Liquid cooling system control method and electronic equipment

Abstract

The present disclosure provides a control method and electronic equipment for a liquid cooling system, which relate to the field of computer technology. Since the liquid cooling pipelines between multiple cooling distribution units in the liquid cooling system are interconnected, when the liquid cooling system is in an operating state, by obtaining the operating data of at least one cooling distribution unit among the multiple cooling distribution units, the load resources and coolant resources between the multiple cooling distribution units can be dynamically regulated based on the operating data and the topological relationship between the multiple cooling distribution units, thereby solving the problem that each CDU in the liquid cooling system operates in isolation and cannot share load and heat dissipation resources, resulting in local overload or resource waste.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a control method for a liquid cooling system and an electronic device. Background Art

[0002] The Cooling Distribution Unit (CDU) is a core device in a liquid cooling system, primarily responsible for distributing and controlling the flow of coolant within the system, thereby efficiently removing heat generated by the equipment. However, when multiple CDUs operate in a liquid cooling system, independent control of each CDU results in isolated operation, preventing them from sharing load and cooling resources, leading to local overloads and resource waste. Summary of the Invention

[0003] The present disclosure provides a control method and electronic device for a liquid cooling system, the main purpose of which is to solve the problem that each CDU in the liquid cooling system operates in isolation and cannot share load and heat dissipation resources, resulting in local overload or resource waste.

[0004] According to a first aspect of the present disclosure, a control method for a liquid cooling system is provided. The liquid cooling system includes a plurality of cooling distribution units, and liquid cooling pipes between the plurality of cooling distribution units are interconnected. The control method includes:

[0005] When the liquid cooling system is in an operating state, obtaining operating data of at least one cooling distribution unit among the plurality of cooling distribution units;

[0006] According to the operation data and the topological relationship between the multiple cooling distribution units, the load resources and the coolant resources between the multiple cooling distribution units are dynamically regulated.

[0007] According to a second aspect of the present disclosure, there is provided an electronic device, including:

[0008] A liquid cooling system, wherein the liquid cooling system includes a plurality of cooling distribution units, and liquid cooling pipes between the plurality of cooling distribution units are interconnected;

[0009] The cooling distribution unit includes an edge computing unit, which is used to obtain the operating data of at least one cooling distribution unit among multiple cooling distribution units when the liquid cooling system is in working state, and dynamically adjust the load resources and coolant resources between the multiple cooling distribution units based on the operating data and the topological relationship between the multiple cooling distribution units.

[0010] According to a third aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0011] According to a fourth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0012] In summary, the control method of the liquid cooling system provided by the present invention, since the liquid cooling pipes between multiple cooling distribution units in the liquid cooling system are interconnected, therefore, when the liquid cooling system is in a working state, by obtaining the operating data of at least one cooling distribution unit among the multiple cooling distribution units; according to the operating data and the topological relationship between the multiple cooling distribution units, the load resources and cooling liquid resources between the multiple cooling distribution units can be dynamically adjusted, thereby solving the problem that each CDU in the liquid cooling system operates in isolation and cannot share load and heat dissipation resources, resulting in local overload or resource waste.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0015] Figure 1 A flow chart of a control method for a liquid cooling system provided in an embodiment of the present disclosure;

[0016] Figure 2 A test flow chart of an electronic device provided in an embodiment of the present disclosure;

[0017] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure;

[0018] Figure 4 A schematic diagram of a CDU dynamic control process provided by an embodiment of the present disclosure;

[0019] Figure 5 A schematic diagram of the structure of a CDU provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] The control method of the liquid cooling system and the electronic device according to the embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0022] Figure 1 A flow chart of a control method for a liquid cooling system provided in an embodiment of the present disclosure.

[0023] like Figure 1 As shown, the method comprises the following steps:

[0024] Step 101: When the liquid cooling system is in operation, obtain operating data of at least one cooling distribution unit among a plurality of cooling distribution units.

[0025] The liquid cooling system includes a plurality of cooling distribution units, and the liquid cooling pipelines between the plurality of cooling distribution units are interconnected.

