Control method, device, terminal and storage medium of data center refrigeration system

Abstract

The present invention provides a control method, device, terminal and storage medium for a data center refrigeration system. The refrigeration system includes a refrigeration unit and a cold storage device; the method includes: obtaining the predicted cooling demand of the data center in each time period; for each time period, determining the cooling capacity of the refrigeration unit and the cold storage device in the time period based on the predicted cooling demand and electricity price of the time period; based on the cooling capacity of the cold storage device in each time period, determining the cooling parameters of the cold storage device in each time period. The present invention can quantitatively describe the influence of the cooling capacity allocation method of a certain time period on energy saving and power consumption in the entire prediction cycle, so as to reasonably allocate the cooling ratio of the refrigeration host and the cold storage module, and on the basis of using the cold storage system to help realize peak shaving and valley filling of the power grid, it can improve the stability of the operation of the data center refrigeration system and extend the life of the cooling system.

Description

Technical Field

[0001] The present invention relates to the technical field of data center refrigeration, and in particular to a control method, device, terminal and storage medium for a data center refrigeration system. Background Art

[0002] Data centers are filled with electronic equipment such as servers, switches, and storage devices. These devices generate a lot of heat when running and require continuous cooling to ensure system reliability and help data centers improve energy efficiency and reduce energy consumption.

[0003] In order to achieve peak load shaving and valley filling, a cold storage system can be connected to the data center cooling system. During the off-peak period, the standby refrigeration unit is used to operate, and part of the cold capacity is used to supply cold to the terminal, and part of the excess cold capacity is used to charge the cold storage module.

[0004] However, the current switching standards for the refrigeration system working mode are relatively rough, and there is no quantitative evaluation of the peak-shaving and valley-filling effect after connecting to the cold storage system. If the operating characteristics of the cold storage equipment are not taken into account, the cold storage equipment is simply charged with cold during valley hours and the cold storage equipment is discharged during peak hours. The cold amount charged into the cold storage equipment during valley hours is not enough to compensate for the demand during peak hours plus the lost cold amount. Then, the cold demand may not be met during peak hours, resulting in unstable system operation, and frequent charging and discharging of cold is required, which accelerates the aging of the cold storage equipment and shortens its service life. Summary of the invention

[0005] The embodiments of the present invention provide a control method, device, terminal and storage medium for a data center refrigeration system to solve the problem of reasonable planning and scheduling of the refrigeration system.

[0006] In a first aspect, an embodiment of the present invention provides a control method for a data center refrigeration system, the refrigeration system comprising a refrigeration unit and a cold storage device; the method comprising:

[0007] Obtain the predicted cooling demand of the data center at each time period;

[0008] For each time period, the cooling capacity of the refrigeration unit and the cold storage equipment in that time period is determined based on the predicted cooling demand and electricity price in that time period;

[0009] Based on the cooling capacity of the cold storage equipment in each time period, the cooling parameters of the cold storage equipment in each time period are determined.

[0010] In a possible implementation, for each time period, the cooling capacity of the refrigeration unit and the cold storage device in the time period is determined based on the predicted cooling demand and electricity price in the time period, including:

[0011] The predicted cooling demand and electricity price in the first period, as well as the state of the cold storage equipment in the second period are input into the trained deep Q network to obtain the cooling capacity of the refrigeration unit and the cold storage equipment in the first period; wherein the first period is any period, and the second period is the period before the first period.

[0012] In one possible implementation, the state space of the deep Q network includes the predicted cooling demand, electricity price and the state of the cold storage device, the state of the cold storage device includes the cold storage capacity of the cold storage device, the action space includes the cooling capacity of the refrigeration unit and the cooling capacity of the cold storage device, and the reward function is R = f (unit price of cooling capacity);

[0013] Before the predicted cooling demand and electricity price in the first period and the state of the cold storage equipment in the second period are input into the trained deep Q network, it also includes:

[0014] Based on the reward function, the reward values ​​of the refrigeration system performing different actions in various states are calculated and stored as training samples. This step is repeated to obtain a training sample set for the refrigeration system.

