Intelligent control method for data center based on phase change liquid cooling

Abstract

The application relates to the technical field of heat dissipation, and discloses a data center intelligent control method based on phase change liquid cooling. The intelligent control method is used for switching cooling and heat dissipation modes (heat pump cooling and heat dissipation and immersion cooling and heat dissipation). When the heat pump cooling and heat dissipation mode is used, the jet speed of a nozzle is adjusted according to different server node surface temperatures, so that the generation of a fluid boundary film can be avoided, and the heat pump cooling and heat dissipation effect is greatly improved. When the immersion cooling and heat dissipation mode is used, the phase change cooling liquid exchange frequency is controlled according to the surface temperature, so that the server temperature change can be responded in time, and the heat dissipation advantage of the phase change liquid cooling can be fully played. In this way, the heat dissipation efficiency of the data center is effectively improved, the stable operation of the server is ensured, the overall energy consumption of the cooling system is reduced, and different use conditions can be met simultaneously.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of heat dissipation technology, and particularly relates to a data center intelligent control method based on phase change liquid cooling. BACKGROUND

[0002] With the rapid development of information technology, as the core facility of data processing and storage, the scale and complexity of data centers are growing. The server group in the data center will generate a large amount of heat during operation. If the heat cannot be dissipated in time and effectively, it will seriously affect the performance, stability and service life of the server, and even cause server failure, data loss and business interruption, and cause great losses to enterprises and society.

[0003] Traditional data center cooling methods, such as air cooling, often cannot meet the heat dissipation requirements when facing high-density and large-scale server deployment. The air cooling efficiency is relatively low, and its heat dissipation capacity will be further limited in high-temperature environments.

[0004] In recent years, phase change liquid cooling technology has been gradually applied in the field of data center cooling. Phase change liquid cooling utilizes the characteristics of phase change materials in absorbing or releasing a large amount of heat during phase change, which can more efficiently take away the heat generated by the server. However, the existing phase change liquid cooling data center cooling system has certain limitations in control. Most systems only use a single cooling mode, which cannot flexibly switch the cooling mode according to the actual temperature condition of the server, resulting in high energy consumption in some load conditions, and insufficient heat dissipation in high load conditions. SUMMARY

[0005] The main purpose of the present application is to provide a data center intelligent control method based on phase change liquid cooling, a cooling system and a storage medium, which aims to solve the technical problem that the single heat dissipation mode of the prior art data center cannot meet the heat dissipation requirements of different working conditions.

[0006] To achieve the above purpose, a data center intelligent control method based on phase change liquid cooling is provided in the embodiments of the present application, which is applied to a data center cooling system, and the method comprises:

[0007] obtaining the surface temperature of each server node in the server group of the data center;

[0008] starting the heat pump cooling and heat dissipation when the proportion of the surface temperature of each server node being less than or equal to the temperature threshold value is greater than or equal to the proportion threshold value, and controlling the nozzles to spray cold air flow at different spraying speeds during the heat pump cooling and heat dissipation process, the nozzles are arranged above each server node, and the number of nozzles corresponds to the number of server nodes;

[0009] In a case where the proportion of the surface temperatures of the server nodes being greater than the temperature threshold is greater than or equal to the proportion threshold, the immersion cooling heat dissipation is started, and the phase change cooling liquid is exchanged between the immersion pool and the storage pool according to the surface temperatures of the server nodes in the immersion cooling heat dissipation process, wherein the surface temperature and the exchange frequency are in a positive correlation.

[0010] In a possible implementation, the nozzles are controlled to spray the cold air flow at different spraying speeds according to the surface temperatures of the server nodes, including:

[0011] The surface temperature difference of each server node is determined according to the surface temperature of each server node.

[0012] In a case where the surface temperature difference of each server node is less than or equal to a preset difference value, the nozzles are controlled to spray the cold air flow at a preset spraying speed gradient to prevent the formation of a fluid boundary film on the outer surface of the server group in the data center.

[0013] In a possible implementation, after the surface temperature difference of each server node is determined according to the surface temperature of each server node, the method further includes:

[0014] In a case where the surface temperature difference of each server node is greater than a preset difference value, the data center is divided into a high-load area and a low-load area.

[0015] The heat dissipation indexes of the high-load area and the low-load area are determined according to the surface temperatures of the high-load area and the low-load area, and the heat dissipation indexes represent the heat dissipation degrees when the cold air flow is blown to the surfaces of different areas.

[0016] The spraying speeds of the nozzles corresponding to different areas are determined according to the heat dissipation indexes of the high-load area and the low-load area.

[0017] In a possible implementation, the nozzles are controlled to spray the cold air flow at different spraying speeds according to the surface temperatures of the server nodes, including:

[0018] The surface temperature difference of an adjacent server node is determined according to the surface temperature of each server node.