[0026] The operation data refers to the relevant data generated by the cooling distribution unit during operation.

[0027] Step 102 : Dynamically adjust the load resources and coolant resources among the multiple cooling distribution units according to the operating data and the topological relationship among the multiple cooling distribution units.

[0028] The topological relationship is used to indicate the relative positional relationship between multiple cooling distribution units.

[0029] The load resource refers to the total amount of load that the cooling distribution unit needs to bear.

[0030] The coolant resource refers to the total amount of coolant in the cooling distribution unit.

[0031] In summary, the method provided by the embodiments of the present invention, since the liquid cooling pipes between multiple cooling distribution units in the liquid cooling system are interconnected, therefore, when the liquid cooling system is in working state, by obtaining the operating data of at least one cooling distribution unit among the multiple cooling distribution units; according to the operating data and the topological relationship between the multiple cooling distribution units, the load resources and cooling liquid resources between the multiple cooling distribution units can be dynamically adjusted, thereby solving the problem that each CDU in the liquid cooling system operates in isolation, cannot share load and heat dissipation resources, and causes local overload or resource waste.

[0032] It should be noted that the embodiments of the present disclosure may include multiple steps. For the convenience of description, these steps are numbered, but these numbers do not limit the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of the present disclosure do not limit this.

[0033] Furthermore, in a possible implementation of this embodiment, since the liquid cooling system can be applied to scenarios with extremely high heat dissipation requirements, such as data centers, high-performance computing (HPC), electric vehicles, and 5G base stations, the liquid cooling system can be set in the electronic equipment to achieve efficient testing and thermal management of the electronic equipment.

[0034] The electronic device may be, for example, a large-scale, distributed electronic device, including but not limited to a server cluster system, a battery module system, a multi-node power system, and the like.

[0035] For example, Figure 2 This is a test flow chart of an electronic device provided by an embodiment of the present disclosure. Figure 2 As shown, the method comprises the following steps:

[0036] Step 201: System initialization and establishment.

[0037] It should be noted that a cloud computing unit can be provided in the electronic device to implement global task planning during the testing process of the electronic device. This cloud computing unit can be, for example, a cloud server. In addition, an edge computing unit can be provided in the CDU to implement dynamic control of the CDU. This edge computing unit can be, for example, an edge controller.

[0038] In some embodiments, edge computing units in multiple CDUs can communicate with each other to exchange information, thereby ensuring the coordination and consistency between the CDUs. The multiple edge computing units can communicate with each other via the OPC UA protocol.

[0039] According to some embodiments, by setting up a ring interconnection of liquid cooling pipes of multiple CDUs in an electronic device, communication can be established between the edge controller and the cloud server, and each CDU can be controlled to self-check, thereby realizing system initialization and assembly.

[0040] Take a scenario as an example, Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present disclosure. The electronic device is a server cluster system, which includes a liquid cooling system composed of CDU1, CDU2, CDU3, and CDU4, as well as server cluster 1, server cluster 2, server cluster 3, and server cluster 4.

[0041] The primary side cooling liquid ports of CDU1, CDU2, CDU3 and CDU4 are all connected to the primary side cooling liquid pipeline (i.e. Figure 3 The primary hot liquid ports are connected to the primary hot liquid pipeline (the blue ring pipeline in the primary side pipeline). Figure 3The secondary side coolant ports are connected to the secondary side coolant pipe (the red ring pipe in the primary side pipe). Figure 3 The secondary hot liquid ports are connected to the secondary hot liquid pipeline (the blue ring pipeline in the secondary side pipeline). Figure 3 This enables ring interconnection of CDU1, CDU2, CDU3, and CDU4, sharing coolant resources and implementing a redundant switching mechanism.

[0042] Among them, the cold liquid ports of server cluster 1, server cluster 2, server cluster 3, and server cluster 4 are all connected to the secondary side cold liquid pipeline, and the hot liquid ports are all connected to the secondary side hot liquid pipeline, so that the heat generated by the server cluster can be absorbed through the coolant circulation to ensure temperature stability during the test.

