Heat supply control method and device for medium-deep geothermal units based on temperature node network analysis

Abstract

The present invention relates to the field of geothermal unit technology, and is a method and device for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis, comprising: obtaining a directed edge set of a control node, extracting directed edges from the directed edge set, constructing a directed edge network based on the directed edges, extracting subnodes based on the directed edge network and calculating subnode temperatures, constructing a directed edge network based on subnode temperatures, aggregating multiple directed edge networks and importing them into an initial node network, performing a calibration operation on the initial node network using a pre-constructed prediction value correction method, obtaining a temperature node network, obtaining a predicted temperature supply value, and completing heating supply control of a medium-deep geothermal unit based on temperature node network analysis based on the predicted temperature supply value and the temperature node network. The present invention can solve the construction of a temperature node network of a geothermal unit, and use the temperature node network to predict the temperature values ​​corresponding to different nodes, thereby realizing a control strategy for low-loss regulation of geothermal units.

Description

Technical Field

[0001] The present invention relates to the technical field of geothermal units, and in particular to a method, device, electronic equipment and computer-readable storage medium for controlling heating of a medium-deep geothermal unit based on temperature node network analysis. Background Art

[0002] With the rapid development of the world, clean energy as the driving force of the new energy industry needs to be explored urgently. Among them, geothermal energy, as an energy that has not been fully developed among clean energy, needs to be explored even more. Therefore, how to monitor the geothermal energy heating system is of great significance to the utilization of geothermal energy.

[0003] At present, geothermal energy mainly comes from the middle and deep layers, and geothermal units are used for heating, which mainly relies on a simple temperature feedback mechanism.

[0004] Although the above method can monitor and control the geothermal unit through feedback, it cannot accurately predict and control the temperature changes inside the geothermal unit and its system. When temperature control is required, it is often based on experience and is achieved through multiple debugging. Summary of the invention

[0005] The present invention provides a method for controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis and a computer-readable storage medium. The main purpose of the method is to solve the construction of a temperature node network for a geothermal unit, and to use the temperature node network to predict the temperature values ​​corresponding to the changes in different nodes, thereby realizing a control strategy for low-loss regulation of the geothermal unit.

[0006] To achieve the above object, the present invention provides a method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis, comprising:

[0007] Acquire multiple control nodes, acquire control coordinates corresponding to each of the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates;

[0008] Wherein, the obtaining of multiple control nodes includes:

[0009] Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit;

[0010] Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit;

[0011] Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit;

[0012] Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units:

[0013] Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit;

[0014] Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit;

[0015] Constructing a compression water return node based on the heat exchange unit and the first water return unit;

[0016] A second water supply node is constructed by using a heat exchange unit and a second water supply unit;

[0017] The second water return node is constructed by using the heat exchange unit and the second water return unit;

[0018] Obtaining a user usage node according to the second water supply node and the second water return node;

[0019] Summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user nodes to obtain multiple control nodes;

[0020] Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes:

[0021] Obtain the directed edge set of the extracted control node, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges:

[0022] Dividing the extracted directed edges by using a preset prediction step length to obtain a plurality of child nodes, obtaining the child node coordinates of each child node in the plurality of child nodes to obtain a child node coordinate set, and constructing a directed edge network based on the child node coordinate set and the extracted directed edges;

[0023] Subnodes are extracted from the multiple subnodes in sequence, and the following operations are performed on the extracted subnodes:

[0024] Acquiring a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculating a subnode temperature of the extracted subnode based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and importing the subnode temperature into the directed edge network to complete the construction of the directed edge network;

[0025] Aggregating multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and importing the directed edge network set into the initial node network;

[0026] Acquire multiple network nodes based on an initial node network, extract network nodes from the multiple network nodes in sequence, acquire node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network;

[0027] The predicted heating value is obtained, and after the predicted heating value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating regulation of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

[0028] Optionally, the acquiring of multiple control nodes includes:

[0029] Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit;

[0030] Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit;

[0031] Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit;

[0032] Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units:

[0033] Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit;

[0034] Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit;

[0035] Constructing a compression water return node based on the heat exchange unit and the first water return unit;

[0036] A second water supply node is constructed by using a heat exchange unit and a second water supply unit;

[0037] The second water return node is constructed by using the heat exchange unit and the second water return unit;

[0038] Obtaining a user usage node according to the second water supply node and the second water return node;

[0039] The heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user use nodes are summarized to obtain multiple control nodes.

