Cold source group control system and control method for data center

Abstract

The embodiment of the present application relates to the technical field of infrastructure, and discloses a cold source group control system and method of a data center, the system comprising: a group control server, a group control controller, an AI platform, a switch and at least one refrigeration unit, the AI platform and the group control controller being in communication connection with the group control server through the switch, and the group control controller being in communication connection with the refrigeration unit; wherein the AI platform is used to calculate an energy-saving operation strategy; the AI platform is also used to receive an energy-saving control instruction, and send the energy-saving control instruction and the energy-saving operation strategy to the group control server; the group control server is used to send the energy-saving operation instruction and the energy-saving operation strategy to the group control controller; and the group control controller is used to control the refrigeration unit to work according to the energy-saving operation instruction and the energy-saving operation strategy, so that the cold source group control system enters an energy-saving operation state. Through the above manner, the embodiment of the present application can realize fine adjustment of the operation strategy of the group control system according to multiple factors.

Description

Technical Field

[0001] This invention relates to the field of infrastructure technology, specifically to a cold source group control system and control method for a data center. Background Technology

[0002] A central air conditioning system consists of one or more cold and heat source group control systems and multiple air conditioning systems. The cold source group control system is the most crucial part of the central air conditioning system. It includes all the hardware equipment in the central air conditioning system's computer room and connects these devices through effective logical relationships. The system adjusts the equipment according to changes in the terminal load, which is more conducive to energy saving and equipment management.

[0003] Traditional control logic in existing technologies considers three operating conditions: refrigeration system cooling mode, partial natural cooling mode, and complete natural cooling mode. While this provides some guidance for energy-saving operation of cold source systems, it remains a basic energy-saving strategy and cannot be finely adjusted based on other factors, such as outdoor environmental factors, thus failing to achieve the desired cooling effect. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a data center-based cold source group control system and control method, which overcomes the problem that traditional operating strategies cannot be finely adjusted based on other factors.

[0005] According to one aspect of the present invention, a data center cooling source group control system is provided, including a group control server, a group control controller, an AI platform, a switch, and at least one cooling unit. The AI ​​platform and the group control controller are communicatively connected to the group control server via the switch, and the group control controller is communicatively connected to the cooling unit. The AI ​​platform is used to calculate energy-saving operation strategies; The AI ​​platform is further configured to receive energy-saving operation instructions and send the energy-saving operation instructions and the energy-saving operation strategy to the group control server; the group control server is configured to send the energy-saving operation instructions and the energy-saving operation strategy to the group control controller; the group control controller is configured to control the operation of the refrigeration unit according to the energy-saving operation instructions and the energy-saving operation strategy, thereby causing the cold source group control system to enter an energy-saving operation state. In an optional embodiment, the AI ​​platform is configured to calculate the energy-saving operation strategy, further comprising: Receive real-time operating data and real-time operating parameters; calculate the energy-saving operation strategy based on the real-time operating data and real-time operating parameters according to the preset model.

[0006] In an alternative approach, the AI ​​platform is further configured to: detect the actual accuracy of the preset model when the cold source group control system is in an energy-saving operation state; and send an automatic operation command to the group control server when the actual accuracy is lower than the preset accuracy. The group control server is also used to: send the automatic operation command to the group control controller; The group control controller is also used to: control the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command, so that the cold source group control system switches from the energy-saving operation state to the automatic operation state, wherein the automatic operation strategy is pre-stored on the group control controller.

[0007] In one alternative approach, the AI ​​platform is further configured to: receive the indoor temperature value of the cold source group control system, determine whether the indoor temperature value exceeds a preset temperature threshold, and when it exceeds the preset temperature threshold, send an emergency operation command and an emergency cooling strategy to the group control server. The group control server is also used to: send the emergency operation command and the emergency cooling strategy to the group control controller; The group control controller is also used to: control the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, so that the cold source group control system enters or switches to the emergency cooling state.

[0008] In one alternative approach, the AI ​​platform is further configured to: receive the indoor temperature value of the cold source group control system, determine whether the indoor temperature value exceeds a preset temperature threshold, and when it exceeds the preset temperature threshold, send an emergency operation command and an emergency cooling strategy to the group control server. The group control server is also used to: send the emergency operation command and the emergency cooling strategy to the group control controller; The group control controller is also used to: control the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, so that the cold source group control system enters or switches to the emergency cooling state.

[0009] According to another aspect of the present invention, a control method for group control of data center cold sources is provided, comprising: AI platform computing energy-saving operation strategy; The AI ​​platform receives energy-saving operation instructions and sends the energy-saving operation instructions and the energy-saving operation strategy to the group control server; The group control server sends the energy-saving operation command and the energy-saving operation strategy to the group control controller; The group controller controls the operation of the refrigeration unit according to the energy-saving operation instructions and energy-saving operation strategies.

[0010] In one optional approach, the AI ​​platform calculates the energy-saving operation strategy by: receiving real-time operation data and real-time operating parameters; and calculating the real-time operation data and real-time operating parameters according to a preset model to obtain the energy-saving operation strategy.

[0011] In one alternative approach, when the cold source group control system is in energy-saving operation mode, the AI ​​platform detects the actual accuracy of the preset model, and when the actual accuracy is lower than the preset accuracy, sends an automatic operation command to the group control server. The group control server sends the automatic operation command to the group control controller; The group controller controls the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command, so that the cold source group control system switches from energy-saving operation mode to automatic operation mode. The automatic operation strategy is pre-stored on the group controller.