[0015] The initial deep Q network is trained based on the training sample set to obtain a trained Q network.

[0016] In a possible implementation, the formula for calculating the cooling unit price is:

[0017]

[0018] Among them, P Q is the unit price of cooling capacity during the forecast period, p i is the electricity price in time period i, i = 1, 2, ..., I, I is the total number of time periods in the forecast period, η unit is the electricity-to-cooling conversion efficiency of the refrigeration unit, W i Demand is the predicted cooling demand for period i, Q i Dissipation is the amount of cooling energy lost by the cold storage equipment in period i, Q i The loss is the cooling capacity charge and discharge loss of the cold storage equipment in time period i, and Qtotal is the total cooling capacity demand in the prediction period.

[0019] In a possible implementation, the cold storage device includes a plurality of phase change material containers connected in parallel, and the cooling parameter includes the phase change material containers involved in the cooling;

[0020] Based on the cooling capacity of the cold storage equipment in each period, the cooling parameters of the cold storage equipment in each period are determined, including:

[0021] If the cold storage capacity of the cold storage device is greater than the cold supply capacity in the first period, each phase change material container is sorted according to the number of cycles, and the first N phase change material containers are selected in turn as the phase change material containers participating in the cold supply; wherein, the first period is any period, and the sum of the cold storage capacities of the first N phase change material containers is greater than or equal to the cold supply capacity of the cold storage device in the first period.

[0022] In a possible implementation, after selecting the first N phase change material containers in sequence as the phase change material containers participating in cooling, the method further includes:

[0023] The phase change material containers participating in cooling are sorted from large to small according to the cooling loss rate, and the order is used as the cooling order of the phase change material containers participating in cooling.

[0024] In a second aspect, an embodiment of the present invention provides a control device for a data center refrigeration system, the refrigeration system comprising a refrigeration unit and a cold storage device; the device comprises:

[0025] An acquisition module is used to obtain the predicted cooling demand of the data center in each time period;

[0026] An allocation module is used to determine the cooling capacity of the refrigeration unit and the cold storage device in each time period based on the predicted cooling demand and electricity price in the time period;

[0027] The control module is used to determine the cooling parameters of the cold storage device in each time period based on the cooling capacity of the cold storage device in each time period.

[0028] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0029] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0030] The embodiment of the present invention provides a control method, device, terminal and storage medium for a data center refrigeration system. By dividing the time periods, the cold load changes of the data center in different time periods within a cycle are analyzed, the predicted cooling demand of the data center in each time period is combined with the cooling characteristics of the cold storage system, the cold loss of the cold storage system in the cold storage state and the conversion loss when releasing the cold are considered, and the peak and valley time period electricity prices are used to quantify the impact of the cooling capacity allocation method in a certain time period on energy saving and power consumption in the entire prediction cycle, so as to reasonably allocate the cooling ratio of the refrigeration host and the cold storage module. On the basis of using the cold storage system to help realize peak shaving and valley filling of the power grid, the stability of the operation of the data center refrigeration system can be improved and the life of the cooling system can be extended. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0032] Figure 1 is a flow chart of an implementation method of a data center refrigeration system control method provided by an embodiment of the present invention;

[0033] Figure 2 is a schematic diagram of the structure of a control device for a data center refrigeration system provided by an embodiment of the present invention;

[0034] Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0036] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0037] See also Figure 1 , which shows a flow chart of the implementation of the control method of the data center refrigeration system provided by an embodiment of the present invention, and is described in detail as follows:

[0038] The refrigeration system comprises a refrigeration unit and a cold storage device; the method comprises:

[0039] Step 101, obtaining the predicted cooling demand of the data center in each time period.

[0040] In this embodiment, a phase change cold storage system is connected in parallel to the chilled water system of the original refrigeration unit, and the following operating modes are realized by switching the control system during operation:

[0041] Operation mode 1: The refrigeration unit directly supplies cooling, the inlet and outlet valves of the cold storage system are closed, and the unit supplies cooling in the original working mode;

[0042] Operation mode 2: The refrigeration unit supplies cold to the cold storage module while providing cold. During off-peak hours, the standby refrigeration unit is used to supply cold to the terminal, and the remaining cold is used to charge the cold storage module.

