Heat dissipation control method and device, electronic equipment and storage medium

Abstract

The application provides a heat dissipation control method and device, electronic equipment and storage medium, and relates to the technical field of data processing. The method comprises the following steps: determining a first heat dissipation factor of a first baseboard management controller according to first self-temperature information of the first baseboard management controller and heat dissipation capacity information of the first baseboard management controller; determining a third heat dissipation factor according to the first heat dissipation factor and second heat dissipation factors of each second baseboard management controller; wherein the second baseboard management controller is a baseboard management controller device whose positioning information is less than a first distance threshold value from the positioning information of the first baseboard management controller; and performing heat dissipation control based on a heat dissipation control scheme corresponding to the third heat dissipation factor.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a heat dissipation control method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continuous development of technology, large models and big data are being used more and more widely in reality. The computing power and storage performance of machines are a very critical factor. Usually, computing power and storage are provided by servers to support huge computing power and storage needs.

[0003] Servers typically contain high-performance computing units, which generate a significant amount of heat during operation. Therefore, the heat generated by a server cluster is substantial. The various chip components within the server must maintain a stable temperature to prevent overheating; otherwise, system crashes or damage may occur. The failure or damage of the server's high-performance computing units can result in substantial losses.

[0004] Therefore, how to better control server heat dissipation has become an urgent problem to be solved in the industry. Summary of the Invention

[0005] This invention provides a heat dissipation control method, device, electronic device, and storage medium to solve the problem of how to better control the heat dissipation of servers in the prior art.

[0006] This invention provides a heat dissipation control method, comprising:

[0007] Based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller, the first heat dissipation factor of the first substrate management controller is determined.

[0008] A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller;

[0009] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0010] Heat dissipation control is performed based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0011] According to a heat dissipation control method provided by the present invention, a third heat dissipation factor is determined based on a first heat dissipation factor and a second heat dissipation factor of each of the second substrate management controllers, comprising:

[0012] Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained;

[0013] The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers;

[0014] A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

[0015] According to a heat dissipation control method provided by the present invention, after the step of determining a third heat dissipation factor based on a first heat dissipation factor and a second heat dissipation factor of each of the second substrate management controllers, the method further includes:

[0016] Every first preset time period, the second self-temperature information of the first substrate management controller is re-collected;

[0017] Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the preset iteration conditions are met, and the iteration is completed.

[0018] According to a heat dissipation control method provided by the present invention, after the step of re-acquiring the second self-temperature information of the first substrate management controller, the method further includes:

[0019] Based on the second self-temperature information and the preset excitation function, determine the state transition probability corresponding to the third heat dissipation factor;

[0020] The state transition probability, the third heat dissipation factor, and the first self-temperature information are stored as a set of target state information.

[0021] According to the heat dissipation control method provided by the present invention, after the step of determining a third heat dissipation factor based on a first heat dissipation factor and a second heat dissipation factor of each of the second substrate management controllers,

[0022] After each of the first preset time intervals, the third self-temperature information of the first substrate management controller is re-collected;

[0023] In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor;

[0024] Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed.

[0025] Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

[0026] According to a heat dissipation control method provided by the present invention, the method for calculating the first heat dissipation factor specifically includes:

[0027] F pirme =T 2 / A+C;

[0028] Among them, F pirme Let T be the first heat dissipation factor, T be the first self-temperature information, A be the heat dissipation capacity information of the first substrate management controller, and C be the basic heat dissipation factor constant.

[0029] According to a heat dissipation control method provided by the present invention, the calculation method of the third heat dissipation factor specifically includes:

[0030] F final =f(F prime ,n,[g,F])

[0031]

[0032] Among them, F pirme The first heat dissipation factor is given by function f, which calculates the third heat dissipation factor F. final n represents the number of second substrate management controllers, g represents the distance between the first and second substrate management controllers, F represents the second heat dissipation factor, and i represents the i-th second substrate management controller. These are the parameters for heat dissipation in the surrounding area.