[0012] In an alternative approach, the method further includes: The AI ​​platform receives the indoor temperature value of the cold source group control system, determines whether the indoor temperature value exceeds the preset temperature threshold, and sends an emergency operation command and an emergency cooling strategy to the group control server when the indoor temperature value exceeds the preset temperature threshold. The group control server sends the emergency operation command and the emergency cooling strategy to the group control controller; The group control controller controls the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, causing the cold source group control system to enter or switch to emergency cooling state.

[0013] In an alternative approach, the method further includes: The AI ​​platform receives manual operation instructions and manual operation strategies, and sends the manual operation instructions and manual operation strategies to the group control server; The group control server sends the manual operation command and the manual operation strategy to the group control controller; The group control controller controls the operation of the refrigeration unit according to the manual operation command and the manual operation strategy, so that the cold source group control system enters or switches to manual operation mode.

[0014] This invention incorporates an AI platform and a group control controller. A switch enables communication between the AI ​​platform and the group control controller and a group control server. The group control controller communicates with at least one refrigeration unit. The AI ​​platform calculates energy-saving operation strategies. When the AI ​​platform receives an energy-saving operation command, it sends the command and strategy to the group control server. The group control server then sends the command and strategy to the group control controller located near the refrigeration unit. The group control controller then controls the refrigeration unit according to the command and strategy, putting the cold source group control system into an energy-saving operation state. This allows for more refined adjustments to the system's operation strategy. Furthermore, the AI ​​platform can also receive manual and automatic operation commands, enabling the group control controller to control the refrigeration unit according to the corresponding operation strategies. This allows the cold source group control system to switch between various operating states, making it more flexible and energy-efficient.

[0015] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of the structure of a prior art cold source group control system is shown; Figure 2 A schematic diagram of the cold source group control system provided in an embodiment of the present invention is shown; Figure 3 Another structural schematic diagram of the cold source group control system provided in an embodiment of the present invention is shown; Figure 4 A flowchart of the control method for cold source group control provided in an embodiment of the present invention is shown; Detailed Implementation Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0017] To facilitate understanding of the technical solution provided by this invention, existing cold source group control systems will be introduced first, such as... Figure 1 As shown, the existing data center cold source group control system architecture consists of a group control server, a cold storage tank unit, and multiple refrigeration units.

[0018] The group control server communicates with each refrigeration unit through a two-layer gateway structure. It contains the management software for the cold source group control system, which is mainly used for unified management of the entire cold source group control system. It collects, analyzes, and processes data from the refrigeration units, manually adjusts system operating parameters, and adjusts the system control mode. The group control server can also analyze and report data from the refrigeration units, such as alarm management, data reports, equipment information management, access control, energy efficiency management, remote equipment control, manual / automatic operation switching, and operating parameter adjustment.

[0019] Each refrigeration unit includes actuators and control devices. The actuators include electric on / off valves, electric regulating valves, chillers, cooling water pumps, cooling towers, chilled water pumps, and various sensors. The sensors include at least pressure sensors, temperature sensors, and flow sensors. The control devices include a refrigeration controller and a cold storage tank controller. The refrigeration controller is connected to the group control server through a two-layer gateway structure. The sensors collect operating data and send it to the group control server through the refrigeration controller. The refrigeration unit receives the operating parameters sent by the group control server and controls the electric on / off valves, electric regulating valves, chillers, cooling water pumps, cooling towers, and chilled water pumps to operate according to the operating parameters. For example, the operating parameters include the outlet water temperature of the chillers, the frequency of the cooling water pumps, the fan frequency of the cooling tower, and the frequency of the chilled water pumps.

[0020] The cold storage tank unit includes a cold storage tank controller and a cooling tower, cooling water pump, chiller, plate heat exchanger, electrically operated on / off valves, electrically controlled regulating valves, and various sensors connected to the controller. The cold storage tank controller is also connected to a group control server to act as an emergency cold source in the event of a mains power outage or a complete failure of the cooling units, ensuring cooling during generator startup or after cooling system recovery. The cold storage tank and the cooling units are located in the same water supply network. Under normal cooling conditions, the cooling units supply cooling to the load while simultaneously charging the cold storage tank. In the event of a failure, the cold storage tank adjusts its valves to supply cold energy to the load.

[0021] Because central air conditioning systems are large and energy-intensive, and the required cooling effect varies with the seasons, the group control server needs to collect, analyze, and process data from the refrigeration units to improve the operational efficiency of the cold source group control system. This includes manually adjusting system operating parameters and the system control mode, enabling functions such as switching between manual and automatic operation and adjusting operating parameters. To achieve this, existing group control servers use automatic operation strategies based on outdoor wet-bulb temperatures. These strategies include three cooling modes: refrigeration unit cooling mode, partial natural cooling mode, and complete natural cooling mode. For example, the partial natural cooling mode is used during seasons with moderate temperatures, where the refrigeration unit and plate heat exchanger... Combined cooling involves the return water first entering the plate heat exchanger for cooling before entering the chiller to achieve the final cooling effect. This mode primarily utilizes some natural cooling sources to achieve energy savings. The switching between the three cooling modes is determined by the outdoor wet-bulb temperature. For example, the group control server has a working condition switching logic. This logic can adjust the stabilization time of the wet-bulb temperature and the working condition switching according to different local climate conditions to achieve the three cooling modes. For example, the conditions for a partial natural cooling mode are an outdoor wet-bulb temperature below 16℃ (adjustable, corresponding to a cooling tower outlet water temperature of 20℃) and above 8℃ (adjustable), running continuously for 20 minutes (adjustable). This allows the data center's group control to automatically run three operating conditions.

