Control method and device for regional cooling system participating in secondary frequency modulation of power grid

Abstract

The present application discloses a control method and device for a regional cooling system to participate in secondary frequency modulation of a power grid. In the method, according to the power difference between the current operating power of the regional cooling system and the target power, and the temperature difference between the current indoor temperature of the building in the regional cooling system and the target temperature, the flow adjustment amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm, and the power release value of the regional cooling system load caused by the flow adjustment amount is compensated to the power of the power grid, thereby ensuring that when the regional cooling system participates in the secondary frequency modulation, the actual cooling temperature of the cooling system building is maintained within the specified range.

Description

Technical Field

[0001] The present application relates to the technical field of power system dispatching, and in particular to a control method and device for a regional refrigeration system participating in secondary frequency modulation of a power grid. Background Art

[0002] The rapid development of renewable energy such as wind power and photovoltaics has reduced society's dependence on traditional fossil energy, but the randomness and volatility of their output have brought new challenges to the safe and stable operation of power systems with a high proportion of new energy access.

[0003] In order to alleviate the power fluctuation problem caused by the access of new energy to the distribution network, modern information technology can be used to regulate the power consumption of the power system through demand-side resources, achieve demand-side response, and thus provide secondary frequency regulation services for the power system.

[0004] As a large-scale centralized refrigeration equipment, the district cooling system has great regulation potential. District cooling systems are now increasingly deployed in large-scale building clusters such as railway stations and international airports in cities. A district cooling system can serve multiple buildings, and its power regulation is obviously easier to achieve than large-scale distributed air conditioning with the same regulation capacity. Due to the thermal inertia of the building, temporary adjustments to its power distribution usually have little effect on the temperature comfort of the building. We can participate in the active power dispatch of the power system on multiple time scales by short-term switching or changing control parameters without users' obvious perception.

[0005] In this case, the district cooling system, as a high-energy-consuming object on the demand side, can provide direct active power regulation for the power grid, thereby achieving secondary frequency regulation. This advantage can effectively avoid communication and coordination problems in distributed resource regulation. At the same time, due to the large thermal inertia of pipelines and buildings, the temperature impact caused by power regulation is small, so the district cooling system has great advantages in providing regulation services.

[0006] In the related art, the district cooling system's frequency control of the power grid usually makes it difficult to accurately ensure that the cooling temperature of the district cooling system meets the preset requirements after the district cooling system participates in the power grid regulation and control. Summary of the invention

[0007] In view of this, the present application provides a control method and device for a regional refrigeration system to participate in secondary frequency modulation of a power grid, which can ensure that the refrigeration temperature of the regional refrigeration system meets preset requirements.

[0008] In a first aspect, the present application provides a control method for a regional cooling system to participate in secondary frequency modulation of a power grid, comprising:

[0009] determining a power difference between a current operating power of the district cooling system and a target power, and a temperature difference between a current indoor temperature of a building within the district cooling system and a target temperature;

[0010] Determine, based on the Q-learning algorithm, the flow rate adjustment amount of the pipeline flow of each building in the regional cooling system according to the power difference and the temperature difference;

[0011] The power release value of the regional cooling system load caused by the flow regulation amount is compensated to the power grid power to perform secondary frequency regulation of the grid.

[0012] Optionally, determining the temperature difference includes:

[0013] The actual rate of temperature change of a building within a district cooling system is determined by the following formula,

[0014]

[0015] In the above formula, For the district cooling system The current indoor temperature of the building, For the district cooling system The current outdoor temperature of the building, For the district cooling system The heat capacity of the air and objects in a building, Indicates Thermal resistance of a building, is the current ambient temperature of the building in the district cooling system, Indicates the number of The heat exchange efficiency of a building, Represents the intensity of human activities, Indicates Current pipe flow in the district cooling system in the building, It is the secondary frequency regulation period of the power grid. is the specific heat capacity of water;

[0016] The integral of the actual temperature change rate during the secondary frequency modulation period of the power grid is established as the temperature difference.

