Heat dissipation strategy determination method and device, electronic equipment and storage medium

Abstract

The invention provides a heat dissipation strategy determination method and device, electronic equipment and a storage medium, and is applied to the technical field of energy-saving control, and the method comprises the steps: responding to the operation of a first service, determining the operation probability of the first service, and determining the first probability of the temperature rise of a first part under the condition of the operation of the first service; determining a second probability of temperature rise of the first component; determining a posterior probability of temperature rise of the first component caused by the first service based on the operation probability of the first service, a first probability of temperature rise of the first component under the condition of operation of the first service, and a second probability of temperature rise of the first component; and determining a heat dissipation strategy of the electronic equipment based on the posterior probability that the temperature of the first component rises due to the first service, so that regulation and control can be carried out without waiting for the temperature to reach a certain threshold value, noise caused by sudden operation of a fan can be reduced, and meanwhile, server performance reduction caused by rapid change of the temperature of the components can be avoided.

Description

Technical Field

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

[0002] In the related technology, the PID (proportional, integral and differential) control mode is relied upon for server heat dissipation. The principle is: when the temperature of the component reaches the preset threshold, the heat dissipation control strategy will be activated; however, the PID heat dissipation control technology has obvious disadvantages: first, since the control is only started after the temperature reaches the threshold, it will cause the problem of high fan noise at certain stages, which not only affects the quietness of the server operating environment, but may also cause certain interference to the surrounding equipment; second, the temperature of the component changes greatly, and when the temperature is close to the threshold, the start and stop of the control will easily cause large temperature fluctuations; finally, the rapid change of the component temperature will also cause the server performance to decline, affect the normal working efficiency of the server, reduce its stability and reliability, and fail to meet the growing demand for high-performance server operation. Summary of the invention

[0003] The present disclosure provides a method, device, electronic device and 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, comprising: In response to the first service being run, confirming the probability of the first service being run, and confirming a first probability of a temperature increase of the first component when the first service is run; determining a second probability that the temperature of the first component is increased; Determine a posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases; Based on the a posteriori probability that the first service causes the temperature of the first component to rise, a heat dissipation strategy of the electronic device is determined.

[0005] In the above solution, the confirming the operation probability of the first service includes: Collect historical operation data of each business in electronic equipment; Determining the operation probability of each business based on the historical operation data of each business; Among them, the various services include the first service.

[0006] In the above scheme, the method further includes: Collect updated operation data of each business in electronic equipment; Based on the updated operation data and the historical operation data, the operation probability of each service is updated.

[0007] In the above solution, the first probability that the temperature of the first component rises when confirming that the first service is running includes: Collect historical temperature data of the first component when each service is running; Based on the historical temperature data of the first component, the probability of the temperature of the first component increasing when each service is running is determined.

[0008] In the above scheme, the method further includes: Collect updated temperature data of the first component when each service is running; Based on the updated temperature data and the historical temperature data, the probability of the temperature of the first component increasing when each service is running is updated.

[0009] In the above solution, the first probability that the temperature of the first component rises when confirming that the first service is running includes: The operation data corresponding to the first service is input into a component temperature prediction model, and an output of the component temperature prediction model is determined to be a first probability of a temperature increase of the first component.

[0010] In the above scheme, the method further includes: Acquire historical operation data of each service and historical temperature data of the first component when each service is running; Training a component temperature prediction model based on the historical operation data of each service and the historical temperature data of the first component; In the above solution, the determining the second probability that the temperature of the first component increases includes: A second probability of the temperature of the first component increasing is determined based on the operating probability of each service, the probability of the temperature of the first component increasing when each service is operating, and a total probability formula.

[0011] In the above solution, the second probability of the temperature of the first component rising is determined based on the operation probability of each service, the probability of the temperature of the first component rising when each service is running, and the total probability formula, including: Determine the probability that the temperature of the first component increases due to the operation of each service based on the operation probability of each service in each service and the probability that the temperature of the first component increases when the service is operated; The sum of the probabilities that all business operations result in a temperature increase of the first component is determined as a second probability that the temperature of the first component increases.

[0012] In the above solution, determining the posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases, includes: Based on the Bayesian formula, the running probability of the first service, the first probability of the first component temperature rising when the first service is running, and the second probability of the first component temperature rising, the posterior probability that the first service causes the first component temperature rising is determined.

[0013] In the above scheme, determining the posterior probability that the first service causes the temperature of the first component to rise based on the Bayesian formula, the operation probability of the first service, the first probability that the temperature of the first component rises when the first service is running, and the second probability that the temperature of the first component rises, includes: The product of the operating probability of the first service and the first probability of the temperature increase of the first component when the first service is running, divided by the second probability of the temperature increase of the first component, is the posterior probability that the first service causes the temperature increase of the first component.

[0014] In the above solution, the step of determining 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 includes: Determining a heat dissipation strategy for the electronic device based on a posterior probability that the first service causes a temperature increase of the first component and a corresponding relationship between the posterior probability and the heat dissipation strategy; 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.

[0015] In the above solution, the first service includes one of the following: Network service business, data management business, application service business, virtualization business and agency business.

[0016] In the above solution, the first component includes one of the following: CPU, graphics processor, storage disk, memory card and network card.

[0017] According to a second aspect of the present disclosure, a heat dissipation strategy determination device is provided, the device comprising: a priori probability determination unit, configured to, in response to the first service being run, confirm the probability of the first service being run, and confirm a first probability of a temperature increase of the first component when the first service is run; a total probability determination unit, configured to determine a second probability of a temperature increase of the first component; a posterior probability determination unit, configured to determine a posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases; The heat dissipation strategy determining unit is used to determine a heat dissipation strategy of the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0018] According to a third aspect of the present disclosure, there is provided an electronic device, including: 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 perform the method described in the present disclosure.