[0019] In a case where the surface temperature difference of the adjacent server node is less than or equal to a preset difference value, the corresponding nozzles are controlled to spray the cold air flow at a preset different spraying speed to prevent the formation of a fluid boundary film between the adjacent server nodes.

[0020] In a possible implementation, the phase change cooling liquid is exchanged between the immersion pool and the storage pool according to the surface temperatures of the server nodes, including:

[0021] The exchange frequency of the phase change cooling liquid between the immersion pool and the storage pool is determined according to the surface temperatures of the server nodes.

[0022] The phase change coolant is exchanged between the immersion pool and the storage pool according to the exchange frequency.

[0023] In a possible implementation, the storage pool comprises a storage area provided with storage micro-pipes, a deposition area arranged on both sides of the storage area, and a first power unit and a second power unit arranged on both sides of the storage pool, and the method further comprises:

[0024] After the immersion cooling heat dissipation is completed, the first power unit and the second power unit are controlled to drive the phase change coolant to the storage pool while the debris is deposited in the deposition area.

[0025] In a possible implementation, the first power unit and the second power unit are controlled to operate cooperatively, comprising:

[0026] A first load parameter and a second load parameter are determined according to the current load states of the first power unit and the second power unit.

[0027] In a case where a difference between the first load parameter and the second load parameter is greater than or equal to a load difference threshold value, a corresponding working sub-power is determined according to the first load parameter and the second load parameter.

[0028] The first power unit and the second power unit are controlled to start at the corresponding working sub-power at the same time to operate cooperatively, wherein a difference between the working sub-powers of the first power unit and the second power unit is in a positive correlation with the difference between the first load parameter and the second load parameter.

[0029] In a possible implementation, the first power unit and the second power unit are controlled to operate cooperatively, comprising:

[0030] A first load parameter and a second load parameter are determined according to the current load states of the first power unit and the second power unit.

[0031] In a case where a difference between the first load parameter and the second load parameter is less than a difference threshold value, the first power unit and the second power unit are controlled to start alternately and intermittently to operate cooperatively.

[0032] Differing from the prior art, the intelligent control method for a data center based on phase change liquid cooling provided in the embodiments of the present application first acquires the surface temperatures of the server nodes in the data center server group, and then accurately selects the cooling mode according to the surface temperatures of the server nodes. Specifically, when the proportion of the surface temperatures of the server nodes that are less than or equal to the temperature threshold is greater than or equal to the proportion threshold, the heat pump cooling is started, and the corresponding nozzles are controlled to spray the cold air flow at different spraying speeds according to the surface temperatures of the server nodes during the heat pump cooling; when the proportion of the surface temperatures of the server nodes that are greater than the temperature threshold is greater than or equal to the proportion threshold, the immersion cooling is started, and the phase change cooling liquid is exchanged between the immersion pool and the storage pool according to the surface temperatures of the server nodes during the immersion cooling, and the surface temperature and the exchange frequency are in a positive correlation. That is, the intelligent control method is used to switch the cooling modes in the present application, and when the heat pump cooling is used, the spraying speed of the nozzles is adjusted according to the surface temperatures of the different server nodes, so that the generation of the fluid boundary film can be avoided, and the effect of the heat pump cooling is greatly improved; when the immersion cooling is used, the exchange frequency of the phase change cooling liquid is controlled according to the surface temperatures, so that the server temperature change can be responded in time, and the cooling advantage of the phase change liquid cooling can be fully played. In this way, the cooling efficiency of the data center is effectively improved, the stable operation of the server is ensured, the overall energy consumption of the cooling system is reduced, and different use conditions can be met at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0034] Figure 1 The structure schematic diagram of the data center cooling system in some embodiments of the present application;

[0035] Figure 2 The flow schematic diagram of the intelligent control method for a data center based on phase change liquid cooling in some embodiments of the present application;

[0036] Figure 3 The flow schematic diagram of step S300 of the intelligent control method for a data center based on phase change liquid cooling in some embodiments of the present application;

[0037] Figure 4 The hardware structure schematic diagram of the data center cooling system in some embodiments of the present application.

[0038] The objectives, functional features and advantages of the present application will be further described with reference to the embodiments in combination with the accompanying drawings. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0040] It should be noted that all the directionality indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directionality indications also change accordingly.

[0041] In addition, the descriptions involving “first”, “second” and the like in the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by “first” and “second” can explicitly or implicitly include at least one of the features. In addition, “and / or” throughout the text includes three schemes, taking A and / or B as an example, including A technical solution, B technical solution, and A and B simultaneously satisfying the technical solution. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of a person of ordinary skill in the art, and when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor is it within the protection scope required by the present application.

[0042] With the rapid development of information technology, as the core facility of data processing and storage, the scale and complexity of data centers are growing. The server group in the data center will generate a large amount of heat during operation. If the heat cannot be dissipated in time and effectively, it will seriously affect the performance, stability and service life of the server, and even may cause server failure, data loss and business interruption, and cause huge losses to enterprises and society.

