CN113068374B

CN113068374B - Control method, device and equipment of heat exchange system and storage medium

Info

Publication number: CN113068374B
Application number: CN202110269449.8A
Authority: CN
Inventors: 曹建超; 肖羽佳; 李彪; 余兴林; 吕恩茂; 李岩; 刘伟民; 衣斌
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-03-12
Filing date: 2021-03-12
Publication date: 2022-12-20
Anticipated expiration: 2041-03-12
Also published as: CN113068374A

Abstract

The disclosure provides a control method, a control device, control equipment and a storage medium of a heat exchange system, and relates to the field of heat exchange systems. The specific implementation scheme is as follows: the heat exchange system is configured in a modularized mode to obtain at least one sub-module; performing attribute description on a control object operating at least one sub-module to obtain attribute description information; obtaining a thermal flow graph based on a graph optimization strategy according to the attribute description information; and obtaining control parameters according to the environmental parameters of the cold source end and the hot source end and the thermal flow diagram, and keeping the heat exchange system in an energy consumption balance state under the driving of the control parameters. According to the method disclosed by the embodiment of the disclosure, the rapid construction and deployment capability of the heat exchange system is provided, and the rapid solving and adaptive capability can be realized aiming at the complex series-parallel relation among the heat exchange system models.

Description

Control method, device and equipment of heat exchange system and storage medium

Technical Field

The disclosure relates to the technical field of heat exchange systems, in particular to the technical field of diagram optimization.

Background

In the related art, a heat exchange system is generally constructed and optimized in a subsystem modeling or integral modeling manner. The modeling mode based on the subsystem characteristics has strong interpretability and is easy to position the strategic system problem, but different heat exchange systems have different structures, and the system modeling and solving processes are complex; the whole black box modeling mode couples the heat exchange system architecture with the optimization strategy, but the defects of poor system interpretability, difficult problem positioning and the like exist.

Disclosure of Invention

The disclosure provides a control method, a control device, control equipment and a storage medium of a heat exchange system.

According to an aspect of the present disclosure, there is provided a method for controlling a heat exchange system, including:

the heat exchange system is configured in a modularized mode to obtain at least one sub-module;

performing attribute description on a control object operating at least one sub-module to obtain attribute description information;

obtaining a thermal flow graph based on a graph optimization strategy according to the attribute description information;

and obtaining control parameters according to the environmental parameters of the cold source end and the hot source end and the thermal flow diagram, and keeping the heat exchange system in an energy consumption balance state under the driving of the control parameters.

According to another aspect of the present disclosure, there is provided a control device of a heat exchange system, including:

the configuration module is used for modularly configuring the heat exchange system to obtain at least one sub-module;

the attribute description module is used for carrying out attribute description on a control object running at least one sub-module to obtain attribute description information;

the thermal flow graph generating module is used for obtaining a thermal flow graph based on a graph optimization strategy according to the attribute description information;

and the control parameter calculation module is used for obtaining control parameters according to the environmental parameters of the cold source end and the hot source end and the thermal flow diagram, and keeping the heat exchange system in an energy consumption balance state under the driving of the control parameters.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method in any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a data center including:

the heat exchange system adopts the method in any embodiment of the disclosure to be in an energy consumption balance state.

According to the technology disclosed by the invention, the rapid construction and deployment capability of the heat exchange system is realized, and the rapid solving and adaptive capability can be realized aiming at the complex series-parallel relation among the heat exchange system models.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of controlling a heat exchange system according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of a construction of a thermodynamic flow diagram according to an embodiment of the present disclosure;

FIG. 3 is a detailed flow diagram of solving a thermodynamic flow graph target solution in accordance with an embodiment of the present disclosure;

FIG. 4 is a detailed flow diagram of calculating control parameters for graph vertices according to an embodiment of the present disclosure;

FIG. 5 is a detailed flow chart of a feasible domain to derive a thermal flow graph in accordance with an embodiment of the present disclosure;

FIG. 6 is a detailed flow chart of a feasible domain to derive a thermal flow graph in accordance with an embodiment of the present disclosure;

FIG. 7 is a detailed flow diagram of pruning a homomorphic solution according to an embodiment of the present disclosure;

FIG. 8 is a detailed schematic diagram of a graph vertex in a thermal flow graph according to an embodiment of the present disclosure;

FIG. 9 is a detailed schematic diagram of a thermal flow diagram according to an embodiment of the present disclosure;

FIG. 10 is a schematic diagram of a control method according to an embodiment of the disclosure;

FIG. 11 is a block diagram of a control device of a heat exchange system according to an embodiment of the present disclosure;

fig. 12 is a block diagram of an electronic device used to implement the control method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The electric energy consumed by the data center in the whole IT (Internet technology) industry is huge, so that how to reduce the energy consumption of the data center and improve the operation and maintenance efficiency of equipment is significant for energy conservation and emission reduction. The intelligent exploration of data centers aiming at high efficiency and low energy consumption is a hot spot in the industry at present. How to construct and optimize a heat exchange system of the data center so as to enable the heat exchange system to maintain operation in a low energy consumption balance state and be beneficial to realizing the purposes of energy conservation and emission reduction of the data center.

The modeling and control modes of the heat exchange system in the related technology are mainly as follows:

(1) Model-free control, that is, optimization control based on PID (proportional Integral Differential) algorithm feedback and operation and maintenance experience. This approach is typically a single point feedback control, such as a feedback control of water pump flow rate via water pump frequency. The disadvantage of this approach is that feedback control is a way of state maintenance, and generally requires expert experience to achieve optimal control.

(2) And (4) optimizing and controlling the system based on the theoretical model. The method is to model the system based on the thermodynamic theory, and has the defects of large difference between the working states of a theoretical model and actual equipment and poor landing effect.

