Heat Dissipation Strategy Determination Method, Device, Electronic Device and Storage Medium

Abstract

The present disclosure provides a heat dissipation strategy determination method, device, electronic device and storage medium, which are applied to the field of energy-saving control technology. The method includes: in response to the operation of a first service, determining the operation probability of the first service and the first probability of the temperature of a first component rising when the first service is running; determining the second probability of the temperature of the first component rising; based on the operation probability of the first service, the first probability of the temperature of the first component rising when the first service is running, and the second probability of the temperature of the first component rising, determining the posterior probability of the temperature of the first component rising caused by the first service; and determining the heat dissipation strategy of the electronic device based on the posterior probability of the temperature of the first component rising caused by the first service. In this way, it is not necessary to wait until the temperature reaches a certain threshold for regulation, which can reduce the noise caused by the sudden operation of the fan. At the same time, it can also avoid the decrease in server performance caused by the rapid change of the component temperature.

Description

Technical Field

[0001] The present disclosure relates to the field of energy-saving control technologies, and in particular, to a method, an apparatus, an electronic device, and a storage medium for determining a heat dissipation strategy. Background Art

[0002] In the related art, the PID (Proportional-Integral-Derivative) control mode is relied on for server heat dissipation. The principle is that when the component temperature reaches a pre-set threshold, a heat dissipation regulation strategy will be activated. However, the PID heat dissipation regulation technology has obvious drawbacks. First, since the regulation starts only after the temperature reaches the threshold, it will cause the problem of loud fan noise in stages, which not only affects the quietness of the server operating environment but may also cause certain interference to surrounding devices. Second, the component temperature changes greatly, and when the temperature is close to the threshold, the start and stop of the regulation are likely to cause large temperature fluctuations. Finally, the rapid change of the component temperature will also cause the server performance to decline, affecting the normal working efficiency of the server, reducing its stability and reliability, and unable to meet the growing high-performance server operation requirements. Summary of the Invention

[0003] The present disclosure provides a method, an apparatus, an electronic device, and a storage medium for determining a heat dissipation strategy, so as to at least solve the above technical problems existing in the prior art.

[0004] According to a first aspect of the present disclosure, a method for determining a heat dissipation strategy is provided, including:

[0005] In response to the operation of a first service, confirm the operation probability of the first service and, in the case of the operation of the first service, the first probability of the temperature rise of a first component;

[0006] Determine a second probability of the temperature rise of the first component;

[0007] Based on the operation probability of the first service, the first probability of the temperature rise of the first component in the case of the operation of the first service, and the second probability of the temperature rise of the first component, determine the posterior probability of the temperature rise of the first component caused by the first service;

[0008] Based on the posterior probability of the temperature rise of the first component caused by the first service, determine the heat dissipation strategy of the electronic device.

[0009] In the above solution, the confirmation of the operation probability of the first service includes:

[0010] Collect the historical operation data of each service in the electronic device;

[0011] Based on the historical operation data of each service, determine the operation probability of each service;

[0012] Among them, the above-mentioned various services include the first service.

[0013] In the above solution, the method further includes:

[0014] Collect the updated operation data of each service in the electronic device;

[0015] Based on the updated operation data and the historical operation data, update the operation probability of each service.

[0016] In the above solution, when confirming the operation of the first service, the first probability of the temperature rise of the first component includes:

[0017] Collect the historical temperature data of the first component when each service is running;

[0018] Based on the historical temperature data of the first component, determine the probability of the temperature rise of the first component when each service is running.

[0019] In the above solution, the method further includes:

[0020] Collect the updated temperature data of the first component when each service is running;

[0021] Based on the updated temperature data and the historical temperature data, update the probability of the temperature rise of the first component when each service is running.

[0022] In the above solution, when confirming the operation of the first service, the first probability of the temperature rise of the first component includes:

[0023] Input the operation data corresponding to the first service into the component temperature prediction model, and determine that the output of the component temperature prediction model is the first probability of the temperature rise of the first component.

[0024] In the above solution, the method further includes:

[0025] Obtain the historical operation data of each service and the historical temperature data of the first component when each service is running;

[0026] Based on the historical operation data of each service and the historical temperature data of the first component, train the component temperature prediction model;

[0027] In the above solution, the determination of the second probability of the temperature rise of the first component includes:

[0028] Based on the operation probability of each service, the probability of the temperature rise of the first component when each service is running, and the total probability formula, determine the second probability of the temperature rise of the first component.

[0029] In the above solution, determining the second probability of the temperature rise of the first component based on the operating probabilities of each service, the probability of the temperature rise of the first component when each service is operating, and the total probability formula includes:

[0030] Based on the operating probability of each service in each service and the probability of the temperature rise of the first component when the service is operating, determine the probability of the temperature rise of the first component caused by the operation of each service;

[0031] Determine the sum of the probabilities of the temperature rise of the first component caused by the operation of all services as the second probability of the temperature rise of the first component.

[0032] In the above solution, determining the posterior probability of the temperature rise of the first component caused by the first service based on the operating probability of the first service, the first probability of the temperature rise of the first component when the first service is operating, and the second probability of the temperature rise of the first component includes:

[0033] Based on Bayes' formula, the operating probability of the first service, the first probability of the temperature rise of the first component when the first service is operating, and the second probability of the temperature rise of the first component, determine the posterior probability of the temperature rise of the first component caused by the first service.

[0034] In the above solution, determining the posterior probability of the temperature rise of the first component caused by the first service based on Bayes' formula, the operating probability of the first service, the first probability of the temperature rise of the first component when the first service is operating, and the second probability of the temperature rise of the first component includes:

[0035] Based on the product of the operating probability of the first service and the first probability of the temperature rise of the first component when the first service is operating, divide the result by the second probability of the temperature rise of the first component, which is the posterior probability of the temperature rise of the first component caused by the first service.

[0036] In the above solution, determining the heat dissipation strategy of the electronic device based on the posterior probability of the temperature rise of the first component caused by the first service includes:

[0037] Based on the posterior probability of the temperature rise of the first component caused by the first service and the corresponding relationship between the posterior probability and the heat dissipation strategy, determine the heat dissipation strategy of the electronic device;

[0038] Among them, the corresponding relationship between the posterior probability and the heat dissipation strategy includes the corresponding relationship between the posterior probability range and different heat dissipation strategies.

[0039] In the above solution, the first service includes one of the following:

[0040] Network service business, data management business, application service business, virtualization business, and proxy business.

[0041] In the above solution, the first component includes one of the following:

[0042] A central processing unit, an image processor, a storage disk, a memory card, and a network card.