[0043] Operation mode 3: The cold storage module provides independent cooling. During peak / off-peak hours, the refrigeration host is turned off and the cold storage module is used directly to provide cooling to the terminal.

[0044] Operation mode 4: Refrigeration host and cold storage module jointly supply cooling. The refrigeration host and cold storage module distribute the cooling load in a certain proportion and operate jointly, which can not only meet the cooling demand but also reduce the power load of the refrigeration unit.

[0045] By directly switching between the above-mentioned operating modes, it can help to achieve peak load shaving and valley filling of the power system. On this basis, combining the cooling characteristics of the cold storage system with the cooling demand of the data center, and reasonably allocating the cooling ratio of the refrigeration host and the cold storage module is the key to achieving efficient and energy-saving operation.

[0046] The cooling load of a data center is relatively stable, but there will be short-term peak demands. Therefore, it is possible to analyze the changes in cooling load in different time periods within a cycle, such as a day, as well as seasonal changes. In combination with the cooling characteristics of the refrigeration unit and the cold storage equipment, the cooling ratio of the refrigeration unit and the cold storage module can be reasonably allocated to meet the cooling load demand of the data center while achieving efficient use of electrical energy.

[0047] Step 102: for each time period, determine the cooling capacity of the refrigeration unit and the cold storage device in the time period based on the predicted cooling demand and electricity price in the time period.

[0048] In this embodiment, since the cooling demand of the data center is cyclical and usually changes regularly over a period of time, a prediction cycle can be divided into multiple time periods, and the predicted cooling demand of each time period is combined with the electricity price during the peak, valley and flat power periods to select the operation mode and allocate the cooling ratio of each refrigeration unit and cold storage module. Since there are three operating states of the cold storage module, namely, charging, discharging and not operating, the cooling capacity of the cold storage device when discharging can be set to a positive value, the cooling capacity when charging can be set to a negative value, and the cooling capacity when not operating can be set to 0.

[0049] Step 103: determining cooling parameters of the cold storage device in each time period based on the cooling capacity of the cold storage device in each time period.

[0050] In this embodiment, there are currently a variety of cold storage devices, such as water storage, ice storage, and phase change storage. There are differences in the operating characteristics of various types of cold storage devices, such as the total cold storage capacity and cold release rate of the cold storage system, the efficiency during the cold charging and release process, and the water storage system may be affected by temperature stratification. In this regard, after determining the cold supply capacity of the cold storage device, the cold supply parameters of the cold storage device within the time period can be adjusted in combination with the specific characteristics of the cold storage device to achieve the effects of improving the stability of the cold supply rate and extending the life of the cooling system.

[0051] The embodiment of the present invention divides the time periods, analyzes the changes in the cooling load of the data center in different time periods within a cycle, combines the predicted cooling demand of the data center in each time period with the cooling characteristics of the cold storage system, considers the cooling loss of the cold storage system in the cold storage state and the conversion loss when releasing the cooling, and uses the peak and valley time period electricity prices to quantify the impact of the cooling capacity allocation method in a certain time period on energy saving and power consumption in the entire prediction cycle, so as to reasonably allocate the cooling ratio of the refrigeration host and the cold storage module. On the basis of using the cold storage system to help achieve peak shaving and valley filling of the power grid, it can improve the stability of the operation of the data center refrigeration system and extend the life of the cooling system.

[0052] In a possible implementation, for each time period, the cooling capacity of the refrigeration unit and the cold storage device in the time period is determined based on the predicted cooling demand and electricity price in the time period, including:

[0053] The predicted cooling demand and electricity price in the first period, as well as the state of the cold storage equipment in the second period are input into the trained deep Q network to obtain the cooling capacity of the refrigeration unit and the cold storage equipment in the first period; wherein the first period is any period, and the second period is the period before the first period.