(3) The method comprises the steps of whole black box modeling based on a heat exchange system framework and optimization control based on intelligent algorithms such as a neural network and reinforcement learning. Among them, neural networks are effective tools for learning complex functions, and the model can learn and capture linear and nonlinear functional relationships, and has the disadvantages of poor interpretability and difficult problem location. In addition, the neural network cannot introduce constraints into the system and directly generate a control strategy; the neural network has errors, and the errors cannot be compensated and managed in a targeted mode. Reinforcement learning is a machine learning algorithm which can imitate the process of human cognition, so that a machine can learn experiences from an actual environment, and the essence is a self-feedback learning mode. The core of the reinforcement learning algorithm is to calculate the income of each action and continuously record the attempt, but for the heat exchange system, the defects of huge action (namely, regulation and control strategy) space and long debugging period exist, and other risks such as overtemperature of a machine room exist in the debugging process.

Based on the technical problems existing in the related art, the present disclosure provides a control method of a heat exchange system.

Fig. 1 shows a flow chart of a control method according to an embodiment of the present disclosure.

As shown in fig. 1, the method includes:

step S101: the heat exchange system is configured in a modularized mode to obtain at least one sub-module;

step S102: performing attribute description on a control object operating at least one sub-module to obtain attribute description information;

step S103: obtaining a thermal flow graph based on a graph-based optimization strategy (graph-based optimization) according to the attribute description information;

step S104: and obtaining control parameters according to the environmental parameters of the cold source end and the hot source end and the thermal flow diagram, and keeping the heat exchange system in an energy consumption balance state under the driving of the control parameters.

For example, in step S101, the heat exchange system may specifically be an air conditioning system, and the air conditioning system is decoupled to split the equipment configuration of the air conditioning system into three types, such as heat exchange equipment, power equipment, and connection equipment, so as to obtain sub-modules corresponding to the respective equipment. Wherein, heat exchange equipment can be used for realizing the equipment of heat exchange for plate heat exchanger, cooling tower etc. power equipment can be for other equipment that are used for providing circulation power to heat transfer medium such as cooling pump, and connecting device can be for connecting pipeline etc. between the equipment and the heat exchange equipment of leading to more for thereby realize that the heat uses heat transfer medium to circulate between different heat exchange equipment or the equipment of leading to more as the carrier.

Illustratively, in step S102, the control object of the sub-module, i.e. the specific device corresponding to the sub-module. For example, for an air conditioning system, the control object of the sub-module may be any one of a heat exchange device, a multi-pass device, a power device, and a connection device. The attribute description information may include a series of information such as control parameters of the sub-module, an out-connection device or an in-connection device of the sub-module, location information (for example, located at a cold source end or a hot source end) where the sub-module is located, and the like.

Further, the model management module may be used to perform attribute description on a control object for operating at least one sub-module according to an actual HAVC (Heating, ventilation and Air Conditioning) architecture of the heat exchange system. The model management module can realize maintenance of the equipment model base and can describe the heat exchange system by combining with an actual HAVC framework.

Illustratively, in step S103, a graph optimization strategy is a graph optimization algorithm. Specifically, a thermal flow graph containing nodes and edges is constructed according to the attribute description information, the nodes are used for representing heat exchange equipment or multi-pass equipment, the edges are used for representing connecting equipment, and then the parameterized forms of the nodes and the edges are determined.

Further, a heating and ventilation system architecture constructed by a graph on the basis of a configuration file or a user through a graph on an interface can be obtained through a graph construction module, and a heating power flow graph based on a graph optimization strategy is obtained according to attribute description information.

In step S104, the environmental parameters of the hot source end and the cold source end may include dry bulb temperature, wet bulb temperature, relative humidity, and the like. The heat source end refers to one end for inputting heat to the whole heat exchange system, and the cold source end refers to one end for inputting cold to the whole heat exchange system. For example, a heat exchange system for a data center is configured to transmit heat of a machine room outdoors and transmit outdoor cold to the inside of the data center, where a heat source end may be the machine room and a cold source end may be an outdoor environment. The environmental parameters of the cold source end or the hot source end are used as the input of the thermal flow diagram, and the control parameters are obtained based on the diagram optimization strategy. The control parameters may include relevant parameters of each sub-module. For example, for a heat exchange system of a data center, the control parameter may be the temperature and flow rate of the heat exchange medium flowing into or out of the heat exchange device.

It can be understood that, the heat exchange system is kept in the energy consumption balance state under the driving of the control parameter, that is, each device of the heat exchange system operates under the control parameter, so that the heat exchange system can maintain the operation state in the minimum energy consumption balance state. The threshold value can be set correspondingly according to the expected range of the energy consumption of the heat exchange system in actual conditions.

According to the control method of the heat exchange system, the heat exchange system is configured in a modularized mode, the heat flow diagram based on the diagram optimization strategy is obtained according to the attribute description information of the sub-modules, and finally the control parameters can be obtained according to the environmental parameters of the cold source end and the hot source end and the heat flow diagram, so that the heat exchange system can reach the minimum energy consumption balance state meeting the threshold value. Therefore, the universal abstraction and optimization algorithm design of the heat exchange system can be realized, the thermodynamic flow diagram of the heat exchange system is built by the subsystem model, the thermodynamic flow diagram is solved by the diagram optimization algorithm, the framework and the strategy optimization algorithm of the heat exchange system are decoupled, the interpretability and the algorithm adaptability are improved, and the strategy optimization of the heat exchange systems with different structures is realized. In addition, by the method of the embodiment of the disclosure, the optimal control parameters (control parameters of heat exchange equipment and power equipment) of the heat exchange system under the current environmental conditions (i.e. environmental parameters of the cold source end and the hot source end) can be obtained by solving, and even if the heat exchange system maintains the combination of the control parameters under the operation state with the lowest energy consumption, the purpose of energy saving is achieved, and the optimization scheme of energy saving and emission reduction of the data center is further realized.