[0019] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described in the present disclosure when executed by a processor.

[0021] The heat dissipation strategy determination method disclosed in the present invention confirms the operation probability of the first business in response to the operation of the first business, and confirms the first probability of the temperature increase of the first component when the first business is running; determines the second probability of the temperature increase of the first component; determines the posterior probability that the temperature increase of the first component is caused by the first business based on the operation probability of the first business, the first probability of the temperature increase of the first component when the first business is running, and the second probability of the temperature increase of the first component; determines the heat dissipation strategy of the electronic device based on the posterior probability that the temperature increase of the first component is caused by the first business; in this way, when the business starts to run, the posterior probability that the business causes the temperature increase of the first component 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 to adjust, which can reduce the noise caused by the sudden operation of the fan, and at the same time, it can also avoid the rapid change of component temperature causing the server performance to decline.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended 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

[0023] The above and other purposes, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which: In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0024] Figure 1 A schematic diagram of the total probability formula is shown; Figure 2 A first optional flow chart of the method for determining a heat dissipation strategy provided by an embodiment of the present disclosure is shown; Figure 3 A second optional flow chart of the method for determining a heat dissipation strategy provided by an embodiment of the present disclosure is shown; Figure 4 A third optional flow chart of the method for determining a heat dissipation strategy provided by an embodiment of the present disclosure is shown; Figure 5 A fourth optional flow chart of the method for determining a heat dissipation strategy provided by an embodiment of the present disclosure is shown; Figure 6 A fifth optional flow chart of the method for determining a heat dissipation strategy provided by an embodiment of the present disclosure is shown; Figure 7 A first optional structural diagram of a heat dissipation strategy determination device provided in an embodiment of the present disclosure is shown; Figure 8 A second optional structural diagram of the heat dissipation strategy determination device provided in an embodiment of the present disclosure is shown; Fig. 9 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0025] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0026] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0027] In the following description, the terms "first\second" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0028] Unless otherwise defined, all technical and scientific terms used in this disclosure have the same meaning as those commonly understood by those skilled in the art to which this disclosure belongs. The terms used in this disclosure are only for the purpose of describing the embodiments of this disclosure and are not intended to limit this disclosure.

[0029] It should be understood that in the various embodiments of the present disclosure, the size of the serial 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 on the implementation process of the embodiments of the present disclosure.

[0030] Before further describing the embodiments of the present disclosure in detail, the nouns and terms involved in the embodiments of the present disclosure are described. The nouns and terms involved in the embodiments of the present disclosure are subject to the following interpretations.

[0031] 1) Baseboard Management Controller (BMC) is an embedded microcontroller, usually integrated on the server motherboard, used to monitor, manage and maintain server hardware and systems.

[0032] 2) PID control, PID is the acronym for Proportion, Integral, and Differential, and adjusts the system output based on the calculation method of proportion, integration, and differentiation. The proportional link (P) adjusts the output according to the current error, the integral link (I) considers the past error accumulation, 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.

[0033] 3) Bayesian estimation is a method that uses Bayes’ theorem to combine new evidence with previous prior probabilities to obtain new probabilities. It provides a method for calculating 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.

[0034] 4) Bayesian formula.

[0035] Bayes mainly solves the problem of "inverse probability", because the information faced by most decisions in life is incomplete, and we can only use the limited information at hand to make an accurate prediction as much as possible. For example, the weather forecast says that the probability of rain tomorrow is 30%. This is a typical case of using Bayes' theorem for prediction, because it is impossible to repeatedly live tomorrow 100 times like calculating frequency probability, and then calculate that it will rain about 30 times (number of rainy days / total number of days). Instead, we can only use limited information (past weather measurement data) and use Bayes' theorem to predict the probability of rain tomorrow. Bayes' formula includes:

[0036] is a prior probability, which means that without considering Under the premise of the event, the probability is calculated based on previous information such as historical data, experience, domain knowledge or assumptions. In this invention, we calculate the operation probability of each business from the historical operation data of the server; In the Bayesian formula is the likelihood function, which represents the new event The prior probability of occurrence The adjustment brought about is an adjustment factor, which is used to adjust the prior probability (Previous subjective judgment) is adjusted to be closer to the true probability. In the embodiment of the present disclosure Indicates that the component temperature has increased. It can be seen that: If the likelihood function , which means that the "prior probability" is enhanced, the event The possibility of occurrence increases; If the likelihood function ,mean Events do not help judge events possibility; If the likelihood function , which means that the "prior probability" is weakened, and the event The possibility becomes smaller.

[0037] In the formula It is also a priori probability, which can be calculated through statistical data. In the embodiment of the present disclosure, it represents the probability of a component temperature rising when a certain service is running; In the formula is a standardized constant that can be calculated using the total probability formula, Figure 1 A schematic diagram of the total probability formula is shown.

[0038] Figure 1 middle The sample space A division of is an observation event. Indicates the first Business, Indicates that the component temperature rises, then:

[0039] In the Bayesian formula is the posterior probability, which means that After the event occurs, recalculate The incident occurred because The probability caused by the occurrence of an event, in the embodiment of the present disclosure, is the probability that the event of component temperature increase is caused by the operation of a certain business.