[0043] In some embodiments, when controlling each CDU to self-check, the contents of the self-check include but are not limited to the liquid cooling pump group, sensor calibration, etc.

[0044] In some embodiments, when the liquid cooling pipelines of multiple CDUs are interconnected in a ring, the pipeline ports of each CDU can be connected to the corresponding ring pipeline by setting flexible pipelines and intelligent valves, thereby realizing multi-machine sharing and dynamic allocation of coolant flow and temperature.

[0045] According to some embodiments, after the system initialization is completed, the topological relationship between the multiple CDUs can also be obtained. This topological relationship can be reflected in the form of a topological relationship table for each CDU node. The content of the topological relationship table for each CDU node includes, but is not limited to, the location coordinates, load capacity, and remaining heat dissipation capacity of each CDU.

[0046] Step 202: Task issuance and bidding.

[0047] According to some embodiments, in response to receiving a test task set for an electronic device, a task allocation priority set can be determined for at least one cooling allocation unit among multiple cooling allocation units, wherein the task allocation priorities in the task allocation priority set correspond one-to-one with the test tasks in the test task set; the test task set is allocated to the multiple cooling allocation units based on the task allocation priority set; and the order in which the test tasks are executed is determined based on the task priorities corresponding to the multiple test tasks in the test task set. Therefore, the efficiency and accuracy of allocating the test task set can be improved, the accuracy of determining the order in which the test tasks are executed can be improved, and optimal task allocation for multiple CDUs can be achieved through distributed decision-making.

[0048] In some embodiments, a cloud server can send a set of test tasks to the edge computing units, allowing the edge computing units in each CDU to calculate their own task allocation priority, thereby obtaining the bid value of each CDU. Ultimately, the edge computing units in each CDU can communicate with each other and generate a task allocation plan and test task execution order based on the bid value of each CDU.

[0049] The test task set (Task Set) issued by the cloud server includes each test task's test task type, task priority, and resource requirements. Test task types include, but are not limited to, pressure test tasks and temperature test tasks. Resource requirements include, but are not limited to, coolant flow rate and pressure range.

[0050] According to some embodiments, status data of at least one of the multiple cooling distribution units can be obtained, where the status data includes at least one of load rate, remaining heat dissipation capacity, and location coordinates; a weight coefficient corresponding to the status data is determined; and a task allocation priority set for the at least one of the multiple cooling distribution units is determined based on the status data and the weight coefficient. Therefore, by comprehensively considering the CDU status data, the accuracy of task allocation priority determination can be improved, and energy consumption, test time, and temperature rise uniformity can be balanced.

[0051] In some embodiments, when the task allocation priority set is first determined, it can be determined based on the initial status data of each CDU obtained after the system is initialized in step 201. Thereafter, if the status data of the CDU changes during operation, the task allocation priority set can be re-determined based on the changed status data.

[0052] The initial state data of each CDU can be obtained from the topology relationship table of each CDU node.

[0053] In some embodiments, the task allocation priority of each CDU may be determined according to the following formula:

[0054]

[0055] Where Bidi is the task assignment priority of the i-th CDU relative to test task j. Loadi is the current load rate of the i-th CDU, and its value range can be, for example, 0-1. CoolingMargini is the remaining cooling capacity of the i-th CDU, and its unit can be, for example, kW. Distancei,j is the physical distance between the location coordinates of the i-th CDU and the location coordinates of test task j; for example, if test task j is a test task for server cluster 1, then Distancei,j is the physical distance between the location coordinates of the i-th CDU and the location coordinates of server cluster 1.

[0056] Here, α, β, and γ are weight coefficients, and their values ​​are not fixed and can be adjusted according to the actual application scenario. For example, the values ​​of α, β, and γ can be dynamically adjusted through reinforcement learning. For example, the values ​​of α, β, and γ can be dynamically adjusted through a reinforcement learning model deployed on a cloud computing unit.