In addition, compared with the method based on PID control in the related technology, the method of the embodiment of the disclosure is based on the modular configuration of the heat exchange system, can provide an equipment model library to improve the modeling and control accuracy of the subsystem, and optimizes the energy efficiency from the global aspect; compared with a mode based on a neural network in the related technology, the heat flow graph obtained based on the graph optimization strategy in the scheme has the advantages of strong interpretability and convenience in problem positioning; compared with a mode based on reinforcement learning in the related technology, the scheme can reduce the risk caused by frequent random regulation and control of the heat exchange system.

Based on this, facing the challenge of various heterogeneous heat exchange system architectures in the industry, the method disclosed by the embodiment of the disclosure has the capability of quickly constructing and deploying the heat exchange system, and can realize the capability of quickly solving and adapting to the complex series-parallel relation between heat exchange system models.

In one embodiment, as shown in FIG. 2, at least one sub-module includes at least one of a heat exchange module, a power module, and a connection module. The heat exchange module is used for representing the heat exchange equipment, the power module is used for representing the power equipment, and the connection module is used for representing the connection equipment.

In the case where the at least one sub-module includes a heat exchange module, a power module, and a connection module, the method further includes:

step S201: the heat exchange module is connected with the power module through the connecting module, indoor heat is transmitted to the outdoor, and outdoor cold is transmitted to the indoor.

It can be understood that, for the heat exchange system of the data center, the working purpose is to transmit the outdoor cooling capacity to the inside of the data center, i.e. the machine room, and simultaneously transmit the indoor heat capacity to the outside of the machine room, so the heat exchange system can be regarded as a heat flow diagram in the working state. To achieve this, the heat exchange system at least includes a heat exchange device, a power device and a connection device, the heat exchange device is used for completing heat exchange, the power device is used for driving energy to flow in the connection device, and the connection device is used for connecting (such as a pipeline) the heat exchange device so as to realize the circulation of energy by taking a heat medium as a carrier.

Through the implementation mode, the control method still has the capability of rapid construction and deployment aiming at the architectures of various heterogeneous heat exchange systems in the industry, so that the universality and the application range of the control method disclosed by the embodiment of the disclosure are improved.

In one embodiment, a thermal flow graph based on a graph optimization strategy includes: and the graph vertex is used for describing heat exchange and multi-channel connection attributes, and the graph directed edge is used for describing the pipeline attributes in the multi-channel connection attributes.

Illustratively, as shown in fig. 8, the control parameters for the map vertices may include cold-end inlet water temperature, cold-end outlet water temperature, cold-end flow, hot-end inlet water temperature, hot-end outlet water temperature, and hot-end flow. Wherein, the cold end refers to a control parameter at one side of the graph vertex close to the cold source end, for example, the left side of vertex 1 in the graph is the cold end; the hot end refers to the control parameter on the side of the graph vertex close to the hot end, for example, the right side of vertex 1 in the figure is the hot end.

In one particular example, the control parameters for the vertices of each graph in the thermal flow graph may satisfy the following characteristics:

(1) The directed edges between the associated two graph vertexes form a closed loop, and the flow of each point on the directed edge of any one graph in the closed loop is equal. For example, the directed graph edge 1 and the directed graph edge 2 form a closed loop, and the flow rates of each point on the directed graph edge 1 and the directed graph edge 2 are both Qc; the directed graph edge 3 and the directed graph edge 4 form a closed loop, and the flow rates of all points on the directed graph edge 3 and the directed graph edge 4 are both Qh.

(2) The water inlet temperature or the water outlet temperature of each point on the directional edge of the same graph are equal. For example, the inlet water temperature at each point on the graph directional edge 1 is Tc _ in, and the outlet water temperature at each point on the graph directional edge 3 is Tc _ out.

(3) The inflow and outflow values on the same side at the apex of the same graph are equal. For example, on the cold source side of graph vertex 1, the cold end flow on graph directed edge 1 is the inlet flow value of graph vertex 1, the cold end flow on graph directed edge 2 is the outlet flow value of graph vertex 1, and both the inlet flow value and the outlet flow value of graph vertex 1 are Qc; for the heat source side of the graph vertex 1, the hot end flow on the graph directed edge 3 is the output flow value of the graph vertex 1, the hot end flow on the graph directed edge 4 is the input flow value of the graph vertex 1, and both the output flow value and the input flow value are Qh.

By the implementation mode, the complex series-parallel relation among the submodules of the heat exchange system can be quickly established and deployed according to the attribute description information, and the control parameters of the vertexes of the graphs can be quickly solved through the graph optimization strategy.

As shown in fig. 3, in one embodiment, step S104 includes:

step S301: sequentially solving the control parameters of each graph vertex through model constraint conditions and a preset value set of each graph vertex according to the environmental parameters of the cold source end and the hot source end;

step S302: generating feasible domains of the thermal flow graph based on the control parameters of the vertexes of the graphs, wherein the feasible domains comprise a plurality of feasible solutions, and the feasible solutions are sets of the control parameters of the vertexes of the graphs;

step S303: and taking the feasible solution of the minimum energy consumption equilibrium state for keeping the heat exchange system in accordance with the threshold value as a target solution of the thermodynamic diagram.

For example, in step S301, the model constraint condition may be a function constructed for the control parameter of each vertex. For example, the control parameters for the vertices may satisfy the following function:

T _{h_out} ＝F(T _{c_in} ,T _{c_out} ,Q _c ,T _{h_in} ,Q _h )，

wherein F is the rule of correspondence, T _{h_out} Is hot end outlet water temperature, T _{c_in} At cold end water entry temperature, T _{c_out} Is the cold end outlet water temperature, Q _c Is cold side flow, T _{h_in} The hot end water inlet temperature, Q _h Is the hot end flow.

By determining the known parameters or the value ranges of the known parameters in the control parameters, the position parameters or the value ranges of the position parameters can be solved through the model constraint conditions, so that a plurality of solutions of the control parameters of the vertex of the graph are formed. And then, based on the heat flow graph, sequentially determining the control parameters of all the graph vertexes according to the mutual relation among the graph vertexes.