[0022] Although the existing automatic operation strategy of the central data's cold source group control system takes into account the above three operating conditions and has certain guiding significance for the energy-saving operation of the cold source system, it is still a most basic energy-saving operation strategy and cannot be finely adjusted according to the outdoor environment. For example, in some natural cooling modes, it only mentions that the chiller and plate heat exchanger operate together, without giving specific chiller cooling capacity parameters. Moreover, the cold source group control system becomes a closed loop, which only considers the internal situation and cannot be adjusted in combination with other factors. For example, the automatic operation logic only considers the case of full load in the computer room and is not linked to the dynamic environmental system of the data center, so it cannot automatically respond to the case of a sudden increase in the temperature of the computer room in the cold source group control system.

[0023] Furthermore, in the existing cold source group control system architecture, the automatic operation strategy of the data center is placed in the group control server. The group control server is connected to the cooling unit through the network. According to the general construction standard, the group control server is placed between the low-voltage equipment, and the network line is relatively long. Therefore, the real-time performance of the group control server sending operating parameters to the cooling unit is easily affected by the network environment. Moreover, since the server room is opened in stages, it is inevitable to expand the low-voltage equipment in the low-voltage equipment room during the subsequent opening construction process. Misoperation during the construction process may cause network failure, at which time group control and other related commands will not be able to be issued.

[0024] In view of this, the embodiments of the present invention introduce an AI platform, which provides a more reasonable operating strategy and switches the operating state of the cold source group control system according to various factors, thereby realizing fine-tuning of the operating strategy.

[0025] The approach to finely adjusting the operating strategy in this embodiment of the invention is as follows: The AI ​​platform calculates the energy-saving operating strategy and receives control instructions based on the actual situation. When the AI ​​platform receives the energy-saving operating instruction, it sends the energy-saving operating strategy and the energy-saving operating instruction to the cold source group control system. The cold source group control system executes the energy-saving operating strategy, enabling the cold source group control system to enter a more energy-efficient operating state. The AI ​​platform can also receive other operating instructions, causing the cold source group control system to execute corresponding operating strategies and enter or switch to corresponding operating states, making the operation of the cold source group control system more refined and more energy-efficient.

[0026] See Figure 2 The architecture of the data center cold source group control system in this embodiment of the invention is as follows: Figure 1 As shown, the system includes a group control server 1, an AI platform 2, a switch 3, and at least one cooling unit 4. The AI ​​platform 2 communicates with the group control server 1 through the switch 3. For example, the AI ​​platform 2 communicates with the group control server 1 through a communication protocol and network cable of the interface. The specific communication protocol is based on the software interface of the group control server 1, such as Mdobus, OPC, BACnet, etc. The communication between the group control server 1 and the cooling unit 4 is mainly through a two-layer network structure. For example, the two-layer network structure is the TCP / IP network protocol layer and the fieldbus protocol for bottom-end devices, represented by BACnet, Modbus, OPC, etc.

[0027] The data center cold source group control system in this embodiment of the invention also includes a group control controller 5. The group control controller 5 is communicatively connected to the group control server 1 via a switch 3. The group control server 1 is also communicatively connected to the cooling unit 4. Specifically, the group control controller 5 is connected to the cooling unit 4 via hardwiring and sends operating parameters corresponding to the operating strategy to the cooling unit 4 to control the operation of the cooling unit 4. The group control controller 5 is also connected to the cooling unit 4 via a heartbeat line to determine the online status of the cooling unit 4. Group control server 1 is only responsible for receiving operating instructions and / or operating strategies sent by AI platform 2, such as energy-saving operating instructions, automatic operating instructions, and manual operating instructions, and operating strategies such as energy-saving operating strategies and manual operating strategies. Group control server 1 does not execute the operating strategies; it only needs to send the operating instructions and / or operating strategies to group control controller 5. Group control controller 5 controls the operation of cooling unit 4 according to the specific operating instructions and / or operating strategies, and stores the automatic operating strategies on group control controller 5. This forms the control logic for the automatic operation of the cold source group control system at the cooling station site. Regardless of the operating state of the cold source group control system, when the network fails and group control controller 5 cannot receive the information sent by group control server 1, group control controller 5 can automatically use the automatic operating strategy and control the operation of cooling unit 4 according to the automatic operating strategy. This avoids the situation where group control server 1 cannot issue operating strategies due to network interruption, ensuring the safe and energy-saving operation of the data center.

[0028] Based on this, the data center cold source group control system of this invention includes a group control server 1, a group control controller 5, an AI platform 2, a switch 3, and at least one cooling unit 4. The AI ​​platform 2 and the group control controller 5 are communicatively connected to the group control server 1 through the switch, and the group control controller 5 is communicatively connected to the cooling unit 4.

[0029] In this embodiment of the invention, the AI ​​platform 2 is used to calculate energy-saving operation strategies; it is also used to receive energy-saving operation instructions and send the energy-saving operation instructions and energy-saving operation strategies to the group control server 1; the group control server 1 is used to send the energy-saving operation instructions and energy-saving operation strategies to the group control controller 5; the group control controller 5 is used to control the operation of the refrigeration unit 4 according to the energy-saving operation instructions and energy-saving operation strategies, so that the cold source group control system enters the energy-saving operation state.