[0017] Optionally, determining the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the Q learning algorithm according to the power difference and the temperature difference includes:

[0018] According to the power difference and the temperature difference, determine the state space set , as expressed in the following formula,

[0019]

[0020] In the above formula, For the district cooling system The current indoor temperature of the building, is the power difference, For the district cooling system Temperature difference between buildings;

[0021] The flow regulation of each building pipeline flow in the district cooling system is established as a discrete action space set , as expressed in the following formula,

[0022]

[0023] In the above formula, Indicates Current pipe flow in the district cooling system in the building, , is the total number of buildings;

[0024] Constructing a state space collection and the discrete action space set of , As expressed in the following formula,

[0025]

[0026]

[0027] In the above formula, is at the time step Instant rewards, is the discount factor, , is the weight factor of the balancing objective;

[0028] based on Maximize target update iteration , to obtain the flow regulation of the pipeline flow of each building in the district cooling system.

[0029] Optionally, based on Maximize target update iteration In the process, the following constraints are met:

[0030]

[0031] In the above formula, For the The indoor temperature change of the building, For the The initial indoor temperature value of the building, For the The maximum temperature allowed for users of a building.

[0032] Optionally, the flow regulation amount of the pipeline flow of each building in the regional cooling system satisfies the following constraints:

[0033]

[0034] In the above formula, is the total amount of flow regulation of the pipeline flow of each building in the district cooling system, District Cooling District Cooling System The total pipeline flow at time, District Cooling District Cooling System The total pipeline flow at time, Buildings in district cooling systems Indoor temperature at all times, Buildings in district cooling systems Outdoor temperature at any time, Buildings in district cooling systems Outdoor temperature at any time, for The power difference at each moment, is the specific heat of water.

[0035] Optionally, the state space set , discrete action space set , satisfying the following constraints

[0036]

[0037]

[0038] In the above formula, is the next state value, is the current state value, is the coefficient, is the compensation factor, is the mean of the distribution, is the variance of the distribution; is a parameter determined by the required confidence probability of the Gaussian process.

[0039] Optionally, it also includes:

[0040] Detect whether the grid frequency is disturbed;

[0041] When the grid frequency is disturbed, the operation of "determining the power difference between the current operating power of the regional cooling system and the target power, and the temperature difference between the current indoor temperature of the buildings in the regional cooling system and the target temperature; determining the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the Q learning algorithm according to the power difference and the temperature difference; compensating the power release value of the regional cooling system load caused by the flow adjustment amount to the grid power, so as to perform secondary frequency modulation of the grid" is performed.

[0042] In a second aspect, the present application provides a control device for a regional cooling system to participate in secondary frequency modulation of a power grid, comprising:

[0043] A first determination module is used to determine a power difference between a current operating power of the regional cooling system and a target power, and a temperature difference between a current indoor temperature of a building in the regional cooling system and a target temperature;

[0044] A second determination module is used to determine the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the power difference and the temperature difference based on the Q learning algorithm;

[0045] The compensation module is used to compensate the power release value of the regional cooling system load caused by the flow regulation amount to the power grid power, so as to perform secondary frequency regulation of the power grid.

[0046] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above method when the computer program is executed by a processor.

[0047] In a fourth aspect, the present application provides an execution device, comprising a processor and a memory, wherein the processor is coupled to the memory;

[0048] The memory is used to store programs;

[0049] The processor is used to execute the program in the memory, so that the execution device executes the above method.

[0050] In the method disclosed in the present application, according to the power difference between the current operating power of the regional cooling system and the target power, and the temperature difference between the current indoor temperature of the buildings in the regional cooling system and the target temperature, the flow regulation amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm, and the power release value of the regional cooling system load caused by the flow regulation amount is compensated to the grid power, thereby ensuring that the actual cooling temperature reached by the buildings in the cooling system is maintained within the specified range while the regional cooling system participates in the secondary frequency modulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The technical solution and other beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.

[0052] Figure 1 An operational flow chart of a control method for a regional cooling system participating in secondary frequency regulation of a power grid provided by an exemplary embodiment is shown.

[0053] Figure 2 A schematic diagram of a topological connection diagram of a regional cooling system provided by an exemplary embodiment when participating in secondary frequency regulation of a power grid is shown.