[0033] The present invention also provides a heat dissipation control device, comprising:

[0034] The first determining module is used to determine the first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller.

[0035] The second determining module is used to determine the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each second substrate management controller;

[0036] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0037] A heat dissipation control module is used to perform heat dissipation control based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0038] According to a heat dissipation control device provided by the present invention, the second determining module is specifically used for:

[0039] Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained;

[0040] The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers;

[0041] A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

[0042] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0043] Every first preset time period, the second self-temperature information of the first substrate management controller is re-collected;

[0044] Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the preset iteration conditions are met, and the iteration is completed.

[0045] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0046] Based on the second self-temperature information and the preset excitation function, determine the state transition probability corresponding to the third heat dissipation factor;

[0047] The state transition probability, the third heat dissipation factor, and the first self-temperature information are stored as a set of target state information.

[0048] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0049] After each of the first preset time intervals, the third self-temperature information of the first substrate management controller is re-collected;

[0050] In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor;

[0051] Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed.

[0052] Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

[0053] According to a heat dissipation control device provided by the present invention, the method for calculating the first heat dissipation factor specifically includes:

[0054] F pirme =T 2 / A+C;

[0055] Among them, F pirme Let T be the first heat dissipation factor, T be the first self-temperature information, A be the heat dissipation capacity information of the first substrate management controller, and C be the basic heat dissipation factor constant.

[0056] According to a heat dissipation control device provided by the present invention, the method for calculating the third heat dissipation factor specifically includes:

[0057] F final =f(F prime ,n,[g,F])

[0058]

[0059] Among them, F pirme The first heat dissipation factor is given by function f, which calculates the third heat dissipation factor F. final n represents the number of second substrate management controllers, g represents the distance between the first and second substrate management controllers, F represents the second heat dissipation factor, and i represents the i-th second substrate management controller. These are the parameters for heat dissipation in the surrounding area.

[0060] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the heat dissipation control method as described above.

[0061] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the heat dissipation control method as described above.

[0062] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the heat dissipation control method as described above.

[0063] The heat dissipation control method, apparatus, electronic device, and storage medium provided by the present invention, after determining the first heat dissipation factor of the first substrate management controller based on its own temperature information and its own heat dissipation capacity information, further considers the influence of the second substrate management controller around the first substrate management controller on heat dissipation. Therefore, the second heat dissipation factor of the second substrate management controller can be further considered to determine the third heat dissipation factor of the area. Then, heat dissipation control is performed according to the heat dissipation control scheme corresponding to the third heat dissipation factor that can reflect the heat characteristics of the area, effectively realizing precise heat dissipation control of the server. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0065] Figure 1 This is a schematic flowchart of the heat dissipation control method provided in the embodiments of this application;

[0066] Figure 2 This is a schematic diagram of the control flow provided in the embodiments of this application;

[0067] Figure 3 This is a schematic diagram of the refrigeration control described in the embodiments of this application;

[0068] Figure 4 This is a schematic diagram of the heat dissipation control device provided in an embodiment of this application;

[0069] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0071] Figure 1 This is a schematic flowchart of the heat dissipation control method provided in the embodiments of this application, such as... Figure 1 As shown, it includes:

[0072] Step 110: Determine the first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller.

[0073] In this embodiment, the servers in the data center may come from many different manufacturers, and their heat generation and cooling performance vary. This is because servers typically have a Baseboard Management Controller (BMC), an embedded computer system usually integrated onto the motherboard of a server or other network device. The BMC has its own processor, memory, and network interface, and is primarily used for remote monitoring and management of hardware devices.

[0074] Therefore, by properly managing the BMC modules in each server, the current temperature information of the server equipment can be accurately obtained.

[0075] In an optional embodiment, the different baseboard management controllers described in this application specifically refer to baseboard management controllers set in different servers.