The value range of part of known parameters or known parameters can be determined according to the environmental parameters of the cold source end or the hot source end of the heat exchange system, or according to the preset value set of the sub-modules corresponding to the vertex of the graph.

Illustratively, in step S302, a plurality of feasible solutions of the thermal flow graph are formed by associating the control parameters of the vertices, so as to obtain feasible domains of the thermal flow graph.

For example, in step S303, a cost value corresponding to each feasible solution may be obtained according to a sum of energy consumptions of all heat exchange devices and other energy consumption devices such as connection devices, and the feasible solution with the smallest cost value may be selected as the target solution of the thermal flow graph.

It can be understood that the control parameter of each vertex in the target solution is the optimal control parameter for controlling the heat exchange system to maintain the minimum energy consumption equilibrium state meeting the threshold value.

By the embodiment, the optimal control parameters of all the devices in the operating state of the heat exchange system can be obtained through solving, so that the heat exchange system operates in the lowest energy consumption balance state, and the purpose of energy saving and optimization of the energy consumption of the heat exchange system is achieved.

As shown in fig. 4, in an embodiment, the control parameters include a cold-end water inlet temperature, a cold-end water outlet temperature, a cold-end flow rate, a hot-end water inlet temperature, a hot-end water outlet temperature, and a hot-end flow rate, and step S301 includes:

step S401: selecting a graph vertex at a cold source end and a graph vertex at a hot source end from a plurality of graph vertices as a starting graph vertex and an ending graph vertex respectively;

step S402: and executing control parameter calculation operation on the vertexes of the graphs in sequence according to the direction from the vertex of the starting graph to the vertex of the ending graph.

Wherein, step S402 may specifically include:

step S4021: determining initial side parameters of the graph vertex;

step S4022: determining the parameters of the termination side of the graph vertex through the model constraint conditions and the preset value set of the termination side of the graph vertex to obtain the control parameters of the graph vertex;

step S4023: determining the ending side parameter of the graph vertex as the starting side parameter of the next graph vertex, and circulating the previous calculation step;

and determining the starting side parameters of the starting graph vertex according to the environment parameters corresponding to the starting graph vertex.

For example, in step S401, for the heat exchange system of the data center, the graph vertex at the cold source end may be a graph vertex corresponding to a heat exchange device located outdoors; the map vertices at the hot end may be map vertices corresponding to heat exchange devices located indoors. The diagram vertex at the cold source end can be used as an initial diagram vertex, the diagram vertex at the hot source end can be used as a termination diagram vertex, and the environment parameter of the cold source end can be used as a cold input parameter of the heat exchange system, namely the input quantity of the diagram optimization strategy; or, the graph vertex at the hot source end may be used as a start graph vertex, the graph vertex at the cold source end may be used as a stop graph vertex, and the environment parameter at the hot source end may be used as a heat input parameter of the heat exchange system, that is, an input amount of the graph optimization strategy.

Illustratively, in step S402, referring to fig. 9, the thermodynamic flow diagram includes seven diagram vertices, where the control objects of diagram vertex 1, diagram vertex 2, diagram vertex 3, diagram vertex 4, and diagram vertex 6 are heat exchange devices, and the control objects of diagram vertex 5 and diagram vertex 7 are multi-pass devices. The left end of the thermal flow diagram is a cold source end, the right end of the thermal flow diagram is a hot source end, wherein diagram vertex 1 and diagram vertex 2 are diagram vertices at the cold source end, and diagram vertex 6 is a diagram vertex at the hot source end. Taking the graph vertex at the cold source end as an initial vertex, the graph vertex 1 and/or the graph vertex 2 may be used as a starting vertex of the thermal flow graph, and the graph vertex 6 may be used as an ending vertex of the thermal flow graph. The control parameter calculation operation is performed for each graph vertex in turn in the direction from graph vertex 1 or graph vertex 2 to graph vertex 6.

Further, the states of the diagram vertex may include a cooling state, an activated state, and a frozen state, wherein the cooling state is used to characterize the diagram vertex that has not performed the control parameter calculation operation, and the color of the diagram vertex in the cooling state may be configured as white; the activated state is used for representing that the graph vertex is executing the control parameter calculation operation, and the color of the graph vertex in the activated state can be configured to be red; the frozen state is used for representing that the graph vertex has completed the control parameter calculation operation, namely the control parameter of the graph vertex is obtained, and the color of the graph vertex in the frozen state can be configured to be blue. In the figure, the state of the vertices 1 to 5 is the frozen state, and the state of the vertices 6 and 7 is the cooled state.

Specifically, the state of each graph vertex may be set to the activated state in sequence according to the direction from the starting graph vertex to the ending graph vertex, and the state of each graph vertex may be set to the frozen state after the control parameter calculation operation is performed. And then setting the next graph vertex related to the graph vertex in the freezing state as an activated state, and executing control parameter calculation operation until the control parameters of the graph vertex are calculated and terminated.

For example, in step S4021, the start side parameter of the graph vertex may be a parameter on the cold source side or the hot source side where the adjacent graph vertex is located. Taking the diagram vertex at the cold source end as an example, the parameters of the starting side of the diagram vertex may be the cold end water inlet temperature, the cold end water outlet temperature, and the cold end flow rate. Taking the vertex of the initial graph as the vertex of the graph at the hot end as an example, the parameters of the initial side of the vertex of the graph can be the hot end water inlet temperature, the hot end water outlet temperature and the hot end flow.

For example, in step S4022, taking the start graph vertex as the graph vertex at the cold source end as an example, the model constraint condition may be that the following function is satisfied:

T _{h_out} ＝F(T _{c_in} ,T _{c_out} ,Q _c ,T _{h_in} ,Q _h )。

obtaining a starting side parameter, i.e., T, based on step S4021 _{c_in} (temperature of water entering from cold source end), T _{c_out} (Cold Source end Water temperature) and Q _c (cold source flow), and then, determining T according to the preset value set of the termination side _{h_in} (hot end Water temperature) and Q _h (hot end flow), and then determining T according to the model constraint conditions _{h_out} And the hot end water outlet temperature is obtained, so that the control parameters of the top point of the graph are obtained.