[0043] According to a second aspect of the present disclosure, there is provided a heat dissipation strategy determination device, the device includes:

[0044] A prior probability determination unit, configured to, in response to the operation of a first service, confirm the operation probability of the first service and, in the case where the first service is operating, the first probability of the temperature of the first component rising;

[0045] A total probability determination unit, configured to determine a second probability of the temperature of the first component rising;

[0046] A posterior probability determination unit, configured to determine a posterior probability that the temperature rise of the first component is caused by the first service based on the operation probability of the first service, the first probability of the temperature of the first component rising in the case where the first service is operating, and the second probability of the temperature of the first component rising;

[0047] A heat dissipation strategy determination unit, configured to determine a heat dissipation strategy of the electronic device based on the posterior probability that the temperature rise of the first component is caused by the first service.

[0048] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0049] At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the present disclosure.

[0050] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to cause the computer to execute the method described in the present disclosure.

[0051] According to a fifth aspect of the present disclosure, there is provided a computer program product, including a computer program, where the computer program, when executed by a processor, implements the method described in the present disclosure.

[0052] The heat dissipation strategy determination method of the present disclosure includes: upon responding to the operation of a first service, confirming the operation probability of the first service and the first probability of the temperature rise of a first component when the first service is operating; determining the second probability of the temperature rise of the first component; based on the operation probability of the first service, the first probability of the temperature rise of the first component when the first service is operating, and the second probability of the temperature rise of the first component, determining the posterior probability of the temperature rise of the first component caused by the first service; and based on the posterior probability of the temperature rise of the first component caused by the first service, determining the heat dissipation strategy of the electronic device. In this way, when the service starts to operate, the posterior probability of the temperature rise of the first component caused by this service can be obtained according to the prior probability, and then the heat dissipation strategy can be determined based on the posterior probability. There is no need to wait until the temperature reaches a certain threshold for regulation, which can reduce the noise caused by the sudden operation of the fan. At the same time, it can also avoid the decline of server performance caused by the rapid change of component temperature.

[0053] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present disclosure will become easily understood. In the drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, where:

[0055] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0056] Figure 1 The schematic diagram of the total probability formula is shown;

[0057] Figure 2 The first alternative flow schematic diagram of the heat dissipation strategy determination method provided by the embodiment of the present disclosure is shown;

[0058] Figure 3 The second alternative flow schematic diagram of the heat dissipation strategy determination method provided by the embodiment of the present disclosure is shown;

[0059] Figure 4 The third alternative flow schematic diagram of the heat dissipation strategy determination method provided by the embodiment of the present disclosure is shown;

[0060] Figure 5 The fourth alternative flow schematic diagram of the heat dissipation strategy determination method provided by the embodiment of the present disclosure is shown;

[0061] Figure 6 The fifth alternative flow schematic diagram of the heat dissipation strategy determination method provided by the embodiment of the present disclosure is shown;

[0062] Figure 7 shows a first alternative structural schematic diagram of the heat dissipation strategy determination device provided by an embodiment of the present disclosure;

[0063] Figure 8 shows a second alternative structural schematic diagram of the heat dissipation strategy determination device provided by an embodiment of the present disclosure;

[0064] Figure 9 shows a composition structural schematic diagram of an electronic device according to an embodiment of the present disclosure. Detailed implementation manners

[0065] To make the objectives, features, and advantages of the present disclosure more obvious and understandable, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present disclosure.

[0066] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0067] In the following description, the terms "first / second" involved are only used to distinguish similar objects, and do not represent a specific order for the objects. It can be understood that "first / second" can be interchanged with a specific order or sequence when allowed, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0068] Unless otherwise defined, all technical and scientific terms used in the present disclosure have the same meaning as commonly understood by those skilled in the technical field to which the present disclosure belongs. The terms used in the present disclosure are only for the purpose of describing the embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0069] It should be understood that in various embodiments of the present disclosure, the magnitude of the sequence number of each implementation process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0070] Before further elaborating on the embodiments of the present disclosure, the nouns and terms involved in the embodiments of the present disclosure are explained. The nouns and terms involved in the embodiments of the present disclosure are applicable to the following explanations.

[0071] 1) The Baseboard Management Controller (BMC) is an embedded microcontroller, usually integrated on the server motherboard, used to monitor, manage, and maintain server hardware and systems.

[0072] 2) PID control, where PID are the initials of Proportion, Integral, and Differential respectively, adjusts the output of the system based on the calculation methods of proportion, integral, and differential. The proportional link (P) adjusts the output according to the current error, the integral link (I) takes into account the accumulation of past errors, and the differential link (D) responds to the rate of change of the error, which helps to improve the stability and response speed of the system.

[0073] 3) Bayesian estimation is a method that uses Bayes' theorem to combine new evidence and previous prior probabilities to obtain new probabilities. It provides a way to calculate the probability of a hypothesis based on the prior probability of the hypothesis, the probability of observing different data given the hypothesis, and the observed data itself.

[0074] 4) Bayes' formula.

[0075] Bayes mainly solves the problem of "inverse probability" because most of the decisions in life face incomplete information and can only make an accurate prediction as much as possible using the limited information at hand. For example, the weather forecast says that the probability of rain tomorrow is 30%, which is a typical case of using Bayes' theorem for prediction. Because we cannot, like calculating frequency probability, repeat tomorrow 100 times and then calculate that it will rain about 30 times (the number of rainy days / the total number of days), but can only use the limited information (measurement data of past weather) and use Bayes' theorem to predict the probability of rain tomorrow. Bayes' formula includes:

[0076]

[0077] is a prior probability, which represents the probability calculated based on previous information such as historical data, experience, domain knowledge, or assumptions without considering the event. In the present invention, it is the operating probability of each service statistically obtained from the server historical operation data for us;

[0078] In Bayes' formula is the likelihood function, which represents the adjustment brought by the occurrence of the new event to the prior probability , and it is an adjustment factor whose role is to adjust the prior probability (previous subjective judgment) to be closer to the true probability. In the embodiments of the present disclosure Indicates that a component temperature increase event has occurred

[0079] It can be seen that:

[0080] If the likelihood function , it means that the "prior probability" is enhanced, and the likelihood of event occurring becomes greater;

[0081] If the likelihood function , it means that the event does not help to judge the likelihood of event ;

[0082] If the likelihood function , it means that the "prior probability" is weakened, and the likelihood of event becomes smaller.

[0083] In the formula is also a prior probability, which can be calculated from statistical data and represents the probability of a component temperature increase when a certain service is running in the embodiments of the present disclosure;

[0084] In the formula is a normalization constant, which can be calculated by the total probability formula, Figure 1 shows a schematic diagram of the total probability formula.

[0085] Figure 1 In is the sample space is a partition of is an observed event. In the present invention represents the th service running in the electronic device, represents the component temperature increase event, then:

[0086]

[0087] In Bayes' formula is the posterior probability, which represents the probability that after the event occurs, it is recalculated that the occurrence of event is caused by the occurrence of event . In the embodiments of the present disclosure, it is the probability that the component temperature increase event is caused by the running of a certain service.