[0030] When the cold source group control system is first started, before the AI ​​platform 2 receives specific operating instructions, the group controller 5 in the cold source group control system will work according to the automatic operation strategy stored on it in advance. When the AI ​​platform 2 is in working state, the AI ​​platform 2 will continuously calculate the energy-saving operation strategy so that when it receives the energy-saving operation instruction, it will send the energy-saving operation instruction and the energy-saving operation strategy to the group control server 1.

[0031] It should be noted that when the cold source group control system is operating stably and in a healthy state, the AI ​​platform 2 receives the energy-saving operation command sent by the user. In one embodiment of the present invention, the user can input the energy-saving operation command on the visual editing interface provided by the AI ​​platform 2 based on experience and specific circumstances. In another embodiment of the present invention, the AI ​​platform 2 can also automatically determine whether to put the cold source group control system into an energy-saving operation state based on the operating status of the cold source group control system. When it is determined that the operating status of the cold source group control system meets the conditions for entering the energy-saving operation state, it automatically generates an energy-saving operation command and an energy-saving operation strategy and displays them to the user. For example, if the AI ​​platform 2 detects that the energy consumption required by its calculated energy-saving operation strategy is lower than the energy consumption required by the current automatic operation strategy of the cold source group control system, the AI ​​platform 2 can automatically generate an energy-saving operation command and send the energy-saving operation command to the group control server 1, or the AI ​​platform 2 can send a prompt message so that the staff can obtain the result of the AI ​​platform's judgment based on the prompt message, and the staff can decide whether to send the energy-saving operation command based on the result.

[0032] In this system, after receiving the energy-saving operation command and strategy, the group control server 1 sends them to the group control controller 5. The group control controller 5 then controls the operation of the refrigeration units according to the energy-saving operation strategy. In one embodiment of this invention, the energy-saving operation strategy includes a refrigeration unit addition / reduction strategy and corresponding energy-saving operation parameters, such as the number of chillers, cooling towers, chilled pumps, and cooling pumps, and the corresponding parameters for each chiller, cooling tower, chilled pump, and cooling pump. The group control controller 5 determines which refrigeration units are operating based on the refrigeration unit addition / reduction strategy and sends the corresponding energy-saving operation parameters to the refrigeration controller of the corresponding refrigeration unit 4. The refrigeration controller then controls the operating equipment according to the energy-saving operation parameters.

[0033] Furthermore, the AI ​​platform 2's calculation of energy-saving operation strategy further includes: receiving real-time operation data and real-time operating parameters; and calculating the real-time operation data and real-time operating parameters according to a preset model to obtain the energy-saving operation strategy.

[0034] The method of obtaining the energy-saving operation strategy by calculating real-time operating data and real-time operating parameters according to a preset model can be as follows: optimize the operating parameters of each energy consumption in the acquired real-time operating data using various energy consumption models to obtain energy-saving operating parameters and generate an energy-saving operation strategy.

[0035] In this embodiment, the preset model includes various energy consumption models, which are trained using historical operating data and historical operating parameters from the data center. These models include chiller energy consumption models, pump and fan energy consumption models, etc. The corresponding energy consumption model is an hourly energy consumption model for the air-cooled source group control system covering 8760 hours throughout the year. By changing various operating parameters of the air-cooled source group control system, such as cooling water temperature and flow rate, number and speed of cooling tower fans, chilled water temperature and flow rate, and fully utilizing outdoor weather conditions while meeting cooling demand, energy consumption data curves of the air conditioning system under different operating strategies are generated. An energy-saving algorithm is then used to optimize and output the first optimized value of the operating parameters of the air-cooled source group control system. This optimization can be achieved through artificial neural networks, deep learning algorithms, etc. Based on each energy consumption model and the first optimized value of the operating parameters, various energy consumption data curves of the air-cooled source group control system are obtained. Based on these energy consumption data curves, the energy consumption data under the minimum total energy consumption state of the air-cooled source group control system is obtained, and the corresponding second optimized value of the operating parameters is determined. An iterative optimization calculation method can be adopted, first optimizing the refrigeration side, then controlling the cooling side, and then optimizing the refrigeration side again, to finally obtain the optimized operating parameters of the entire cooling system. After obtaining the second optimized value, the second optimized value can be directly used as the energy-saving operating parameter to generate an energy-saving operating strategy. Alternatively, the energy consumption model, load rate, outdoor meteorological parameters, and the second optimized value of the operating parameters can be used to adjust the step size for different operating parameters, calculate the energy consumption data under the optimal operating condition, determine the corresponding third optimized value of the operating parameter, use the third optimized value as the energy-saving operating parameter, and generate an energy-saving operating strategy. When calculating the third optimized value, an traversal optimization algorithm can be used to calculate the third optimized value, or a genetic algorithm, particle swarm optimization algorithm, etc. can be used, which is not limited here.