[0043] Traditional data center cooling methods, such as air cooling, often have difficulty meeting the cooling requirements when facing high-density and large-scale server deployment. The air cooling efficiency is relatively low, and its cooling capacity will be further limited in high-temperature environments.

[0044] In recent years, phase-change liquid cooling technology has been increasingly adopted in data center cooling. By leveraging the ability of phase-change materials to absorb and release large amounts of heat during phase transitions, phase-change liquid cooling can more efficiently remove heat generated by servers. However, existing data center cooling systems for phase-change liquid cooling have limitations in terms of control. Most systems employ a single cooling mode, unable to flexibly adjust cooling methods based on actual server temperature conditions. This results in excessive energy consumption under partial load conditions and insufficient heat dissipation under high load conditions.

[0045] like Figure 1 As shown, Figure 1 This is a schematic diagram of the structure of a data center cooling system in some embodiments of the present application. The data center cooling system of the present application includes an immersion tank 100, a storage tank 200, a heat pump device (not shown), a server cluster 300 located within the immersion tank 100, and a cold air flow nozzle 400 located above the server cluster 300. The immersion tank 100 is used to contain phase-change coolant. The server cluster 300 is arranged within the immersion tank 100 and can be immersed in the phase-change coolant. The cold air flow nozzle 400 is installed above the server cluster 300. The server cluster 300 includes multiple server nodes, each of which can perform data processing independently or collaboratively.

[0046] The heat pump unit comprises an evaporator, a condenser, a compressor, and a coolant that undergoes phase change within the evaporator and condenser. Its heat exchange principle utilizes existing technology. The system is equipped with an air collection fan at the evaporator of the heat pump unit to efficiently collect the cold airflow and direct it to the nozzle 400. After the cold airflow passes through the nozzle 400 and is accelerated and ejected, it forms a high-velocity cold airflow, providing strong heat dissipation and cooling for the data center's server cluster.

[0047] The storage tank 200 of the present application comprises a storage area 210, a settling area 220, a first power unit 230, and a second power unit 240. The storage area 210 is equipped with storage microtubes 250, which insulate and protect the phase-change coolant from light, effectively preventing environmental factors from adversely affecting its cooling performance. The storage area 210 utilizes a stacked arrangement of multiple layers of storage microtubes 250, which improves the storage capacity and stability of the phase-change coolant. The settling areas 220, located on either side of the storage area 210, primarily serve to settle powder particles, debris, and other debris generated during system operation, preventing them from being carried along with the coolant, thereby ensuring the coolant's cooling efficiency. The first power unit 230 and the second power unit 240 utilize liquid pumps to drive the circulation of the phase-change coolant, thereby meeting the coolant circulation requirements during immersion cooling and enabling efficient storage and management of the coolant within the storage tank.

[0048] Exemplarily, the phase change cooling liquid is R1234yf, which has comprehensive advantages in environmental compliance, thermal management efficiency, system safety, and engineering adaptability.

[0049] Thus, the data center cooling system of the present application can provide both heat pump cooling and immersion cooling.

[0050] It should be noted that an immersion cooling condenser 500 is also provided above the immersion pool 100. During immersion cooling, a large amount of heat generated by the server group 300 is conducted to the phase change cooling liquid, causing it to rapidly evaporate into a gaseous state. The gaseous phase change cooling liquid rises to the top of the immersion pool 100 and, after contacting the low-temperature immersion cooling condenser 500, undergoes a condensation phase change and is reconverted into a liquid state. The liquid cooling liquid returns to the bottom of the immersion pool 100 under the action of gravity, completing an efficient immersion cooling cycle.

[0051] As shown in Figures 1-2 The following will be described by taking the data center cooling system as an example, which executes the intelligent control method of the data center based on phase change liquid cooling. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here. Please refer to the accompanying Figure 2 The method includes the following steps S100-S300:

[0052] Step S100, obtaining the surface temperature of each server node in the data center server group;

[0053] In the present application, temperature sensors are arranged on the surfaces of each server node in the data center server group, and the surface temperature of each server node is detected by the surface-arranged temperature sensors.

[0054] Exemplarily, as shown in Figure 1 The server group includes server nodes A1-An (n≥4). Thus, temperature sensors can be arranged on the outer surfaces of the server nodes A1-An for surface temperature detection.

[0055] Step S200, starting heat pump cooling when the proportion of the surface temperature of each server node being less than or equal to a temperature threshold value is greater than or equal to a proportion threshold value, and controlling the nozzles to spray cold air flow at different spraying speeds during the heat pump cooling, the nozzles being arranged above each server node and the number of nozzles corresponding to the number of server nodes;

[0056] It can be understood that when the surface temperature of the server nodes is low as a whole, it indicates that the data center server has less demand for cooling at this time, and at this time, the relatively low-cost air cooling can be used, such as the high-speed cold air flow sprayed to the server nodes by the plurality of nozzles 400.