[0040] With the rapid development of artificial intelligence technology, all walks of life are actively embracing artificial intelligence technology. As the cornerstone of the development of artificial intelligence, the server industry is facing a huge revolution. Major CPU, GPU, and storage manufacturers at home and abroad are constantly making breakthroughs around 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 relies mainly on traditional control technology in the process of managing and maintaining server operations, especially in the heat dissipation control of the server, which still uses the PID control mode for control. PID control is widely used in various industrial process controls due to its advantages such as simple algorithm and strong robustness, such as temperature control, pressure control, motor control and other traditional industrial fields. However, in the era of artificial intelligence, AI servers are mainly used in high-performance computing scenarios of complex systems, which also puts higher requirements on the heat dissipation control of the system. Conventional PID controllers can no longer achieve ideal control effects.

[0041] In related technologies, PID heat dissipation control technology is a closed-loop control system with feedback. It is a closed-loop control algorithm that combines three links: proportional, integral and differential. In the application of heat dissipation control, 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 to avoid deviation from the predetermined target. The server heat dissipation control system is a closed-loop control system. After the developer sets the target temperature according to the requirements of the system components, the temperature sensor will collect the actual temperature 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 control to ensure that the temperature of each component of the system is controlled within the target range.

[0042] However, PID heat dissipation control technology will only start the heat dissipation control strategy when the component temperature reaches a preset threshold. It will face problems such as high fan noise at certain stages, large temperature changes of components, and decreased server performance due to rapid changes in component temperature.

[0043] In view of the defects existing in the related art, the embodiment of the present disclosure provides a method for determining a heat dissipation strategy. The BMC collects the temperature information of each component of the system in real time according to the component monitoring system, and combines the current running services of each component of the system to calculate the temperature changes of each component of the system when running different services. After 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 system operation can be calculated. The above information can be used to calculate the probability of component temperature rise caused by a specific business according to the Bayesian formula. The higher the calculated probability, the greater the possibility that the business causes the component temperature to rise. Once the BMC detects that the business is running and the temperature of the relevant components rises and falls, the corresponding heat dissipation control strategy can be adopted to replace the strategy adopted by the existing PID control technology that only starts the heat dissipation control when the temperature information reaches the set threshold, so as to make the server run more smoothly and efficiently.

[0044] Figure 2 A first optional flow chart of the method for determining a heat dissipation strategy provided in an embodiment of the present disclosure is shown, and will be described according to each step.

[0045] Step S201 : in response to a first service being run, confirming the running probability of the first service and confirming a first probability of a temperature rise of a first component when the first service is run.

[0046] In some embodiments, the operating probability of the first service and the first probability that the temperature of the first component increases when the first service is operating are both prior probabilities.

[0047] During specific implementation, a carrier (hereinafter referred to as the carrier) that implements the heat dissipation strategy determination method collects operating data of each service as historical operating data during the operation of the electronic device, and calculates the operating probability of each service; the carrier also collects temperature changes of each component during the operation of each service, and the probability of the temperature of the first component rising when the first service is running (i.e., the first probability).

[0048] 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 may be software or hardware capable of implementing an algorithm or method flow. In the embodiments of the present disclosure, the carrier may be a motherboard management controller.

[0049] In some embodiments, the electronic device may include devices with heat dissipation function, such as servers, desktop computers, laptop computers, smart phones, tablet computers, game consoles, projectors and switches.

[0050] In some embodiments, the first service may include: one of network service, data management service, application service, virtualization service and proxy service. 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 network 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 cache 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 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.

[0051] Step S202: determining a second probability that the temperature of the first component increases.

[0052] 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 can determine the probability of the temperature rise of each component based on the operation data of each service collected in step S201 and the temperature change of each component.

[0053] In some embodiments, the first component includes at least one of a central processing unit, a graphics processor, a storage disk, a memory card, and a network card.

[0054] Step S203 , determining a 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 running, and the second probability that the temperature of the first component rises.

[0055] In some embodiments, the carrier calculates the posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases, in combination with the Bayesian formula.

[0056] Step S204: determining a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0057] In some embodiments, from the perspective of energy saving, 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 due to the first business 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 that the temperature of the first component is increased due to the first business is very high, it means that there is a high probability that the temperature of the first component will increase. In order to avoid damage to the first component caused by sudden temperature changes 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.

[0058] In this way, through the cooling strategy determination method provided by the embodiment of the present invention, when it is monitored that the business starts to run, the a posteriori probability that the business causes the temperature of the first component to rise can be obtained based on the prior probability, and then the cooling strategy is determined based on the a posteriori probability. There is no need to wait until the temperature reaches a certain threshold before adjusting it. The noise caused by the sudden operation of the fan can be reduced. At the same time, the rapid change of component temperature can also be avoided to prevent the server performance from being reduced.

[0059] Figure 3 A second optional flow chart of the method for determining a heat dissipation strategy provided in an embodiment of the present disclosure is shown and will be described according to each step.

[0060] Step S301: determining the operation probability of a first service based on historical operation data of each service in the electronic device.

[0061] In some embodiments, the carrier obtains the historical operation data of each service during the operation of the electronic device; based on the historical operation data, the operation probability of the first service is determined. The historical operation data includes 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-relationship between services, such as the premise of running service B is to run service A, then there is an association relationship between service A and service B; if the two services are independent of each other and there is no pre-relationship, then there is no association relationship between the two. The number of operations may include the number of operations of all services of the electronic device from the power-on state to the power-off state; or, the number of operations may include the number of operations of all services 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, a week, etc., and the present disclosure does not make specific restrictions. Among them, each service includes the first service.

[0062] The operating duration may include the operating duration of all services of the electronic device from the power-on state to the power-off state; or, the operating duration may include the operating duration of any service of the electronic device within a time interval; the time interval may be set according to actual needs, such as 1 hour, 6 hours, 12 hours, 24 hours, 2 days, 3 days, a week, etc., and the present disclosure does not make specific limitations.