[0036] Historical operating data, historical operating parameters, real-time operating data, and real-time operating parameters are collected and calculated by each cooling unit and then sent to the group control server 1, which in turn sends them to the AI ​​platform. The group control server 1 is communicatively connected to the cooling units 4. Each cooling unit 4 includes a cooling controller and electrically operated on / off valves, electrically operated regulating valves, chillers, cooling water pumps, cooling towers, chilled water pumps, and various sensors connected to the cooling controller. These sensors include at least pressure sensors, temperature sensors, and flow sensors. The cooling controller is communicatively connected to the group control server. During the operation of the data center, the sensors in each cooling unit 4 continuously collect the data center's operating data and operating parameters. The operational data includes the operating parameters of each actuator in refrigeration unit 4 and the dry-bulb and wet-bulb temperatures of the outdoor environment, such as the inlet and outlet temperatures of the chiller's cooling water, the inlet and outlet temperatures of the chilled water, the flow rate and pressure of the cooling water pump, the flow rate and pressure of the chilled water pump, etc. This operational data can be collected by various sensors. The operating parameters include the energy consumption and electrical energy of the chiller unit, the energy consumption and electrical energy and fan efficiency of the cooling tower, the energy consumption and electrical energy of the cooling water pump, the energy consumption and electrical energy of the chilled water pump, etc. The refrigeration controller sends the operational data and operating parameters to the group control server 1, and the group control server 1 sends the operational data and operating parameters to the AI ​​platform 2. The most recently received operational data and operating parameters by the AI ​​platform 2 are the real-time operational data and real-time operating parameters, while the operational data and operating parameters prior to the real-time operational data and real-time operating parameters are the historical operational data and historical operating parameters.

[0037] Energy-saving operation strategies should at least include the number of chillers, cooling towers, chilled water pumps, and cooling pumps, as well as the corresponding parameters for each chiller, cooling tower, chilled water pump, and cooling pump. For example, this includes the chilled water outlet temperature and cooling water outlet temperature of the chillers, the fan frequency of the cooling towers, the frequency of the chilled water pumps and cooling pumps, and the optimal total energy consumption. For instance, a cold source group control system might have three refrigeration units: Refrigeration Unit 1, Refrigeration Unit 2, and Refrigeration Unit 3. When the group control server 1 sends historical data information to the AI ​​platform 2, Refrigeration Units 1 and 2 are running. Upon receiving the energy-saving operation strategy sent by AI platform 2, which includes the energy-saving operation parameters for cooling unit 2 and cooling unit 3, group control server 1 sends the energy-saving operation strategy to group control controller 5. Group control controller 5 then determines that cooling unit 1 needs to stop working, cooling unit 2 needs to continue working, and cooling unit 3 needs to be started. At the same time, it sends the energy-saving operation parameters of cooling units 2 and 3 to the corresponding cooling controllers so that cooling units 2 and 3 can operate according to their respective energy-saving operation parameters.

[0038] In this embodiment, since the data center's cold source group control system operates in real time, and the preset model is trained, the preset model has a certain degree of accuracy. The AI ​​platform 2 needs to continuously adjust and improve the preset model. The preset model is trained based on historical operating data and historical operating parameters, and it considers limited situations. Based on this, the AI ​​platform 2 is also used to: detect the actual accuracy of the preset model when the cold source group control system is in energy-saving operation mode; when the actual accuracy of the preset model is lower than the preset accuracy, send an automatic operation command to the group control server 1; the group control server 1 is also used to: send the automatic operation command to the group control controller 5; the group control controller 5 is also used to: control the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command, so that the cold source group control system switches from energy-saving operation mode to automatic operation mode, wherein the automatic operation strategy is pre-stored on the group control controller 5.

[0039] In this embodiment, the actual accuracy can be determined based on the total energy consumption. Specifically, the group control server 1 sends real-time operating data and real-time operating parameters to the AI ​​platform 2. The real-time operating parameters include the actual total energy consumption of the cold source group control system. The AI ​​platform 2 calculates the preset total energy consumption required for the real-time operating data using a preset model, compares the actual total energy consumption with the preset total energy consumption calculated by the preset model, and determines the accuracy of the preset model, such as whether the preset total energy consumption is equal to or close to the actual total energy consumption. If the preset total energy consumption is not equal to or close to the actual total energy consumption, it indicates that the accuracy of the preset model is problematic. If the preset total energy consumption is divided by the actual total energy consumption and multiplied by 100%, this is taken as the actual accuracy of the preset model. A preset value is set, for example, the preset accuracy is 97%. If the actual accuracy of the preset model is lower than 97%, it is determined that the accuracy of the preset model is insufficient. Therefore, the energy-saving operation strategy obtained after calculation and optimization through the preset model is not optimal. The AI ​​platform 2 automatically sends an automatic operation command to the group control server 1. The group control server 1 sends the automatic operation command to the group control controller 5. The group control controller controls the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command of 5, so that the cold source group control system switches from the energy-saving operation state to the automatic operation state. The automatic operation strategy is pre-stored on the group control controller 5. Meanwhile, the group control server 1 will continue to send historical operating data and historical operating parameters to the AI ​​platform 2. The AI ​​platform 2 will continue to train the preset model using the historical operating data and historical operating parameters, and continuously detect the accuracy of the preset model until the actual accuracy of the preset algorithm exceeds the preset accuracy. When the AI ​​platform 2 has not received any other instructions and the cold source group control system is still in automatic operation, it will automatically reissue energy-saving operation instructions and energy-saving operation parameters to achieve the effect of self-operation of the cold source group control system.