Wherein, the preset value set of the terminating side may include T _{h_in} (hot end inlet temperature) and Q _h A preset value set for (hot-end traffic).

Exemplarily, in step S4023, taking the starting graph vertex as the graph vertex at the cold source end as an example, after determining the terminating-side parameter of the graph vertex, taking the terminating-side parameter of the graph vertex as the starting-side parameter of the next graph vertex associated with the terminating-side parameter, calculating the control parameter of the next graph vertex according to the model constraint condition and the preset value set of the terminating side of the graph vertex, and repeating the steps until the control parameters of all the graph vertices are obtained.

It should be noted that the starting-side parameter of the starting graph vertex can be determined according to the environment parameter corresponding to the starting graph vertex. Taking the graph vertex at the cold source end as an example, the starting side parameter of the starting graph vertex may determine an approximate value range according to the environmental parameter (such as dry-bulb temperature, wet-bulb temperature, relative humidity, and the like) of the cold source end, and divide the value range into a plurality of reference values according to a preset step length, so as to obtain a preset value set of the starting side parameter of the starting graph vertex.

By the implementation mode, the control parameters of each graph vertex can be rapidly solved, the control parameters of a plurality of graph vertices meeting the dynamic balance of the thermal flow graph are provided, and the calculation accuracy is high.

As shown in fig. 5, in one embodiment, step S302 includes:

step S501: associating control parameters of each graph vertex to generate a plurality of feasible solutions;

step S502: determining the value range of the termination side parameter of the vertex of the termination graph according to the environment parameter of the vertex of the termination graph;

step S503: and filtering the feasible solutions according to the value range of the termination side parameter of the vertex of the termination graph to obtain the feasible region of the thermal flow graph.

For example, in step S501, the control parameters of all map vertices in the frozen state may be associated to form a plurality of feasible solutions of the thermal flow map.

Exemplarily, in step S502, taking the termination graph vertex as the graph vertex at the heat source end as an example, a rough value range of the termination side parameter of the termination graph vertex is determined according to the environment parameters (such as dry-bulb temperature, wet-bulb temperature, relative humidity, and the like) of the heat source end, and the value range is divided into a plurality of reference values according to a preset step length, so as to obtain a preset value set of the termination side parameter of the termination graph vertex.

Exemplarily, in step S503, the feasible solutions are filtered according to the preset value set of the termination side parameter at the vertex of the termination graph, the feasible solutions meeting the preset value set of the termination side parameter at the vertex of the termination graph are selected, and finally the feasible region of the thermal flow graph is obtained.

Through the implementation mode, a plurality of feasible solutions of the thermal flow diagram can be filtered, so that the finally obtained feasible domain meets the dynamic balance of the heat exchange system under the current environmental condition, and the calculation precision of the feasible domain is further improved.

As shown in fig. 6, in one embodiment, step S402 may include:

step S601: associating control parameters of each graph vertex to generate a plurality of feasible solutions;

step S602: and under the condition that homomorphic solutions exist in the plurality of feasible solutions, pruning the homomorphic solutions to obtain feasible domains of the thermal flow graph.

It should be noted that the thermal flow graph search space of the heat exchange system is usually large, and pruning is performed on homomorphic solutions in multiple feasible solutions, so that the efficiency of graph optimization is improved, and it is ensured that the finally obtained feasible domain does not include the same or similar feasible solutions.

In one embodiment, the homomorphic solution satisfies the following condition:

for the vertex of the graph with the outlet degree and the inlet degree of the end side both larger than 0, a plurality of feasible solutions with the same product of the difference value of the inlet water temperature and the outlet water temperature and the flow rate of the end side are homomorphic solutions; and/or the presence of a gas in the gas,

for the graph vertex of which the output degree of the ending side is greater than 0 and the input degree of the ending side is equal to 0, a plurality of feasible solutions with the same flow rate and the same output water temperature of the ending side are homomorphic solutions.

In one example, as shown in fig. 9, taking the initial graph vertex as the graph vertex at the cold source end as an example, the graph vertex with the out-degree and the in-degree both greater than 0 at the termination side may be the graph vertices with the out-degree and the in-degree both greater than 0 at the side adjacent to the hot source end, i.e., graph vertex 4 and graph vertex 3 in the diagram. For either graph vertex 4 or graph vertex 3, Q exists among the multiple possible solutions _h (T _{h_in} -T _{h_out} ) And under the condition of equal feasible solutions, determining the feasible solutions as homomorphic solutions.

In another example, as shown in FIG. 9, taking an initial graph vertex as the graph vertex at the cold source end as an example, a graph vertex with an out-degree greater than 0 at the terminal side and an in-degree equal to 0 at the terminal side may be a graph vertex with an out-degree greater than 0 and an in-degree equal to 0 at the adjacent hot source end side, i.e., graph vertex 5 in the graph _h And T _{h_out} And determining the feasible solutions as homomorphic solutions under the condition of the feasible solutions which are all equal.

As shown in fig. 7, in one embodiment, step S702 may include:

step S701: respectively calculating the cost value corresponding to each feasible solution for a plurality of feasible solutions in the homomorphic solution;

step S702: and reserving the feasible solution with the minimum cost value, and rejecting the rest feasible solutions.

The cost value corresponding to the feasible solution is the sum of the energy consumption of each energy consumption device of the heat exchange system under the feasible solution. The cost value corresponding to each feasible solution can be obtained through calculation of a model for describing the vertex cost.

Through the implementation mode, pruning processing of homomorphic solutions in the multiple feasible solutions can be realized, and the feasible solutions left after pruning processing are guaranteed to be the feasible solutions with the lowest cost values in the homomorphic solutions, so that the calculation accuracy of the target solution is improved.

A control method of the heat exchange system according to an embodiment of the present disclosure is described below as one specific example with reference to fig. 9 and 10.