[0063] In some embodiments, the carrier may determine the operation probability of the first service based on the number of operations and / or the operation duration of the first service. For example, the carrier may determine the operation probability of the first service based on the number of operations of the first service and the total number of operations of all services within a statistical time interval; or, determine the operation probability of the first service based on the operation duration of the first service, the total operation duration of all services, or the duration of the statistical time interval within a statistical time interval; or, determine the operation probability of the first service based on the number of operations of the first service and the total number of operations of all services within a statistical time interval, the operation duration of the first service, the total operation duration of all services, or the duration of the statistical time interval, and the weight. Among them, the weight can be set according to actual needs; the statistical time interval may include a time interval corresponding to a power-on state to a power-off state, or the above-mentioned time interval.

[0064] Step S302: confirming a first probability of a temperature increase of a first component when a first service is running.

[0065] In some embodiments, the carrier collects historical temperature data of the first component when each service is running, and determines the probability of the temperature of the first component rising when each service is running based on the historical temperature data of the first component, wherein the historical temperature data includes the temperature change of the first component.

[0066] In a specific implementation, in response to the operation of the first service, the carrier samples the temperature of the first component, and determines the temperature sampling value of the first component in the time interval from the start to the end of the operation of the first service, which is the historical temperature data of the first component when each service is operated. Based on the difference between each temperature sampling value in the historical temperature data, the first probability of the temperature of the first component increasing during the operation of the first service is determined.

[0067] Step S303: determining a second probability that the temperature of the first component increases.

[0068] In some embodiments, the carrier determines the operation probability of each service based on the historical operation data of each service in the electronic device. The specific determination method can refer to step S201 and will not be repeated here.

[0069] In some embodiments, the carrier confirms the probability of the temperature of the first component increasing when each service is running. The specific determination method can refer to step S202 and will not be repeated here.

[0070] In some embodiments, the carrier calculates the second probability of the temperature of the first component increasing based on the operation probability of each service, the probability of the temperature of the first component increasing when each service is running, and the full probability disclosure.

[0071] In specific implementation, the carrier determines the probability that the temperature of the first component will increase due to the operation of each service based on the operation probability of each service in each service and the probability of the temperature of the first component increasing when the service is running; and determines the sum of the probabilities that the temperature of the first component will increase due to the operation of all services as the second probability of the temperature of the first component increasing.

[0072] That is, the product of the operating probability of the first business and the probability of the temperature rising of the first component when the first business is running, the product of the operating probability of the second business and the probability of the temperature rising of the first component when the second business is running, and so on, are summed up, and the sum result is determined to be the second probability of the temperature rising of the first component.

[0073] Step S304: determining the posterior probability that the first service causes the temperature of the first component to rise.

[0074] In some embodiments, the carrier determines the posterior probability that the first service causes the temperature of the first component to rise based on the Bayesian formula, the operation probability of the first service, the first probability that the temperature of the first component rises when the first service is running, and the second probability that the temperature of the first component rises.

[0075] Step S305 : determining a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0076] In some embodiments, different a posteriori probabilities correspond to different heat dissipation strategies. For example, from the perspective of energy saving, corresponding heat dissipation strategies are determined according to different a posteriori probabilities. For example, if the a posteriori probability that the temperature of the first component is increased due to the first business 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 a posteriori probability that the temperature of the first component is increased due to the first business is very high, it means that there is a high probability that the temperature of the first component will increase. In order to avoid damage to the first component caused by a sudden temperature change 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.

[0077] In some embodiments, the correspondence between different a posteriori probabilities and heat dissipation strategies can be pre-set, and the correspondence between the a posteriori probabilities and the heat dissipation strategies can include the correspondence between the a posteriori probability range and the heat dissipation strategy, determining in which a posteriori probability range the posterior probability that the first service causes the temperature increase of the first component falls, and determining the heat dissipation strategy corresponding to the a posteriori probability range as the heat dissipation strategy of the electronic device.

[0078] The posterior probability range may include setting a range every 10%, for a total of 10 posterior probability ranges, or may be determined based on energy efficiency, such as 0% to 30%, 30% to 50%, 50% to 60%, 60% to 70%, and subsequently setting a range every 10% or every 5%. The specific setting method may be determined based on actual needs.

[0079] In some embodiments, different heat dissipation strategies may be set from the perspective of power consumption or heat dissipation effect, corresponding one-to-one to the posterior probability range.

[0080] Step S306: collecting updated operation data of each service in the electronic device, and updating the operation probability of each service based on the updated operation data and the historical operation data.

[0081] In some embodiments, in order to ensure the accuracy of determining the heat dissipation strategy, the carrier can continuously collect 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 can also continuously collect updated temperature data of the first component, and update the probability of the temperature of the first component rising when each service is running based on the updated temperature data and the historical temperature data.

[0082] In some embodiments, the carrier repeats steps S301 to S305 based on the updated running probability of each service and the updated probability of the temperature of the first component increasing when each service is running.

[0083] In this way, through the cooling strategy determination method provided by the embodiment of the present invention, the prior probability is determined based on the historical operation data. When it is monitored that the business starts to run, the posterior probability that the business causes the temperature of the first component to rise can be obtained based on the prior probability, and then the cooling strategy is determined based on the posterior probability. There is no need to wait until the temperature reaches a certain threshold before adjusting it. The noise caused by the sudden operation of the fan can be reduced. At the same time, the rapid change of component temperature can also be avoided to cause the server performance to decline.

[0084] Figure 4 A third optional flow chart of the method for determining a heat dissipation strategy provided in an embodiment of the present disclosure is shown and will be described according to each step.