[0076] In this embodiment, the heat dissipation capability information of the first baseboard management controller can specifically refer to the ability of the heat dissipation system (such as heat sink, fan, etc.) to effectively dissipate heat from the device under specific conditions, which can be preset according to the hardware performance of the first baseboard management controller.

[0077] In this embodiment of the application, the first self-temperature information can be obtained by monitoring the self-temperature information of the first substrate management controller.

[0078] In this embodiment, the higher the temperature of the device, the more heat dissipation resources are required, while the stronger the heat dissipation capacity, the less heat dissipation resources are required. Therefore, the heat dissipation factor is inversely proportional to the heat dissipation capacity. Finally, the first heat dissipation factor of the first substrate management controller can be determined based on the first self-temperature information and the heat dissipation capacity information of the first substrate management controller.

[0079] In an optional embodiment, the method for calculating the first heat dissipation factor specifically includes:

[0080] F pirme =T 2 / A+C;

[0081] Among them, F pirme Let T be the first heat dissipation factor, T be the first self-temperature information, A be the heat dissipation capacity information of the first substrate management controller, and C be the basic heat dissipation factor constant.

[0082] Step 120: Determine the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each second substrate management controller;

[0083] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0084] In this embodiment of the application, since the location of each server is relatively fixed, the location of the BMC in each server is also relatively fixed. Therefore, based on the positioning information of the first baseboard management controller as the center and the first preset distance threshold as the radius, the BMC within the radius coverage area can be selected as the second baseboard management controller.

[0085] The second BMC described in this application embodiment may specifically refer to a BMC that is close to the first BMC and may affect each other's heat dissipation.

[0086] The second heat dissipation factor of the second baseboard management controller described in this application embodiment can specifically be data directly read from the second baseboard management controller.

[0087] In an optional embodiment, after obtaining the first heat dissipation factor and the second heat dissipation factor of each second substrate management controller, they can be substituted into the environmental influence function to finally calculate the third heat dissipation factor.

[0088] Step 130: Perform heat dissipation control based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0089] In this embodiment of the application, after calculating the heat dissipation factor, the BMC will transmit the value to the heat dissipation system controller via the network, and will reserve a period of time to wait for changes in the environment.

[0090] For example, the operating status of the cooling system can be adjusted based on the thermal factor of the third baseboard management controller. If the thermal factor is low, it indicates that the cooling system's heat dissipation capacity is insufficient, and it is necessary to increase the heat dissipation capacity by adding heat sinks or increasing the fan speed; if the thermal factor is high, it indicates that the cooling system's heat dissipation capacity is sufficient, and the heat dissipation capacity can be reduced by appropriately decreasing the size of the heat sinks or reducing the fan speed.

[0091] In this embodiment, after determining the first heat dissipation factor of the first baseboard management controller based on its own temperature information and heat dissipation capacity information, the influence of the second baseboard management controller around the first baseboard management controller on heat dissipation is further considered. Therefore, the second heat dissipation factor of the second baseboard management controller can be further considered to determine the third heat dissipation factor of the area. Then, heat dissipation control is carried out according to the heat dissipation control scheme corresponding to the third heat dissipation factor that can reflect the heat characteristics of the area, so as to effectively realize the precise heat dissipation control of the server.

[0092] Optionally, a third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factors of each of the second substrate management controllers, including:

[0093] Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained;

[0094] The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers;

[0095] A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

[0096] In this embodiment of the application, to obtain the distance information between the first substrate management controller and each of the second substrate management controllers, it can be calculated using positioning information and location data.

[0097] For example, we can assume that the position coordinates of the first substrate management controller are (x1, y1), and the position coordinates of the second substrate management controller are (x2, y2), (x3, y3), (x4, y4), and so on. These position coordinates can be coordinate values ​​in a Cartesian coordinate system.