[0054] Figure 3 A power curve diagram of a regional cooling system provided by an exemplary embodiment when participating in secondary frequency regulation of a power grid is shown.

[0055] Figure 4 A comparison diagram of a regional cooling system participating in secondary frequency regulation of a power grid and a regional cooling system not participating in secondary frequency regulation of a power grid provided by an exemplary embodiment is shown.

[0056] Figure 5 A block diagram of a control device for a regional cooling system participating in secondary frequency regulation of a power grid provided by an exemplary embodiment is shown.

[0057] Figure 6 A block diagram of the execution device provided by an exemplary embodiment is shown. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0059] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of units in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the units or sub-units described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0060] Please refer to Figure 1 ,in Figure 1 A flowchart of a control method for a regional cooling system participating in secondary frequency regulation of a power grid is shown in an exemplary embodiment. The method is implemented through steps 102-106.

[0061] In step 102, a power difference between a current operating power of a district cooling system and a target power, and a temperature difference between a current indoor temperature of a building in the district cooling system and a target temperature are determined.

[0062] Here, as discussed above, the temperature difference It is equal to the real-time indoor temperature value minus the set temperature value, expressed as,

[0063] (1)

[0064] In the above formula (1), For the The temperature setting value corresponding to each building, No. Real-time indoor temperature values ​​of buildings.

[0065] Here, as discussed above, the power difference The actual operating power and target power The difference between them is expressed in the form of formula (2):

[0066] (2)

[0067] It is understandable that the temperature difference between the current indoor temperature of a building in the regional cooling system and the target temperature can be determined by collecting the current indoor temperature of the building in real time, such as by a temperature sensor, and then calculating the difference between the current indoor temperature and the target temperature.

[0068] As another exemplary embodiment of determining a certain temperature difference, it can be determined by the temperature change rate, specifically:

[0069] The actual rate of temperature change of a building within a district cooling system is determined by the following formula,

[0070] (3)

[0071] In the above formula, For the district cooling system The current indoor temperature of the building, For the district cooling system The current outdoor temperature of the building, For the district cooling system The heat capacity of the air and objects in a building, Indicates Thermal resistance of a building, is the current ambient temperature of the building in the district cooling system, Indicates the number of The heat exchange efficiency of a building, Represents the intensity of human activities, Indicates the number of Current pipe flow in buildings, It is the secondary frequency regulation period of the power grid. is the specific heat capacity of water;

[0072] The integral of the actual temperature change rate during the secondary frequency modulation period of the power grid is established as the temperature difference.

[0073] In order to facilitate the understanding of the above formula (1), the derivation process of the above formula (1) is now described:

[0074] Since each building in the building cluster has different characteristics such as house structure and house orientation, its heat dissipation capacity will be different, and the cooling efficiency will be different. The specific data of all other parameters can be known, so the different cooling efficiency of each building can be calculated by formula (4): value.

[0075] Please refer to Figure 2 Specifically, the working medium of the regional cooling system is water, and cooling relies on the circulation of water flowing in and out to reduce the temperature in the regional cooling system. Based on this, the real-time cooling power is expressed by the following formula:

[0076] (4)

[0077] In the above formula (4), is the real-time cooling power, is the regional cooling pipeline flow per unit time, is the specific heat of water, is the real-time outlet water temperature. is the real-time return water temperature, is the cooling efficiency.

[0078] According to the law of conservation of energy, when the indoor temperature of a building is constant, the cooling power is equal to the dissipated power, which can be expressed as:

[0079] (5)

[0080] In formula (4), Indicates the number of The power dissipated by the building, is the total number of buildings in the district cooling system.

[0081] Since the power dissipated in the building of the district cooling system is affected by the room volume, the difference between the indoor set temperature and the outdoor temperature, and the heat transfer coefficient, the first The formula for power dissipation of a building is:

[0082] (6)

[0083] in: It is The volume of the building. It is The difference between the indoor set temperature and the outdoor temperature of a building. is a heat transfer coefficient, reflecting the Thermal insulation performance of buildings.

