In combination with the execution process of the heat dissipation control method, the method is described in detail. The method can first detect the state changes of each hardware partition in the server to obtain state data. Among them, the hardware partition contains an independently running host system, and based on the state data, the control weight of the heat dissipation device is allocated to the hardware partition. Then, the heat dissipation device can be controlled based on the control weight to dissipate heat from the hardware partition, so that the state of the hardware partition reaches the target state, thereby dynamically allocating the control weight of the heat dissipation device to dynamically optimize the heat dissipation power of the global heat dissipation device and avoid local overheating or power consumption waste of the server.

[0033] According to an embodiment of the present invention, an embodiment of a heat dissipation control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0034] In this embodiment, a heat dissipation control method is provided, which can be used for servers, such as servers in data centers, etc. Figure 1 It is a flowchart of the heat dissipation control method according to an embodiment of the present invention, as Figure 1 shown, the process includes the following steps:

[0035] Step S101, detect the status changes of each hardware partition in the server to obtain status data, where the hardware partition includes an independently operating host system.

[0036] In the embodiments of the present disclosure, hardware partitioning technology can be adopted in the server, that is, the server is divided into multiple hardware partitions. Among them, the hardware partition can be multiple independently operating "bare metal" host systems obtained by physically isolating the computing resources (such as CPU, memory, and input / output devices, etc.) of a single server. Each hardware partition has exclusive hardware resources and can directly run native operating systems, such as the linux system, the windows system, etc.

[0037] During the operation of the server, it is necessary to monitor the status data of each hardware partition in real time. This status data can be used to indicate the load and temperature of the processor, memory, etc. in the hardware partition, so that the corresponding heat dissipation device of the hardware partition can be adjusted immediately according to this status data to dissipate heat from the hardware partition.

[0038] Step S102, based on the status data, allocate the control weight of the heat dissipation device for the hardware partition.

[0039] In the embodiments of the present disclosure, the management unit (baseboard management controller, hereinafter referred to as BMC) in the server can be partitioned in advance, and a corresponding BMC partition is allocated to each hardware partition, so that the BMC partition controls the heat dissipation device based on the control weight of the heat dissipation device. In addition, the heat dissipation device can be a fan.

[0040] It should be understood that for the same heat dissipation device, it can correspond to multiple hardware partitions, and the sum of the control weights corresponding to all hardware partitions is 1. For example, if the hardware partition 1 and the hardware partition 2 corresponding to the heat dissipation device 1, the control weight corresponding to the hardware partition 1 can be 0.6, and the control weight corresponding to the hardware partition 2 can be 0.4.

[0041] Here, the control weight of the heat dissipation device corresponding to the hardware partition can be dynamically adjusted. For example, the higher the real-time temperature determined according to the status data corresponding to the hardware partition, it indicates that the hardware partition has a greater demand for heat dissipation, and the control weight allocated to the heat dissipation partition can also be higher.

[0042] Step S103: Control the heat dissipation device to dissipate heat from the hardware partition based on the control weight, so that the state of the hardware partition reaches the target state.

[0043] In the embodiments of the present disclosure, when the heat dissipation device includes a fan, the control weight can be used to control the rotation speed of the heat dissipation device, so that the state of the hardware partition reaches the target state, where the target state can be used to indicate that the hardware temperature in the hardware partition has returned to the normal temperature, or the hardware load has returned to the normal load.

[0044] Specifically, when controlling the heat dissipation device based on the control weight, the PWM (Pulse Width Modulation) duty cycle of the heat dissipation device can be calculated based on the control weight, so as to adjust the fan frequency based on the PWM duty cycle, and then control the rotation speed. Here, if a heat dissipation device serves two started hardware partitions at the same time, the control right of its PWM duty cycle will be split according to this ratio. Through the remapping of the BMC physical PWM pins, multiple logical channels are established and independently adjusted by the corresponding partitions respectively.

[0045] For example, if the control weight of the hardware partition 1 corresponding to the fan is 0.6, and the control weight of the corresponding hardware partition 2 is 0.4, where the PWM duty cycle output by the BMC partition of the hardware partition 1 is PWM1, and the PWM duty cycle output by the BMC partition of the hardware partition 2 is PWM2. Then, the total PWM duty cycle corresponding to the fan can be expressed as 0.6PWM1 + 0.4PWM2.

[0046] It can be seen from the above description that in the embodiments of the present disclosure, first, the state changes of each hardware partition in the server can be detected to obtain state data, where the hardware partition includes an independently operating host system, and based on the state data, the control weight of the heat dissipation device is assigned to the hardware partition. Then, the heat dissipation device can be controlled based on the control weight to dissipate heat from the hardware partition, so that the state of the hardware partition reaches the target state, thereby dynamically allocating the control weight of the heat dissipation device to dynamically optimize the heat dissipation power of the global heat dissipation device and avoid local overheating or power consumption waste of the server.

[0047] In some optional embodiments, before assigning the control weight of the heat dissipation device to the hardware partition, the above Figure 1 corresponding embodiment further includes:

[0048] Step S11: Partition the management unit in the server based on the hardware partition to obtain a sub-management unit, where the management unit is used for global heat dissipation management based on the running state of the server.

[0049] Step S12: Assign the corresponding sub-management unit to the hardware partition, where the sub-management unit is used to control the heat dissipation device corresponding to the hardware partition.

[0050] In the embodiments of the present disclosure, the management unit is the above-mentioned BMC. Here, through the co - design of software and hardware of the BMC and the CPLD (complex programmable logic device, a programmable logic device), an intelligent heat dissipation management system composed of a dynamically topologically aware fan allocation module and a cross - partition thermal co - operation closed - loop control module can be realized. Among them, the operating status of each hardware partition can be obtained through the BMC, and the CPLD aggregates the temperature, power consumption and historical data of each hardware partition, runs a heat conduction prediction model and an emergency priority assessment, generates a globally optimized fan speed regulation strategy, and distributes control instructions to the corresponding heat dissipation devices through controlling PWM signals to control the fans.

[0051] Specifically, the BMC hardware in the server can be partitioned first to obtain multiple sub - management units (i.e., the above - mentioned BMC units). Here, each sub - management unit can be used to manage one or more corresponding hardware partitions and control the heat dissipation devices corresponding to the hardware partitions. Here, the sub - management unit can allocate the control weight of the heat dissipation device for the hardware partition by running a dynamic heat dissipation management program (the dynamic heat dissipation management program runs through the dynamically topologically aware fan allocation module) to control the heat dissipation device.