[0057] For example, the number of nozzles 400 corresponds to the number of server nodes, and the nozzles 400 are arranged above the server nodes.

[0058] In an embodiment of the present application, when the proportion of the surface temperature of each server node being less than or equal to the temperature threshold value is greater than or equal to the proportion threshold value, such as when the proportion of the number of server nodes with a temperature lower than 40℃ exceeds 80%, it indicates that the surface temperature of the server nodes is low as a whole, at which time the heat pump cooling is started, and the immersion cooling is turned off. When the heat pump device is started, the air collecting fan arranged at the evaporator of the heat pump device collects the cold air flow and guides the cold air flow to the nozzle 400, and the nozzle 400 sprays the cold air flow to the server group for air cooling.

[0059] It should be noted that during the air cooling of the server group, when the cold air flow is sprayed to the equipment surface, the speed of the cold air flow close to the server surface will gradually decay due to the influence of fluid viscosity. Under the same heat dissipation index, the development process of the boundary layer in different temperature regions tends to be synchronized, and then a fluid boundary film is formed near the outer surface of the server. At this time, the flow rates of the hot air flow and the cold air flow are balanced with each other, causing the fluid velocity at the boundary film to be zero, forming a stagnation layer. Since the thermal conductivity of the fluid boundary film is extremely low, it will cause the heat transfer efficiency to deteriorate sharply, resulting in a significant decrease in the heat dissipation performance.

[0060] The heat dissipation index is used to represent the heat dissipation efficiency when the cold air flow blows to the surface of different temperature regions, and its value is directly related to the object surface temperature and the cold air flow speed. Specifically, under the condition that other conditions are constant, the higher the object surface temperature, the greater the heat dissipation intensity; the greater the flow rate of the cold air flow to the object surface, the greater the heat dissipation intensity. Therefore, when the object surface temperature and the cold air flow speed are consistent, the heat dissipation index will also be relatively close. In this way, if the heat dissipation indexes of different regions of the server are consistent (the surface temperature and the cold air flow speed are close), the probability of forming a fluid boundary film on the surface will increase significantly.

[0061] In an embodiment, the nozzles spray the cold air flow at different spraying speeds according to the surface temperature of each server node, including: determining the surface temperature difference of each server node according to the surface temperature of each server node; in the case that the surface temperature difference of each server node is less than or equal to a preset difference value, controlling the nozzles to spray the cold air flow at a preset spraying speed gradient to prevent the formation of a fluid boundary film on the outer surface of the data center server group.

[0062] Specifically, first, the difference between each two server nodes is calculated, and all the obtained differences are compared with a preset difference value. If the difference between any two server nodes is less than or equal to the preset difference value, it indicates that the temperature difference between the server nodes is not obvious. For example, the temperature of server node A1 is 38℃, the temperature of server node A2 is 38.5℃, the temperature of server node A3 is 39℃, and the temperature of server node A4 is 38.6℃. At this time, the corresponding nozzles are controlled to spray cold air flow at a preset spray speed gradient, so as to ensure that the heat dissipation indexes of the server nodes are different. Since the heat dissipation indexes of the server nodes are different, the synchronism of the boundary layer is destroyed, and by destroying the synchronism of the boundary layer, the formation of the fluid boundary film can be effectively inhibited, thereby improving the heat dissipation effect of air cooling.

[0063] For example, in the case where the surface temperature difference of each server node is less than or equal to the preset difference value, taking the heat dissipation of four nozzles as an example, the spray speeds of the four nozzles are set to 10, 8, 6, and 4 respectively. In this way, the spray speeds of the corresponding nozzles form a speed gradient, thereby inhibiting the formation of the boundary film, and further improving the heat dissipation and cooling effect of air cooling.

[0064] In another embodiment, after calculating the difference between each two server nodes and comparing all the obtained differences with a preset difference value, if there is a case where the obtained difference is greater than the preset difference value, it indicates that the temperature difference between the server nodes is relatively obvious, or at least there are two server nodes with obvious temperature difference. At this time, the data center is divided into a high-load area and a low-load area. The high-load area refers to a data center with a large operation load, thereby resulting in a high heat generation. The low-load area refers to a data center with a small operation load, thereby resulting in a low heat generation. Since the heat generation of different server nodes in the data center server group is different, the spray speed of each nozzle needs to be controlled so that the heat dissipation indexes of the server nodes are different, thereby inhibiting the formation of the fluid boundary film.

[0065] Based on this, the embodiments of the present application match a higher heat dissipation index for the high-load area and a lower heat dissipation index for the low-load area according to the surface temperature distribution of the high-load area and the low-load area. On the one hand, by making the heat dissipation indexes of different load areas different, the synchronism of the boundary layer development is destroyed, thereby inhibiting the formation of the fluid boundary film from the root; on the other hand, the high heat dissipation index configuration for the high-load area ensures the efficient heat dissipation of the high-temperature area. After matching the corresponding heat dissipation indexes, the spray speed of the cold air flow corresponding to the nozzles in different areas is determined according to the heat dissipation indexes of the high-load area and the low-load area.