[0084] Formula (6), example calculation:

[0085] Assume that the volume of a room is , set the temperature to , the outdoor temperature is , heat transfer coefficient , then the room power is , which means that the room requires 750W of cooling power per hour to maintain the set temperature.

[0086] According to the relationship between inflow and outflow, the regional cooling pipeline flow satisfies that the total flow is equal to the sum of the flow of each building, which is expressed as follows:

[0087] (7)

[0088] here, Indicates The regional cooling pipe flow per unit time in the building, of which there are Buildings.

[0089] According to the specific heat formula It can be seen that the total For a total of from 1 to n Buildings sum

[0090] (8)

[0091] For Real-time indoor temperatures of buildings , which is determined by three parts: the heat exchange with the outdoor environment, the uncertain heat load in the building caused by random human activities, and the cooling energy obtained from the district cooling pipe. Therefore, based on the above formulas (4)-(8), the above formula (3) can be derived.

[0092] In step 104, the flow adjustment amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm according to the power difference and the temperature difference.

[0093] It is known from general knowledge of regional cooling systems that, combined with the above formula (4), it is not difficult to understand that the flow rate changes of the pipeline flow of each building in the regional cooling system are The indoor temperature of the building will change. Define the flow change of the pipeline flow of each building in the district cooling system Expressed as

[0094] (9)

[0095] In the above formula (9), is the current time of the district cooling system The pipeline flow rate, The next moment for district cooling systems The pipeline flow rate of the next moment is It is equal to the sum of the regional cooling pipe flow of all buildings at the next moment, which is:

[0096] (10)

[0097] District cooling pipe flow The real-time water output must be equal to the real-time water return, that is, the following conditions must be met:

[0098] (11)

[0099] in The current time for the district cooling pipeline flow, The last moment of the district cooling pipeline The pipeline flow rate, For the Control coefficient of the building.

[0100] Based on the above formula, the flow rate regulation of the pipeline flow of each building in the district cooling system can be obtained, which satisfies the following constraints:

[0101] (12)

[0102] In the above formula (12), is the total amount of flow regulation of the pipeline flow of each building in the district cooling system, District Cooling District Cooling System The total pipeline flow at time, District Cooling District Cooling System The total pipeline flow at time, Buildings in district cooling systems Indoor temperature at all times, Buildings in district cooling systems Outdoor temperature at any time, Buildings in district cooling systems Outdoor temperature at any time, for The power difference at each moment, is the specific heat of water.

[0103] It is known to those skilled in the art that the input objects of Q learning are the following basic items:

[0104] State (S): The state of the environment that the agent is currently in. Usually represented as a number or vector, the specific form depends on the definition of the problem.

[0105] Action (A): A set of actions that the agent can take in the current state. The choice of action will affect the next state of the agent.

[0106] Reward (R): When the agent performs an action, the environment returns an immediate reward signal. This reward is usually a numerical value that indicates whether the agent has taken the action well or not.

[0107] Learning Rate (α): controls the speed at which the Q value is updated. It is a constant between 0 and 1 that represents the weight of new information.

[0108] Discount Factor (γ): A constant between 0 and 1 that represents the present value of future rewards. The closer the value is to 1, the more important the future rewards are.

[0109] The output objects of Q learning are the following basic items:

[0110] Q-value (Q(s,a)Q): The core output of the Q-learning algorithm is a Q table (or Q function), which represents the expected cumulative reward that can be obtained by taking action a in state s. The Q value is updated iteratively to approach the optimal value.

[0111] Policy: The policy learned through Q-learning. Usually expressed as the action selected in each state.

[0112] Based on the above general technical knowledge of Q learning, as a demonstrative specific example, according to the power difference and the temperature difference, the flow adjustment amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm, including:

[0113] Step 1041: Determine the state space set according to the power difference and the temperature difference. , as expressed in the following formula,

[0114] (13)

[0115] In the above formula, For the district cooling system The current indoor temperature of the building, is the power difference, For the district cooling system Temperature difference between buildings.

[0116] Step 1042: Establish the flow regulation amount of each building pipeline flow in the regional cooling system as a discrete action space set , as expressed in the following formula,

[0117] (14)

[0118] In the above formula, Indicates Current pipe flow in the district cooling system in the building, , is the total number of buildings.