[0098] Then, the distance between the first baseboard management controller and each of the second baseboard management controllers can be calculated using mathematical distance formulas. In a Cartesian coordinate system, the distance between two points (x1, y1) and (x2, y2) can be calculated using the following formula:

[0099] [distance=\sqrt{(x2-x1)^2+(y2-y1)^2}] According to the above formula, the distance information between the first substrate management controller and each of the second substrate management controllers can be calculated separately. This allows us to obtain the distance information between the first substrate management controller and each of the second substrate management controllers.

[0100] In an optional embodiment, the method for calculating the third heat dissipation factor specifically includes:

[0101] F final =f(F prime ,n,[g,F])

[0102]

[0103] Among them, F pirme The first heat dissipation factor is given by function f, which calculates the third heat dissipation factor F. final n represents the number of second substrate management controllers, g represents the distance between the first and second substrate management controllers, F represents the second heat dissipation factor, and i represents the i-th second substrate management controller. These are the parameters for heat dissipation in the surrounding area.

[0104] In this embodiment of the application, when performing heat dissipation control analysis, the first BMC and the surrounding second BMCs are treated as a swarm intelligence model composed of network connections. Therefore, after calculating the first heat dissipation factor, it is necessary to further determine the surrounding heat dissipation parameters by using the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers. Then, the third heat dissipation factor is determined by using the first heat dissipation factor and the surrounding heat dissipation parameters, thus obtaining the third heat dissipation factor for the region.

[0105] Optionally, after determining the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factors of each of the second substrate management controllers, the method further includes:

[0106] Every first preset time period, the second self-temperature information of the first substrate management controller is re-collected;

[0107] Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the preset iteration conditions are met, and the iteration is completed.

[0108] In this embodiment of the application, the first preset time period may specifically refer to a time period preset by the user, which may be 3 minutes or 5 minutes.

[0109] In this embodiment of the application, a loop is executed after each first preset time interval. During each loop, the second self-temperature information of the first substrate management controller can be re-acquired.

[0110] In the embodiments of the present application, the fourth heat dissipation factor is determined according to the second self-temperature information and each of the second heat dissipation factors, and the specific calculation method thereof is similar to the manner of calculating the third heat dissipation factor in the above embodiments, which will not be repeated here.

[0111] In the embodiments of the present application, the preset iteration condition may specifically be that a preset number of cycles is satisfied, or a converged solution is obtained for certain self-temperature information, and the preset cycle condition is finally satisfied, the cycle is terminated, and the iteration is completed.

[0112] In an optional embodiment, after the step of re-collecting the second self-temperature information of the first baseboard management controller, the method further comprises:

[0113] determining the state transition probability corresponding to the third heat dissipation factor according to the second self-temperature information and a preset excitation function;

[0114] storing the state transition probability, the third heat dissipation factor and the first self-temperature information as a piece of state information into a target state set.

[0115] In the embodiments of the present application, the self-temperature information of the second baseboard management controller may be mapped to the third heat dissipation factor according to a preset excitation function. The excitation function may be a mathematical function or an empirical model, which maps the self-temperature to the heat dissipation factor.

[0116] In the embodiments of the present application, the preset excitation function may specifically refer to:

[0117]

[0118] Wherein, the heat dissipation effect E: the amplitude of temperature change in this round of iteration, that is, the change of temperature T / the time elapsed in the iteration cycle; the preset temperature change interval Section: a reference range for evaluating that the heat dissipation execution effect is reasonable, which includes an upper bound Lup and a lower bound Ldown. If the temperature does not decrease but rises, a large negative feedback is given, that is, when E<0, R=γE, where γ is understood as an amplification coefficient, which is a preset parameter greater than 1, and is specifically used to amplify the negative feedback brought by this situation.

[0119] If the amplitude of temperature decrease is very small, a certain negative feedback is given, that is, when 0<E<Ldown, R=E-Ldown

[0120] If the amplitude of temperature decrease conforms to the preset interval, a positive feedback is given, that is, when Ldown<E<Lup, R=max(E-Ldown, Lup-E)

[0121] If the temperature drops too much, exceeding the preset range, it indicates that too much heat dissipation resources have been allocated, requiring negative feedback adjustment. That is, when E > Lup, R = Lup - E.