[0052] Next, in view of the load imbalance characteristics of the sub - management units in the hardware partition scenario, an elastic scaling heat dissipation control module scheduling mechanism can be adopted to run the above - mentioned dynamic heat dissipation management program, which specifically includes the following processes:

[0053] Step S21: Determine the target sub - management unit with a load lower than a preset threshold in the sub - management unit.

[0054] Step S22: Based on the target sub - management unit, run the dynamic heat dissipation management program to perform the step of allocating the control weight of the heat dissipation device for the hardware partition based on the state data according to the dynamic heat dissipation management program.

[0055] In the embodiments of the present disclosure, the target sub - management unit with a load lower than the preset threshold can be the sub - management unit with the lowest load. For example, when the hardware partition is in the shutdown state, the sub - management unit is in a low - load state because it does not run real - time monitoring tasks.

[0056] Here, the load level of each sub - management unit can be directly associated with the operating status of the corresponding hardware partition. For example, when a certain hardware partition is in the shutdown state, its associated sub - management unit is in a low - load state due to no real - time monitoring tasks. At this time, the system automatically schedules the dynamic heat dissipation management program to run on this low - load sub - management unit to fully utilize the idle computing resources to generate a global control strategy.

[0057] For another example, if all hardware partitions are in the powered-on state, the system monitors the processor utilization rate of each hardware partition in real time through the BMC inter-core communication method, migrates the dynamic thermal management program to the target sub-management unit with the lowest current core load, and uses the state snapshot and incremental synchronization technology to achieve the switch, ensuring that the program operation always occupies the lowest resources.

[0058] Specifically, the above step S21 of determining the target sub-management unit with a load lower than the preset threshold in the sub-management unit includes:

[0059] When the running time of the dynamic thermal management program meets the load migration condition, determine the target sub-management unit based on the sub-management unit with the current lowest load.

[0060] In the embodiments of the present disclosure, it is considered that the load change rate of the server is closely related to the usage scenario and the running period. For example, for some usage scenarios, certain specific periods of each day are usually the peak periods of user access, such as the shopping time at night, the working time during the day, etc. Taking a social media platform as an example, seven or eight o'clock in the evening is a period with high user activity, and a large number of users will log in, post content, and interact at the same time. Therefore, the load migration condition can be established based on the usage scenario and the running period, and the load migration operation of the dynamic thermal management program is executed when the load migration condition is met, so as to avoid overly frequent migration of the dynamic thermal management program.

[0061] Specifically, a migration detection program can be set in advance, and the migration detection program is run when the running time of the dynamic thermal management program meets the load migration condition to detect the target sub-management unit and migrate the dynamic thermal management program.

[0062] After determining the target sub-management unit, the above step S22 of running the dynamic thermal management program based on the target sub-management unit includes:

[0063] Step a1, when the number of target sub-management units is multiple, obtain the inter-core communication efficiency of the target sub-management units, and determine whether the inter-core communication efficiency meets the parallel processing condition. If so, execute step a2; if not, execute step a3.

[0064] Step a2, run the dynamic thermal management program jointly based on the target sub-management units.

[0065] Step a3, run the dynamic thermal management program based on any one of the target sub-management units.

[0066] In an embodiment of the present disclosure, the BMC may be multi-core, and data transmission between sub-management units is performed through inter-core communication. Therefore, when the inter-core communication efficiency is high, it indicates that the communication bus is less occupied, and the dynamic thermal management program can be run in parallel by multiple target sub-management units. Conversely, the dynamic thermal management program can be run by any one of the target sub-management units alone.

[0067] Specifically, as Figure 2 shown in the schematic diagram of the dynamic thermal management program scheduling, in (a), all hardware partitions are closed, and at this time, there is no need to schedule the thermal control module. In (b), partitions 1 and 2 are in the power-on state, so the dynamic thermal management program is scheduled on the target sub-management units of partitions 3 and 4. Specifically, the dynamic thermal management program can be run simultaneously through the target sub-management units of partitions 3 and 4, or can be run through the target sub-management unit of partition 3 or partition 4. In (c), hardware partitions 1-3 are in the startup state, while partition 4 is closed, and at this time, the dynamic thermal management program runs on the target sub-management unit of partition 4. In (d), all hardware partitions are in the power-on state, and the dynamic thermal management program will migrate among the 4 sub-management units to ensure that it always runs in the target sub-management unit with the lowest load. At the same time, the load conditions are synchronized among the 4 sub-management units through inter-core communication.

[0068] In an embodiment of the present disclosure, a corresponding sub-management unit can be assigned to each hardware partition in the server, so as to provide a basis for the dynamic control of the partitions of the heat dissipation device, and the dynamic thermal management program is automatically transferred to the target sub-management unit with low load for operation, so as to make full use of the idle computing resources to generate a global control strategy.

[0069] In this embodiment, another heat dissipation regulation method is provided, which can be used for servers, such as servers in data centers, etc. Figure 3 It is a flowchart of the heat dissipation regulation method according to an embodiment of the present invention. As Figure 3 shown, the process includes the following steps:

[0070] Step S301, detecting the state changes of each hardware partition in the server to obtain state data, where the hardware partition includes an independently operating host system. For details, please refer to Figure 1 step S101 of the embodiment shown herein, which will not be elaborated herein.

[0071] Step S302, based on the state data, allocating the control weight of the heat dissipation device to the hardware partition.

[0072] Specifically, the above step S302 includes:

[0073] Step S3021: Obtain a preset weight matrix, where the preset weight matrix is used to indicate the original weights pre-assigned to each hardware partition for controlling the corresponding heat dissipation device.

[0074] Step S3022: Adjust the original weights corresponding to the hardware partitions in the preset weight matrix based on the status data to obtain control weights.

[0075] In the dynamic topology-aware fan allocation mechanism proposed in the embodiments of the present disclosure, an association weight between the heat dissipation device and the hardware partition can be constructed based on the real-time perception of the server's physical heat dissipation topology and the hardware partition status to obtain a preset weight matrix, so as to achieve dynamic and precise allocation of the control right based on this preset weight matrix.

[0076] Specifically, the following process may be included when determining the above preset weight matrix:

[0077] Step S31: Obtain the position information corresponding to the heat dissipation device.

[0078] Step S32: Based on the position information, determine the distance data between the heat dissipation device and the hardware partition.

[0079] Step S33: Perform simulation based on the distance data to obtain the original weights for the hardware partitions to control the corresponding heat dissipation devices, and determine the preset weight matrix according to the original weights corresponding to each hardware partition.