[0040] Furthermore, before calculating the energy-saving operation strategy, AI Platform 2 also tests the preset model to determine its accuracy. If the preset model's accuracy meets the requirements, the energy-saving operation strategy is calculated. When the AI ​​platform receives an energy-saving operation command, it does not immediately send the energy-saving operation strategy and command to the group control server. Instead, it first determines if the preset model's accuracy meets the requirements. If the preset model's accuracy does not meet the requirements, the AI ​​platform will not issue the energy-saving operation strategy and command to Group Control Server 1. Instead, it generates an automatic operation command and sends it to Group Control Server 1. Group Control Server 1 then sends the automatic operation command to Group Control Controller 5. The Group Control Controller 5 controls the refrigeration unit's operation according to the automatic operation strategy corresponding to the automatic operation command, switching the cold source group control system from energy-saving operation mode to automatic operation mode. In an embodiment of the present invention, the AI ​​platform 2 is further configured to: receive the indoor temperature value of the cold source group control system, determine whether the indoor temperature value exceeds a preset temperature threshold, and when it exceeds the preset temperature threshold, send an emergency operation command and an emergency cooling strategy to the group control server; the group control server is further configured to: send the emergency operation command and the emergency cooling strategy to the group control controller 5; the group control controller 5 is further configured to: control the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, so that the cold source group control system enters or switches to the emergency cooling state.

[0041] It should be noted that AI Platform 2 connects to the data center's environmental monitoring system. This system monitors the power and environment of the computer room, such as the temperature and humidity within the cooling source control system. After AI Platform 2 connects to the environmental monitoring system, the system sends the monitored indoor temperature of the cooling source control system to AI Platform 2 in real time. Emergency cooling strategies can be pre-stored on AI Platform 2. For example, the logic for this emergency cooling strategy might be to activate all cooling units and increase their workload. Specifically, this can be pre-set by staff according to actual conditions. Through the communication connection between AI Platform 2 and the environmental monitoring system, the cooling source control system can achieve emergency cooling in the event of a sudden increase in computer room temperature.

[0042] In this embodiment, the group control server 1 also needs to monitor whether the AI ​​platform 2 malfunctions. When the AI ​​platform 2 malfunctions, the group control server 1 automatically sends an automatic operation command to the group control controller. For example, if the group control server 1 receives feedback that the transmission of historical data information failed, it determines that the AI ​​platform 2 has malfunctioned. The group control server 1 sends an automatic operation command to the group control controller, so that the group control controller 5 receives the automatic operation command and controls the cooling unit to work according to the automatic operation strategy corresponding to the automatic operation command. Similarly, the group control controller 5 will also monitor whether the group control server 1 or the network communicating with the group control server 1 malfunctions. If the group control controller 5 detects that the group control server or the communication network has malfunctioned, the group control controller 5 will automatically use the automatic operation strategy to control the cooling unit to work, causing the cold source group control system to enter or switch to automatic operation mode until it receives a new operation command and / or operation strategy from the group control server 1 again.

[0043] Specifically, when the cold source group control system enters automatic operation mode and AI platform 2 returns to normal, AI platform 2 will not immediately send energy-saving operation commands to group control server 1. However, AI platform 2 will continuously calculate energy-saving strategies, requiring staff to resend energy-saving operation commands to AI platform 2. After receiving the energy-saving operation commands, AI platform 2 will then send the energy-saving operation strategies and commands. Alternatively, AI platform 2 can also determine automatically whether to put the cold source group control system into energy-saving operation mode based on its operating status. When it determines that the operating status of the cold source group control system meets the conditions for entering energy-saving operation mode, it will automatically send energy-saving operation commands and strategies. Alternatively, AI platform 2 can send a prompt message to inform staff of its judgment result, allowing staff to decide whether to send energy-saving operation commands based on that result.

[0044] Furthermore, to make the cold source group control system easier to adjust, the AI ​​platform 2 is also used to: receive manual operation instructions and manual operation strategies, and send the manual operation instructions and manual operation strategies to the group control server; the group control server 1 sends the manual operation instructions and manual operation strategies to the group control controller 5; the group control controller 5 controls the operation of the refrigeration unit according to the manual operation instructions and manual operation strategies, so that the cold source group control system enters or switches to manual operation mode.

[0045] It should be noted that the manual operation strategy is generated in real time by the staff based on the site and environment of the cold source group control system and its current operating status. The AI ​​platform 2 is set up or connected to a visual editing interface, which can display the historical and current operating status of the cold source group control system. The staff can input the operating parameters of the manual operation strategy through this visual editing interface to generate the manual operation strategy, and send the manual operation strategy and manual operation instructions to the AI ​​platform 2. The AI ​​platform 2 receives the manual operation instructions and manual operation strategy.

[0046] Furthermore, such as Figure 3 As shown, to prevent the cold source group control system from malfunctioning due to a failure of either the group control server 1 or the group control controller 5, two mutually redundant group control servers 1 and two mutually redundant group control controllers 5 are configured. Each group control server 1 and each group control controller 5 has the same function. The switches include an AI switch and a group control interactive unit. There are two group control switches; one group control server 1 connects to one group control switch, and the AI ​​switch connects to both group control switches. The AI ​​platform communicates with the two mutually redundant group control servers through the AI ​​interactive unit. The two mutually redundant servers communicate with the two mutually redundant group control controllers through the two group control switches. The two mutually redundant group control controllers are each connected to the refrigeration unit. In this way, the AI ​​platform 2 is connected to both group control servers 1. When one group control switch or group control server 1 fails, the AI ​​platform can communicate with the other group control server 1 through the other group control switch, and the AI ​​platform can still interact with the group control server 1. Similarly, when one of the group control switches or group control servers fails, the group control controller can communicate with the group control server 11 through another group control switch, and the group control controller can still interact with the group control server 1. The two mutually backup group control servers 1 and the two mutually backup group control controllers 5 have the same function. The roles of the group control server 1, group control controller, AI platform and refrigeration unit in the cold source group control system architecture with two mutually backup group control servers 1 and two mutually backup group control controllers 5 are the same as those in the previous embodiment, and will not be repeated here.