[0085] Step S401: training a service operation probability model based on historical operation data of each service in the electronic device.

[0086] In some embodiments, the carrier trains a business operation probability model based on the historical operation data of each business in the electronic business. The historical operation data of each business may include the operation information of each business in the electronic device, such as the number of operations, the operation duration, and the association between each business; the association between each business may include whether there is a pre-relationship between the businesses. Or the association between data traffic and each business, for example, after receiving the data of the first application, a certain business will be run.

[0087] In some embodiments, the carrier inputs the historical operation data of each business into a business operation probability model, and determines that the output of the business operation probability model is the predicted operation probability of each business; determines the loss function of the business operation probability model based on the marked operation probability and the predicted operation probability, and adjusts the weight of the operation probability model based on the loss function of the operation probability model.

[0088] During the application process, the carrier inputs the current operation data of each service into the operation probability model, and determines that the output of the operation probability model is the operation probability of at least one service, wherein the at least one service includes the first service.

[0089] Step S402: inputting operation data corresponding to the first service into a component temperature prediction model, and determining that an output of the component temperature prediction model is a first probability that the temperature of the first component increases.

[0090] In some embodiments, the carrier pre-trains a component temperature prediction model, specifically, obtains historical operation data of each business and historical temperature data of the first component when each business is running; and trains the component temperature prediction model based on the historical operation data of each business and the historical temperature data of the first component.

[0091] In a specific implementation, the input of the component temperature prediction model is the historical transportation data of each business, and the output is the probability of temperature rise of at least one component in the electronic device. Optionally, the carrier can determine the loss function of the component temperature prediction model based on the cross entropy function and adjust the weight of the component temperature prediction model.

[0092] Step S403: determining a second probability that the temperature of the first component increases.

[0093] In some embodiments, the specific step flow of step S403 is the same as step S303 and will not be repeated here.

[0094] Step S404: determine the posterior probability that the first service causes the temperature of the first component to rise.

[0095] In some embodiments, the specific step flow of step S404 is the same as step S304 and will not be repeated here.

[0096] Step S405 : determining a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0097] In some embodiments, the specific step process of step S405 is the same as step S305 and will not be repeated here.

[0098] Step S406, collecting updated operation data of each service in the electronic device, and updating the weight of the component temperature prediction model and the weight of the service operation probability model based on the updated operation data and the historical operation data.

[0099] In some embodiments, in order to ensure the accuracy of component temperature prediction by the component temperature prediction model, and to ensure the accuracy of business operation probability prediction by the business operation probability model, during the operation of the electronic device, updated operation data of each business and updated temperature data of each component are collected, and based on the updated operation data and historical operation data, the business operation probability model is repeatedly trained to adjust its weight; based on the updated temperature data and historical temperature data, the component temperature prediction model is repeatedly trained to adjust the weight of the component temperature prediction model.

[0100] Based on the adjusted component temperature prediction model and the business operation probability model, the updated operation probability of each business and the updated probability of the temperature of the first component rising when each business is running are obtained, and steps S401 to S405 are repeated based on the updated operation probability of each business and the updated probability of the temperature of the first component rising when each business is running.

[0101] In this way, through the cooling strategy determination method provided by the embodiment of the present invention, the prior probability is determined based on the prediction model. When it is monitored that the business starts to run, the posterior probability that the business causes the temperature of the first component to rise can be obtained based on the prior probability, and then the cooling strategy is determined based on the posterior probability. There is no need to wait until the temperature reaches a certain threshold before adjusting it. The noise caused by the sudden operation of the fan can be reduced. At the same time, the rapid change of component temperature can also be avoided to cause the server performance to decline.

[0102] Figure 5 A fourth optional flow chart of the method for determining a heat dissipation strategy provided in an embodiment of the present disclosure is shown and will be described according to each step.

[0103] Step S501: determine the first service.

[0104] In some embodiments, the carrier determines the first service that needs to be monitored based on the service or application scenario of the electronic device.

[0105] In some embodiments, the application scenarios of the electronic device are different, and the corresponding services are also different. In this case, it is necessary to determine the services that the application scenario will involve; that is, determine at least one service running in the application scenario, and any one of the at least one services is the first service.

[0106] Step S502 , collecting historical temperature information of each component and historical operation data of the first service.

[0107] In some embodiments, during the operation of the electronic device, historical operation data of the first service and historical temperature information of each component during the operation of each service are determined, wherein the components include the first component.

[0108] Step S503, determining the operation probability of the first service based on the historical operation data; and confirming the first probability of the temperature of the first component rising when the first service is running based on the historical temperature information of each component.

[0109] In some embodiments, the carrier uses time as a coordinate to calculate the operation probability of each service. , the probability of component temperature rising during the operation of each business ;in, Indicates a component temperature rise event; Indicates a certain operation business. .

[0110] Step S504: determining a second probability that the temperature of the first component increases.

[0111] In some embodiments, the carrier calculates the probability of component temperature increase using a total probability formula, which may specifically include:

[0112] Step S505 : determining the posterior probability that the first service causes the temperature of the first component to rise.

[0113] In some embodiments, the vector utilizes the Bayesian formula And the total probability formula, the probability that the first component temperature rise event is caused by a certain service (that is, the posterior probability that the first service causes the first component temperature rise) is determined as:

[0114] Step S506: determining a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0115] In some embodiments, the carrier adopts a corresponding heat dissipation control strategy according to the probability calculation result and the temperature change information obtained by component monitoring. The higher the calculated probability is, the greater the possibility that the service will cause the component temperature to rise.