[0057] According to some embodiments, when allocating a test task set to multiple cooling allocation units according to a task allocation priority set, a task-CDU mapping relationship can be generated according to the task allocation priority set, and the test task set can be allocated to multiple cooling allocation units according to the task-CDU mapping relationship.

[0058] In some embodiments, the task allocation priorities in the task allocation priority set may be used as bid values, and a task-CDU bidding matrix (Task×CDU Bid Table) may be generated according to the task-CDU mapping relationship.

[0059] For example, the cloud server issues a set of test tasks including Task 1 (high voltage test) and Task 2 (temperature shock test), and each CDU calculates its own bid value. The resulting task-CDU bidding matrix is ​​as follows:

[0060] CDU-1 bids for Task 1 (Bid=0.8) and Task 2 (Bid=0.6).

[0061] CDU-2 bids for Task 1 (Bid=0.7) and Task 2 (Bid=0.9).

[0062] CDU-3 only bids for Task 2 (Bid=0.85).

[0063] Since the value of CDU-3 bidding for Task 1 is 0, it can be determined that CDU-3 does not bid for Task 1, and it is not necessary to describe it in the task-CDU bidding matrix.

[0064] Therefore, according to the task-CDU bidding matrix, a task allocation scheme is obtained, which assigns Task 1 to CDU-1 and Task 2 to CDU-2.

[0065] Step 203: Dynamic collaborative testing.

[0066] According to some embodiments, the liquid cooling system can be controlled to execute a set of test tasks in the order of test task execution so that the liquid cooling system is in a working state, and while the liquid cooling system is in a working state, the operating data of at least one cooling distribution unit among the multiple cooling distribution units is obtained; based on the operating data and the topological relationship between the multiple cooling distribution units, the load resources and cooling liquid resources between the multiple cooling distribution units are dynamically adjusted.

[0067] In some embodiments, during the execution of the test task and the dynamic regulation, operation data can be collected, and the operation data includes but is not limited to pressure data, flow data, temperature data, etc.

[0068] In some embodiments, when controlling the liquid cooling system to execute a set of test tasks in a test task execution order, the operating states of multiple cooling distribution units can be controlled according to the test task execution order, the test task types, and resource requirements corresponding to the test tasks. This can improve the control effect on the CDU.

[0069] For example, when the test task type is a pressure test task, the pressure applied to the liquid cooling pipeline in the cooling distribution unit can be adjusted to the pressure range indicated by the resource demand; when the test task type is a temperature test task, the flow rate of the coolant in the liquid cooling pipeline in the cooling distribution unit can be adjusted to the coolant flow rate indicated by the resource demand.

[0070] In some embodiments, in the process of controlling the CDU to execute the corresponding test task, the CDU can be closed-loop controlled by taking the resource demand as the target value by acquiring the CDU's operation data in real time.

[0071] For example, during the stress test execution process, the CDU is controlled to apply dynamic pressure according to the assigned tasks, and pressure data and temperature data are collected synchronously. The pressure range indicated by the resource demand is used as the target value to perform closed-loop control on the CDU pressure.

[0072] According to some embodiments, when controlling the CDU to perform a corresponding test task, whether the CDU is in an abnormal state can be determined through the CDU's operating data. If the CDU is in an abnormal state, a dynamic adjustment strategy is triggered to achieve dynamic regulation of the CDU.

[0073] In some embodiments, in response to abnormal CDU temperature rise, if there is a first cooling distribution unit among multiple cooling distribution units whose temperature data change rate is greater than a change rate threshold, the coolant resource call amount can be determined, and the coolant resources of the cooling distribution units adjacent to the first cooling distribution unit can be called to the first cooling distribution unit based on the coolant resource call amount. In response to abnormal CDU load, if there is a second cooling distribution unit among multiple cooling distribution units whose pressure data is greater than a pressure data threshold, the pressure load to be taken over corresponding to the second cooling distribution unit can be determined based on the pressure data and the pressure data threshold, and the cooling distribution units adjacent to the second cooling distribution unit can be controlled to take over the pressure load to be taken over. Therefore, by interconnecting each CDU in a ring through liquid cooling pipelines during initial networking, global optimal distribution of coolant can be achieved. The high heat load CDU can preferentially call the low-temperature coolant of the adjacent node CDU, reduce the power consumption of the local pump group, and the surrounding CDUs can be synchronously pressurized to compensate, keeping the total test intensity unchanged.