[0122] The corresponding state transition probability is calculated based on the third heat dissipation factor. This process can be modeled and calculated based on the specific system and background knowledge. For example, statistical models, machine learning algorithms, or physical equations can be used to determine the state transition probability.

[0123] The state transition probability, the third heat dissipation factor, and the temperature information of the first substrate management controller are treated as a complete set of state information and stored in the target state set. This set can be a data structure, such as an array, list, or database, used to record and manage information about different states.

[0124] In another alternative embodiment, if the same self-temperature information is detected during the loop, the updated state transition probability, i.e. the corresponding heat dissipation factor, can be evaluated and updated into the target state set, and then the parameters in the target state set can be continuously updated during the loop.

[0125] In this embodiment, there are multiple heat dissipation factors corresponding to a given temperature. The state transition probability can be understood as the probability of choosing different heat dissipation factors. When making a strategy decision, all situations must be considered. As the iteration process progresses, the heat dissipation efficiency of a certain strategy will be better, and its corresponding state transition probability will be relatively higher during the iteration process, meaning it is easier to select that strategy.

[0126] In this embodiment, the BMC incorporates its current and previous temperatures into the activation function to calculate the performance of its heat dissipation factor under these conditions. Based on this calculation, it updates the heat dissipation factor and state transition probabilities in the state set array. This enables the BMC's swarm intelligence to achieve self-feedback adjustment.

[0127] Optionally, after the step of determining the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each of the second substrate management controllers,

[0128] After each of the first preset time intervals, the third self-temperature information of the first substrate management controller is re-collected;

[0129] In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor;

[0130] Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed.

[0131] Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

[0132] In this embodiment of the application, the third self-temperature information of the first substrate management controller is re-acquired every preset time period.

[0133] Match the data set corresponding to the third self-temperature information within the target state set. The data set should include the target heat dissipation factor and the target state transition probability. Matching data sets can be found by comparing the third self-temperature information with the data in the target state set.

[0134] A fifth heat dissipation factor is determined based on the heat dissipation factor with the highest target state transition probability. The heat dissipation factor with the highest target state transition probability is selected as the fifth heat dissipation factor from the matched data set.

[0135] Implement a heat dissipation control scheme based on the fifth heat dissipation factor. Depending on the specific application and system requirements, different heat dissipation control methods can be adopted, such as adjusting fan speed or controlling the surface area of ​​the heat sink.

[0136] Check if the preset iteration conditions are met. If the conditions are met, complete the iteration; otherwise, return to collect temperature information again and continue the iteration.

[0137] In this embodiment, the heat dissipation factor is optimized based on past experience. A heat dissipation factor is selected from the array of existing state sets according to temperature and state transition probability to participate in the subsequent heat dissipation scheduling. This can effectively utilize existing data, improve analysis efficiency, and reduce computational load.

[0138] For example, for each server's BMC, the system provides the following parameters: its physical location in its environment, detection range, temperature, heat dissipation capacity, heat dissipation factor, iteration cycle, environmental influence function, excitation function, and iteration decay factor. Detailed explanations of these parameters are as follows:

[0139] The physical location of the server itself, that is, its relative position within the entire server cluster.

[0140] The detection range indicates the search range that BMC will use to search for data information in other locations during future iterations.

[0141] The server BMC collects temperature information from various key locations during actual operation. However, the temperature that usually affects the heat dissipation of the server cluster is the temperature of its own exhaust vent. Therefore, the exhaust vent temperature collected by a single server BMC is taken as its own temperature.

[0142] The self-heating capacity varies depending on the type of server, meaning the efficiency of utilizing heat dissipation resources differs. This parameter is a fixed value.