[0088] With the rapid development of artificial intelligence technology, all industries are actively embracing it. As the cornerstone of the development of artificial intelligence, the server industry is facing a huge revolution. Major domestic and foreign CPU, GPU, and storage manufacturers are continuously making breakthroughs in the core competitiveness of AI servers, such as big data processing capabilities, parallel computing capabilities, data storage capabilities, and network transmission capabilities. However, as an embedded microcontroller of the server, the motherboard management controller still mainly relies on traditional control technologies in the process of managing and maintaining the server operation. Especially in the aspect of server heat dissipation regulation, the PID control mode is still used for regulation. Due to its advantages such as simple algorithm and strong robustness, PID control is widely used in various industrial process controls, such as traditional industrial fields like temperature control, pressure control, and motor control. However, in the era of artificial intelligence, AI servers are mainly applied to high-performance computing scenarios of complex systems, which also puts forward higher requirements for the heat dissipation regulation of the system. Conventional PID controllers can no longer achieve ideal control effects.

[0089] In related technologies, the PID heat dissipation control technology is a closed-loop control system with feedback. It is a closed-loop control algorithm that combines the three links of proportion, integral, and differential. In the application of heat dissipation regulation, the PID algorithm mainly uses the deviation between the output (actual temperature value) and the input (set target temperature value) to control the heat dissipation system and avoid deviation from the predetermined target. The server heat dissipation regulation system is a closed-loop control system. After developers set the target temperature according to the requirements of system components, the temperature sensor will collect the actual temperatures of each detection point, and then calculate the deviation between the target temperature and the actual temperature. The calculated result is input into the control circuit, and the control circuit further controls the fan speed for temperature regulation to ensure that the temperatures of all system components are controlled within the target range.

[0090] However, the PID heat dissipation regulation technology only starts the heat dissipation regulation strategy when the component temperature reaches the pre-set threshold, and will face problems such as large stage fan noise, large amplitude of component temperature change, and performance degradation of the server caused by rapid change of component temperature.

[0091] In view of the deficiencies in the related art, embodiments of the present disclosure provide a method for determining a heat dissipation strategy. The BMC collects the temperature information of each component in the system in real time according to the component monitoring system, and combines the current running services of each component in the system to count the temperature change of each component when running different services. Through a large number of experiments, the running probability of different services, the probability of component temperature rise when different services are running, and the probability of component temperature rise during the system operation can be calculated. Using the above information, the probability of component temperature rise caused by a specific service can be calculated according to the Bayesian formula. The higher the calculated probability, the greater the possibility that the service causes the component temperature to rise. Once the BMC monitors the running of the service and the temperature of the relevant component rises or falls, corresponding heat dissipation control strategies can be adopted to replace the strategy of starting heat dissipation control only when the temperature information reaches the set threshold used in the existing PID control technology, so as to make the operation of the server more stable and efficient.

[0092] Figure 2 FIG. 4 shows a first optional flowchart of the heat dissipation strategy determination method provided by the embodiments of the present disclosure, and will be described according to each step.

[0093] Step S201, in response to the running of the first service, confirm the running probability of the first service and the first probability of the temperature rise of the first component when the first service is running.

[0094] In some embodiments, both the running probability of the first service and the first probability of the temperature rise of the first component when the first service is running are prior probabilities.

[0095] Specifically, when implementing the heat dissipation strategy determination method, the carrier (hereinafter referred to as the carrier) collects the running data of each service during the operation of the electronic device as historical running data, and calculates the running probability of each service; the carrier also collects the temperature changes of each component during the running of each service, and the probability of the temperature rise of the first component when the first service is running (i.e., the first probability).

[0096] In some embodiments, the carrier may be a computer program, an electronic circuit, a database, a mobile application, an electronic device, a cloud computing platform, a distributed system, an artificial intelligence framework, a mathematical model, an automation tool, a microcontroller, etc., which are software or hardware capable of implementing algorithms and method flows. In the embodiments of the present disclosure, the carrier may be a motherboard management controller.

[0097] In some embodiments, the electronic device may include devices with heat dissipation functions such as servers, desktop computers, laptop computers, smart phones, tablet computers, game consoles, projectors, and switches.

[0098] In some embodiments, the first service may include one of network service, data management service, application service, virtualization service, and proxy service. Among them, the network service may include at least one of Domain Name System (DNS) service, Dynamic Host Configuration Protocol (DHCP) service, and mail service; the application service may include at least one of Web Service (Web service), database service, file service, game service, and video service; the data management service includes at least one of data backup and recovery, data caching, and big data analysis; the virtualization service includes dividing a physical server into multiple virtual servers through virtualization technology to improve server resource utilization and reduce costs, such as the services provided by virtualization software such as VMware and KVM; the proxy service includes acting as an intermediary between the client and the server, sending requests to the server on behalf of the client, and returning the server's response to the client, which can be used to improve access efficiency, implement access control, and security protection, etc.

[0099] Step S202, determine the second probability of the temperature rise of the first component.

[0100] In some embodiments, the second probability is the overall probability of the temperature rise of the first component, that is, the total probability, including the probability of the temperature rise of the first component during the operation of the electronic device. The carrier may determine the probability of the temperature rise of each component based on the operation data of each service and the temperature change of each component collected in step S201.

[0101] In some embodiments, the first component includes at least one of a central processing unit, an image processor, a storage disk, a memory card, and a network card.

[0102] Step S203, based on the operation probability of the first service, the first probability of the temperature rise of the first component when the first service is running, and the second probability of the temperature rise of the first component, determine the posterior probability of the temperature rise of the first component caused by the first service.

[0103] In some embodiments, the carrier combines the operation probability of the first service, the first probability of the temperature rise of the first component when the first service is running, and the second probability of the temperature rise of the first component, and calculates the posterior probability of the temperature rise of the first component caused by the first service according to Bayes' formula.

[0104] Step S204, based on the posterior probability of the temperature rise of the first component caused by the first service, determine the heat dissipation strategy of the electronic device.

[0105] In some embodiments, from the perspective of energy conservation, corresponding heat dissipation strategies are determined according to different posterior probabilities. For example, if the posterior probability that the first component temperature rises due to the first service is very low, a more energy-efficient heat dissipation strategy can be adopted, such as increasing the fan speed by a certain percentage. If the posterior probability that the first component temperature rises due to the first service is very high, it indicates that the temperature of the first component is likely to rise. To avoid damage caused by sudden temperature changes of the first component in a short period of time, a more effective heat dissipation strategy can be adopted, such as increasing the flow rate of the condensate while increasing the fan speed.