[0054] In this embodiment, as time changes, the cold storage device will lose a certain amount of cold after being charged. At the same time, when the cold storage device releases the charged cold and provides it to the data center, there will also be a certain proportion of conversion loss. Therefore, if the cold storage device is simply charged with cold during off-peak hours and supplied with cold during peak hours, if the time interval between charging and releasing is too long, the cold loss will also be large, and a good energy-saving effect may not necessarily be achieved.

[0055] Since the cold storage state of the cold storage equipment has a continuous impact on the feasibility of subsequent cold charging and cooling release actions, that is, the cold storage state at the current moment affects the cold charging and cooling release actions at the current moment, and the cold charging and cooling release actions at the current moment will affect the cold storage state at the next moment, this embodiment selects the cooling capacity of the refrigeration unit and the cold storage equipment in the first time period through a deep Q network.

[0056] In one possible implementation, the state space of the deep Q network includes the predicted cooling demand, electricity price and the state of the cold storage device, the state of the cold storage device includes the cold storage capacity of the cold storage device, the action space includes the cooling capacity of the refrigeration unit and the cooling capacity of the cold storage device, and the reward function is R = f (unit price of cooling capacity);

[0057] Before inputting the predicted cooling demand and electricity price in the first period and the state of the cold storage equipment in the second period into the trained deep Q network, it also includes:

[0058] Based on the reward function, the reward values ​​of the refrigeration system performing different actions in various states are calculated and stored as training samples. This step is repeated to obtain a training sample set for the refrigeration system.

[0059] The initial deep Q network is trained based on the training sample set to obtain a trained Q network.

[0060] In this embodiment, the cold storage capacity of the cold storage device, the cold supply capacity of the refrigeration unit, and the cold supply capacity of the cold storage device can generate discrete states and actions in proportion. For example, the value of the cold storage capacity of the cold storage device in the state space may include {5%, 10%, 15%, 25%, 35%, 45%, 55%, 65%, 80%, 90%, 100%}, and the specific value can be set according to the actual situation. The same applies to the cold supply capacity of the refrigeration unit and the cold supply capacity of the cold storage device.

[0061] The determination of peak-valley electricity prices needs to consider the cost of power generation, transmission and distribution, and grid maintenance costs, as well as the cost differences of different power generation methods, such as fossil fuel power generation, nuclear power, and renewable energy power generation. The average cost of providing electricity in different time periods is calculated, so that users can be guided to reduce peak-time electricity consumption through higher peak-time electricity prices, and users can be encouraged to use electricity in valley hours through lower valley-time electricity prices. Therefore, peak-valley electricity prices can be used as a standard to measure the demand for power energy consumption, calculate the unit price of cooling capacity within the entire forecast period, and be used to quantify the impact of the cooling capacity allocation method in a certain time period on energy conservation and power consumption in the entire forecast period. The lower the cooling capacity unit price, the higher the calculated reward value, so as to select a cooling capacity allocation method with better peak-shaving and valley-filling effects.

[0062] In a possible implementation, the formula for calculating the cooling unit price is:

[0063]

[0064] Among them, P Q is the unit price of cooling capacity during the forecast period, p i is the electricity price in time period i, i = 1, 2, ..., I, I is the total number of time periods in the forecast period, η unit is the electricity-to-cooling conversion efficiency of the refrigeration unit, Q i Demand is the predicted cooling demand for period i, Q i Dissipation is the amount of cooling energy lost by the cold storage equipment in period i, Q i The loss is the cooling capacity charge and discharge loss of the cold storage equipment in time period i, and Qtotal is the total cooling capacity demand in the prediction period.

[0065] In this embodiment, the electric-to-cooling conversion efficiency of the refrigeration unit refers to the power consumption when the refrigeration unit supplies unit cooling capacity, and the cooling capacity charging and discharging loss refers to the difference between the cooling capacity provided by the refrigeration unit to the cold storage device and the cooling capacity provided by the cold storage device to the data center.