[0143] The heat dissipation factor is a factor provided to the heat dissipation system controller, which will allocate heat dissipation resources by taking into account the heat dissipation factors of all swarm intelligence agents.

[0144] The iteration cycle is determined because the heat dissipation factor cannot be a perfect value from the outset. Therefore, an iterative process is set up to continuously adjust the heat dissipation factor under different states, eventually causing the heat dissipation factor under different states to converge to a reasonable value. This is the time required for each iteration.

[0145] In a clustered heat dissipation environment, strategies cannot be formulated solely based on the device's own temperature. Other servers also generate high heat, and their impact on the device gradually decreases with increasing distance. Therefore, an impact function is provided to describe this effect.

[0146] The activation function describes the feedback of the actual heat dissipation effect of the heat dissipation factor corresponding to the current state during iteration, and is used to adjust the heat dissipation factor subsequently. If the cooling effect is not achieved, the heat dissipation factor is increased; if the cooling is too fast, the heat dissipation factor is decreased until the temperature can be maintained at a reasonable value.

[0147] The iterative decay factor γ, as can be seen from the excitation function, requires reference to the values ​​under previous historical states when maintaining the heat dissipation factor. Therefore, an iterative decay factor is given to limit the influence of historical data on the current heat dissipation factor.

[0148] Figure 2 This is a schematic diagram of the control flow provided for an embodiment of this application, such as... Figure 2 As shown, the process includes: First, initialization: After the server starts, BMC begins to initialize the parameters in the above model, where its own position, detection range, heat dissipation capacity, iteration cycle, and decay factor are given by a pre-set configuration file.

[0149] Simultaneously, an array of state sets is initialized. A state set mainly contains four elements: its own temperature, heat dissipation factor, heat dissipation factor of other devices in the environment, and state transition probability. A temperature state can correspond to multiple sets of heat dissipation factors and state transition probabilities, thus forming a set. Several temperature state sets constitute the array.

[0150] Then proceed to the iteration process: first, determine which method to use for iteration.

[0151] One approach is to calculate the heat dissipation factor based on the temperature collected from the environment. This approach first calculates a preliminary heat dissipation factor after collecting its own temperature and combining it with its own heat dissipation capacity. Then, it visits the surrounding BMC nodes according to a preset range to obtain their heat dissipation factors and inputs them into the environmental influence function to finally calculate a heat dissipation factor.

[0152] Another approach is to optimize the heat dissipation factor based on past experience. A heat dissipation factor is selected from the existing array of states according to temperature and state transition probability and then used in the subsequent heat dissipation scheduling.

[0153] To ensure that the agent can explore the natural environment as much as possible, an epsilon-greedy strategy can be applied, which prioritizes the first approach in the early stages of the overall iteration, and then tends to use the second approach to optimize the existing set of states in the later stages.

[0154] Entering the heat dissipation control phase: After calculating the heat dissipation factor, the BMC will transmit the value to the heat dissipation system controller via the network, and will reserve a period of time to wait for changes in the environment.

[0155] Maintaining the state set array: After a period of time, the BMC incorporates its current temperature and previous temperatures into the activation function to calculate the performance of the heat dissipation factor under this state. Based on this, it updates the heat dissipation factor and state transition probability in the state set array. This gives the swarm intelligence the ability to self-regulate, and ultimately, each temperature state will yield a convergent solution.

[0156] Continue iterating: Repeat the iteration process until the iteration is complete.

[0157] Figure 3 This is a schematic diagram of the refrigeration control described in the embodiments of this application, such as... Figure 3 As shown, the cooling system controller operates on the hardware device that controls the cooling system and maintains a network connection with the swarm intelligence. It collects cooling factors from the swarm intelligence at regular intervals (i.e., iteration cycles) to determine the required cooling level for each part of the computer room. Based on this, it controls the temperature within the computer room.

[0158] In an optional embodiment, a first heat dissipation factor of the first substrate management controller is determined based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller.