[0106] Thus, through the heat dissipation strategy determination method provided by the embodiments of the present disclosure, when it is monitored that a service starts to run, the posterior probability that the service causes the temperature of the first component to rise can be obtained according to the prior probability, and then the heat dissipation strategy can be determined based on the posterior probability, without waiting until the temperature reaches a certain threshold for regulation, which can reduce the noise caused by sudden fan operation. At the same time, it can also avoid the degradation of server performance caused by rapid temperature changes of components.

[0107] Figure 3 The second optional flowchart of the heat dissipation strategy determination method provided by the embodiments of the present disclosure is shown, and will be described according to each step.

[0108] Step S301: Determine the running probability of the first service based on the historical running data of each service in the electronic device.

[0109] In some embodiments, the carrier obtains the historical running data of each service during the operation of the electronic device; based on the historical running data, the running probability of the first service is determined. The historical running data includes the running information of each service in the electronic device, such as the number of runs, running duration, and the association relationship between services; the association relationship between services may include whether there is a precondition relationship between services. For example, if the precondition for running service B is to run service A, then there is an association relationship between service A and service B; if two services are independent of each other and there is no precondition relationship, then there is no association relationship between them. The number of runs may include the number of runs of all services from the power-on state to the power-off state of the electronic device; or, the number of runs may include the number of runs of all services within a certain time interval; the certain time interval can be set according to actual needs, such as 1 hour, 6 hours, 12 hours, 24 hours, 2 days, 3 days, one week, etc., and the present disclosure does not make specific limitations. Among them, each service includes the first service.

[0110] The running duration may include the running duration of all services from the powered-on state to the powered-off state of the electronic device; alternatively, the running duration may include the running duration of any service of the electronic device within a period of time. The period of time may be set according to actual needs, such as 1 hour, 6 hours, 12 hours, 24 hours, 2 days, 3 days, one week, etc., and the present disclosure does not make specific limitations.

[0111] In some embodiments, the carrier may determine the running probability of the first service based on the running times and / or running duration of the first service. For example, the carrier may determine the running probability of the first service based on the running times of the first service and the total running times of all services within a statistical time interval; or based on the running duration of the first service, the total running duration of all services, or the duration of the statistical time interval within the statistical time interval; or the carrier determines the running probability of the first service based on the running times of the first service and the total running times of all services, the running duration of the first service, the total running duration of all services, or the duration of the statistical time interval, and weights. Among them, the weights may be set according to actual needs; the statistical time interval may include the time interval corresponding to the powered-on state to the powered-off state, or the above-mentioned period of time.

[0112] Step S302, when it is confirmed that the first service runs, determine the first probability of the temperature rise of the first component.

[0113] In some embodiments, when the carrier collects the historical temperature data of the first component during the running of each service; based on the historical temperature data of the first component, determine the probability of the temperature rise of the first component during the running of each service. Among them, the historical temperature data includes the temperature change of the first component.

[0114] Specifically in implementation, in response to the running of the first service, the carrier samples the temperature of the first component, and determines the temperature sampling values of the first component within the time interval from the start to the end of the running of the first service, which are the historical temperature data of the first component during the running of each service. Based on the differences between the temperature sampling values in the historical temperature data, determine the first probability of the temperature rise of the first component during the running of the first service.

[0115] Step S303, determine the second probability of the temperature rise of the first component.

[0116] In some embodiments, the carrier determines the running probability of each service based on the historical running data of each service in the electronic device. The specific determination method may refer to step S201, and will not be repeated here.

[0117] In some embodiments, when the carrier respectively confirms the operation of each service, the probability of the temperature rise of the first component can be determined with reference to step S202, and the specific determination method will not be repeated here.

[0118] In some embodiments, the carrier calculates the second probability of the temperature rise of the first component based on the operation probability of each service, the probability of the temperature rise of the first component when each service is operating, and the total probability formula.

[0119] Specifically, when implemented, the carrier determines the probability of the temperature rise of the first component caused by the operation of each service based on the operation probability of each service in each service and the probability of the temperature rise of the first component when the service is operating; the sum of the probabilities of the temperature rise of the first component caused by the operation of all services is determined as the second probability of the temperature rise of the first component.

[0120] That is, the product of the operation probability of the first service and the probability of the temperature rise of the first component when the first service is operating, the product of the operation probability of the second service and the probability of the temperature rise of the first component when the second service is operating, etc., the product of the operation probability of each service and the probability of the temperature rise of the first component when each service is operating are summed up, and the summation result is determined as the second probability of the temperature rise of the first component.

[0121] Step S304, determine the posterior probability of the temperature rise of the first component caused by the first service.

[0122] In some embodiments, the carrier determines the posterior probability of the temperature rise of the first component caused by the first service based on Bayes' formula, the operation probability of the first service, the first probability of the temperature rise of the first component when the first service is operating, and the second probability of the temperature rise of the first component.

[0123] Step S305, determine the heat dissipation strategy of the electronic device based on the posterior probability of the temperature rise of the first component caused by the first service.

[0124] In some embodiments, different posterior probabilities correspond to different heat dissipation strategies. For example, from the perspective of energy conservation, corresponding heat dissipation strategies are determined according to different posterior probabilities; for example, if the posterior probability of the temperature rise of the first component caused by the first service is very low, a more energy-saving heat dissipation strategy can be adopted, such as increasing the fan speed by a certain percentage; if the posterior probability of the temperature rise of the first component caused by the first service is very high, it means that the temperature of the first component has a high probability of rising. In order to avoid damage caused by sudden temperature changes of the first component in a short time, a more effective heat dissipation strategy can be adopted, such as increasing the flow rate of the condensate while increasing the fan speed.

[0125] In some embodiments, a corresponding relationship between different posterior probabilities and heat dissipation strategies may be preset. The corresponding relationship between the posterior probability and the heat dissipation strategy may include the corresponding relationship between the posterior probability range and the heat dissipation strategy. Determine which posterior probability range the posterior probability that the first service causes the temperature of the first component to rise falls into, and determine the heat dissipation strategy corresponding to this posterior probability range as the heat dissipation strategy of the electronic device.

[0126] The posterior probability range may include setting a range every 10%, for a total of 10 posterior probability ranges, or determined according to energy efficiency, such as 0% - 30%, 30% - 50%, 50% - 60%, 60% - 70%, and then setting a range every 10% or every 5%. The specific setting method can be determined according to actual needs.

[0127] In some embodiments, different heat dissipation strategies may be set from the perspective of power consumption or heat dissipation effect, and they correspond one by one to the posterior probability ranges.

[0128] Step S306, collect the updated operation data of each service in the electronic device, and update the operation probability of each service based on the updated operation data and the historical operation data.