[0066] Since the cooling demand of the data center must be met first, and the cooling loss in the cold storage equipment is continuous, the cooling of the data center through the cold storage equipment will inevitably cause cooling loss. All of this cooling is generated by the refrigeration unit. Therefore, the cooling loss can be calculated according to the time period of cooling, and the sum of the above three can be calculated according to the time period and multiplied by the electric cooling conversion efficiency, which is the total power consumed by the refrigeration unit. Then multiply it with the electricity price of each time period to get the total electricity price in the forecast period, and then calculate the cooling unit price in the forecast period.

[0067] The calculation formulas for the cold dissipation and cold charging and discharging losses are as follows:

[0068] Cooling loss = cooling rate × duration of cooling capacity > 0

[0069] Cold energy charging and discharging loss = (1-cold energy conversion efficiency of cold storage equipment) × cold energy charging

[0070] Among them, the cooling rate and the cooling conversion efficiency of the cold storage equipment are preset values ​​set according to actual conditions.

[0071] Based on the unit price of cooling capacity within the forecast period, the cooling capacity of refrigeration units and cold storage equipment can be reasonably allocated, and the time periods of cold storage equipment charging and cooling can be adjusted to seek a balance between reducing the loss of cold storage and utilizing off-peak electricity prices.

[0072] In a possible implementation, the cold storage device includes a plurality of phase change material containers connected in parallel, and the cooling parameter includes the phase change material containers involved in the cooling;

[0073] Based on the cooling capacity of the cold storage equipment in each period, the cooling parameters of the cold storage equipment in each period are determined, including:

[0074] If the cold storage capacity of the cold storage device is greater than the cold supply capacity in the first period, each phase change material container is sorted according to the number of cycles, and the first N phase change material containers are selected in turn as the phase change material containers participating in the cold supply; wherein, the first period is any period, and the sum of the cold storage capacities of the first N phase change material containers is greater than or equal to the cold supply capacity of the cold storage device in the first period.

[0075] In this embodiment, when the cold storage capacity of the cold storage equipment is greater than the cold supply capacity in the first period, only some phase change material containers may be required to participate in the cold supply. At this time, the phase change material containers participating in the cold supply are selected according to the number of cycles, so that the number of cycles of each phase change material container can be as close as possible, and the remaining service life can be as close as possible, so as to achieve optimal utilization of resources and long-term stable operation of the system.

[0076] In a possible implementation, after selecting the first N phase change material containers in sequence as the phase change material containers participating in cooling, the method further includes:

[0077] The phase change material containers participating in cooling are sorted from large to small according to the cooling loss rate, and the order is used as the cooling order of the phase change material containers participating in cooling.

[0078] In this embodiment, if all phase change material containers contain at least two phase change materials, the cooling rates of each phase change material container may be different. The cooling rates of each phase change material container can be determined through experiments, and cooling is preferentially provided through phase change material containers with large cooling loss rates, thereby reducing the cooling time of phase change material containers with large cooling loss rates and reducing the overall cooling loss.

[0079] Similarly, when charging the cold storage equipment with cold through the refrigeration unit, the cold storage units are sorted from small to large according to the cold loss rate, and the cold charging order of each cold storage unit is used to reduce the cold dissipation time of the phase change material container with a large cold loss rate, thereby reducing the overall cold loss.

[0080] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0081] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0082] Figure 2 The structure diagram of the control device of the data center refrigeration system provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0083] like Figure 2 As shown, the refrigeration system includes a refrigeration unit and a cold storage device; the control device 2 of the data center refrigeration system includes:

[0084] An acquisition module 21 is used to obtain the predicted cooling demand of the data center in each time period;

[0085] The allocation module 22 is used to determine the cooling capacity of the refrigeration unit and the cold storage device in each time period based on the predicted cooling demand and electricity price in the time period;

[0086] The control module 23 is used to determine the cooling parameters of the cold storage device in each time period based on the cooling capacity of the cold storage device in each time period.

[0087] In a possible implementation, the allocation module 22 is specifically configured to:

[0088] The predicted cooling demand and electricity price in the first period, as well as the state of the cold storage equipment in the second period are input into the trained deep Q network to obtain the cooling capacity of the refrigeration unit and the cold storage equipment in the first period; wherein the first period is any period, and the second period is the period before the first period.