[0080] In the embodiments of the present disclosure, the heat dissipation contribution of the fan to each partition can be quantified through a thermodynamic association model. Specifically, first, determine the distance data according to the physical distance between the heat dissipation device and the hardware partition, and define a spatial distance attenuation factor based on this distance data, where the weight value is inversely proportional to the square of the distance. Here, simulation can be performed based on the distance data to obtain the original weights for the hardware partitions to control the corresponding heat dissipation devices to produce the best heat dissipation effect. It should be understood that normalization processing can be used to ensure that the sum of the original weights of a single heat dissipation device for all hardware partitions is 1.

[0081] For example, as Figure 4 shown is a schematic diagram of the arrangement of the processors and heat dissipation devices of the hardware partitions of a four-way server, where Processors 1 - 4 correspond to Hardware Partitions 1 - 4, and F1 - F6 correspond to Heat Dissipation Devices 1 - 6.

[0082] For Figure 4For the server layout shown, the simulation results corresponding to the heat dissipation device F1 can be: the original weight for processor 1 is 0.6, the original weight for processor 2 is 0, the original weight for processor 3 is 0, and the original weight for processor 4 is 0.4. The simulation results corresponding to the heat dissipation device F3 can be: the original weight for processor 1 is 0.2, the original weight for processor 2 is 0.3, the original weight for processor 3 is 0.3, and the original weight for processor 4 is 0.2. The simulation results corresponding to the heat dissipation device F5 can be: the original weight for processor 1 is 0, the original weight for processor 2 is 0.7, the original weight for processor 3 is 0.3, and the original weight for processor 4 is 0.

[0083] Then, the preset weight matrix determined according to the original weights of the hardware partitions corresponding to the heat dissipation device 1, the heat dissipation device 3, and the heat dissipation device 4 can be expressed as: .

[0084] Step S303, based on the control weights, control the heat dissipation device to dissipate heat from the hardware partition so that the state of the hardware partition reaches the target state. For details, please refer to Figure 1 Step S103 of the embodiment shown, which will not be elaborated here.

[0085] In the embodiments of the present disclosure, the distance data between the heat dissipation device and the hardware partition can be determined based on the position information corresponding to the heat dissipation device, so as to perform simulation based on the distance data to obtain the original weight of the hardware partition controlling the corresponding heat dissipation device, and determine the preset weight matrix according to the original weights corresponding to each hardware partition, thereby combining the hardware position, the air duct direction, and the radiator distribution, generating a preset weight matrix for heat dissipation device control that is strongly correlated with the physical structure, assigning higher weights to the heat dissipation devices of adjacent hardware partitions to directionally enhance the heat dissipation efficiency, and laying the foundation for the optimal allocation of basic heat dissipation resources.

[0086] In some alternative embodiments, the above step S3022, adjusting the original weight corresponding to the hardware partition in the preset weight matrix based on the state data to obtain the control weight, includes:

[0087] Step S41, based on the state data, determine the first hardware partition where the processor is powered on and the second hardware partition where the processor is in the sleep or shutdown state in the hardware partition.

[0088] Step S42, increase the original weight corresponding to the first hardware partition in the preset weight matrix, and decrease the original weight corresponding to the second hardware partition in the preset weight matrix to obtain the control weight.

[0089] In the embodiments of the present disclosure, the status data can be used to indicate the power-on state, power-off state, and sleep state of the processor in the hardware partition. Here, when the processor is in the power-off state or the sleep state, the original weight corresponding to the hardware partition of the processor can be adjusted to zero, and the extra weight can be allocated to other hardware partitions corresponding to the heat dissipation device to keep the sum of the control weights corresponding to the heat dissipation device unchanged.

[0090] Specifically, the hardware partition where the processor is powered on can be determined as the first hardware partition, and the hardware partition where the processor is in the sleep state or powered off can be determined as the second hardware partition. Then, the above step S42 can be executed to increase the original weight corresponding to the first hardware partition in the preset weight matrix and decrease the original weight corresponding to the second hardware partition in the preset weight matrix to obtain the control weight, which specifically includes the following process:

[0091] Step S421, determine the target heat dissipation devices corresponding to the first hardware partition and the second hardware partition in the heat dissipation device.

[0092] Step S422, reduce the original weight corresponding to the second hardware partition to the preset weight, and increase the original weight of the first hardware partition based on the proportion of the original weight of the first hardware partition in the target heat dissipation device to obtain the control weight, where the preset weight matches the state of the second hardware partition.

[0093] In the embodiments of the present disclosure, if the target heat dissipation devices corresponding to the first hardware partition and the second hardware partition are the same, the sum of the control weights corresponding to the first hardware partition and the second hardware partition is 1. On this basis, the above step S422 can be executed to increase the original weight of the first hardware partition based on the proportion of the original weight of the first hardware partition in the target heat dissipation device to obtain the control weight, which specifically includes:

[0094] Step b1, obtain the sum of the original weights corresponding to the first hardware partition.

[0095] Step b2, increase the original weight of the corresponding first hardware partition based on the proportion value of the original weight of each first hardware partition in the weight sum to obtain the control weight.

[0096] In the embodiments of the present disclosure, the total weight sum of the original weights corresponding to the above target heat dissipation device can be 1, and the sum of the original weights corresponding to the first hardware partition can be the total weight sum minus the original weight of the second hardware partition. For example, if the weight of the second hardware partition is 0.2, the sum of the original weights corresponding to the first hardware partition can be 1 - 0.2 = 0.8.

[0097] Then, the proportion of the original weight of each first hardware partition in the corresponding original weight sum of the first hardware partition can be calculated separately to obtain the control weight corresponding to the first hardware partition in the target heat dissipation device. Specifically, if the original weight corresponding to the first hardware partition is and the original weight corresponding to the second hardware partition is , then the control weight corresponding to the first hardware partition can be successively expressed as: ,..., .

[0098] For example, taking the server arrangement corresponding to Figure 4 as an example, the rotation speed of the target heat dissipation device F4 is jointly determined by processors 1 - 4. If the system state changes at this time and processor 3 goes into sleep or shutdown, a weight reallocation will be triggered, adjusting the control weight of processor 3 to 0 and reallocating the control weights for the hardware partitions corresponding to processors 1, 2, and 4. Here, as can be seen from above, the simulation results corresponding to the heat dissipation device F3 can be: the original weight for processor 1 is 0.2, the original weight for processor 2 is 0.3, the original weight for processor 3 is 0.3, and the original weight for processor 4 is 0.2. Therefore, the control weight corresponding to hardware partition 1 can be expressed as , the control weight corresponding to hardware partition 2 can be expressed as , and the control weight corresponding to hardware partition 4 can be expressed as . That is to say, the rotation speed of the target heat dissipation device F3 is jointly controlled by processor 1 (29%), processor 2 (43%), and processor 4 (29%).