[0119] In this step 1042, the state space set , discrete action space set , satisfying the following constraints

[0120] (15)

[0121] (16)

[0122] In the above formula, is the next state value, is the current state value, is the coefficient, is the compensation factor, is the mean of the distribution, is the variance of the distribution; is a parameter determined by the required confidence probability of the Gaussian process.

[0123] Step 1043: Constructing a state space set and the discrete action space set of , As expressed in the following formula,

[0124] (17)

[0125] (18)

[0126] In the above formula, is at the time step Instant rewards, is a discount factor (ranging between 0 and 1, used to weigh the importance of future rewards), , is the weight factor for the balancing objective.

[0127] Based on formula (18), for multiple buildings in the district cooling system, the total reward function can be selected as , expressed as (19), where n is the total number of buildings, For the district cooling system Buildings.

[0128] Step 1044: Based on Maximize target update iteration , to obtain the flow regulation of the pipeline flow of each building in the district cooling system.

[0129] The following is a brief introduction to the update iteration operation process.

[0130] Step 10441: Initialize all state-action pairs The value is zero. .

[0131] Step 10442, ε-greedy strategy selects action. In each state, The probability of randomly selecting an action is Probability of choosing current The action with the largest value is shown in the following formula (19):

[0132] (20)

[0133] Step 10443: Execute the action and observe the result. Execute the selected action in the system , observe the results, including the new state and rewards .

[0134] Step 10444, update using the following formula value:

[0135] (twenty one)

[0136] In the above formulas (17) and (18): is the current state, is the current action, is the reward after performing the action, is the next state after executing the action, is the learning rate, is the discount factor, Is in the new state Next, choose the best action The maximum you can get Value. New Value equal to old value, plus a learning step ( ) multiplied by the error of the current estimate, i.e. the immediate reward plus the future Value discount and old The difference between the values.

[0137] Step 10445, i.e. repeating the above steps 10441 to 10444, updating the execution control action Refrigeration system environmental status after ;Store state transfer data Control gradually reduces the exploration probability The value of is iterated until the Q value converges or reaches the preset number of iterations .

[0138] In a preferred specific example, it is confirmed that one of the outputs of the Q learning method to achieve the specific strategy method of maximizing the Q value will not cause the temperature to exceed the maximum temperature value allowed by the user. That is, (22), where (twenty three).

[0139] If the requirements are met, continue training until the Q value converges or the preset number of iterations is reached If it does not meet the requirements, the training is stopped, and the output Q value of the last training result that meets the requirements and the specific strategy method for maximizing the Q value are output as the result.

[0140] In step 106, the power release value of the regional cooling system load caused by the flow regulation amount is compensated to the grid power to perform secondary grid frequency regulation.

[0141] In this step 106, the implementation of compensation is known to those skilled in the art. Figure 3 Indicated.

[0142] Please refer to Figure 4 The participation of regional cooling systems in the secondary frequency regulation of the power grid can significantly increase the power on the load side of the power grid while maintaining stability.

[0143] As an exemplary specific example, the present application method also includes:

[0144] Detect whether the grid frequency is disturbed;

[0145] When the grid frequency is disturbed, the operations of “steps 102 - 106 ” are executed.

[0146] When the grid frequency is stable, the operations of “steps 102 - 106 ” may be terminated.

[0147] Please refer to Figure 5 , which shows a block diagram of a control device for a regional cooling system participating in secondary frequency modulation of a power grid provided by the present application. The device 200 includes:

[0148] A first determination module 202 is used to determine a power difference between a current operating power of the regional cooling system and a target power, and a temperature difference between a current indoor temperature of a building in the regional cooling system and a target temperature;

[0149] A second determination module 204 is used to determine the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the power difference and the temperature difference based on the Q learning algorithm;

[0150] The compensation module 206 is used to compensate the power release value of the regional cooling system load caused by the flow regulation amount to the power grid power, so as to perform secondary frequency regulation of the power grid.

[0151] Since the above methods have been discussed in detail, the specific implementation of the above modules will not be repeated here.