[0089] In one possible implementation, the state space of the deep Q network includes the predicted cooling demand, electricity price and the state of the cold storage device, the state of the cold storage device includes the cold storage capacity of the cold storage device, the action space includes the cooling capacity of the refrigeration unit and the cooling capacity of the cold storage device, and the reward function is R = f (unit price of cooling capacity);

[0090] The allocation module 22 is also used for:

[0091] Before inputting the predicted cooling demand and electricity price in the first period and the state of the cold storage equipment in the second period into the trained deep Q network, based on the reward function, the reward values ​​of the refrigeration system performing different actions in multiple states are calculated and stored as training samples. This step is repeated to obtain the training sample set of the refrigeration system.

[0092] The initial deep Q network is trained based on the training sample set to obtain a trained Q network.

[0093] In a possible implementation, the formula for calculating the unit price of cooling capacity is:

[0094]

[0095] Among them, P Q is the unit price of cooling capacity during the forecast period, p i is the electricity price in time period i, i = 1, 2, ..., I, I is the total number of time periods in the forecast period, η unit is the electricity-to-cooling conversion efficiency of the refrigeration unit, Q i Demand is the predicted cooling demand for period i, Q i Dissipation is the amount of cooling energy lost by the cold storage equipment in period i, Q i The loss is the cooling capacity charge and discharge loss of the cold storage equipment in time period i, and Qtotal is the total cooling capacity demand in the prediction period.

[0096] In a possible implementation, the cold storage device includes a plurality of phase change material containers connected in parallel, and the cooling parameter includes the phase change material containers involved in the cooling;

[0097] The control module 23 is specifically used for:

[0098] If the cold storage capacity of the cold storage device is greater than the cold supply capacity in the first period, each phase change material container is sorted according to the number of cycles, and the first N phase change material containers are selected in turn as the phase change material containers participating in the cold supply; wherein, the first period is any period, and the sum of the cold storage capacities of the first N phase change material containers is greater than or equal to the cold supply capacity of the cold storage device in the first period.

[0099] In a possible implementation, the control module 23 is further configured to:

[0100] After selecting the first N phase change material containers in turn as the phase change material containers participating in cooling, the phase change material containers participating in cooling are sorted from large to small according to the cold loss rate, and the order is used as the cooling order of the phase change material containers participating in cooling.

[0101] The embodiment of the present invention divides the time periods, analyzes the changes in the cooling load of the data center in different time periods within a cycle, combines the predicted cooling demand of the data center in each time period with the cooling characteristics of the cold storage system, considers the cooling loss of the cold storage system in the cold storage state and the conversion loss when releasing the cooling, and uses the peak and valley time period electricity prices to quantify the impact of the cooling capacity allocation method in a certain time period on energy saving and power consumption in the entire prediction cycle, so as to reasonably allocate the cooling ratio of the refrigeration host and the cold storage module. On the basis of using the cold storage system to help achieve peak shaving and valley filling of the power grid, it can improve the stability of the operation of the data center refrigeration system and extend the life of the cooling system.

[0102] Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 3 As shown, the terminal 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned control method of each data center cooling system are implemented, for example Figure 1 Alternatively, when the processor 30 executes the computer program 32, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 2 Functions of modules / units 21 to 23 are shown.

[0103] Exemplarily, the computer program 32 may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 32 in the terminal 3. For example, the computer program 32 may be divided into Figure 2 Modules / units 21 to 23 are shown.

[0104] The terminal 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of terminal 3 and does not constitute a limitation on terminal 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0105] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0106] The memory 31 may be an internal storage unit of the terminal 3, such as a hard disk or memory of the terminal 3. The memory 31 may also be an external storage device of the terminal 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 3. Further, the memory 31 may also include both an internal storage unit of the terminal 3 and an external storage device. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0107] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0108] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0110] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the control method embodiments of the above-mentioned data center refrigeration system can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A control method for a data center refrigeration system, characterized in that: The refrigeration system comprises a refrigeration unit and a cold storage device; the method comprises: Obtain the predicted cooling demand of the data center at each time period; For each time period, determining the cooling capacity of the refrigeration unit and the cold storage device in the time period based on the predicted cooling demand and electricity price in the time period; Based on the cooling capacity of the cold storage device in each time period, the cooling parameters of the cold storage device in each time period are determined.