[0099] Another example, the rotation speed of the target heat dissipation device F5 is jointly determined by processor 1 and processor 3. After processor 3 goes into sleep or shutdown, the control weight of processor 3 is adjusted to 0, and the control weight of processor 2 is adjusted to 1, that is, the target heat dissipation device F5 will be completely controlled by the local duty cycle of CPU2. At this time, F5 still dissipates heat for processor 2 but is no longer affected by the demand of processor 3.

[0100] It should be understood that in addition to indicating the above-mentioned machine state, shutdown state, and sleep state, the operating state can also include the load state of the hardware partition, such as processor load, memory load, etc. Therefore, the original weight and control weight of the hardware partition can also be adjusted based on the load state of the hardware partition.

[0101] For example, if the load of processor 2 suddenly increases and the system detects that the temperature rise rate of processor 2 exceeds the threshold, the control weight of its associated heat dissipation device will be temporarily increased. As can be seen from above, the heat dissipation devices associated with processor 2 can be heat dissipation device F3 and heat dissipation device F5. Then, the control weights of the heat dissipation devices associated with this processor 2 can be adjusted.

[0102] Specifically, the control weight of the processor 2 corresponding to the heat dissipation device F3 can be increased from 0.43 to 0.6, and the control weights of the processor 1 and the processor 2 can be reduced to 0.2. Additionally, considering that the control weight corresponding to the heat dissipation device F5 is already 100%, then, the duty cycle of the heat dissipation device F5 can be allowed to exceed the safety upper limit, for example, increased from 70% to 90%. It should be understood that the duty cycle of the heat dissipation device can be close to 100%, specifically subject to the heat dissipation requirements in the actual use process.

[0103] In the embodiment of the present disclosure, based on the status data, the first hardware partition where the processor is powered on and the second hardware partition where the processor is in the sleep or shutdown state are determined in the hardware partition, so as to increase the original weight corresponding to the first hardware partition in the preset weight matrix and reduce the original weight corresponding to the second hardware partition in the preset weight matrix, thereby obtaining the control weight, realizing the innovative design of the dynamic weight, ensuring the reasonable migration of the fan control right when any processor is in the sleep or shutdown state, avoiding the systematic heat dissipation risk caused by local failure, and adjusting the server heat dissipation efficiency by further optimizing the initial preset weight matrix, and further achieving the optimal heat dissipation device control efficiency on the multi-hardware partition platform.

[0104] In this embodiment, another heat dissipation regulation method is provided, which can be used for a server, for example, a server in a data center, etc. Figure 5 It is a flowchart of the heat dissipation regulation method according to the embodiment of the present invention, as Figure 5 shown, and this process includes the following steps:

[0105] Step S501, detecting the status change of each hardware partition in the server to obtain status data, where the hardware partition includes an independently operating host system. For details, please refer to Figure 1 step S101 of the embodiment shown, which will not be elaborated here.

[0106] Step S502, based on the status data, allocating the control weight of the heat dissipation device to the hardware partition. For details, please refer to Figure 1 step S102 of the embodiment shown, which will not be elaborated here.

[0107] Step S503, controlling the heat dissipation device to dissipate heat from the hardware partition based on the control weight, so that the status of the hardware partition reaches the target status.

[0108] Specifically, the above step S503, controlling the heat dissipation device to dissipate heat from the hardware partition based on the control weight, includes:

[0109] Step S5031, obtaining the pulse width modulation parameter output by the hardware partition corresponding to the heat dissipation device, where the pulse width modulation parameter is used to control the rotation speed of the fan in the heat dissipation device.

[0110] Step S5032: Based on the control weight corresponding to the pulse width modulation parameter, determine the control parameter corresponding to the heat dissipation device, and control the heat dissipation device to dissipate heat from the hardware partition based on the control parameter.

[0111] In the embodiment of the present disclosure, the pulse width modulation parameter may be the above-mentioned PWM duty cycle, and this pulse width modulation parameter may be determined and output to the heat dissipation device by the sub-management unit corresponding to the hardware partition in real time to control the fan speed.

[0112] Specifically, when the sub-management unit determines the pulse width modulation parameter corresponding to the hardware partition, it may monitor the temperature of the hardware partition. For example, the sub-management unit will monitor the temperature of key components in the hardware partition in real time, such as the processor, memory, hard disk, etc. When the temperature of these components rises, the sub-management unit will increase the pulse width modulation parameter according to the preset strategy, so that the fan speed increases, thereby enhancing the heat dissipation effect and ensuring that the key components operate within the safe temperature range. For another example, the sub-management unit may also consider the overall temperature distribution of the hardware partition. Through the data collected by multiple temperature sensors, the sub-management unit can judge the temperature conditions in different regions of the hardware partition and adjust the pulse width modulation parameter as needed to achieve the overall heat dissipation balance. For example, if the temperature at the rear of the hardware partition is relatively high while the temperature at the front is relatively low, the sub-management unit may adjust the pulse width modulation parameter to allow cold air to enter the server interior better and hot air to be discharged faster.

[0113] Alternatively, when the sub-management unit determines the pulse width modulation parameter corresponding to the hardware partition, it may also monitor the power consumption of the hardware partition. For example, it may monitor the device power consumption and the power supply power consumption (if any) respectively, and combine other temperature data to comprehensively judge the heat dissipation requirements of the hardware partition, and then adjust the pulse width modulation parameter corresponding to the heat dissipation device to control the fan speed.

[0114] Alternatively, when the sub-management unit determines the pulse width modulation parameter corresponding to the hardware partition, it may also monitor the system load of the hardware partition. For example, it monitors the utilization rates of the processor and memory. When there are more tasks running in the hardware partition and the utilization rates of the processor and memory are high, more heat will be generated. At this time, the sub-management unit will increase the pulse width modulation parameter and increase the fan speed to ensure the stable operation of the system. For example, in a data center, when a large number of users access a certain hardware partition simultaneously, the utilization rates of the processor and memory will increase significantly, and the sub-management unit will automatically adjust the fan speed to ensure that the hardware partition does not malfunction due to overheating.