[0152] Next, an execution device provided by an embodiment of the present application is introduced. Figure 6 , Figure 6 This is a schematic diagram of a structure of an execution device provided in an embodiment of the present application. The execution device 300 can be specifically manifested as an autonomous driving vehicle, a mobile phone, a tablet, a laptop computer, a desktop computer, a monitoring data processing device, etc., which is not limited here. Figure 1 The functions of the execution device in the corresponding embodiment. Specifically, the execution device 300 includes: a receiver 301, a transmitter 302, a processor 303 and a memory 304 (wherein the number of the processor 303 in the execution device 300 can be one or more, Figure 6 In the example of FIG. 3 , the processor 303 may include an application processor 3031 and a communication processor 3032. In some embodiments of the present application, the receiver 301, the transmitter 302, the processor 303 and the memory 304 may be connected via a bus or other means.

[0153] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 303. A portion of the memory 304 may also include a non-volatile random access memory (NVRAM). The memory 304 stores processor and operation instructions, executable modules or data structures, or subsets thereof, or extended sets thereof, wherein the operation instructions may include various operation instructions for implementing various operations.

[0154] The processor 303 controls the operation of the execution device. In a specific application, the various components of the execution device are coupled together through a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus, etc. However, for the sake of clarity, various buses are referred to as bus systems in the figure.

[0155] The method disclosed in the above embodiment of the present application can be applied to the processor 303, or implemented by the processor 303. The processor 303 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 303. The above processor 303 can be a general processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and can further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The processor 303 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 304, and the processor 303 reads the information in the memory 304 and completes the steps of the above method in combination with its hardware.

[0156] The receiver 301 can be used to receive input digital or character information and generate signal input related to the relevant settings and function control of the execution device. The transmitter 302 can be used to output digital or character information through the first interface; the transmitter 302 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group; the transmitter 302 can also include a display device such as a display screen.

[0157] In the embodiment of the present application, the processor 303 is used to execute Figure 1 The specific manner in which the application processor 3031 in the processor 303 performs the above steps is the same as that in the present application. Figure 1The corresponding method embodiments are based on the same concept, and the technical effects they bring are the same as those in this application. Figure 1 The corresponding method embodiments are the same. For specific contents, please refer to the description in the method embodiments shown above in this application, which will not be repeated here.

[0158] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

Claims

1. A control method for a regional cooling system participating in secondary frequency modulation of a power grid, characterized in that: include: determining a power difference between a current operating power of the district cooling system and a target power, and a temperature difference between a current indoor temperature of a building within the district cooling system and a target temperature; Determine, based on the Q-learning algorithm, the flow rate adjustment amount of the pipeline flow of each building in the regional cooling system according to the power difference and the temperature difference; Compensating the power release value of the regional cooling system load caused by the flow regulation amount to the power grid power to perform secondary frequency regulation of the grid; Determine the temperature difference, including: The actual rate of temperature change of a building within a district cooling system is determined by the following formula, In the above formula, For the district cooling system The current indoor temperature of the building, For the district cooling system The current outdoor temperature of the building, For the district cooling system The heat capacity of the air and objects in a building, Indicates Thermal resistance of a building, is the current ambient temperature of the building in the district cooling system, Indicates the number of The heat exchange efficiency of a building, Represents the intensity of human activities, Indicates Current pipe flow in the district cooling system in the building, It is the secondary frequency regulation period of the power grid. is the specific heat capacity of water; The integral of the actual temperature change rate during the secondary frequency modulation period of the power grid is established as the temperature difference; According to the power difference and the temperature difference, the flow rate adjustment amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm, including: Determine the state space set according to the power difference and the temperature difference , as expressed in the following formula, In the above formula, For the district cooling system The current indoor temperature of the building, is the power difference, For the district cooling system Temperature difference between buildings; The flow regulation of each building pipeline flow in the district cooling system is established as a discrete action space set , as expressed in the following formula, In the above formula, Indicates Current pipe flow in the district cooling system in the building, , is the total number of buildings; Constructing a state space collection and the discrete action space set of , It is expressed as follows: In the above formula, is at the time step Instant rewards, is the discount factor, , is the weight factor of the balancing objective; based on Maximize target update iteration , to obtain the flow regulation of the pipeline flow of each building in the district cooling system.