[0074] In some embodiments, it is also possible to integrate the operating data of multiple CDUs and build a global thermodynamic model through federated learning to predict potential risk areas and determine corresponding dynamic adjustment strategies.

[0075] Take a scenario as an example, Figure 4 This is a flow chart of a CDU dynamic control process provided by an embodiment of the present disclosure. Figure 4 As shown, the edge controller in CDU2 detects that CDU2 is a high-heat-load CDU, experiencing both abnormal temperature rise and abnormal load. It then uses topological relationships to identify CDU2's neighboring CDUs, CDU1 and CDU3. The edge controller in CDU2 then calculates the required low-temperature coolant resource and the pressure load value to be taken over. It then notifies the edge controller in CDU1 to call the corresponding low-temperature coolant in CDU1 and notifies the edge controller in CDU3 to take over the pressure load value to be taken over by CDU2.

[0076] Step 204: Anomaly detection and fault recovery.

[0077] According to some embodiments, anomaly detection of the CDU can be implemented using an edge computing unit. The edge computing unit can filter, extract features, and perform anomaly detection on operational data. Alternatively, multiple operational data sets can be fused to create a unified real-time test data stream for filtering, feature extraction, and anomaly detection.

[0078] For example, when the edge computing unit detects that the pressure data exceeds the pressure data threshold, it can be determined that the CDU where the edge computing unit is located is in an abnormal pressure measurement state. Alternatively, when the edge computing unit detects that it has not received a communication message sent by other edge computing units for a preset period of time, it can be determined that the CDU where the edge computing unit is located is in a communication interruption state. Alternatively, when the edge computing unit detects that the conductivity of the coolant is within the abnormal conductivity range, it can be determined that the CDU where the edge computing unit is located is in an abnormal coolant leakage state.

[0079] In some embodiments, if an edge computing unit detects an anomaly in a CDU, it can automatically broadcast a fault confirmation signal from its CDU to edge computing units in other CDUs, triggering a "chain takeover" protocol to enable adjacent CDUs to take over the test tasks of the faulty CDU. It also adjusts the topological relationships between multiple CDUs, updates the test task execution order, and updates the task allocation table to ensure data continuity. Therefore, by providing a redundant switching mechanism, it can resolve the situation where a single CDU anomaly may cause overall test interruption.

[0080] That is to say, when there is a faulty cooling distribution unit among multiple cooling distribution units, the faulty cooling distribution unit can be isolated from the cooling distribution units other than the faulty cooling distribution unit among the multiple cooling distribution units, the test tasks performed by the faulty cooling distribution unit can be assigned to the cooling distribution units adjacent to the faulty cooling distribution unit, and the topological relationship and the order of execution of the test tasks can be updated.

[0081] For example, if a pump group failure is detected in CDU4, the adjacent CDUs, namely CDU3 and / or CDU5, can be controlled to initiate a takeover protocol, with CDU3 taking over the liquid cooling cycle of CDU4 and CDU5 taking over the pressure test task of CDU4.

[0082] In some embodiments, the update of the execution order of the test tasks can be implemented in the cloud computing unit to ensure that the overall progress is not affected.

[0083] In summary, the method provided in this embodiment achieves high efficiency, energy saving, reliability and intelligence in multi-machine collaborative testing by adopting technologies such as group intelligent scheduling, liquid cooling resource pooling, and decentralized fault tolerance. It can significantly improve the efficiency, reliability and safety of testing, and can provide a disruptive solution for the field of industrial testing, especially for large-scale testing scenarios with high precision and high reliability requirements. Among them, in group intelligent scheduling, by adopting collaborative scheduling based on auction mechanism and reinforcement learning, global optimal scheduling of task allocation can be achieved; in liquid cooling resource pooling, by adopting a liquid cooling interconnected network across CDUs, high heat load CDUs can dynamically call the low-temperature coolant of adjacent CDUs, thereby improving heat dissipation efficiency; in decentralized fault tolerance, by adopting a "chain takeover" protocol, when a single CDU fails, the adjacent CDU automatically takes over tasks and liquid cooling resources, thereby improving fault tolerance.