[0159] A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller;

[0160] In the first iteration cycle phase, after every first preset time period, the second self-temperature information of the first substrate management controller is re-acquired;

[0161] Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the first preset iteration condition is met, the iteration is completed, and the second iteration stage is entered.

[0162] In the second iteration cycle phase, after every second preset time period, the third self-temperature information of the first substrate management controller is re-acquired;

[0163] In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor;

[0164] Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed.

[0165] Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

[0166] The heat dissipation control device provided by the present invention is described below. The heat dissipation control device described below can be referred to in correspondence with the heat dissipation control method described above.

[0167] Figure 4 This is a schematic diagram of the heat dissipation control device provided in the embodiments of this application, as shown below. Figure 4 As shown, it includes:

[0168] The first determining module 410 is used to determine the first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller.

[0169] The second determining module 420 is used to determine a third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each second substrate management controller;

[0170] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0171] The heat dissipation control module 430 is used to perform heat dissipation control based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0172] According to a heat dissipation control device provided by the present invention, the second determining module is specifically used for:

[0173] Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained;

[0174] The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers;

[0175] A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

[0176] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0177] Every first preset time period, the second self-temperature information of the first substrate management controller is re-collected;

[0178] Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the preset iteration conditions are met, and the iteration is completed.

[0179] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0180] Based on the second self-temperature information and the preset excitation function, determine the state transition probability corresponding to the third heat dissipation factor;

[0181] The state transition probability, the third heat dissipation factor, and the first self-temperature information are stored as a set of target state information.

[0182] According to a heat dissipation control device provided by the present invention, the device is further used for:

[0183] After each of the first preset time intervals, the third self-temperature information of the first substrate management controller is re-collected;

[0184] In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor;

[0185] Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed.

[0186] Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

[0187] According to a heat dissipation control device provided by the present invention, the method for calculating the first heat dissipation factor specifically includes:

[0188] F pirme =T 2 / A+C;

[0189] Among them, F pirme Let T be the first heat dissipation factor, T be the first self-temperature information, A be the heat dissipation capacity information of the first substrate management controller, and C be the basic heat dissipation factor constant.

[0190] According to a heat dissipation control device provided by the present invention, the method for calculating the third heat dissipation factor specifically includes:

[0191] F final =f(F prime ,n,[g,F])

[0192]

[0193] Among them, F pirme The first heat dissipation factor is given by function f, which calculates the third heat dissipation factor F. final n represents the number of second substrate management controllers, g represents the distance between the first and second substrate management controllers, F represents the second heat dissipation factor, and i represents the i-th second substrate management controller. These are the parameters for heat dissipation in the surrounding area.

[0194] In this embodiment, after determining the first heat dissipation factor of the first baseboard management controller based on its own temperature information and heat dissipation capacity information, the influence of the second baseboard management controller around the first baseboard management controller on heat dissipation is further considered. Therefore, the second heat dissipation factor of the second baseboard management controller can be further considered to determine the third heat dissipation factor of the area. Then, heat dissipation control is carried out according to the heat dissipation control scheme corresponding to the third heat dissipation factor that can reflect the heat characteristics of the area, so as to effectively realize the precise heat dissipation control of the server.

[0195] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 5As shown, the electronic device may include a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call logic instructions in the memory 530 to execute a heat dissipation control method, which includes: determining a first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller;

[0196] A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller;

[0197] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0198] Heat dissipation control is performed based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0199] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0200] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, the computer program being executed by a processor, the computer being able to execute the heat dissipation control method provided by the above methods, the method including: determining a first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller;

[0201] A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller;

[0202] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0203] Heat dissipation control is performed based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0204] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the heat dissipation control method provided by the above methods, the method comprising: determining a first heat dissipation factor of the first substrate management controller based on first self-temperature information of the first substrate management controller and heat dissipation capacity information of the first substrate management controller;

[0205] A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller;

[0206] Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller;

[0207] Heat dissipation control is performed based on the heat dissipation control scheme corresponding to the third heat dissipation factor.