[0129] In some embodiments, to ensure the accuracy of determining the heat dissipation strategy, the carrier may continuously collect the updated operation data of each service during the operation of the electronic device, and update the operation probability of each service based on the updated operation data and the historical operation data; specifically, the operation probability of each service can be recalculated with reference to step S201. The carrier may also continuously collect the updated temperature data of the first component, and update the probability that the temperature of the first component rises when each service runs based on the updated temperature data and the historical temperature data.

[0130] In some embodiments, the carrier repeats steps S301 to S305 based on the updated operation probability of each service and the updated probability that the temperature of the first component rises when each service runs.

[0131] In this way, through the heat dissipation strategy determination method provided by the embodiments of the present disclosure, the prior probability is determined based on the historical operation data. When it is monitored that a service starts to run, the posterior probability that this service causes the temperature of the first component to rise can be obtained according to the prior probability, and then the heat dissipation strategy is determined based on the posterior probability, without waiting until the temperature reaches a certain threshold for regulation, which can reduce the noise caused by the sudden operation of the fan. At the same time, it can also avoid the decline in server performance caused by the rapid change of the component temperature.

[0132] Figure 4 The third optional flowchart of the heat dissipation strategy determination method provided by the embodiments of the present disclosure is shown, and it will be described according to each step.

[0133] Step S401: Train a service operation probability model based on the historical operation data of each service in the electronic device.

[0134] In some embodiments, the carrier trains a service operation probability model based on the historical operation data of each service in the electronic service. The historical operation data of each service may include the operation information of each service in the electronic device, such as the number of operations, the operation duration, and the association relationship between each service; the association relationship between each service may include whether there is a pre - existing relationship between services. Or the association relationship between data traffic and each service, for example, after receiving data from the first application, a certain service will run, etc.

[0135] In some embodiments, the carrier inputs the historical operation data of each service into the service operation probability model, determines the output of the service operation probability model as the predicted operation probability of each service; determines the loss function of the service operation probability model based on the marked operation probability and the predicted operation probability, and adjusts the weights of the operation probability model based on the loss function of the operation probability model.

[0136] During the application process, the carrier inputs the current operation data of each service into the operation probability model, and determines the output of the operation probability model as the operation probability of at least one service. Among them, the at least one service includes the first service.

[0137] Step S402: Input the operation data corresponding to the first service into the component temperature prediction model, and determine the output of the component temperature prediction model as the first probability of the first component temperature rising.

[0138] In some embodiments, the carrier pre - trains the component temperature prediction model. Specifically, when each service runs, obtain the historical operation data of each service and the historical temperature data of the first component; based on the historical operation data of each service and the historical temperature data of the first component, train the component temperature prediction model.

[0139] Specifically, when implemented, the input of the component temperature prediction model is the historical operation data of each service, and the output is the probability of at least one component temperature rising in the electronic device. Optionally, the carrier may determine the loss function of the component temperature prediction model based on the cross - entropy function and adjust the weights of the component temperature prediction model.

[0140] Step S403: Determine the second probability of the first component temperature rising.

[0141] In some embodiments, the specific step - by - step process of step S403 is the same as that of step S303, and will not be repeated here.

[0142] Step S404: Determine the posterior probability that the first component temperature rises due to the first service.

[0143] In some embodiments, the specific step process of step S404 is the same as that of step S304, and will not be repeated here.

[0144] Step S405: Determine the heat dissipation strategy of the electronic device based on the posterior probability that the first component temperature rises due to the first service.

[0145] In some embodiments, the specific step process of step S405 is the same as that of step S305, and will not be repeated here.

[0146] Step S406: Collect the updated operation data of each service in the electronic device, and update the weights of the component temperature prediction model and the service operation probability model based on the updated operation data and the historical operation data.

[0147] In some embodiments, to ensure the accuracy of the component temperature prediction model in predicting the component temperature and the accuracy of the service operation probability model in predicting the service operation probability, during the operation of the electronic device, collect the updated operation data of each service and the updated temperature data of each component, and repeatedly train the service operation probability model based on the updated operation data and the historical operation data to adjust its weights; repeatedly train the component temperature prediction model based on the updated temperature data and the historical temperature data to adjust the weights of the component temperature prediction model.

[0148] And based on the adjusted component temperature prediction model and service operation probability model, obtain the updated operation probabilities of each service and the probabilities that the first component temperature rises when each service runs, and repeat steps S401 to S405 based on the updated operation probabilities of each service and the probabilities that the first component temperature rises when each service runs.

[0149] In this way, through the heat dissipation strategy determination method provided by the embodiments of the present disclosure, the prior probability is determined based on the prediction model. When it is monitored that a service starts to run, the posterior probability that the service causes the first component temperature to rise can be obtained according to the prior probability, and then the heat dissipation strategy can be determined based on the posterior probability, without waiting until the temperature reaches a certain threshold for regulation, which can reduce the noise caused by the sudden operation of the fan. At the same time, it can also avoid the decline of server performance caused by the rapid change of component temperature.

[0150] Figure 5 Fig. shows the fourth optional process schematic diagram of the heat dissipation strategy determination method provided by the embodiments of the present disclosure, and will be described according to each step.

[0151] Step S501: Determine the first service.

[0152] In some embodiments, based on the services or application scenarios of the electronic device, the carrier determines a first service to be monitored.

[0153] In some embodiments, since different application scenarios of the electronic device correspond to different services, it is necessary to determine the services involved in the application scenario; that is, to determine at least one service running in the application scenario, and any one of the at least one service is the first service.

[0154] Step S502: Collect the historical temperature information of each component and the historical operation data of the first service.

[0155] In some embodiments, during the operation of the electronic device, the historical operation data of running the first service is determined, and during the operation of each service, the historical temperature information of each component is determined. The each component includes a first component.

[0156] Step S503: Determine the operation probability of the first service based on the historical operation data; based on the historical temperature information of each component, confirm the first probability of the temperature increase of the first component when the first service is running.

[0157] In some embodiments, with time as the coordinate, the carrier respectively counts the operation probabilities of each service and the probabilities of the temperature increase of components when each service is running ; where represents the event of component temperature increase; represents a certain running service, .

[0158] Step S504: Determine the second probability of the temperature increase of the first component.

[0159] In some embodiments, the carrier uses the total probability formula to calculate the probability of the component temperature increase, which may specifically include:

[0160]

[0161] Step S505: Determine the posterior probability that the temperature increase of the first component is caused by the first service.

[0162] In some embodiments, the carrier uses the Bayes formula and the total probability formula to determine the probability that the event of the temperature increase of the first component is caused by a certain service (i.e., the posterior probability that the temperature increase of the first component is caused by the first service) as:

[0163]

[0164] Step S506: Determine the heat dissipation strategy of the electronic device based on the posterior probability that the first component temperature rises due to the first service.