2. The method according to claim 1, characterized in that based on Maximize target update iteration In the process, the following constraints are met: In the above formula, For the The indoor temperature change of the building, For the The initial indoor temperature of the building, For the The maximum temperature allowed for users of a building.

3. The method according to claim 1, characterized in that The flow rate regulation amount of the pipeline flow of each building in the regional cooling system meets the following constraints: In the above formula, is the total amount of flow regulation of the pipeline flow of each building in the district cooling system, For district cooling systems The total pipeline flow at time, For district cooling systems The total pipeline flow at time, Buildings in district cooling systems Indoor temperature at all times, Buildings in district cooling systems Outdoor temperature at any time, Buildings in district cooling systems Outdoor temperature at any time, for The power difference at each moment, is the specific heat of water.

4. The method according to claim 1, characterized in that: The state space set , discrete action space set , satisfying the following constraints In the above formula, is the next state value, is the current state value, is the coefficient, is the compensation factor, is the mean of the distribution, is the variance of the distribution; is a parameter determined by the required confidence probability of the Gaussian process.

5. The method according to claim 1, characterized in that Also includes: Detect whether the grid frequency is disturbed; When the grid frequency is disturbed, executing "determining the power difference between the current operating power of the regional cooling system and the target power, and the temperature difference between the current indoor temperature of the building in the regional cooling system and the target temperature; determining the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the Q learning algorithm according to the power difference and the temperature difference; The power release value of the regional cooling system load caused by the flow regulation amount is compensated to the power grid power to perform the "secondary frequency regulation of the power grid" operation.

6. A control device for a regional cooling system participating in secondary frequency modulation of a power grid, characterized in that: include: A first determination module is used to determine a power difference between a current operating power of the regional cooling system and a target power, and a temperature difference between a current indoor temperature of a building in the regional cooling system and a target temperature; A second determination module is used to determine the flow adjustment amount of the pipeline flow of each building in the regional cooling system based on the power difference and the temperature difference based on the Q learning algorithm; A compensation module, used for compensating the power release value of the regional cooling system load caused by the flow regulation amount to the power grid power, so as to perform secondary frequency regulation of the power grid; Determine the temperature difference, including: The actual rate of temperature change of a building within a district cooling system is determined by the following formula, In the above formula, For the district cooling system The current indoor temperature of the building, For the district cooling system The current outdoor temperature of the building, For the district cooling system The heat capacity of the air and objects in a building, Indicates Thermal resistance of a building, is the current ambient temperature of the building in the district cooling system, Indicates the number of The heat exchange efficiency of a building, Represents the intensity of human activities, Indicates Current pipe flow in the district cooling system in the building, It is the secondary frequency regulation period of the power grid. is the specific heat capacity of water; The integral of the actual temperature change rate during the secondary frequency modulation period of the power grid is established as the temperature difference; According to the power difference and the temperature difference, the flow rate adjustment amount of the pipeline flow of each building in the regional cooling system is determined based on the Q learning algorithm, including: Determine the state space set according to the power difference and the temperature difference , as expressed in the following formula, In the above formula, For the district cooling system The current indoor temperature of the building, is the power difference, For the district cooling system Temperature difference between buildings; The flow regulation of each building pipeline flow in the district cooling system is established as a discrete action space set , as expressed in the following formula, In the above formula, Indicates Current pipe flow in the district cooling system in the building, , is the total number of buildings; Constructing a state space collection and the discrete action space set of , It is expressed as follows: In the above formula, is at the time step Instant rewards, is the discount factor, , is the weight factor of the balancing objective; based on Maximize target update iteration , to obtain the flow regulation of the pipeline flow of each building in the district cooling system.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. An execution device, characterized in that: comprising a processor and a memory, wherein the processor is coupled to the memory; The memory is used to store programs; The processor is configured to execute the program in the memory so that the execution device executes the method according to any one of claims 1 to 5.

Images