[0066] Exemplarily, a mathematical mapping model of the surface temperature of the server node, the heat dissipation index of the server node and the jet speed of the cold air flow can be established in advance. After the current surface temperature of the server node and the heat dissipation index of the server node are obtained, the corresponding jet speed of the cold air flow can be obtained according to the mathematical mapping model.

[0067] In other embodiments, the server nodes can also be divided into high-load areas, medium-load areas and low-load areas according to temperature difference conditions. The determination method of the jet speed of the cold air flow corresponding to different load areas is similar to the above, which will not be described here.

[0068] In another embodiment, the jet speed of the cold air flow is controlled according to the surface temperature of each server node, including: determining the surface temperature difference of adjacent server nodes according to the surface temperature of each server node; in the case that the surface temperature difference of adjacent server nodes is less than or equal to a preset difference value, controlling the corresponding nozzle to jet the cold air flow at a preset different jet speed to prevent the formation of a fluid boundary film between adjacent server nodes.

[0069] Specifically, when the temperature difference between adjacent server nodes is small (such as ≤ preset difference value), the surface temperature distribution is similar, and if the jet speed of the cold air flow at the corresponding position is similar at this time, the heat dissipation index of the adjacent server nodes is close, and a stable fluid boundary film is easy to form in the gap between the nodes. Therefore, in order to avoid the formation of a stable fluid boundary film at the node gap, the embodiment of the application controls the corresponding nozzle to jet the cold air flow at a preset different jet speed to prevent the formation of a fluid boundary film between adjacent server nodes in the case that the surface temperature difference of adjacent server nodes is less than or equal to a preset difference value.

[0070] Exemplarily, as shown in Figure 1 When it is judged by temperature detection that the temperatures of the server node A1 and the server node A2 are close, the nozzles P1 and P2 are controlled to jet the cold air flow at different preset jet speeds. For example, the jet speed of the nozzle P1 is 5, and the jet speed of the nozzle P2 is 3.

[0071] Step S300, in the case that the proportion of the surface temperature of each server node being greater than the temperature threshold value is greater than or equal to the proportion threshold value, starting the immersion cooling heat dissipation, and in the process of the immersion cooling heat dissipation, the phase change cooling liquid is exchanged between the immersion pool and the storage pool according to the surface temperature of each server node, wherein the surface temperature and the exchange frequency are in a positive correlation.

[0072] It can be understood that when the surface temperature of the server nodes is high as a whole, it indicates that the server of the data center has a strong demand for heat dissipation cooling at this time, and at this time, the immersion cooling heat dissipation mode with higher cooling efficiency can be adopted. At this time, the phase change cooling liquid can be driven and guided from the storage pool 200 to the immersion pool 100 by the first power unit 230 and / or the second power unit 240, so that the phase change cooling liquid completely immerses the server group to achieve efficient cooling.

[0073] In order to improve the cooling and heat dissipation effect of the phase change cooling liquid, the present application controls the exchange of the phase change cooling liquid between the immersion pool and the storage pool according to the surface temperature of each server node.

[0074] In an embodiment, the step of controlling the exchange of the phase change cooling liquid between the immersion pool and the storage pool according to the surface temperature of each server node comprises:

[0075] determining the exchange frequency of the phase change cooling liquid between the immersion pool and the storage pool according to the surface temperature of each server node;

[0076] controlling the exchange of the phase change cooling liquid between the immersion pool and the storage pool according to the exchange frequency.

[0077] Specifically, a mapping relationship table of surface temperature and exchange frequency can be established in advance, the average value of the surface temperature of each server node is calculated as the surface temperature of the entire server group, and after obtaining the surface temperature of the server group, the exchange frequency can be obtained according to the mapping relationship table. Then, the exchange of the phase change cooling liquid between the immersion pool and the storage pool is controlled according to the exchange frequency. Moreover, the higher the surface temperature of the server group is, the higher the exchange frequency of the phase change cooling liquid between the immersion pool and the storage pool is, so as to realize the dynamic optimization of the heat exchange efficiency.

[0078] It can be understood that the exchange and flushing process of the phase change cooling liquid in the immersion pool 100 and the storage pool 200 will cause the original residual scraps and debris in the immersion pool 100 and the storage pool 200 to fall off, and mix the metal powder and other impurities generated by flushing into the phase change cooling liquid. The metal powder or the scrap debris is easy to cause the blockage of the storage micro-pipe 250, especially when the first power unit 230 and the second power unit 240 are synchronously started to store the phase change cooling liquid, the risk of micro-pipe blockage is significantly increased. The blockage of the storage micro-pipe 250 will cause the efficiency of the phase change cooling liquid entering the immersion pool 100 to be low when the next immersion cooling heat dissipation is started, thereby affecting the immersion cooling heat dissipation efficiency.