[0208] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0209] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0210] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A heat dissipation control method, characterized in that, include: Based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller, the first heat dissipation factor of the first substrate management controller is determined. A third heat dissipation factor is determined based on the first heat dissipation factor and the second heat dissipation factor of each second baseboard management controller; Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller; Heat dissipation control is performed based on the heat dissipation control scheme corresponding to the third heat dissipation factor. The determination of the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factors of each of the second substrate management controllers includes: Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained; The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers; A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

2. The heat dissipation control method according to claim 1, characterized in that, After the step of determining the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factors of each of the second substrate management controllers, the method further includes: Every first preset time period, the second self-temperature information of the first substrate management controller is re-collected; Based on the second self-temperature information and each of the second heat dissipation factors, a fourth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fourth heat dissipation factor until the preset iteration conditions are met, and the iteration is completed.

3. The heat dissipation control method according to claim 2, characterized in that, After the step of re-acquiring the second self-temperature information of the first substrate management controller, the method further includes: Based on the second self-temperature information and the preset excitation function, determine the state transition probability corresponding to the third heat dissipation factor; The state transition probability, the third heat dissipation factor, and the first self-temperature information are stored as a set of target state information.

4. The heat dissipation control method according to claim 3, characterized in that, After determining the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each of the second substrate management controllers, After each of the first preset time intervals, the third self-temperature information of the first substrate management controller is re-collected; In the target state set, at least one data group corresponding to the third self-temperature information is matched; wherein, the data group includes at least one target heat dissipation factor corresponding to the third self-temperature information and a target state transition probability corresponding to the target heat dissipation factor; Based on the heat dissipation factor corresponding to the maximum target state transition probability, a fifth heat dissipation factor is determined, and heat dissipation control is performed according to the heat dissipation control scheme corresponding to the fifth heat dissipation factor until the preset iteration condition is met, and the iteration is completed. Wherein, the maximum target state transition probability is the maximum value among the target state transition probabilities.

5. The heat dissipation control method according to claim 1, characterized in that, The calculation method for the first heat dissipation factor specifically includes: ； in, As the first heat dissipation factor, For the first self-temperature information, Information on the heat dissipation capability of the first baseboard management controller. It is the basic heat dissipation factor constant.

6. The heat dissipation control method according to claim 1, characterized in that, The calculation method for the third heat dissipation factor specifically includes: ； ； in, As the first heat dissipation factor, the function The calculation is for the third heat dissipation factor. , The number of management controllers for the second baseboard. This refers to the distance information between the first substrate management controller and the second substrate management controller. As the second heat dissipation factor, Indicates the first A second baseboard management controller, These are the parameters for heat dissipation in the surrounding area.

7. A heat dissipation control device, characterized in that, include: The first determining module is used to determine the first heat dissipation factor of the first substrate management controller based on the first self-temperature information of the first substrate management controller and the heat dissipation capacity information of the first substrate management controller. The second determining module is used to determine the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factor of each second substrate management controller; Wherein, the second substrate management controller is a substrate management controller device whose positioning information is less than a first distance threshold compared with the positioning information of the first substrate management controller; The heat dissipation control module is used to perform heat dissipation control based on the heat dissipation control scheme corresponding to the third heat dissipation factor. The determination of the third heat dissipation factor based on the first heat dissipation factor and the second heat dissipation factors of each of the second substrate management controllers includes: Based on the positioning information of the first substrate management controller and the positioning information of each of the second substrate management controllers, the distance information between the first substrate management controller and the second substrate management controller is obtained; The surrounding heat dissipation parameters are determined based on the second heat dissipation factor of the second baseboard management controller, the distance information, and the number of the second baseboard management controllers; A third heat dissipation factor is determined based on the first heat dissipation factor and the surrounding heat dissipation parameters.

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

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the heat dissipation control method as described in any one of claims 1 to 6.

Images