As shown in fig. 10, the method includes the steps of:

step S1001: constructing a thermal flow diagram according to the structure of the heat exchange system;

step S1002: determining a cold source vertex and a heat source vertex of a thermal flow diagram; wherein, the cold source vertex is the graph vertex at the cold source end, and the heat source vertex is the graph vertex at the heat source end;

step S1003: the cold source vertex is initially taken as an activated vertex; in other words, the state of the cold source vertex is initialized to the activated state;

step S1004: and generating a feasible domain after the freezing network is associated with and activates the vertex according to the vertex parameter value set, the model constraint condition and the preset rule of the thermal flow diagram. The vertex parameter value set can be obtained by intercepting a plurality of reference values by setting corresponding step length according to the preset value range of each control parameter of the vertex; the model constraints may be a function preset based on a plurality of control parameters of the vertices; the feasible region includes a plurality of feasible solutions for all of the frozen vertices, each feasible solution including control parameters for all of the frozen vertices.

Referring to fig. 9, the step of optimizing the control parameter will be described in detail by taking the vertex of the cold source as the vertex of the initial graph.

(1) As shown in Table 1, the determination is based on the environmental parameters of the cold source sideCold source side parameter S of cold source vertex namely vertex 1 _1c 。

	T _{c_in}	Q _c	T _{c_out}
				S _1c1	T _{c_in_1}	Q _c1	T _{c_out_1}
S _1c2	T _{c_in_2}	Q _c2	T _{c_out_2}

TABLE 1

(2) According to the model constraint condition of vertex 1:

T _{h_out} ＝F(T _{c_in} ,T _{c_out} ,Q _c ,T _{h_in} ,Q _h )，

solving for Heat Source side parameter S of vertex 1 _1h And obtains the control parameter set of vertex 1 as shown in table 2.

TABLE 2

(3) According to a preset T _{h_out} Has a value range of [ T _{h_out_min} ,T _{h_out_max} ]The control parameter set for vertex 1 is filtered and a feasible solution for vertex 1 is obtained as shown in table 3.

T _{c_in}

Q _c

T _{c_out}

T _{h_in}

Q _h

T _{h_out}

S ₁₁

T _{c_in_1}

Q _c1

T _{c_out_1}

T _{h_in_1}

Q _h1

F(S ₁₁ ')

S ₁₃

T _{c_in_1}

Q _c1

T _{c_out_1}

T _{h_in_1}

Q _h2

F(S ₁₃ ')

S ₁₅

T _{c_in_2}

Q _c2

T _{c_out_2}

T _{h_in_1}

Q _h1

F(S ₁₅ ')

S ₁₆

T _{c_in_2}

Q _c2

T _{c_out_2}

T _{h_in_2}

Q _h1

F(S ₁₆ ')

TABLE 3

(4) And judging whether homomorphic solutions exist in the feasible solutions of the top point 1, and pruning the homomorphic solutions under the condition that the homomorphic solutions meet pruning conditions. Specifically, referring to table 4, assuming states S52 and S53, corresponding to arc 5 → 6 in fig. 9, for the same hot side flow and hot side leaving water temperature, only the least costly one of

solutions

2 and 3 remains.

TABLE 4

(5) The state of vertex 1 is set to the frozen state, and vertex 2 associated with vertex 1 is set to the activated state, and the control parameter calculation operation is performed on vertex 2.

And (3) taking the next cooling vertex related to the freezing vertex as an activated vertex in the process of executing the control parameter calculation operation, and executing the steps (3) and (4).

(6) If the next cooling vertex associated with the freeze vertex is a heat source vertex, then performing constrained filtering on the feasible region according to the heat source vertex characteristics and setting the heat source vertex as the freeze vertex.

(7) And evaluating the cost value of each solution in the final feasible region, and replacing the solution with the minimum value as the optimal solution. And the cost value is the sum of the energy consumptions of all energy consumption equipment of the heat exchange system under the solution.

According to an embodiment of the present disclosure, the present disclosure also provides a data center.

The data center comprises a heat exchange system, and the heat exchange system adopts the control method according to any one of the above embodiments of the present disclosure to be in an energy consumption balance state.

According to the embodiment of the disclosure, the disclosure also provides a control device of the heat exchange system.

As shown in fig. 11, the apparatus includes:

a configuration module 1101, configured to perform modular configuration on the heat exchange system to obtain at least one sub-module;

an attribute description module 1102, configured to perform attribute description on a control object in which at least one sub-module is operated, to obtain attribute description information;

a thermal flow graph generating module 1103, configured to obtain a thermal flow graph based on a graph optimization strategy according to the attribute description information;

and the control parameter calculation module 1104 is configured to obtain a control parameter according to the environmental parameters of the cold source end and the hot source end and the thermal flow diagram, and keep the heat exchange system in an energy consumption balance state under the driving of the control parameter.

In one embodiment, at least one sub-module comprises at least one of a heat exchange module, a power module, and a connection module; the device also includes:

and the connecting module is used for connecting the heat exchange module and the power module through the connecting module under the condition that at least one sub-module comprises the heat exchange module, the power module and the connecting module, transmitting indoor heat to the outdoor and transmitting outdoor cold to the indoor.

In one embodiment, the thermal flow diagram generation module 1103 is further configured to:

the graph vertex for describing the heat exchange and multi-channel connection attribute and the graph directed edge for describing the pipeline attribute in the multi-channel connection attribute.

In one embodiment, the control parameter calculation module 1104 includes:

the control parameter calculation submodule is used for sequentially solving the control parameters of the vertexes of the graphs through model constraint conditions and preset value sets of the vertexes of the graphs according to the environmental parameters of the cold source end and the hot source end;

the feasible region generation submodule is used for generating a feasible region of the thermal flow graph based on the control parameters of the vertexes of each graph, the feasible region comprises a plurality of feasible solutions, and the feasible solutions are a set of the control parameters of the vertexes of each graph;

and the target solution determining submodule is used for taking the feasible solution of the minimum energy consumption equilibrium state for keeping the heat exchange system in accordance with the threshold value as the target solution of the thermal flow diagram.