[0165] In some embodiments, the carrier adopts corresponding heat dissipation control strategies according to the probability calculation results and the temperature change information obtained by component monitoring. The higher the calculated probability, the greater the possibility that the service causes the component temperature to rise.

[0166] Thus, through the heat dissipation strategy determination method provided by the embodiments of the present disclosure, the probability that a certain service may cause the component temperature to rise is calculated according to Bayes' formula. Once it is detected that a high-probability service starts running and the temperature of the relevant component rises or falls, corresponding heat dissipation regulation strategies can be adopted to ensure the more stable and efficient operation of the server. The embodiments of the present disclosure can effectively overcome the problems faced by the traditional PID heat dissipation regulation technology, such as large stage fan noise, large component temperature change range, and server performance degradation caused by rapid component temperature change, when the heat dissipation regulation strategy is started after the component temperature reaches the preset threshold, which is beneficial to reducing enterprise costs, improving R & D efficiency, and is conducive to popularization and use in the engineering field.

[0167] Figure 6 Fig. 5 shows an optional flowchart of the heat dissipation strategy determination method provided by the embodiments of the present disclosure, which will be described according to each step.

[0168] Step S601: The BMC monitors the service running status.

[0169] In some embodiments, the carrier may be the BMC. After the system of the electronic device is powered on, the BMC monitors the running status of each service in the electronic device; the running status may include running or not running. The first service is included in each service.

[0170] Step S602: Calculate the posterior probability that the first service causes the first component temperature to rise.

[0171] In some embodiments, in response to the first service running, calculate the posterior probability that the first service causes the first component temperature to rise. The specific calculation method may refer to any one of steps S201 to S203, steps S301 to S304, or steps S401 to S404, which will not be repeated here.

[0172] Step S603: Determine whether the posterior probability is greater than a preset threshold.

[0173] In some embodiments, the BMC determines whether the posterior probability is greater than a preset threshold. If it is greater than the preset threshold, it is highly probable that the first service causes the first component in the electronic device to operate with increased temperature, and the state of the first component needs to be further monitored, that is, step S604 is executed; if the BMC determines that the posterior probability is less than or equal to the preset threshold, it is less probable that the first service causes the first component in the electronic device to operate with increased temperature, that is, the first service does not necessarily cause the first component to heat up, and then return to step S601 for repeated monitoring. The preset threshold can be set according to actual requirements.

[0174] Step S604, the BMC monitors the operating state of the first component.

[0175] In some embodiments, the operating state of the first component may include the temperature change state of the first component, and the BMC can sample the temperature of the first component at a certain frequency to monitor the operating state of the first component.

[0176] Step S605, determine whether the temperature of the first component shows an upward or downward trend.

[0177] In some embodiments, the BMC determines the temperature rise and fall trend of the first component based on any two temperature sampling results on the time axis. If the sampling temperature at a later time is greater than the sampling temperature at an earlier time, it is determined that the first component shows a temperature increase trend; if the sampling temperature at a later time is less than the sampling temperature at an earlier time, it is determined that the first component shows a temperature decrease trend.

[0178] In some embodiments, in order to save energy consumption, after the temperature of the first component drops, it is also necessary to adaptively adjust the heat dissipation strategy, such as reducing the fan speed, reducing the condensate flow rate, etc. Therefore, not only the heat dissipation strategy needs to be adjusted when the first component shows a temperature increase trend, but also the heat dissipation strategy needs to be adjusted when the first component shows a temperature decrease trend.

[0179] In some embodiments, if the temperature of the first component shows an upward or downward trend, step S606 is executed; if the temperature of the first component does not show an upward or downward trend, the prior probability and the likelihood function are updated, and step S602 is executed again.

[0180] Step S606, determine the heat dissipation strategy based on the posterior probability.

[0181] In some embodiments, different posterior probabilities correspond to different heat dissipation strategies. For example, from the perspective of energy conservation, corresponding heat dissipation strategies are determined according to different posterior probabilities. For example, if the posterior probability that the temperature of the first component is increased by the first service is very low, a more energy-efficient heat dissipation strategy can be adopted, such as increasing the fan speed by a certain percentage. If the posterior probability that the temperature of the first component is increased by the first service is very high, it indicates that the temperature of the first component has a high probability of increasing. To avoid damage caused by sudden temperature changes of the first component in a short period of time, a more effective heat dissipation strategy can be adopted, such as increasing the flow rate of the condensate while increasing the fan speed, etc.

[0182] In some embodiments, the corresponding relationship between different posterior probabilities and heat dissipation strategies can be preset. The corresponding relationship between the posterior probability and the heat dissipation strategy may include the corresponding relationship between the posterior probability range and the heat dissipation strategy. Determine which posterior probability range the posterior probability that the first service causes the temperature of the first component to increase falls into, and determine the heat dissipation strategy corresponding to this posterior probability range as the heat dissipation strategy of the electronic device.

[0183] In this way, for traditional electronic devices that adopt the PID heat dissipation control technology to start the heat dissipation control strategy only when the component temperature reaches the preset threshold, the embodiments of the present disclosure propose to predict the probability that the operation of the server service may cause the component temperature to increase based on Bayesian estimation. Once it is detected that a high-probability service starts to run and the temperature of the relevant component rises or falls, the BMC can adopt the corresponding heat dissipation control strategy to ensure that the electronic device runs more smoothly and efficiently. The embodiments of the present disclosure can effectively solve the problems faced by traditional PID control, such as large fan noise in stages, large temperature change range of components, and server performance degradation caused by rapid temperature changes of components. It is beneficial to reduce enterprise costs, improve R & D efficiency, and is conducive to popularization and use in the engineering field.

[0184] Next, the embodiments of the present disclosure will be further explained and illustrated with actual data as an example.

[0185] Suppose the first component is the CPU in an electronic device (server), and the services involved include A1, A2, A3, ……, A7, a total of 7 services. After collecting data for a period of time, the operation probability of each service is calculated , and the probability that the first component is heated when the service runs is:

[0186]

[0187]

[0188]

[0189]

[0190]

[0191]

[0192]

[0193] Furthermore, according to the total probability formula, the second probability of the temperature rise of the first component can be obtained. It is:

[0194]

[0195] Substituting into the Bayesian formula for calculation, it can be obtained that the probabilities of each service causing the temperature rise of the component are:

[0196]

[0197]

[0198]

[0199]

[0200]

[0201]

[0202]

[0203] During the operation of the electronic device, continuously collect and update the operation probability of the service and the first probability that the service causes the first component to heat up. After repeated iterations, the probabilities of different services causing the temperature rise of the first component will be continuously updated. The heat dissipation control module can adopt corresponding-level control strategies based on the calculated probabilities. It should be particularly noted that the prior probabilities and The accuracy of the statistics directly determines the level of the posterior probability close to the true situation.