[0116] In this way, through the heat dissipation strategy determination method provided by the embodiment of the present disclosure, the probability that a certain business may cause the temperature of a component to rise is calculated according to the Bayesian formula. Once it is monitored that a high-probability business starts to run and the temperature of the relevant components rises and falls, the corresponding heat dissipation control strategy can be adopted to ensure that the operation of the server is more stable and efficient. The embodiment of the present disclosure can effectively overcome the problems faced by the traditional PID heat dissipation control technology when the heat dissipation control strategy is started after the component temperature reaches a preset threshold, such as large staged fan noise, large component temperature variation, and server performance degradation caused by rapid changes in component temperature. It is beneficial to reduce enterprise costs, improve R&D efficiency, and promote its use in the engineering field.

[0117] Figure 6 A fifth optional flow chart of the method for determining a heat dissipation strategy provided in an embodiment of the present disclosure is shown and will be described according to each step.

[0118] Step S601: BMC monitors the business operation status.

[0119] In some embodiments, the carrier may be a BMC, and 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 services include the first service.

[0120] Step S602: Calculate the posterior probability that the first service causes the temperature of the first component to rise.

[0121] In some embodiments, in response to the first service running, the posterior probability that the first service causes the temperature of the first component to rise is calculated. The specific calculation method can refer to any of steps S201 to S203, steps S301 to S304, or steps S401 to S404, and will not be repeated here.

[0122] Step S603: determine whether the posterior probability is greater than a preset threshold.

[0123] In some embodiments, the BMC determines whether the posterior probability is greater than a preset threshold. If it is greater than the preset threshold, the first service has a high probability of causing the first component in the electronic device to heat up, and further monitoring of the state of the first component is required, that is, executing step S604; if the BMC determines that the posterior probability is less than or equal to the preset threshold, the first service has a low probability of causing the first component in the electronic device to heat up, that is, the first service may not necessarily cause the first component to heat up, and then returns to step S601 for repeated monitoring. The preset threshold can be set according to actual needs.

[0124] Step S604: The BMC monitors the operating status of the first component.

[0125] In some embodiments, the operating state of the first component may include a temperature change state of the first component, and the BMC may sample the temperature of the first component at a certain frequency to monitor the operating state of the first component.

[0126] Step S605, determining whether the temperature of the first component shows a rising and falling trend.

[0127] 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 later sampling temperature is greater than the earlier sampling temperature, it is determined that the first component has a temperature rise trend; if the later sampling temperature is less than the earlier sampling temperature, it is determined that the first component has a temperature drop trend.

[0128] In some embodiments, in order to save energy, after the temperature of the first component drops, the heat dissipation strategy also needs to be adaptively adjusted, such as reducing the fan speed, reducing the condensate flow rate, etc. Therefore, the heat dissipation strategy needs to be adjusted not only when the first component shows a heating trend, but also when the first component shows a cooling trend.

[0129] In some embodiments, if the temperature of the first component shows an upward and downward trend, step S606 is executed; if the temperature of the first component does not show an upward and downward trend, the prior probability and the possibility function are updated and step S602 is re-executed.

[0130] Step S606: determining a heat dissipation strategy based on the posterior probability.

[0131] In some embodiments, different a posteriori probabilities correspond to different heat dissipation strategies. For example, from the perspective of energy saving, corresponding heat dissipation strategies are determined according to different a posteriori probabilities. For example, if the a posteriori probability that the temperature of the first component is increased due to the first business 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 a posteriori probability that the temperature of the first component is increased due to the first business is very high, it means that there is a high probability that the temperature of the first component will increase. In order to avoid damage to the first component caused by a sudden temperature change 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.

[0132] In some embodiments, the correspondence between different a posteriori probabilities and heat dissipation strategies can be pre-set, and the correspondence between the a posteriori probabilities and the heat dissipation strategies can include the correspondence between the a posteriori probability range and the heat dissipation strategy, determining in which a posteriori probability range the posterior probability that the first service causes the temperature increase of the first component falls, and determining the heat dissipation strategy corresponding to the a posteriori probability range as the heat dissipation strategy of the electronic device.

[0133] In this way, traditional electronic devices use PID heat dissipation control technology and only start the heat dissipation control strategy when the component temperature reaches a preset threshold. The disclosed embodiment proposes to predict the probability that the server running business may cause the component temperature to rise based on Bayesian estimation. Once it is monitored that a high-probability business starts to run and the temperature of related components rises and falls, the BMC can adopt a corresponding heat dissipation control strategy to ensure that the operation of the electronic device is more stable and efficient. The disclosed embodiment can effectively solve the problems faced by traditional PID control, such as high stage fan noise, large temperature changes of components, and server performance degradation caused by rapid changes in component temperature. It is conducive to reducing enterprise costs, improving R&D efficiency, and promoting its use in the engineering field.

[0134] Next, the embodiment of the present disclosure is further explained and illustrated by taking actual data as an example.

[0135] Assume that 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 a period of data collection, the operating probability of each service is calculated. , and the probability that the first component will heat up when the service is running for:

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142] Further, according to the total probability calculation formula, the second probability of the first component temperature rising can be obtained: for:

[0143] Substituting the Bayesian formula into the calculation, we can get the probability that each business may cause the temperature of the component to rise:

[0144]

[0145]

[0146]

[0147]

[0148]

[0149]

[0150] During the operation of the electronic device, the operation probability of the service and the first probability that the service causes the temperature of the first component to rise are continuously collected and updated. After repeated iterations, the probability that different services may cause the temperature of the first component to rise will be continuously updated. The heat dissipation control module can adopt the corresponding level of control strategy based on the calculated probability. It should be pointed out that the prior probability and The accuracy of statistics directly determines the posterior probability Close to the real situation.