In one embodiment, the control parameters include cold-end inlet temperature, cold-end outlet temperature, cold-end flow, hot-end inlet temperature, hot-end outlet temperature, and hot-end flow, and the control parameter calculation sub-module includes:

a start graph vertex and end graph vertex determining unit for selecting a graph vertex at a cold source end and a graph vertex at a hot source end from the plurality of graph vertices as a start graph vertex and an end graph vertex, respectively;

the control parameter calculation unit is used for sequentially executing control parameter calculation operation on each graph vertex according to the direction from the starting graph vertex to the ending graph vertex, and specifically comprises the following steps:

a starting side parameter determining subunit, configured to determine a starting side parameter of the graph vertex;

the control parameter generating subunit is used for determining the termination side parameters of the graph vertexes through the model constraint conditions and the preset value set of the termination side of the graph vertexes so as to obtain the control parameters of the graph vertexes;

a circulation unit, configured to determine the ending-side parameter of the graph vertex as the starting-side parameter of the next graph vertex, and circulate the previous calculation step;

and determining the initial side parameter of the initial graph vertex according to the environment parameter corresponding to the initial graph vertex.

In one embodiment, the control parameter calculation module 1104 includes:

the feasible solution generation submodule is used for associating the control parameters of the vertexes of the graphs so as to generate a plurality of feasible solutions;

the termination side parameter determining submodule is used for determining the value range of the termination side parameter of the vertex of the termination graph according to the environment parameter of the vertex of the termination graph;

and the feasible region generation submodule is used for filtering the feasible solutions according to the value range of the termination side parameter of the vertex of the termination graph so as to obtain the feasible region of the thermal flow graph.

In one embodiment, the control parameter calculation module 1104 includes:

and the pruning submodule is used for pruning the homomorphic solution under the condition that the homomorphic solution exists in the feasible solutions so as to obtain the feasible domain of the thermal flow graph.

In one embodiment, the homomorphic solution satisfies the following condition:

In one embodiment, the pruning submodule includes:

the cost value calculating unit is used for calculating the cost value corresponding to each feasible solution for a plurality of feasible solutions in the homomorphic solution;

and the rejecting unit is used for reserving the feasible solution with the minimum cost value and rejecting other feasible solutions.

The functions of each unit, module or sub-module in each apparatus in the embodiments of the present disclosure may refer to the corresponding description in the above method embodiments, and are not described herein again.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 12 shows a schematic block diagram of an example electronic device 1200, which can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 12, the electronic apparatus 1200 includes a computing unit 1201, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1202 or a computer program loaded from a storage unit 1208 into a Random Access Memory (RAM) 1203. In the RAM 1203, various programs and data necessary for the operation of the electronic apparatus 1200 may also be stored. The computing unit 1201, the ROM 1202, and the RAM 1203 are connected to each other by a bus 1204. An input/output (I/O) interface 1205 is also connected to bus 1204.

Various components in the electronic device 1200 are connected to the I/O interface 1205, including: an input unit 1206 such as a keyboard, a mouse, or the like; an output unit 1207 such as various types of displays, speakers, and the like; a storage unit 1208 such as a magnetic disk, optical disk, or the like; and a communication unit 1209 such as a network card, modem, wireless communication transceiver, etc. The communication unit 1209 allows the electronic device 1200 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 1201 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1201 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 1201 performs the various methods and processes described above, such as the control method of the heat exchange system. For example, in some embodiments, the control method of the heat exchange system may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1208. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 1200 via the ROM 1202 and/or the communication unit 1209. When the computer program is loaded into the RAM 1203 and executed by the computing unit 1201, one or more steps of the control method of the heat exchange system described above may be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured by any other suitable means (e.g., by means of firmware) to perform the control method of the heat exchange system.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method of controlling a heat exchange system, comprising:

performing attribute description on a control object operating the at least one sub-module according to a heating and ventilation system architecture of the heat exchange system to obtain attribute description information; the attribute description information comprises a control parameter of each sub-module in the at least one sub-module, position information of each sub-module and output connection equipment or input connection equipment of each sub-module;

obtaining a thermal flow graph based on a graph optimization strategy according to the attribute description information; wherein the thermal flow graph comprises nodes and edges, the nodes are used for representing heat exchange equipment or multi-pass equipment, and the edges are used for representing connecting equipment;

2. The method of claim 1, wherein the at least one sub-module comprises at least one of a heat exchange module, a power module, and a connection module;

in the case where the at least one sub-module includes a heat exchange module, a power module, and a connection module, the method further includes: the heat exchange module is connected with the power module through the connecting module, indoor heat is transmitted to the outdoor, and outdoor cold is transmitted to the indoor.

3. The method of claim 1, wherein the graph-based optimization strategy thermal flow graph comprises: and the graph vertex is used for describing heat exchange and multi-channel connection attributes, and the graph directed edge is used for describing the pipeline attributes in the multi-channel connection attributes.

4. The method of claim 3, wherein obtaining control parameters according to the cold-source-side and hot-source-side environmental parameters and the thermal flow diagram, and keeping the heat exchange system in an energy consumption balance state under the driving of the control parameters comprises:

sequentially solving the control parameters of the graph vertexes through model constraint conditions and preset value sets of the graph vertexes according to the environmental parameters of the cold source end and the hot source end;

generating a feasible domain of the thermal flow graph based on the control parameters of the graph vertices, wherein the feasible domain comprises a plurality of feasible solutions, and the feasible solutions are a set of the control parameters of the graph vertices;

and taking the feasible solution of the minimum energy consumption equilibrium state for keeping the heat exchange system in accordance with the threshold value as the target solution of the thermal flow diagram.