[0084] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0085] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device.

[0086] For example, the electronic device includes:

[0087] A liquid cooling system, wherein the liquid cooling system includes a plurality of cooling distribution units, and liquid cooling pipes between the plurality of cooling distribution units are interconnected;

[0088] The cooling distribution unit includes an edge computing unit, which is used to obtain the operating data of at least one cooling distribution unit among multiple cooling distribution units when the liquid cooling system is in working state, and dynamically adjust the load resources and coolant resources between the multiple cooling distribution units based on the operating data and the topological relationship between the multiple cooling distribution units.

[0089] Furthermore, the electronic device further includes:

[0090] The cloud computing unit is used to send the test task set to the edge computing unit;

[0091] The edge computing unit is also used to determine a task allocation priority set of at least one cooling distribution unit among multiple cooling distribution units in response to receiving a test task set for an electronic device, and allocate the test task set to an edge computing unit among the multiple cooling distribution units according to the task allocation priority set, wherein the task allocation priorities in the task allocation priority set correspond one-to-one to the test tasks in the test task set; determine the test task execution order according to the task priorities corresponding to the multiple test tasks in the test task set, and control the liquid cooling system to execute the test task set in the test task execution order, so that the liquid cooling system is in a working state.

[0092] Furthermore, the edge computing unit can also upload the operation data collected each time to the cloud computing unit, so that the edge computing unit can use these operation data as historical data for global task planning, that is, update the test task execution sequence; it can also update the artificial intelligence model deployed in the edge computing unit, such as the reinforcement learning model, based on the historical data.

[0093] It's important to note that edge computing units enable global task planning, historical data analysis, and AI model updates, as well as dynamic scheduling and exception-based decision-making (such as failover and resource reallocation). This allows for cloud-edge collaborative control, resolving scheduling rigidity caused by task allocation relying on preset static rules. For example, this can lead to an inability to dynamically respond to changes in the test environment (such as sudden high loads or abnormal local temperature rises). Furthermore, collaborative communication is highly efficient, resolving the issue of traditional communications being relatively simple, lacking collaborative and complementary capabilities, and struggling to meet real-time requirements.

[0094] Furthermore, the cooling distribution unit further includes a pressure regulating module, a flow regulating module, a pressure acquisition module, a temperature acquisition module and a flow acquisition module; wherein,

[0095] The pressure regulating module is used to regulate the pressure applied to the liquid cooling pipeline in the cooling distribution unit;

[0096] The flow regulating module is used to regulate the flow of the coolant in the liquid cooling pipeline in the cooling distribution unit;

[0097] The pressure acquisition module is used to collect pressure data of the liquid cooling pipeline in the cooling distribution unit;

[0098] The temperature acquisition module is used to collect temperature data of the liquid cooling pipeline in the cooling distribution unit;

[0099] The flow acquisition module is used to collect flow data of the liquid cooling pipeline in the cooling distribution unit.

[0100] According to some embodiments, the pressure acquisition module may adopt a pressure sensor, for example, the temperature acquisition module may adopt a temperature sensor, for example, and the flow acquisition module may adopt a flow sensor, for example.