[0047] This invention incorporates an AI platform and a group control controller. A switch enables communication between the AI ​​platform and the group control controller with a group control server. The group control controller communicates with at least one cooling unit. The AI ​​platform calculates energy-saving operation strategies and, when the cooling source group control system is operating healthily, receives energy-saving operation instructions and sends these instructions and strategies to the group control server. The group control server then sends these instructions and strategies to the group control controller. The group control controller controls the cooling units according to these instructions and strategies. This fine-tuning of the operation strategy ensures the energy efficiency of the data center. Furthermore, the AI ​​platform can receive additional operation instructions and / or strategies based on multiple factors and send them to the group control controller via the group control server. This allows the group control controller to control the cooling units according to automatic operation strategies, enabling the cooling source group control system to switch to different operating states. The group control controller executes the specific operation strategies and pre-stores existing automatic operation logic. This ensures that the group control server can operate according to the automatic operation logic even in the event of a network failure, guaranteeing the security of the data center.

[0048] Corresponding to the data center cold source group control system provided in the above embodiments, this invention also provides a control method for data center cold source group control, such as... Figure 4 As shown, the method includes the following steps: Step 110: The AI ​​platform calculates energy-saving operation strategies.

[0049] It should be noted that the AI ​​platform's calculation of the energy-saving operation strategy includes: inputting the real-time operating data and real-time operating parameters into a preset energy-saving model to obtain the energy-saving operation strategy. Specifically, before calculating the energy-saving operation strategy, the AI ​​platform further includes: each refrigeration unit sending its real-time operating data and real-time operating parameters to the group control server; the group control server then sends all real-time operating data and real-time operating parameters to the AI ​​platform, enabling the AI ​​platform to input the real-time operating data into the preset model to obtain the energy-saving operation strategy.

[0050] Step 120: The AI ​​platform receives the energy-saving operation instruction and sends the energy-saving operation instruction and the energy-saving operation strategy to the group control server.

[0051] Step 130: The group control server sends the energy-saving operation command and the energy-saving operation strategy to the group control controller; Step 140: The group controller controls the operation of the refrigeration unit according to the energy-saving operation command and energy-saving operation strategy.

[0052] Furthermore, when the cold source group control system is in energy-saving operation mode, the AI ​​platform detects the accuracy of the preset model. When the actual accuracy of the preset algorithm is lower than the preset accuracy, it sends an automatic operation command to the group control server. The group control server sends the automatic operation command to the group control controller. The group control controller controls the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command, so that the cold source group control system switches from energy-saving operation mode to automatic operation mode. The automatic operation strategy is pre-stored on the group control controller.

[0053] In one alternative approach, the method further includes: the AI ​​platform receiving the indoor temperature value of the cold source group control system, determining whether the indoor temperature value exceeds a preset temperature threshold, and when it exceeds the preset temperature threshold, sending an emergency operation command and an emergency cooling strategy to the group control server; the group control server sending the emergency operation command and the emergency cooling strategy to the group control controller; and the group control controller controlling the refrigeration unit to work according to the emergency operation command and the emergency cooling strategy, causing the cold source group control system to enter or switch to emergency cooling mode.

[0054] Furthermore, the group control server 1 also needs to monitor whether the AI ​​platform is malfunctioning. For example, if the group control server 1 receives feedback that the transmission of historical data failed, it determines that the AI ​​platform is malfunctioning. The method further includes: the group control server generating an automatic operation command and sending it to the group control controller; the group control controller receiving the automatic operation command and controlling the cooling unit to operate according to the automatic operation strategy corresponding to the command. Similarly, the group control controller will also monitor whether the group control server or the network communicating with it is malfunctioning. If the group control controller detects a malfunction in the group control server or the communication network, it will automatically use the automatic operation strategy to control the cooling unit to operate, causing the cold source group control system to enter or switch to automatic operation mode until it receives a new operation command and / or operation strategy from the group control server 1.

[0055] Specifically, when the cold source group control system enters automatic operation mode and AI platform 2 returns to normal, AI platform 2 will not immediately send energy-saving operation instructions to group control server 1. However, the AI ​​platform will continuously calculate energy-saving strategies, requiring staff to resend energy-saving operation instructions to the AI ​​platform. After receiving the energy-saving operation instructions, the AI ​​platform will then send the energy-saving operation strategies and instructions. Alternatively, the AI ​​platform can also determine automatically whether to put the cold source group control system into energy-saving operation mode based on its operating status. When the system's operating status meets the conditions for entering energy-saving operation mode, it will automatically send energy-saving operation instructions and strategies. Alternatively, the AI ​​platform can send a notification message to inform staff of its judgment result, allowing staff to decide whether to send energy-saving operation instructions based on that result.

[0056] Furthermore, to make the cold source group control system easier to adjust, the method also includes: the AI ​​platform receiving manual operation instructions and manual operation strategies, and sending the manual operation instructions and manual operation strategies to the group control server; the group control server sending the manual operation instructions and manual operation strategies to the group control controller; the group control controller controlling the operation of the refrigeration unit according to the manual operation instructions and manual operation strategies, causing the cold source group control system to enter or switch to manual operation mode.