[0079] Based on this, in an embodiment, after the end of the immersion cooling heat dissipation, the first power unit 230 and the second power unit 240 are controlled to run cooperatively to drive the phase change cooling liquid to the storage pool 200 for storage while the debris is precipitated in the precipitation area 220, thereby reducing the risk of blockage of the storage micro-pipe 250 and improving the efficiency of immersion cooling heat dissipation.

[0080] As shown in Figure 3 In an embodiment, the step of controlling the first power unit and the second power unit to run cooperatively includes:

[0081] S310, determining a first load parameter and a second load parameter according to the current load state of the first power unit and the second power unit;

[0082] S320, in the case where the difference between the first load parameter and the second load parameter is greater than or equal to a load difference threshold value, determining a corresponding working sub-power according to the first load parameter and the second load parameter;

[0083] S330, controlling the first power unit and the second power unit to start at the corresponding working sub-power at the same time to run cooperatively, wherein the difference between the working sub-power of the first power unit and the second power unit is in a positive correlation with the difference between the first load parameter and the second load parameter.

[0084] Specifically, the current load state can be the current temperature state of the first power unit and the second power unit, or the cumulative working time state of the first power unit and the second power unit. It can be understood that the higher the current temperature of the power unit, the greater the working load of the power unit. The longer the current cumulative working time of the power unit, the greater the working load of the power unit.

[0085] The embodiment of the application first determines a first load parameter and a second load parameter according to current load states of the first power unit and the second power unit, wherein the first load parameter is a load parameter of the first power unit, and the second load parameter is a load parameter of the second power unit. If a difference between the load parameter of the first power unit and the load parameter of the second power unit is greater than or equal to a load difference threshold, it indicates that the current loads of the first power unit and the second power unit are quite different, at this time, corresponding working sub-powers are determined according to the first load parameter and the second load parameter, and the power unit with a larger current load matches a smaller working sub-power, and the power unit with a smaller current load matches a larger working sub-power, and a difference between the working sub-powers of the first power unit and the second power unit is in a positive correlation with the difference between the first load parameter and the second load parameter. In this way, through the power dynamic distribution mechanism, the working loads of the two power units can be balanced, and the overall service life of the power system can be effectively prolonged. After the working sub-powers corresponding to the first power unit and the second power unit are obtained, the first power unit and the second power unit are controlled to start simultaneously at the corresponding working sub-powers to cooperatively operate. In this way, synchronous starting of the first power unit and the second power unit can quickly recycle and store the phase change cooling liquid. Moreover, due to the power output difference, the driving forces of the phase change cooling liquids on the two sides are different, and the flow rate difference formed thereby will generate a scouring effect in the storage micro-pipe 250. When the cooling liquid is synchronously injected into the storage micro-pipe 250, the scouring force can strip off impurities such as debris and metal powder attached to the pipe wall and push them to the sedimentation area to settle, thereby avoiding the risk of micro-pipe blockage and ensuring the long-term smoothness of the cooling liquid circulation passage.

[0086] For example, first, the current temperatures of the first power unit and the second power unit are detected to obtain a first temperature and a second temperature, and when the difference between the first temperature and the second temperature is large (for example, the first temperature is much larger than the second temperature), it indicates that the first power unit is overloaded, at this time, a smaller running power is allocated to the first power unit, and a larger running power is allocated to the second power unit.

[0087] As shown in another embodiment, Figure 3 the step of controlling the first power unit and the second power unit to cooperatively operate includes:

[0088] S310, determining a first load parameter and a second load parameter according to current load states of the first power unit and the second power unit;

[0089] S340, in the case where the difference between the first load parameter and the second load parameter is less than a difference threshold, controlling the first power unit and the second power unit to alternately and intermittently start to cooperatively operate.

[0090] The embodiment of the present application first determines a first load parameter and a second load parameter according to the current load states of the first power unit and the second power unit, wherein the first load parameter is the load parameter of the first power unit, and the second load parameter is the load parameter of the second power unit. If the difference between the load parameter of the first power unit and the load parameter of the second power unit is less than a load difference threshold, it indicates that the current load states of the first power unit and the second power unit are close, and if equal-power synchronous operation is adopted, although load balance can be maintained, effective flushing force cannot be generated due to insufficient flow rate difference, and it is difficult to strip the debris and metal powder attached to the inner wall of the storage micro-pipe.

[0091] Therefore, in the case that the difference between the first load parameter and the second load parameter is less than the difference threshold, the embodiment of the present application controls the two power units to alternately operate at preset time intervals, and the operating power of the first power unit or the second power unit can be the maximum power required (without power distribution). In this way, by controlling one of the power units to operate alone, flow flushing force can be formed in the storage micro-pipe 250, which can also strip the debris, metal powder and other impurities attached to the pipe wall and push them to the sedimentation area to settle, thereby avoiding the risk of micro-pipe blockage and ensuring the long-term smoothness of the cooling liquid circulation passage.