[0115] After the sub-management unit of the hardware partition determines the control weight, the above-mentioned step S5032 may be executed to determine the control parameter corresponding to the heat dissipation device based on the control weight corresponding to the pulse width modulation parameter, including:

[0116] Step c1: Perform weighted summation on the pulse width modulation parameters based on the control weights to obtain the summation result.

[0117] Step c2: Determine the control parameters of the heat dissipation device according to the summation result.

[0118] In the embodiments of the present disclosure, the control parameters may include the PWM duty cycle of the fan in the heat dissipation device, and the control parameters of each heat dissipation device may be expressed as the weighted sum of the pulse width modulation parameters output by its corresponding hardware partition.

[0119] For example, as described above, the control weight of hardware partition 1 corresponding to the heat dissipation device F1 is 0.6, and the control weight of hardware partition 4 is 0.4. If the pulse width modulation parameter output by hardware partition 1 is , and the pulse width modulation parameter output by hardware partition 4 is . Then, the control parameter of the heat dissipation device F1 can be expressed as: ( × 0.6)+( × 0.4).

[0120] Another example, as described above, the control weight of hardware partition 1 corresponding to the heat dissipation device F3 is 0.2, the control weight of hardware partition 2 is 0.3, the control weight of hardware partition 3 is 0.3, and the control weight of hardware partition 4 is 0.2. If the pulse width modulation parameter output by hardware partition 1 is , if the pulse width modulation parameter output by hardware partition 2 is , if the pulse width modulation parameter output by hardware partition 3 is , and the pulse width modulation parameter output by hardware partition 4 is . Then, the control parameter of the heat dissipation device F3 can be expressed as: ( × 0.2)+( × 0.3)+( × 0.3)+( × 0.2).

[0121] In the embodiments of the present disclosure, the control parameters corresponding to the pulse width modulation parameters output by the hardware partitions corresponding to the heat dissipation device can be determined, and the heat dissipation device can be controlled based on the control parameters to dissipate heat from the hardware partitions, so as to realize local heat dissipation optimization according to the physical layout of the server through the heat dissipation distribution method of dynamic topology perception. While reducing the average rotational speed of the fans in the heat dissipation device and extending its service life, it reduces the hardware protection downtime triggered by overheating and significantly improves the availability of the server.

[0122] In some alternative embodiments, the above step S503 further includes:

[0123] Step S51: Predict a first target hardware partition whose change rate exceeds the load change threshold based on the load change of the hardware partition.

[0124] Step S52: Obtain the load prediction result for the first target hardware partition.

[0125] Step S53: Adjust the pulse width modulation parameter output by the hardware partition based on the load prediction result.

[0126] In the embodiment of the present disclosure, considering a hardware partition with a relatively fast load change rate, it means that the temperature will rise or fall relatively fast in a future period. Therefore, a first target hardware partition whose change rate exceeds the load change threshold can be predicted based on the load change of the hardware partition. Here, if the load prediction result is that the load is increasing, it indicates that the temperature of the hardware partition will rise. Therefore, the pulse width modulation parameter can be increased to increase the rotation speed of the fan in the heat dissipation device. Conversely, the pulse width modulation parameter can be decreased to reduce the rotation speed of the fan in the heat dissipation device.

[0127] Here, the predicted change rate of the hardware partition can be predicted by means of a machine learning model, etc., to obtain the load prediction result. Among them, the machine learning model can be a neural network, a decision tree, a random forest, etc., which have strong learning ability and adaptability and can handle complex non-linear relationships.

[0128] Specifically, first, hardware partition data can be collected. For example, performance metric data, application program data, system event data, etc. Among them, the performance metric data can be historical data of key performance metrics such as processor usage rate, memory usage rate, network traffic, etc. obtained through server monitoring tools or operating system metrics. These data can intuitively reflect the load situation of the hardware partition and are the basis for prediction.

[0129] Then, the hardware partition data can be preprocessed. For example, identify and remove outliers in the data. These outliers may be caused by server failures, network attacks or other abnormal situations and will interfere with the prediction result. For missing values in the data, methods such as mean filling and interpolation filling can be used for processing to ensure the integrity of the data. And in order to reduce the fluctuation and noise of the data, the data can be smoothed, such as using the moving average method, etc.

[0130] Next, data feature extraction can be performed. For example, time feature extraction, historical load feature extraction, etc. Here, time is an important feature, including date, hour, minute, etc. The load of the server usually shows certain time patterns. For example, the morning and afternoon of each day may be peak working periods, while the load is relatively low at night; the load is higher on weekdays and lower on weekends. By analyzing the time features, these periodic changes can be captured. Past load data is an important basis for predicting future load. Statistical information such as the average load, maximum load, and minimum load within a past period of time can be calculated, as well as the change trend and fluctuation of the load. Historical load features can help understand the load characteristics and change rules of the hardware partition.

[0131] After selecting the corresponding machine learning model, it can be monitored and updated in real time. Specifically, during the actual operation process, the load situation of the server and other relevant metrics can be monitored in real time, and the real-time data is input into the prediction model to obtain real-time prediction results. This can promptly detect the change trend of the load and take corresponding measures for adjustment. At the same time, as time goes by and the business changes, the load characteristics of the server may also change. Therefore, it is necessary to update and optimize the prediction model regularly, retrain the model to adapt to new data and situations. The incremental learning method can be used to only learn and update the newly added data without retraining the entire model, improving the update efficiency of the model.

[0132] In the embodiments of the present disclosure, considering a hardware partition with a relatively fast load change rate, it means that the temperature will rise or fall relatively fast in a future period of time. Therefore, based on the load change of the hardware partition, the first target hardware partition whose change rate exceeds the load change threshold can be predicted, and the pulse width modulation parameters output by the hardware partition can be adjusted based on the load prediction result for the first target hardware partition, so as to dynamically adjust the pulse width modulation parameters of the hardware partition to adjust the fan speed before the temperature of the hardware partition rises or falls, thus making up for the lag in controlling the heat dissipation device according to the temperature.

[0133] In some optional implementation manners, the above Figure 1 corresponding implementation manner further includes:

[0134] Step S61: Obtain the preset heat dissipation model corresponding to the server.

[0135] Step S62: Based on the preset heat dissipation model, predict the second target hardware partition whose temperature exceeds the temperature threshold in the hardware partition.

[0136] Step S63: Obtain the temperature prediction result for the second target hardware partition.

[0137] Step S64: Adjust the pulse width modulation parameters output by the second target hardware partition based on the temperature prediction result.