[0204] Furthermore, according to the correspondence between the posterior probability and the heat dissipation strategy, determine the heat dissipation strategy of the electronic device. Table 1 shows the correspondence between the posterior probability and the heat dissipation strategy in the embodiments of the present disclosure.

[0205] Table 1

[0206]

[0207] Figure 7FIG. 0 shows a first alternative structural schematic diagram of the heat dissipation strategy determination device provided by an embodiment of the present disclosure, which will be described according to each part.

[0208] In some embodiments, the heat dissipation strategy determination device 700 may include a component monitoring module 701, a service operation monitoring module 702, a Bayesian estimation operation module 703, and a heat dissipation regulation module 704.

[0209] Among them, the component monitoring module 701 is a BMC resident service, which is responsible for providing real-time monitoring for key components of the electronic device, such as: CPU, GPU, storage disk, memory card, network card, etc. Taking the CPU as an example, the component monitoring module 701 needs to record the number, operating status, occupancy rate, temperature and other information of the CPU in real time, so that the service operation monitoring module 702 and the heat dissipation regulation module 704 can perform service optimization and heat dissipation regulation on the CPU according to the monitoring information.

[0210] The function of the service operation monitoring module 702 is divided into two stages. The model training stage is mainly responsible for collecting the operation data of each service in different application scenarios (historical operation data or updated operation data) to calculate the operation probability of each service in the later stage and, in cooperation with the temperature data of each component provided by the component monitoring module 701, calculate the probability of each component rising to provide data support; in the actual operation stage, the service operation monitoring module 702 is responsible for timely transmitting the service operation conditions that may cause the component temperature to rise calculated by the Bayesian estimation operation module 703 to the heat dissipation regulation module 704. Once it is detected that these services start to run and the relevant components have temperature rise and fall conditions, it is necessary to immediately notify the heat dissipation regulation module 704 to start the corresponding level of regulation.

[0211] The Bayesian estimation operation module 703 is used to receive the operation data of the service collected by the service operation monitoring module 702 and the monitoring data of the component by the component monitoring module 701. Based on the data provided by the two, it calculates the service operation conditions that may cause the component temperature to rise, that is, the posterior probability, and sends the posterior probability to the service operation monitoring module 702, so that the service operation monitoring module 702 can timely transmit it to the heat dissipation regulation module 704.

[0212] The heat dissipation regulation module 704 is responsible for timely adopting corresponding levels of regulation strategies according to the component temperature information transmitted by the component monitoring module 701 and the service operation conditions that may cause the component temperature to rise highly transmitted by the service operation monitoring module, as shown in Table 1.

[0213] Compared with the PID control strategy, the heat dissipation strategy determination method provided by the embodiments of the present disclosure can enable the control strategy to intervene in advance, making the temperature change of the component more stable, thereby ensuring the operation efficiency of the server. In addition, the PID control strategy only starts the control strategy when the component temperature reaches the set temperature threshold, which will cause a huge noise due to the rapid increase in the fan speed, thus reducing the user experience. The control strategy with early intervention adopted in the embodiments of the present disclosure can effectively reduce the fan noise.

[0214] Figure 8 Fig. 4 shows a second alternative structural schematic diagram of the heat dissipation strategy determination device provided by the embodiments of the present disclosure, which will be described according to each part.

[0215] In some embodiments, the heat dissipation strategy determination device 700 may include a prior probability determination unit 705, a total probability determination unit 706, a posterior probability determination unit 707, and a heat dissipation strategy determination unit 708.

[0216] The prior probability determination unit 705 is configured to, in response to the operation of the first service, confirm the operation probability of the first service and the first probability of the temperature increase of the first component when the first service is running.

[0217] The total probability determination unit 706 is configured to determine the second probability of the temperature increase of the first component.

[0218] The posterior probability determination unit 707 is configured to determine the posterior probability of the temperature increase of the first component caused by the first service based on the operation probability of the first service, the first probability of the temperature increase of the first component when the first service is running, and the second probability of the temperature increase of the first component.

[0219] The heat dissipation strategy determination unit 708 is configured to determine the heat dissipation strategy of the electronic device based on the posterior probability of the temperature increase of the first component caused by the first service.

[0220] Specifically, the prior probability determination unit 705 is configured to collect historical operation data of each service in the electronic device.

[0221] Based on the historical operation data of each service, determine the operation probability of each service.

[0222] Wherein, the first service is included in each service.

[0223] The prior probability determination unit 705 is further configured to collect updated operation data of each service in the electronic device.

[0224] Based on the updated operation data and the historical operation data, update the operation probability of each service.

[0225] The prior probability determination unit 705 is specifically configured to collect historical temperature data of the first component during the operation of each service;

[0226] Based on the historical temperature data of the first component, determine the probability of temperature increase of the first component during the operation of each service.

[0227] The prior probability determination unit 705 is specifically configured to collect updated temperature data of the first component during the operation of each service;

[0228] Based on the updated temperature data and the historical temperature data, update the probability of temperature increase of the first component during the operation of each service.

[0229] The prior probability determination unit 705 is specifically configured to input the operation data corresponding to the first service into the component temperature prediction model, and determine that the output of the component temperature prediction model is the first probability of temperature increase of the first component.

[0230] The prior probability determination unit 705 is further configured to obtain the historical operation data of each service and the historical temperature data of the first component during the operation of each service;

[0231] Based on the historical operation data of each service and the historical temperature data of the first component, train the component temperature prediction model.

[0232] The total probability determination unit 706 is specifically configured to determine the second probability of temperature increase of the first component based on the operation probabilities of each service, the probability of temperature increase of the first component when each service is operating, and the total probability formula.

[0233] The total probability determination unit 706 is specifically configured to determine the probability of temperature increase of the first component caused by the operation of each service based on the operation probability of each service in each service and the probability of temperature increase of the first component when the service is operating;

[0234] Determine that the sum of the probabilities of temperature increase of the first component caused by the operation of all services is the second probability of temperature increase of the first component.

[0235] The posterior probability determination unit 707 is specifically configured to determine the posterior probability of the first service causing the first component to increase in temperature based on Bayes' formula, the operation probability of the first service, the first probability of the first component increasing in temperature when the first service is operating, and the second probability of the first component increasing in temperature.

[0236] The posterior probability determination unit 707 is specifically configured to use the result of dividing the product of the operation probability of the first service and the first probability of the first component increasing in temperature when the first service is operating by the second probability of the first component increasing in temperature as the posterior probability of the first service causing the first component to increase in temperature.