[0101] Take a scenario as an example, Figure 5 This is a schematic diagram of the structure of a CDU provided by an embodiment of the present disclosure. Figure 5 As shown, the CDU includes an edge computing unit and a liquid cooling module. The liquid cooling module includes a liquid cooling pipeline. The liquid cooling pipeline includes six ports: inlet, outlet, primary side inlet, primary side outlet, secondary side inlet, and secondary side outlet. The following are provided near the ports on the liquid cooling pipeline:

[0102] Electric regulating valve, used to apply high-precision pressure and mechanical load to the liquid cooling pipeline through servo motor M;

[0103] Pressure sensor P is used to monitor the pressure data of the liquid cooling pipeline in real time. Combined with the electric regulating valve, it can achieve closed-loop control of the pressure of the liquid cooling pipeline;

[0104] Temperature sensor T, used to monitor the temperature data of the liquid cooling pipeline in real time;

[0105] Conductivity sensor F is used to monitor the conductivity data of the liquid cooling pipeline in real time.

[0106] In some embodiments, the liquid cooling module may employ a multi-stage adaptive pump assembly to adjust the coolant flow rate based on real-time pressure data. For example, a proportional-integral-derivative (PID) algorithm may be employed to adjust the coolant flow rate.

[0107] In some embodiments, when the edge computing unit detects that the CDU is a faulty CDU, it can trigger the CDU self-locking, control the liquid cooling module to self-lock, and control the electric control valve to shut down urgently to prevent abnormalities such as coolant leakage from causing damage to the equipment.

[0108] It should be noted that, for the description of the features in the embodiments corresponding to the electronic device, reference can be made to the relevant description of the embodiments corresponding to the control method of the liquid cooling system, which will not be repeated here.

[0109] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above-mentioned liquid cooling system control method embodiments when running.

[0110] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0111] An embodiment of the present disclosure further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above-mentioned liquid cooling system control method embodiments are implemented.

[0112] An embodiment of the present disclosure further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above-mentioned liquid cooling system control method embodiments are implemented.

[0113] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0114] The above is a detailed introduction to a control method for a liquid cooling system provided by the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method and core ideas of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present disclosure, several improvements and modifications can be made to the present disclosure, and these improvements and modifications also fall within the scope of protection of the claims of the present disclosure.

Claims

1. A method for controlling a liquid cooling system, characterized in that: The liquid cooling system includes a plurality of cooling distribution units, and the liquid cooling pipelines between the plurality of cooling distribution units are interconnected. The control method includes: When the liquid cooling system is in an operating state, obtaining operating data of at least one cooling distribution unit among the plurality of cooling distribution units; Dynamically regulating load resources and coolant resources among the plurality of cooling distribution units according to the operating data and the topological relationship between the plurality of cooling distribution units; The liquid cooling system is located in the electronic device, and the method further comprises: In response to receiving a test task set for the electronic device, determining a task allocation priority set for at least one cooling allocation unit among the plurality of cooling allocation units; Allocating the test task set to the plurality of cooling allocation units according to the task allocation priority set; Determining a test task execution order according to task priorities corresponding to a plurality of test tasks in the test task set, and controlling the liquid cooling system to execute the test task set according to the test task execution order, so that the liquid cooling system is in a working state; Among them, the edge computing unit of each cooling distribution unit calculates its own task allocation priority, obtains the bid value corresponding to each cooling distribution unit, and generates a task allocation plan and a test task execution order according to the bid value corresponding to each cooling distribution unit.

2. The method according to claim 1, characterized in that The task allocation priorities in the task allocation priority set correspond one-to-one to the test tasks in the test task set.

3. The method according to claim 2, characterized in that Determining a task allocation priority set of at least one cooling allocation unit among the plurality of cooling allocation units includes: Acquiring status data of at least one cooling distribution unit among the plurality of cooling distribution units, wherein the status data includes at least one of a load rate, a remaining heat dissipation capacity, and a location coordinate; A weight coefficient corresponding to the state data is determined, and a task allocation priority set of at least one cooling allocation unit among the plurality of cooling allocation units is determined based on the state data and the weight coefficient.

4. The method according to claim 2, characterized in that After controlling the liquid cooling system to execute the test task set according to the test task queue so that the liquid cooling system is in a working state, the method further includes: In the event that there is a faulty cooling distribution unit among the multiple cooling distribution units, the faulty cooling distribution unit is isolated from the cooling distribution units other than the faulty cooling distribution unit among the multiple cooling distribution units, the test task performed by the faulty cooling distribution unit is assigned to the cooling distribution unit adjacent to the faulty cooling distribution unit, and the topological relationship and the test task execution order are updated.