[0138] In the embodiments of the present disclosure, it is considered that although the control weight allocation of dynamic topology awareness can achieve local heat dissipation optimization according to the physical layout of the server, it is still essentially an open-loop control and is difficult to cope with complex scenarios such as sudden surges in thermal load, multi-partition thermal coupling effects, and global power consumption constraints. Specifically, first, there are problems of thermal inertia and hysteresis. Dynamic topology awareness only relies on the current temperature state to allocate fan resources, and the heat conduction delay may cause local intervention to lag behind the actual thermal risk. Second, there are multi-heat source competition conflicts. When multiple partitions need to speed up heat dissipation simultaneously, dynamic topology awareness may cause fan resource contention due to the lack of a global coordination mechanism, resulting in over-limit of the overall machine power consumption or a decrease in heat dissipation efficiency. At the same time, due to the strong coupling of the temperature fields in each partition of the server, the static weight allocation of dynamic topology awareness cannot correct cross-region thermal interference in real time. Therefore, based on closed-loop control and the PID (Proportional-Integral-Derivative Control Algorithm) algorithm, the control weights of the hardware partitions and the output pulse width modulation parameters can be dynamically adjusted to suppress the temperature oscillation caused by thermal coupling and ensure that the system quickly converges to a steady state.

[0139] Specifically, first, a heat dissipation model of the server can be pre-established to obtain a preset heat dissipation model, so as to predict the second target hardware partition in which the temperature exceeds the temperature threshold in the hardware partition. Here, the optimal scheduling of heat dissipation resources for multi-heat source partitions in the server can be realized through dynamic weight allocation and global power consumption constraints. For example, a partial differential equation for the internal temperature field distribution of the server is established based on Fourier's law of heat conduction to establish a preset heat dissipation model, and the preset heat dissipation model can be expressed as: , where T is the temperature field distribution function, α is the thermal diffusivity, Q is the total heat generation power of the processor, ρ is the air density, is the specific heat capacity of air.

[0140] Then, the above-mentioned step S62 can be executed to predict the second target hardware partition in which the temperature exceeds the temperature threshold in the hardware partition based on the preset heat dissipation model, specifically including:

[0141] Step d1: Discretize the internal space of the server into grids to obtain the target grids corresponding to each hardware partition.

[0142] Step d2: Predict the temperature rise of the target grid within a preset time period based on the preset heat dissipation model to obtain the temperature prediction result corresponding to the hardware partition.

[0143] Step d3: Obtain the temperature threshold and determine, in the hardware partitions, a second target hardware partition whose temperature prediction result exceeds the temperature threshold.

[0144] In the embodiments of the present disclosure, the internal space of the server can be discretized into a grid to divide the internal space of the server into non-uniform grid cells. Here, the grid density in different regions of the server is different. For example, the target grid corresponding to the hardware partition can be relatively dense to improve the accuracy of temperature prediction, and the grid corresponding to the idle area can be relatively sparse to save computing power consumption.

[0145] Specifically, the internal space of the server can be discretized into a grid by the finite difference method to solve the temperature change trend within a future time period and predict the second target hardware partition with potential thermal risks. Here, the temperature prediction result of the target grid can be expressed as where represents the temperature value of the th grid cell at time step is the spatial step size, and is the time step size. Through iterative solution, the temperature distribution trend within a preset time period is predicted. Then, the pulse width modulation parameter output by the second target hardware partition is generated through a proportional-integral-derivative (PID) algorithm.

[0146] Specifically, the pulse width modulation parameter output by the second target hardware partition can be expressed as . Where u(t) is the PWM duty cycle output, is the temperature deviation, and is the set temperature threshold.

[0147] Then, based on the comparison result between the temperature prediction result and the temperature threshold, an adjustment operation can be performed on the pulse width modulation parameter output by the second target hardware partition. Specifically, the above CPLD can receive the temperature data of the hardware partitions sent by each sub-management unit in real time and compare it with the predicted value. When the temperature change rate of a certain hardware partition exceeds the temperature threshold (such as ), the fan speed regulation is triggered to increase the control weight of the heat dissipation device associated with the hot emergency partition. When the temperature of the hot emergency partition drops back to the safe range ( ), the CPLD restores the weight allocation in an exponentially decaying manner.

[0148] In the embodiments of the present disclosure, based on the temperature prediction results of the temperature prediction model, the pulse width modulation parameters output by the second target hardware partition can be adjusted, so as to implement a cross-partition thermal co - control closed-loop control method. Through the collaborative design of thermal field prediction modeling, dynamic speed regulation, and closed-loop feedback correction, multi-partition collaborative decision-making is achieved by means of a CPLD, and the PID algorithm is used to control and suppress environmental temperature fluctuations.

[0149] In summary, in the embodiments of the present disclosure, first, the state changes of each hardware partition in the server can be detected to obtain state data. Among them, the hardware partition contains an independently operating host system, and based on the state data, the control weight of the heat dissipation device is allocated to the hardware partition. Then, based on the control weight, the heat dissipation device can be controlled to dissipate heat from the hardware partition, so that the state of the hardware partition reaches the target state, thereby dynamically allocating the control weight of the heat dissipation device to dynamically optimize the heat dissipation power of the global heat dissipation device and avoid local overheating or power consumption waste of the server.

[0150] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method.

[0151] The embodiments of the present application also provide a heat dissipation regulation device for implementing the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0152] This embodiment provides a heat dissipation regulation device, as Figure 6 shown, including:

[0153] A detection module 601, configured to detect the state changes of each hardware partition in the server to obtain state data, where the hardware partition contains an independently operating host system;

[0154] An allocation module 602, configured to allocate the control weight of the heat dissipation device to the hardware partition based on the state data;

[0155] A heat dissipation module 603, configured to control the heat dissipation device to dissipate heat from the hardware partition based on the control weight, so that the state of the hardware partition reaches the target state.

[0156] In some optional implementation manners, the allocation module 602 is further configured to:

[0157] Obtain a preset weight matrix, where the preset weight matrix is used to indicate the original weights pre-assigned to each hardware partition for controlling the corresponding heat dissipation device;

[0158] Adjust the original weight corresponding to the hardware partition in the preset weight matrix based on the status data to obtain a control weight.

[0159] In some alternative embodiments, the allocation module 602 is further configured to:

[0160] Obtain the position information corresponding to the heat dissipation device;

[0161] Based on the position information, determine the distance data between the heat dissipation device and the hardware partition;

[0162] Perform simulation based on the distance data to obtain the original weight for the hardware partition to control the corresponding heat dissipation device, and determine the preset weight matrix according to the original weights corresponding to each hardware partition.