[0092] For example, first, the current temperatures of the first power unit and the second power unit are detected to obtain a first temperature and a second temperature, and when the difference between the first temperature and the second temperature is small (for example, the first temperature is the same as the second temperature), the first power unit is controlled to operate alone for 2 minutes, and then the second power unit is controlled to operate alone for 2 minutes, and the cycle is repeated.

[0093] In this way, the embodiment of the present application determines the operating mode of the two power units according to the current load states of the first power unit and the second power unit, and through the cooperative operation of the two power units, the risk of micro-pipe blockage is effectively reduced on the basis of ensuring liquid storage recovery and the overall service life of the equipment, thereby greatly improving the efficiency of immersion cooling and heat dissipation.

[0094] Based on this, the present invention provides an intelligent control method for data centers based on phase-change liquid cooling. The method first obtains the surface temperature of each server node in a data center server cluster and then accurately selects a cooling method based on the surface temperature of each server node. Specifically, when the surface temperature of each server node is less than or equal to a temperature threshold and the ratio is greater than or equal to a ratio threshold, heat pump cooling is initiated. During the heat pump cooling process, the corresponding nozzle is controlled to spray cold air at different injection speeds based on the surface temperature of each server node. When the surface temperature of each server node is greater than or equal to the ratio threshold, immersion cooling is initiated. During the immersion cooling process, the phase-change coolant is exchanged between the immersion tank and the storage tank based on the surface temperature of each server node, and the surface temperature and the exchange frequency are positively correlated. In other words, the present invention switches cooling methods through an intelligent control method. During heat pump cooling, the nozzle injection speed is adjusted according to the surface temperature of each server node, which can avoid the formation of fluid boundary film, thereby greatly improving the heat pump cooling effect. During immersion cooling, the phase-change coolant exchange frequency is controlled according to the surface temperature, which can promptly respond to server temperature changes and fully utilize the heat dissipation advantages of phase-change liquid cooling. In this way, the present application effectively improves the heat dissipation efficiency of the data center, ensures the stable operation of the server, and reduces the overall energy consumption of the cooling system.

[0095] like Figure 4 As shown, Figure 4 This is a hardware structure diagram of the data center cooling system in some embodiments of the present application. The data center cooling system provided in the embodiments of the present application also includes a memory 1000 and a processor 2000, wherein the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the data center intelligent control method based on phase change liquid cooling as described above.

[0096] The processor 2000 is configured to provide computing and control capabilities to control the data center cooling system to perform corresponding tasks, for example, to control the data center cooling system to perform the phase-change liquid cooling based intelligent control method of a data center in any of the above method embodiments. The method includes: obtaining surface temperatures of each server node in a data center server group; in a case where a proportion of the surface temperatures of each server node that is less than or equal to a temperature threshold is greater than or equal to a proportion threshold, starting heat pump cooling heat dissipation, and controlling nozzles to spray cold air flow at different spray speeds according to the surface temperatures of each server node during the heat pump cooling heat dissipation, the nozzles being arranged above each server node and the number of the nozzles corresponding to the number of the server nodes; in a case where a proportion of the surface temperatures of each server node that is greater than the temperature threshold is greater than or equal to the proportion threshold, starting immersion cooling heat dissipation, and controlling the phase-change cooling liquid to exchange between an immersion pool and a storage pool according to the surface temperatures of each server node during the immersion cooling heat dissipation, wherein the surface temperature and the exchange frequency are in a positive correlation.

[0097] The processor 2000 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; and can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0098] The memory 1000 is a non-transitory computer readable storage medium, which can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the phase-change liquid cooling based intelligent control method of a data center in the embodiments of the present application. The processor 2000 can implement the phase-change liquid cooling based intelligent control method of a data center in any of the above method embodiments by running the non-transitory software programs, instructions and modules stored in the memory 1000.

[0099] In particular, the memory 1000 can include volatile memory (VM), such as random access memory (RAM); the memory 1000 can also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or other non-transitory solid-state memory device; the memory 1000 can also include a combination of the above-mentioned types of memory.

[0100] In summary, the data center cooling system of the present application adopts the technical solutions of any one of the above-mentioned embodiments of the intelligent control method for a data center based on phase-change liquid cooling, and therefore has at least the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be described here in detail.

[0101] The embodiments of the present application also provide a computer-readable storage medium, such as a memory including program codes, which can be executed by a processor to complete the intelligent control method for a data center based on phase-change liquid cooling in the above-mentioned embodiments. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0102] The embodiments of the present application also provide a computer program product, which includes one or more program codes stored in a computer-readable storage medium. The processor of the early warning system reads the program codes from the computer-readable storage medium, and the processor executes the program codes to complete the intelligent control method for a data center based on phase-change liquid cooling provided in the above-mentioned embodiments.

[0103] Those of ordinary skill in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by program codes related to hardware, which can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disk.