[0237] The heat dissipation strategy determination unit 708 is specifically configured to determine the heat dissipation strategy of the electronic device based on the posterior probability that the first service causes the temperature of the first component to rise, and the correspondence between the posterior probability and the heat dissipation strategy;

[0238] Wherein, the correspondence between the posterior probability and the heat dissipation strategy includes the correspondence between the posterior probability range and different heat dissipation strategies.

[0239] In some embodiments, the first service includes one of the following:

[0240] Network service business, data management business, application service business, virtualization business, and proxy business.

[0241] In some embodiments, the first component includes one of the following:

[0242] Central processing unit, image processor, storage disk, memory card, and network card.

[0243] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0244] Figure 9 A schematic block diagram of an exemplary electronic device 800 that can be used to implement the embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0245] As Figure 9 shown, the electronic device 800 includes a computing unit 801, which can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 802 or the computer program loaded from the storage unit 808 into the random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. The input / output (I / O) interface 805 is also connected to the bus 804.

[0246] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disc, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0247] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the heat dissipation strategy determination method. For example, in some embodiments, the heat dissipation strategy determination method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the heat dissipation strategy determination method described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the heat dissipation strategy determination method in any other suitable manner (e.g., by means of firmware).

[0248] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0249] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0250] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0251] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0252] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0253] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating a blockchain.

[0254] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0255] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of this disclosure, "a plurality of" means two or more unless otherwise specifically defined.

[0256] As described above, it is only the specific implementation manner of the present disclosure. However, the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of changes or substitutions, which should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claimed rights.

Claims

1. A method for determining a heat dissipation strategy, characterized in that, The method includes: Collecting historical operation data of each service in the electronic device, and determining the operation probability of each service based on the historical operation data of each service; the historical operation data includes the number of operations, operation duration, and association relationship of each service; the first service is included in each service. In response to the operation of the first service, confirming the operation probability of the first service, and the first probability of the temperature rise of the first component when the first service operates. Determining the second probability of the temperature rise of the first component. Based on the operation probability of the first service, the first probability of the temperature rise of the first component when the first service operates, and the second probability of the temperature rise of the first component, determining the posterior probability of the temperature rise of the first component caused by the first service. Based on the posterior probability of the temperature rise of the first component caused by the first service and the corresponding relationship between the posterior probability and the heat dissipation strategy, determining the heat dissipation strategy of the electronic device. Wherein, the corresponding relationship between the posterior probability and the heat dissipation strategy includes the corresponding relationship between the posterior probability range and different heat dissipation strategies.

2. The method according to claim 1, characterized in that, The method further includes: Collecting updated operation data of each service in the electronic device. Updating the operation probability of each service based on the updated operation data and the historical operation data.

3. The method according to claim 1, wherein The step of confirming the first probability of the temperature rise of the first component when the first service operates includes: Collecting the historical temperature data of the first component when each service operates. Based on the historical temperature data of the first component, determining the first probability of the temperature rise of the first component when each service operates.

4. The method according to claim 3, characterized in that The method further includes: Collecting the updated temperature data of the first component when each service operates. Based on the updated temperature data and the historical temperature data, updating the first probability of the temperature rise of the first component when each service operates.

5. The method according to claim 1, wherein The step of confirming the first probability of the temperature rise of the first component when the first service operates includes: Inputting the operation data corresponding to the first service into the component temperature prediction model, and determining that the output of the component temperature prediction model is the first probability of the temperature rise of the first component.

6. The method according to claim 5, wherein The method further includes: Obtaining the historical operation data of each service and the historical temperature data of the first component when each service operates. Training the component temperature prediction model based on the historical operation data of each service and the historical temperature data of the first component.

7. The method according to claim 1, wherein The step of determining the second probability of the temperature rise of the first component includes: Determining the second probability of the temperature rise of the first component based on the operation probability of each service, the probability of the temperature rise of the first component when each service operates, and the total probability formula.

8. The method according to claim 7, wherein The step of determining the second probability of the temperature rise of the first component based on the operation probability of each service, the probability of the temperature rise of the first component when each service operates, and the total probability formula includes: Based on the operation probability of each service in each service and the probability of the temperature rise of the first component when the service operates, determining the probability of the temperature rise of the first component caused by the operation of each service. Determining that the sum of the probabilities of the temperature rise of the first component caused by the operation of all services is the second probability of the temperature rise of the first component.

9. The method according to claim 1, characterized in that, Determining the posterior probability that the temperature of the first component rises due to the first service based on the operating probability of the first service, the first probability that the temperature of the first component rises when the first service is operating, and the second probability that the temperature of the first component rises includes: Based on Bayes' formula, the operating probability of the first service, the first probability that the temperature of the first component rises when the first service is operating, and the second probability that the temperature of the first component rises, determine the posterior probability that the first service causes the temperature of the first component to rise.

10. The method according to claim 9, wherein The determining, based on Bayes' formula, the operating probability of the first service, the first probability that the temperature of the first component rises when the first service is operating, and the second probability that the temperature of the first component rises, the posterior probability that the first service causes the temperature of the first component to rise includes: The result of dividing the product of the operating probability of the first service and the first probability that the temperature of the first component rises when the first service is operating by the second probability that the temperature of the first component rises is the posterior probability that the first service causes the temperature of the first component to rise.

11. The method according to claim 1, wherein The first service includes one of the following: Network service business, data management business, application service business, virtualization business, and proxy business.

12. The method according to claim 1, characterized in that, The first component includes one of the following: Central processing unit, image processor, storage disk, memory card, and network card.

13. A heat dissipation strategy determination device, characterized in that, The apparatus includes: A prior probability determination unit, configured to collect historical operation data of each service in the electronic device, and based on the historical operation data of each service, determine the operating probability of each service; the historical operation data includes the number of operations, operation duration, and association relationship of each service; and the first service is included in each service; The prior probability determination unit is further configured to, in response to the operation of the first service, confirm the operating probability of the first service and the first probability that the temperature of the first component rises when the first service is operating; A total probability determination unit, configured to determine the second probability that the temperature of the first component rises; A posterior probability determination unit, configured to determine the posterior probability that the first service causes the temperature of the first component to rise based on the operating probability of the first service, the first probability that the temperature of the first component rises when the first service is operating, and the second probability that the temperature of the first component rises; A heat dissipation strategy determination unit, configured to Based on the posterior probability that the first service causes the temperature of the first component to rise and the corresponding relationship between the posterior probability and the heat dissipation strategy, determine the heat dissipation strategy of the electronic device; Wherein, the corresponding relationship between the posterior probability and the heat dissipation strategy includes the corresponding relationship between the posterior probability range and different heat dissipation strategies.

14. An electronic device, characterized in that, Includes: At least one processor; And a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-12.

15. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause a computer to execute the method according to any one of claims 1-12.

16. A computer program product, characterized in that, Includes a computer program, which when executed by a processor implements the method according to any one of claims 1-12.

Images