2. The control method of a data center refrigeration system according to claim 1, characterized in that: The method of determining the cooling capacity of the refrigeration unit and the cold storage device in each time period based on the predicted cooling capacity demand and electricity price in the time period includes: The predicted cooling demand and electricity price in the first time period and the state of the cold storage device in the second time period are input into the trained deep Q network to obtain the cooling capacity of the refrigeration unit and the cold storage device in the first time period; wherein the first time period is any time period, and the second time period is the previous time period of the first time period.

3. The control method of a data center refrigeration system according to claim 2, characterized in that: The state space of the deep Q network includes predicted cooling demand, electricity price and cold storage equipment state, the cold storage equipment state includes the cold storage capacity of the cold storage equipment, the action space includes the cooling capacity of the refrigeration unit and the cooling capacity of the cold storage equipment, and the reward function is R=f (unit price of cooling capacity); Before inputting the predicted cooling demand and electricity price in the first period and the state of the cold storage device in the second period into the trained deep Q network, the method further includes: Based on the reward function, the reward values ​​of the refrigeration system performing different actions in multiple states are calculated and stored as training samples, and this step is repeated to obtain a training sample set of the refrigeration system; The initial deep Q network is trained based on the training sample set to obtain a trained Q network.

4. The control method of a data center refrigeration system according to claim 3, characterized in that: The formula for calculating the unit price of cooling capacity is: Among them, P Q is the unit price of cooling capacity during the forecast period, p i is the electricity price in time period i, i = 1, 2, ..., I, I is the total number of time periods in the forecast period, η unit is the electricity-to-cooling conversion efficiency of the refrigeration unit, Q i Demand is the predicted cooling demand for period i, Q i Loss is the amount of cold energy lost by the cold storage device in time period i, Q i The loss is the cooling capacity charge and discharge loss of the cold storage device in time period i, and Wtotal is the total cooling capacity demand in the prediction period.

5. The control method of a data center refrigeration system according to claim 1, characterized in that: The cold storage device includes a plurality of phase change material containers connected in parallel, and the cooling parameter includes the phase change material containers involved in cooling; The determining of cooling parameters of the cold storage device in each time period based on the cooling capacity of the cold storage device in each time period includes: If the cold storage capacity of the cold storage device is greater than the cold supply capacity in the first time period, each phase change material container is sorted according to the number of cycles, and the first N phase change material containers are selected in turn as the phase change material containers participating in the cold supply; wherein, the first time period is any time period, and the sum of the cold storage capacities of the first N phase change material containers is greater than or equal to the cold supply capacity of the cold storage device in the first time period.

6. The control method of a data center refrigeration system according to claim 5, characterized in that: After selecting the first N phase change material containers in sequence as the phase change material containers participating in cooling, the method further includes: The phase change material containers participating in cooling are sorted from large to small according to the cooling loss rate, and the order is used as the cooling order of the phase change material containers participating in cooling.

7. A control device for a data center refrigeration system, characterized in that: The refrigeration system includes a refrigeration unit and a cold storage device; the device includes: An acquisition module is used to obtain the predicted cooling demand of the data center in each time period; An allocation module, for determining, for each time period, the cooling capacity of the refrigeration unit and the cold storage device in the time period based on the predicted cooling demand and electricity price of the time period; The control module is used to determine the cooling parameters of the cold storage device in each time period based on the cooling capacity of the cold storage device in each time period.

8. The control device for a data center refrigeration system according to claim 7, characterized in that: The allocation module is specifically used for: The predicted cooling demand and electricity price in the first time period and the state of the cold storage device in the second time period are input into the trained deep Q network to obtain the cooling capacity of the refrigeration unit and the cold storage device in the first time period; wherein the first time period is any time period, and the second time period is the previous time period of the first time period.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images