[0104] It should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate units can or can not be physically separate, and the units displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0105] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0106] The above description is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made according to the inventive concept of the present application, and direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for intelligent control of a data center based on phase change liquid cooling, characterized in that, The method is applied to a data center cooling system, and comprises the following steps: Obtaining surface temperatures of each server node in a data center server group; When a proportion of the surface temperatures of each server node being less than or equal to a temperature threshold is greater than or equal to a proportion threshold, starting heat pump cooling heat dissipation, and controlling nozzles above each server node to spray cold air flow at different spraying speeds according to the surface temperatures of each server node during the heat pump cooling heat dissipation, so as to prevent a fluid boundary film from being generated on an outer surface of the data center server group, wherein the number of the nozzles corresponds to the number of the server nodes; When a proportion of the surface temperatures of each server node being greater than the temperature threshold is greater than or equal to the proportion threshold, starting immersion cooling heat dissipation, and controlling phase change cooling liquid to exchange between an immersion pool and a storage pool according to the surface temperatures of each server node during the immersion cooling heat dissipation, wherein the surface temperature and the exchange frequency are in a positive correlation; The storage pool comprises a storage area provided with storage microtubes, a deposition area provided on both sides of the storage area, and a first power unit and a second power unit provided on both sides of the storage pool, the storage microtubes are used for heat preservation and light-proof storage of the phase change cooling liquid, and the method further comprises the following steps: After the immersion cooling heat dissipation is completed, the first power unit and the second power unit are controlled to drive the phase change cooling liquid to the storage pool while the debris is deposited in the deposition area. 2.The phase change liquid cooling based data center intelligent control method of claim 1, wherein, Controlling the nozzles to spray the cold air flow at different spraying speeds according to the surface temperatures of each server node comprises the following steps: Determining surface temperature difference values of each server node according to the surface temperatures of each server node; When the surface temperature difference values of each server node are all less than or equal to a preset difference value, controlling the nozzles to spray the cold air flow at a preset spraying speed gradient so as to prevent the fluid boundary film from being generated on the outer surface of the data center server group. 3.The phase change liquid cooling based data center intelligent control method of claim 2, wherein, After the surface temperature difference values of each server node are determined according to the surface temperatures of each server node, the method further comprises the following steps: When the surface temperature difference values of each server node are greater than the preset difference value, dividing the data center into a high-load area and a low-load area; Determining corresponding heat dissipation indexes of the high-load area and the low-load area according to the surface temperatures of the high-load area and the low-load area, wherein the heat dissipation indexes represent heat dissipation degrees when the cold air flow blows to the surfaces of different areas; Determining corresponding cold air flow spraying speeds of the nozzles of different areas according to the heat dissipation indexes of the high-load area and the low-load area. 4.The phase change liquid cooling based data center intelligent control method of claim 1, wherein, Controlling the nozzles to spray the cold air flow at different spraying speeds according to the surface temperatures of each server node comprises the following steps: Determining surface temperature difference values of adjacent server nodes according to the surface temperatures of each server node; When the surface temperature difference values of the adjacent server nodes are less than or equal to a preset difference value, controlling corresponding nozzles to spray the cold air flow at preset different spraying speeds so as to prevent the fluid boundary film from being generated between the adjacent server nodes. 5.The phase change liquid cooling based data center intelligent control method of claim 1, wherein, Controlling the phase change cooling liquid to exchange between the immersion pool and the storage pool according to the surface temperatures of each server node comprises the following steps: Determining exchange frequencies of the phase change cooling liquid between the immersion pool and the storage pool according to the surface temperatures of each server node; The phase change coolant is exchanged between the immersion pool and the storage pool according to the exchange frequency. 6.The phase change liquid cooling based data center intelligent control method of claim 1, wherein, The storage area adopts a layout mode of stacking the multiple layers of storage microtubes up and down.

7. The phase change liquid cooling based data center intelligent control method of claim 6, wherein, The first power unit and the second power unit are controlled to operate cooperatively, including: determining a first load parameter and a second load parameter according to current load states of the first power unit and the second power unit; in a case where a difference between the first load parameter and the second load parameter is greater than or equal to a load difference threshold value, determining a corresponding working sub-power according to the first load parameter and the second load parameter; controlling the first power unit and the second power unit to start simultaneously at the corresponding working sub-power to operate cooperatively, wherein a difference between the working sub-power of the first power unit and the working sub-power of the second power unit is in a positive correlation with the difference between the first load parameter and the second load parameter. 8.The phase change liquid cooling based data center intelligent control method of claim 6, wherein, The first power unit and the second power unit are controlled to operate cooperatively, including: determining a first load parameter and a second load parameter according to current load states of the first power unit and the second power unit; in a case where a difference between the first load parameter and the second load parameter is less than a difference threshold value, controlling the first power unit and the second power unit to start alternately and intermittently to operate cooperatively.

Images