5. The method according to claim 2, characterized in that The controlling the liquid cooling system to execute the test task set according to the test task execution order includes: According to the test task execution order and the test task type and resource demand corresponding to the test task, the working states of the plurality of cooling distribution units are controlled.

6. The method according to claim 5, characterized in that The controlling the working states of the plurality of cooling distribution units according to the test task type and resource requirement corresponding to the test task includes: In a case where the test task type is a pressure test task, adjusting the pressure applied to the liquid cooling pipeline in the cooling distribution unit to be within the pressure range indicated by the resource demand; In a case where the test task type is a temperature test task, the flow rate of the coolant in the liquid cooling pipeline in the cooling distribution unit is adjusted to the coolant flow rate indicated by the resource demand.

7. The method according to claim 1, characterized in that The operating data includes temperature data and pressure data, and dynamically regulating the load resources and coolant resources between the multiple cooling distribution units based on the operating data and the topological relationship between the multiple cooling distribution units includes: If there is a first cooling distribution unit among the plurality of cooling distribution units whose temperature data change rate is greater than a change rate threshold, determining a coolant resource call amount, and calling coolant resources of cooling distribution units adjacent to the first cooling distribution unit to the first cooling distribution unit according to the coolant resource call amount; When there is a second cooling distribution unit among the multiple cooling distribution units whose pressure data is greater than the pressure data threshold, the pressure load to be taken over corresponding to the second cooling distribution unit is determined based on the pressure data and the pressure data threshold, and the cooling distribution unit adjacent to the second cooling distribution unit is controlled to take over the pressure load to be taken over.

8. An electronic device, characterized in that: include: A liquid cooling system, wherein the liquid cooling system includes a plurality of cooling distribution units, and the liquid cooling pipelines between the plurality of cooling distribution units are interconnected; The cooling distribution unit includes an edge computing unit, which is used to obtain operating data of at least one cooling distribution unit among the multiple cooling distribution units when the liquid cooling system is in an operating state, and dynamically regulate load resources and coolant resources between the multiple cooling distribution units based on the operating data and the topological relationship between the multiple cooling distribution units; The electronic device further includes: a cloud computing unit for sending a test task set to the edge computing unit; The edge computing unit is further configured to, in response to receiving a test task set for the electronic device, determine a task allocation priority set of at least one cooling distribution unit among the multiple cooling distribution units, and allocate the test task set to an edge computing unit among the multiple cooling distribution units according to the task allocation priority set; determine a test task execution order according to the task priorities corresponding to multiple test tasks in the test task set, and control the liquid cooling system to execute the test task set in accordance with the test task execution order, so that the liquid cooling system is in a working state; Among them, the edge computing unit of each cooling distribution unit calculates its own task allocation priority, obtains the bid value corresponding to each cooling distribution unit, and generates a task allocation plan and a test task execution order according to the bid value corresponding to each cooling distribution unit.

9. The electronic device according to claim 8, wherein: The task allocation priorities in the task allocation priority set correspond one-to-one to the test tasks in the test task set.

10. The electronic device according to claim 8, wherein The cooling distribution unit also includes a pressure regulating module, a flow regulating module, a pressure acquisition module, a temperature acquisition module and a flow acquisition module; wherein, The pressure regulating module is used to regulate the pressure applied to the liquid cooling pipeline in the cooling distribution unit; The flow regulating module is used to regulate the flow of the coolant in the liquid cooling pipeline in the cooling distribution unit; The pressure acquisition module is used to collect pressure data of the liquid cooling pipeline in the cooling distribution unit; The temperature acquisition module is used to collect temperature data of the liquid cooling pipeline in the cooling distribution unit; The flow acquisition module is used to collect flow data of the liquid cooling pipeline in the cooling distribution unit.

Images