5. The method of claim 4, wherein the control parameters include cold-end water inlet temperature, cold-end water outlet temperature, cold-end flow rate, hot-end water inlet temperature, hot-end water outlet temperature, and hot-end flow rate, and the sequentially solving the control parameters of each of the graph vertices through model constraint conditions and preset value sets of each of the graph vertices according to the environmental parameters of the cold-end and the hot-end comprises:

selecting a graph vertex at a cold source end and a graph vertex at a hot source end from the plurality of graph vertices to be used as a starting graph vertex and an ending graph vertex respectively;

according to the direction from the vertex of the starting graph to the vertex of the ending graph, sequentially executing control parameter calculation operation on the vertexes of the graphs, and specifically comprising the following steps:

determining a starting side parameter of the graph vertex;

determining a termination side parameter of the graph vertex through a model constraint condition and a preset value set of the termination side of the graph vertex to obtain a control parameter of the graph vertex;

determining the ending side parameter of the graph vertex as the starting side parameter of the next graph vertex, and circulating the previous calculation step;

and determining the starting side parameter of the starting graph vertex according to the environment parameter corresponding to the starting graph vertex.

6. The method of claim 5, wherein generating a feasible domain of the thermal flow graph based on the control parameters of each graph vertex comprises:

associating control parameters for each of said graph vertices to generate a plurality of feasible solutions;

determining the value range of the termination side parameter of the termination graph vertex according to the environment parameter of the termination graph vertex;

and filtering the feasible solutions according to the value range of the termination side parameter of the vertex of the termination graph to obtain the feasible domain of the thermal flow graph.

7. The method of claim 4, wherein generating a feasible domain of the thermal flow graph based on the control parameters of each graph vertex comprises:

and under the condition that homomorphic solutions exist in the feasible solutions, pruning the homomorphic solutions to obtain feasible domains of the thermal flow graph.

8. The method of claim 7, wherein the homomorphic solution satisfies the following condition:

for the vertex of the graph with the outlet degree and the inlet degree of the final side both larger than 0, a plurality of feasible solutions with the same product of the difference value of the inlet water temperature and the outlet water temperature and the flow rate of the final side are homomorphic solutions; and/or the presence of a gas in the gas,

and for the vertex of the graph with the final side out-degree greater than 0 and the final side in-degree equal to 0, a plurality of feasible solutions with the same flow and outlet water temperature at the final side are homomorphic solutions.

9. The method of claim 7, wherein pruning the homomorphic solution comprises:

for a plurality of feasible solutions in the homomorphic solution, respectively calculating a cost value corresponding to each feasible solution;

and reserving the feasible solution with the minimum cost value, and rejecting the rest feasible solutions.

10. A control device for a heat exchange system comprising:

the attribute description module is used for carrying out attribute description on a control object operating the at least one sub-module according to a heating and ventilation system framework of the heat exchange system to obtain attribute description information; the attribute description information comprises control parameters of each sub-module in the at least one sub-module, position information of each sub-module and outgoing degree connecting equipment or incoming degree connecting equipment of each sub-module;

the thermal flow graph generating module is used for obtaining a thermal flow graph based on a graph optimization strategy according to the attribute description information; wherein the thermal flow graph comprises nodes and edges, the nodes are used for representing heat exchange equipment or multi-pass equipment, and the edges are used for representing connecting equipment;

11. The apparatus of claim 10, wherein the at least one sub-module comprises at least one of a heat exchange module, a power module, and a connection module; the device further comprises:

and the connecting module is used for connecting the heat exchange module with the power module through the connecting module under the condition that the at least one sub-module comprises the heat exchange module, the power module and the connecting module, transmitting indoor heat to the outdoor and transmitting outdoor cold to the indoor.

12. The apparatus of claim 10, wherein the thermal flow graph generation module is further configured to:

the graph vertex is used for describing the attributes of heat exchange and multi-pass connection, and the graph directed edge is used for describing the attributes of the pipelines in the multi-pass connection.

13. The apparatus of claim 12, wherein the control parameter calculation module comprises:

the control parameter calculation submodule is used for sequentially solving the control parameters of the chart vertexes through model constraint conditions and preset value sets of the chart vertexes according to the environmental parameters of the cold source end and the hot source end;

a feasible region generation submodule, configured to generate a feasible region of the thermal flow graph based on the control parameter of each graph vertex, where the feasible region includes multiple feasible solutions, and the feasible solutions are sets of the control parameters of each graph vertex;

14. The apparatus of claim 13, wherein the control parameters include cold end inlet temperature, cold end outlet temperature, cold end flow, hot end inlet temperature, hot end outlet temperature, and hot end flow, the control parameter calculation sub-module comprising:

a start graph vertex and end graph vertex determining unit, configured to select a graph vertex at a cold source end and a graph vertex at a hot source end from the multiple graph vertices, as a start graph vertex and an end graph vertex, respectively;

the control parameter calculation unit is configured to sequentially perform a control parameter calculation operation on each graph vertex according to a direction from the starting graph vertex to the ending graph vertex, and specifically includes:

the control parameter generating subunit is used for determining the termination side parameter of the graph vertex through a model constraint condition and a preset value set of the termination side of the graph vertex so as to obtain the control parameter of the graph vertex;

a loop unit, configured to determine an ending-side parameter of the graph vertex as a starting-side parameter of a next graph vertex, and loop the previous calculation step;

15. The apparatus of claim 14, wherein the control parameter calculation module comprises:

16. The apparatus of claim 13, wherein the control parameter calculation module comprises:

17. The apparatus of claim 16, wherein the homomorphic solution satisfies the following condition:

18. The apparatus of claim 16, wherein the pruning submodule comprises:

a cost value calculation unit, for a plurality of feasible solutions in the homomorphic solution, respectively calculating a cost value corresponding to each feasible solution;

and the rejecting unit is used for reserving the feasible solution with the minimum cost value and rejecting the rest feasible solutions.

19. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-9.

21. A data center, comprising:

a heat exchange system employing the method of any one of claims 1-9 to be in energy consumption equilibrium.