[0163] In some alternative embodiments, the allocation module 602 is further configured to:

[0164] Based on the status data, determine a first hardware partition where the processor is powered on and a second hardware partition where the processor is in a sleep or shutdown state among the hardware partitions;

[0165] Increase the original weight corresponding to the first hardware partition in the preset weight matrix and decrease the original weight corresponding to the second hardware partition in the preset weight matrix to obtain a control weight.

[0166] In some alternative embodiments, the allocation module 602 is further configured to:

[0167] Determine the target heat dissipation devices corresponding to the first hardware partition and the second hardware partition among the heat dissipation devices;

[0168] Reduce the original weight corresponding to the second hardware partition to a preset weight, and increase the original weight of the first hardware partition based on the proportion of the original weight of the first hardware partition in the target heat dissipation device to obtain a control weight, where the preset weight matches the state of the second hardware partition.

[0169] In some alternative embodiments, the allocation module 602 is further configured to:

[0170] Obtain the sum of the original weights corresponding to the first hardware partition;

[0171] Increase the corresponding original weight of the first hardware partition based on the proportion value of the original weight of each first hardware partition in the sum of the weights to obtain a control weight.

[0172] In some alternative embodiments, the device is further configured to:

[0173] Before allocating the control weight of the heat dissipation device to the hardware partition, partition the management units in the server based on the hardware partition to obtain sub-management units, where the management unit is used for global heat dissipation management based on the operating state of the server.

[0174] Allocate corresponding sub-management units to the hardware partitions, where the sub-management units are used to control the heat dissipation devices corresponding to the hardware partitions.

[0175] In some alternative embodiments, the device is further configured to:

[0176] Determine a target sub-management unit with a load lower than a preset threshold in the sub-management units;

[0177] Run a dynamic heat dissipation management program based on the target sub-management unit, so as to execute the step of allocating the control weight of the heat dissipation device to the hardware partition based on the state data according to the dynamic heat dissipation management program.

[0178] In some alternative embodiments, the device is further configured to:

[0179] When the running time of the dynamic heat dissipation management program meets the load migration condition, determine the target sub-management unit based on the sub-management unit with the current lowest load.

[0180] In some alternative embodiments, the device is further configured to:

[0181] When the number of target sub-management units is multiple, obtain the inter-core communication efficiency of the target sub-management units, and determine whether the inter-core communication efficiency meets the parallel processing condition;

[0182] If so, run the dynamic heat dissipation management program jointly based on the target sub-management units;

[0183] If not, run the dynamic heat dissipation management program based on any one of the target sub-management units.

[0184] In some alternative embodiments, the heat dissipation module 603 is further configured to:

[0185] Obtain the pulse width modulation parameters output by the hardware partition corresponding to the heat dissipation device, where the pulse width modulation parameters are used to control the rotation speed of the fan in the heat dissipation device;

[0186] Determine the control parameters corresponding to the heat dissipation device based on the control weight corresponding to the pulse width modulation parameters, and control the heat dissipation device to dissipate heat from the hardware partition based on the control parameters.

[0187] In some alternative embodiments, the heat dissipation module 603 is further configured to: perform weighted summation on the pulse width modulation parameters based on the control weight to obtain a summation result;

[0188] Determine the control parameters of the heat dissipation device according to the summation result.

[0189] In some alternative embodiments, the heat dissipation module 603 is further configured to: predict a first target hardware partition whose change rate exceeds a load change threshold based on the load change of hardware partitioning;

[0190] Obtain a load prediction result for the first target hardware partition;

[0191] Adjust the pulse width modulation parameters output by the hardware partition based on the load prediction result.

[0192] In some alternative embodiments, the heat dissipation module 603 is further configured to: obtain a preset heat dissipation model corresponding to the server;

[0193] Predict a second target hardware partition whose temperature exceeds a temperature threshold in the hardware partition based on the preset heat dissipation model;

[0194] Obtain a temperature prediction result for the second target hardware partition;

[0195] Adjust the pulse width modulation parameters output by the second target hardware partition based on the temperature prediction result.

[0196] In some alternative embodiments, the heat dissipation module 603 is further configured to: perform grid discretization on the internal space of the server to obtain target grids corresponding to each hardware partition;

[0197] Predict the temperature increase of the target grids within a preset time period based on the preset heat dissipation model to obtain a temperature prediction result corresponding to the hardware partition;

[0198] Obtain a temperature threshold, and determine a second target hardware partition in the hardware partition whose temperature prediction result exceeds the temperature threshold.

[0199] In some alternative embodiments, the heat dissipation module 603 is further configured to: perform an adjustment operation on the pulse width modulation parameters output by the second target hardware partition based on the comparison result between the temperature prediction result and the temperature threshold.

[0200] For the description of the features in the embodiments corresponding to the heat dissipation control device, reference may be made to the relevant description in the embodiments corresponding to the heat dissipation control method, which will not be elaborated here one by one.

[0201] An embodiment of the present application further provides an electronic device, as Figure 7 shown, including a memory 10 and a processor 20. A computer program is stored in the memory 10, and the processor 20 is configured to run the computer program to execute the steps in any of the above heat dissipation control method embodiments.

[0202] Embodiments of the present application also provide a computer-readable storage medium storing a computer program, where the computer program is configured to execute the steps in any of the above-described embodiments of the heat dissipation control method when running.

[0203] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, read-only memory (ROM for short), random access memory (RAM for short), external hard drives, magnetic disks, or optical discs that can store computer programs.

[0204] Embodiments of the present application also provide a computer program product. The above computer program product includes a computer program, and when the computer program is executed by a processor, the steps in any of the above-described embodiments of the heat dissipation control method are implemented.

[0205] Embodiments of the present application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above-described embodiments of the heat dissipation control method are implemented.

[0206] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0207] The above has introduced in detail a heat dissipation control method, device, computer device, storage medium, and program product provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope required by the present application.

Claims

1. A heat dissipation control method, characterized in that The method includes: Detecting the state changes of each hardware partition in the server to obtain state data, where the hardware partition includes an independently operating host system; Partitioning the management unit in the server based on the hardware partition to obtain sub-management units, where the management unit is used for global heat dissipation management based on the operating state of the server; Allocating corresponding sub-management units to the hardware partitions; Determining target sub-management units with a load lower than a preset threshold in the sub-management units; When the number of the target sub-management units is multiple, obtaining the inter-core communication efficiency of the target sub-management units and determining whether the inter-core communication efficiency meets the parallel processing condition; If so, jointly running a dynamic heat dissipation management program based on the target sub-management units; Based on the state data, allocating control weights of heat dissipation devices to the hardware partitions through the dynamic heat dissipation management program jointly run on the target sub-management units; Controlling the heat dissipation devices to dissipate heat from the hardware partitions through the sub-management units based on the control weights, so that the state of the hardware partitions reaches the target state.