[0151] Further, according to the corresponding relationship between the posterior probability and the heat dissipation strategy, the heat dissipation strategy of the electronic device is determined. Table 1 shows the corresponding relationship between the posterior probability and the heat dissipation strategy in the embodiment of the present disclosure.

[0152] Table 1

[0153] Figure 7 A first optional structural diagram of a heat dissipation strategy determination device provided in an embodiment of the present disclosure is shown, and will be described according to each part.

[0154] 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 control module 704 .

[0155] Among them, the component monitoring module 701 is a BMC resident service, responsible for providing real-time monitoring for key components of electronic equipment 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 CPU number, operating status, occupancy rate, temperature and other information in real time, so that the business operation monitoring module 702 and the heat dissipation control module 704 can optimize the business and control the heat dissipation of the CPU according to the monitoring information.

[0156] The business operation monitoring module 702 has two stages. The model training stage is mainly responsible for collecting the operation data (historical operation data or updated operation data) of each business under different application scenarios, so as to calculate the operation probability of each business in the later stage. , and the temperature data of each component provided by the component monitoring module 701, calculate the probability of each component experiencing an increase in temperature Provide data support; During the actual operation phase, the business operation monitoring module 702 is responsible for promptly transmitting the business operation conditions that may cause the temperature of components to rise calculated by the Bayesian estimation operation module 703 to the heat dissipation control module 704. Once it is monitored that these businesses start to run and the temperature of related components rises and falls, it is necessary to immediately notify the heat dissipation control module 704 to start the corresponding level of control.

[0157] The Bayesian estimation operation module 703 is used to receive the business operation data collected by the business operation monitoring module 702 and the monitoring data of the components by the component monitoring module 701, and based on the data provided by the two, calculate the business operation conditions that may cause the temperature of the components to rise, that is, the posterior probability, and send the posterior probability to the business operation monitoring module 702 so that the business operation monitoring module 702 can pass it to the heat dissipation control module 704 in a timely manner.

[0158] The heat dissipation control module 704 is responsible for timely taking corresponding level control strategies according to the component temperature information transmitted by the component monitoring module 701 and the business operation status information that may cause the component temperature to rise with a high probability transmitted by the business operation monitoring module, see Table 1.

[0159] Compared with the PID control strategy, the heat dissipation strategy determination method provided in the embodiment of the present disclosure can enable the control strategy to intervene in advance, so that the temperature change of the component is more stable, thereby providing a guarantee for the operation efficiency of the server; in addition, the PID control strategy is only started when the component temperature reaches the set temperature threshold, which will cause the fan speed to increase rapidly and generate huge noise, thereby reducing the user experience. The early intervention control strategy adopted in the embodiment of the present disclosure can effectively reduce the noise of the fan.

[0160] Figure 8 A second optional structural diagram of the heat dissipation strategy determination device provided in an embodiment of the present disclosure is shown, and will be explained according to each part.

[0161] In some embodiments, the heat dissipation strategy determination device 700 may include a priori probability determination unit 705 , a total probability determination unit 706 , a posterior probability determination unit 707 and a heat dissipation strategy determination unit 708 .

[0162] The prior probability determination unit 705 is used to confirm the operation probability of the first service in response to the first service being run, and to confirm the first probability of the temperature of the first component rising when the first service is run; The total probability determination unit 706 is used to determine a second probability of a temperature increase of the first component; The a posteriori probability determination unit 707 is used to determine the a posteriori probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases; The heat dissipation strategy determining unit 708 is configured to determine a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise.

[0163] The prior probability determination unit 705 is specifically used to collect historical operation data of each service in the electronic device; Determining the operation probability of each business based on the historical operation data of each business; Among them, the various services include the first service.

[0164] The prior probability determination unit 705 is also used to collect updated operation data of each service in the electronic device; Based on the updated operation data and the historical operation data, the operation probability of each service is updated.

[0165] The prior probability determination unit 705 is specifically used to collect historical temperature data of the first component when each service is running; Based on the historical temperature data of the first component, the probability of the temperature of the first component increasing when each service is running is determined.

[0166] The prior probability determination unit 705 is specifically used to collect updated temperature data of the first component when each service is running; Based on the updated temperature data and the historical temperature data, the probability of the temperature of the first component increasing when each service is running is updated.

[0167] 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 a first probability that the temperature of the first component increases.

[0168] The prior probability determination unit 705 is further used to obtain the historical operation data of each service and the historical temperature data of the first component when each service is running; A component temperature prediction model is trained based on the historical operation data of each service and the historical temperature data of the first component.

[0169] The total probability determination unit 706 is specifically configured to determine the second probability of the temperature increasing of the first component based on the operation probability of each service, the probability of the temperature increasing of the first component when each service is running, and the total probability formula.

[0170] The total probability determination unit 706 is specifically configured to determine the probability that the temperature of the first component increases due to the operation of each service based on the operation probability of each service in each service and the probability that the temperature of the first component increases when the service is operated; The sum of the probabilities that all business operations result in a temperature increase of the first component is determined as a second probability that the temperature of the first component increases.

[0171] The posterior probability determination unit 707 is specifically used to determine the posterior probability that the first service causes the temperature of the first component to increase based on the Bayesian formula, the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases.

[0172] The posterior probability determination unit 707 is specifically configured to determine a result of dividing the second probability of the temperature increase of the first component by the product of 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, to obtain a posterior probability that the first service causes the temperature increase of the first component.

[0173] The heat dissipation strategy determination unit 708 is specifically configured to determine a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise, and the corresponding relationship between the a posteriori probability and the heat dissipation strategy; 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.

[0174] In some embodiments, the first service includes one of the following: Network service business, data management business, application service business, virtualization business and agency business.