[0057] It should be noted that the manual operation strategy is generated in real time by the staff based on the site and environment of the cold source group control system and its current operating status. The AI ​​platform is set up or connected to a visual editing interface, which can display the historical and current operating status of the cold source group control system. The staff can input the operating parameters of the manual operation strategy through this visual editing interface to generate the manual operation strategy, and send the manual operation strategy and manual operation instructions to the AI ​​platform. The AI ​​platform receives the manual operation instructions and manual operation strategy.

[0058] This invention incorporates an AI platform and a group control controller. The AI ​​platform calculates energy-saving operation strategies. When the cold source group control system is operating healthily, the AI ​​platform receives energy-saving operation instructions and sends these instructions and strategies to the group control server. The group control server then sends these instructions and strategies to the group control controller. The group control controller controls the cooling units according to these instructions and strategies. This fine-tuning of the operation strategy ensures the energy efficiency of the data center. Furthermore, the AI ​​platform can receive other operation instructions and / or strategies based on multiple factors and send them to the group control controller via the group control server. This allows the group control controller to control the cooling units according to automatic operation strategies, enabling the cold source group control system to switch to different operating states. The group control controller executes the specific operation strategies, and it pre-stores the original automatic operation logic. This ensures that the group control server can operate according to the automatic operation logic even in the event of a network failure, guaranteeing the security of the data center.

[0059] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0060] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0061] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0062] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0063] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0064] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A data center cold source group control system, characterized in that, The system includes a group control server, a group control controller, an AI platform, a switch, and at least one cooling unit. The AI ​​platform and the group control controller are communicatively connected to the group control server via the switch, and the group control controller is communicatively connected to the cooling unit. The AI ​​platform is used to receive real-time operating data and real-time operating parameters; and to calculate energy-saving operating strategies based on the real-time operating data and real-time operating parameters according to a preset model. When the cold source group control system is in energy-saving operation mode, the actual accuracy of the preset model is detected. When the actual accuracy is lower than the preset accuracy, an automatic operation command is sent to the group control server. The AI ​​platform is also used to receive energy-saving operation instructions and send the energy-saving operation instructions and the energy-saving operation strategy to the group control server; The group control server is used to send the energy-saving operation instructions and the energy-saving operation strategy to the group control controller, and to send the automatic operation instructions to the group control controller; the group control controller is used to control the operation of the refrigeration unit according to the energy-saving operation instructions and the energy-saving operation strategy, so that the cold source group control system enters the energy-saving operation state; and to control the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation instruction, so that the cold source group control system switches from the energy-saving operation state to the automatic operation state, wherein the automatic operation strategy is pre-stored on the group control controller.

2. The system according to claim 1, characterized in that, The AI ​​platform is also used to: receive the indoor temperature value of the cold source group control system, determine whether the indoor temperature value exceeds the preset temperature threshold, and when it exceeds the preset temperature threshold, send an emergency operation command and an emergency cooling strategy to the group control server. The group control server is also used to: send the emergency operation command and the emergency cooling strategy to the group control controller; The group control controller is also used to: control the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, so that the cold source group control system enters or switches to the emergency cooling state.

3. The system according to any one of claims 1-2, characterized in that, The AI ​​platform is also used to: receive manual operation instructions and manual operation strategies, and send the manual operation instructions and manual operation strategies to the group control server; The group control server is also used to: send the manual operation command and the manual operation strategy to the group control controller; The group control controller is also used to: control the operation of the refrigeration unit according to the manual operation command and the manual operation strategy, so that the cold source group control system enters or switches to manual operation mode.

4. A control method for group control of cold sources in a data center, characterized in that, include: The AI ​​platform receives real-time operational data and real-time operating parameters. Based on the preset model, the real-time operating data and real-time operating parameters are calculated to obtain an energy-saving operation strategy; When the cold source group control system is in energy-saving operation mode, the actual accuracy of the preset model is detected. When the actual accuracy is lower than the preset accuracy, an automatic operation command is sent to the group control server. The AI ​​platform receives energy-saving operation instructions and sends the energy-saving operation instructions and the energy-saving operation strategy to the group control server; The group control server sends the energy-saving operation command and the energy-saving operation strategy to the group control controller, and sends the automatic operation command to the group control controller; The group control controller controls the operation of the refrigeration unit according to the energy-saving operation command and energy-saving operation strategy; it controls the operation of the refrigeration unit according to the automatic operation strategy corresponding to the automatic operation command, so that the cold source group control system switches from the energy-saving operation state to the automatic operation state, wherein the automatic operation strategy is pre-stored on the group control controller.

5. The method according to claim 4, characterized in that, The method further includes: The AI ​​platform receives the indoor temperature value of the cold source group control system, determines whether the indoor temperature value exceeds the preset temperature threshold, and sends an emergency operation command and an emergency cooling strategy to the group control server when the indoor temperature value exceeds the preset temperature threshold. The group control server sends the emergency operation command and the emergency cooling strategy to the group control controller; The group control controller controls the operation of the refrigeration unit according to the emergency operation command and the emergency cooling strategy, causing the cold source group control system to enter or switch to emergency cooling state.

6. The method according to any one of claims 4-5, characterized in that, The method further includes: The AI ​​platform receives manual operation instructions and manual operation strategies, and sends the manual operation instructions and manual operation strategies to the group control server; The group control server sends the manual operation command and the manual operation strategy to the group control controller; The group control controller controls the operation of the refrigeration unit according to the manual operation command and the manual operation strategy, so that the cold source group control system enters or switches to manual operation mode.

Images