2. The method according to claim 1, wherein The allocating control weights of heat dissipation devices to the hardware partitions based on the state data includes: Obtaining a preset weight matrix, where the preset weight matrix is used to indicate the original weights for allocating the corresponding heat dissipation devices to each hardware partition in advance; Adjusting the original weights corresponding to the hardware partitions in the preset weight matrix based on the state data to obtain the control weights.

3. The method according to claim 2, wherein The method further includes: Obtaining the position information corresponding to the heat dissipation device; Based on the position information, determining the distance data between the heat dissipation device and the hardware partition; Performing simulation based on the distance data to obtain the original weights of the hardware partitions for controlling the corresponding heat dissipation devices, and determining the preset weight matrix according to the original weights corresponding to each hardware partition.

4. The method according to claim 2, wherein The adjusting the original weights corresponding to the hardware partitions in the preset weight matrix based on the state data to obtain the control weights includes: Based on the state data, determining a first hardware partition with a powered-on processor and a second hardware partition with a sleeping or powered-off processor in the hardware partitions; Increasing the original weights corresponding to the first hardware partition in the preset weight matrix and decreasing the original weights corresponding to the second hardware partition in the preset weight matrix to obtain the control weights.

5. The method according to claim 4, characterized in that, The increasing the original weights corresponding to the first hardware partition in the preset weight matrix and decreasing the original weights corresponding to the second hardware partition in the preset weight matrix to obtain the control weights includes: Determining target heat dissipation devices corresponding to the first hardware partition and the second hardware partition in the heat dissipation device; Reducing the original weights corresponding to the second hardware partition to a preset weight, and increasing the original weights corresponding to the first hardware partition based on the proportion of the original weights of the first hardware partition in the target heat dissipation device to obtain the control weights, where the preset weight matches the operating state of the second hardware partition.

6. The method according to claim 5, characterized in that, The proportion of the original weight based on the first hardware partition in the target heat dissipation device, increasing the original weight of the first hardware partition to obtain the control weight, includes: Obtaining the sum of the original weights corresponding to the first hardware partition; Based on the proportion of the original weight of each first hardware partition in the sum of weights, increasing the original weight of the corresponding first hardware partition to obtain the control weight.

7. The method according to claim 1, characterized in that Determining the target sub-management unit with a load lower than the preset threshold in the sub-management unit includes: When the running time of the dynamic heat dissipation management program meets the load migration condition, determining the target sub-management unit based on the sub-management unit with the current lowest load.

8. The method according to claim 1, characterized in that, The method further includes: If not, running the dynamic heat dissipation management program based on any target sub-management unit.

9. The method according to claim 1, wherein Controlling the heat dissipation device to dissipate heat from the hardware partition based on the control weight includes: Obtaining the pulse width modulation parameter output by the hardware partition corresponding to the heat dissipation device, where the pulse width modulation parameter is used to control the rotation speed of the fan in the heat dissipation device; Based on the control weight corresponding to the pulse width modulation parameter, determining the control parameter corresponding to the heat dissipation device, and controlling the heat dissipation device to dissipate heat from the hardware partition based on the control parameter.

10. The method according to claim 9, characterized in that Determining the control parameter corresponding to the heat dissipation device based on the control weight corresponding to the pulse width modulation parameter includes: Performing weighted summation on the pulse width modulation parameter based on the control weight to obtain a summation result; Determining the control parameter of the heat dissipation device according to the summation result.

11. The method according to claim 10, wherein, The method further includes: Predicting a first target hardware partition with a change rate exceeding the load change threshold based on the load change of the hardware partition; Obtaining a load prediction result for the first target hardware partition; Adjusting the pulse width modulation parameter output by the hardware partition based on the load prediction result.

12. The method according to claim 9, wherein The method further includes: Obtaining a preset heat dissipation model corresponding to the server; Based on the preset heat dissipation model, predicting a second target hardware partition with a temperature exceeding the temperature threshold in the hardware partition; Obtaining a temperature prediction result for the second target hardware partition; Adjusting the pulse width modulation parameter output by the second target hardware partition based on the temperature prediction result.

13. The method according to claim 12, wherein Predicting a second target hardware partition with a temperature exceeding the temperature threshold in the hardware partition based on the preset heat dissipation model includes: Performing grid discretization on the internal space of the server to obtain target grids corresponding to each hardware partition; Predicting the temperature increase of the target grid within a preset time period based on the preset heat dissipation model to obtain the temperature prediction result corresponding to the hardware partition; Obtaining a temperature threshold, and determining a second target hardware partition in the hardware partition whose temperature prediction result exceeds the temperature threshold.

14. The method according to claim 13, wherein The method further includes: Performing an adjustment operation on the pulse width modulation parameter output by the second target hardware partition based on the comparison result between the temperature prediction result and the temperature threshold.

15. A heat dissipation control device, characterized in that, The device includes: A detection module, configured to detect status changes of each hardware partition in the server to obtain status data, where the hardware partition includes an independently operating host system; An allocation module, configured to partition the management units in the server based on the hardware partitions to obtain sub-management units, where the management units are used for global heat dissipation management based on the operating status of the server; allocate corresponding sub-management units to the hardware partitions; determine target sub-management units with loads lower than a preset threshold in the sub-management units; when the number of the target sub-management units is multiple, obtain the inter-core communication efficiency of the target sub-management units and determine whether the inter-core communication efficiency meets the parallel processing condition; if so, jointly run a dynamic heat dissipation management program based on the target sub-management units; based on the status data, allocate control weights of a heat dissipation device to the hardware partitions through the dynamic heat dissipation management program jointly run on the target sub-management units; A heat dissipation module, configured to control the heat dissipation device to dissipate heat from the hardware partition through the sub-management unit based on the control weights, so that the status of the hardware partition reaches a target status.

16. A computer device, characterized in that, Comprising: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the heat dissipation regulation method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the heat dissipation regulation method according to any one of claims 1 to 14.

18. A computer program product, characterized in that, Including computer instructions, the computer instructions are used to cause a computer to execute the heat dissipation regulation method according to any one of claims 1 to 14.

Images