[0175] In some embodiments, the first component includes one of the following: CPU, graphics processor, storage disk, memory card and network card.

[0176] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0177] Fig. 9 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment 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 processing, 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 required herein.

[0178] like Fig. 9 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a 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 via a bus 804. An input / output (In / Out, I / O) interface 805 is also connected to the bus 804.

[0179] 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 disk, an optical disk, 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 through a computer network such as the Internet and / or various telecommunication networks.

[0180] The computing unit 801 may be a variety of general and / or special 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, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs 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 may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on 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 may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the heat dissipation strategy determination method in any other appropriate manner (for example, by means of firmware).

[0181] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0182] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0183] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0184] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types 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, voice input, or tactile input).

[0185] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0186] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0187] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0188] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0189] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for determining a heat dissipation strategy, characterized in that: The method comprises: In response to the first service being run, confirming the probability of the first service being run, and confirming a first probability of a temperature increase of the first component when the first service is run; determining a second probability that the temperature of the first component is increased; Determine a posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases; Based on the a posteriori probability that the first service causes the temperature of the first component to rise, a heat dissipation strategy of the electronic device is determined.

2. The method according to claim 1, characterized in that: The confirming the operation probability of the first service includes: Collect historical operation data of each business in electronic equipment; Determining the operation probability of each business based on the historical operation data of each business; Among them, the various services include the first service.

3. The method according to claim 2, characterized in that The method further comprises: Collect updated operation data of each business in electronic equipment; Based on the updated operation data and the historical operation data, the operation probability of each service is updated.

4. The method according to claim 1, characterized in that The first probability that the temperature of the first component increases when confirming that the first service is running includes: Collect historical temperature data of the first component when each service is running; Based on the historical temperature data of the first component, a first probability that the temperature of the first component increases when each service is running is determined.

5. The method according to claim 4, characterized in that The method further comprises: Collect updated temperature data of the first component when each service is running; Based on the updated temperature data and the historical temperature data, a first probability that the temperature of the first component increases when each service is running is updated.

6. The method according to claim 1, characterized in that The first probability that the temperature of the first component increases when confirming that the first service is running includes: The operation data corresponding to the first service is input into a component temperature prediction model, and an output of the component temperature prediction model is determined to be a first probability of a temperature increase of the first component.

7. The method according to claim 6, characterized in that The method further comprises: Acquire historical operation data of each service and historical temperature data of the first component when each service is running; A component temperature prediction model is trained based on the historical operation data of each service and the historical temperature data of the first component.

8. The method according to claim 1, characterized in that The determining a second probability that the temperature of the first component increases includes: A second probability of the temperature of the first component increasing is determined based on the operating probability of each service, the probability of the temperature of the first component increasing when each service is operating, and a total probability formula.

9. The method according to claim 8, characterized in that The determining the second probability of the temperature increase of the first component based on the operation probability of each service, the probability of the temperature increase of the first component when each service is running, and the total probability formula includes: Determine the probability that the temperature of the first component increases due to the operation of each service based on the operation probability of each service in each service and the probability that the temperature of the first component increases when the service is operated; The sum of the probabilities that all business operations result in a temperature increase of the first component is determined as a second probability that the temperature of the first component increases.

10. The method according to claim 1, characterized in that The determining, based on the operation probability of the first service, the first probability of the temperature of the first component increasing when the first service is running, and the second probability of the temperature of the first component increasing, the posterior probability that the temperature of the first component increases due to the first service includes: Based on the Bayesian formula, the running probability of the first service, the first probability of the first component temperature rising when the first service is running, and the second probability of the first component temperature rising, the posterior probability that the first service causes the first component temperature rising is determined.

11. The method according to claim 10, characterized in that The determining, based on the Bayesian formula, the operating probability of the first service, the first probability of the temperature of the first component increasing when the first service is operating, and the second probability of the temperature of the first component increasing, the posterior probability that the first service causes the temperature of the first component to increase includes: The product of the operating probability of the first service and the first probability of the temperature increase of the first component when the first service is running, divided by the second probability of the temperature increase of the first component, is the posterior probability that the first service causes the temperature increase of the first component.

12. The method according to claim 1, characterized in that The determining of a heat dissipation strategy of the electronic device based on the a posteriori probability that the temperature of the first component is increased due to the first service includes: Determine a heat dissipation strategy for the electronic device based on the a posteriori probability that the first service causes the temperature of the first component to rise, and the corresponding relationship between the a posteriori probability and the heat dissipation strategy; 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.

13. The method according to claim 1, characterized in that The first service includes one of the following: Network service business, data management business, application service business, virtualization business and agency business.

14. The method according to claim 1, characterized in that The first component includes one of the following: CPU, graphics processor, storage disk, memory card and network card.

15. A device for determining a heat dissipation strategy, characterized in that: The device comprises: a priori probability determination unit, configured to, in response to the first service being run, confirm the probability of the first service being run, and confirm a first probability of a temperature increase of the first component when the first service is run; a total probability determination unit, configured to determine a second probability of a temperature increase of the first component; a posterior probability determination unit, configured to determine a posterior probability that the temperature of the first component increases due to the first service based on the operation probability of the first service, the first probability that the temperature of the first component increases when the first service is running, and the second probability that the temperature of the first component increases; The heat dissipation strategy determining unit is used to determine the heat dissipation strategy of the electronic device based on the a posteriori probability that the temperature of the first component is increased due to the first service.

16. An electronic device, characterized in that: include: 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 to 14.

17. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1-14.

18. A computer program product, characterized in that A computer program is included which, when executed by a processor, implements the method according to any one of claims 1 to 14.

Images