[0040] Optionally, the calculating the sub-node temperature of the extracted sub-node based on the first endpoint temperature, the second endpoint temperature and the extracted sub-node comprises:

[0041] Constructing a prediction node set based on the child node coordinate set, wherein the prediction node set includes a plurality of prediction nodes;

[0042] Prediction nodes are extracted from the prediction node set in sequence, and the following operations are performed on the extracted prediction nodes:

[0043] Obtain the directed edge corresponding to the extracted prediction node to obtain the target edge, obtain the first end and the second end of the target edge based on the target edge, and obtain a real point coordinate set and a real value set based on the first end and the second end, wherein the real point coordinate set includes: a first point coordinate corresponding to the first end and a second point coordinate corresponding to the second end, and the real value set includes: a first temperature corresponding to the first end and a second temperature corresponding to the second end;

[0044] Obtaining the child node coordinates of the extracted prediction node to obtain the prediction node coordinates, calculating the distance influence weight of the extracted prediction node using a pre-constructed distance influence formula and a real point coordinate set, and calculating the node prediction value of the extracted prediction node based on the distance influence weight and the real value set;

[0045] Eliminate the prediction node coordinates of the prediction nodes extracted from the prediction node set to obtain an updated prediction set;

[0046] After confirming that the updated prediction set is a prediction node set, the node prediction value is input into the real value set, and the prediction node coordinate is input into the real point coordinate set, thereby obtaining an updated real value set and an updated real point coordinate set;

[0047] After confirming that the updated true value set is the true value set and the updated true point coordinate set is the true point coordinate set, return to the step of extracting prediction nodes from the prediction node set in sequence, and perform the following operations on the extracted prediction nodes until the updated prediction set is an empty set.

[0048] Optionally, the distance affects the formula as follows:

[0049] ;

[0050] in, Indicates that the sequence number of the real point coordinate set is The distance influence weight of the real point coordinates on the extracted prediction node, represents the predicted node coordinates of the extracted predicted node, and the predicted node coordinates are the coordinates in the corresponding spatial coordinate system in the initial node network, Indicates that the sequence number of the real point coordinate set is The label corresponding to the real point coordinates, Indicates that the sequence number of the real point coordinate set is The distance between the real point coordinates and the predicted node coordinates, represents the weight control coefficient, Indicates the total number of influence point coordinates in the influence point coordinate set.

[0051] Optionally, the calculating the node prediction value of the extracted prediction node based on the distance influence weight and the true value set includes:

[0052] Construct a sub-node temperature prediction formula, and calculate the node prediction value of the extracted prediction node according to the sub-node temperature prediction formula and the distance influence weight, wherein the sub-node temperature prediction formula is:

[0053] ;

[0054] in, represents the node prediction value of the extracted child node, Represents the sequence number of the real point coordinates in the real point coordinate set, Indicates that the sequence number of the real point coordinate set corresponding to the extracted prediction node is The distance influence weight of the real point coordinates on the extracted prediction node, Indicates the serial number is The real value corresponding to the real point coordinates.

[0055] Optionally, the acquiring node temperature data of the extracted network node, after performing an identification operation on the extracted network node based on the node temperature data, comprises:

[0056] Based on the extracted network node, determine whether the network node is a control node, if the extracted network node is a control node, remove the extracted network node, otherwise, retain the extracted network node to obtain a network sub-node;

[0057] Aggregate multiple network sub-nodes to obtain a network sub-node set, extract network sub-nodes from the network sub-node set in sequence, and perform the following operations on the extracted network sub-nodes:

[0058] Node temperature data is obtained based on the extracted network sub-nodes, multiple initial predicted temperature values ​​are obtained based on the node temperature data, the average of the multiple initial predicted temperature values ​​is calculated to obtain the node prediction average, and the node prediction average is used to perform an identification operation on the extracted network sub-nodes.

[0059] Optionally, the performing a calibration operation on the initial node network using a pre-constructed prediction value correction method includes:

[0060] Based on the initial node network, multiple real control nodes are obtained, real control nodes are extracted from the multiple real control nodes in sequence, and the following operations are performed on the extracted real control nodes:

[0061] Obtaining an influence sub-node set of the extracted real control node, and obtaining an influence prediction value set based on the extracted influence sub-node set, wherein the influence sub-nodes in the influence sub-node set correspond one-to-one to the influence prediction values ​​in the influence prediction value set;

[0062] Calculate the control point prediction value of the extracted real control node using the distance influence formula, the sub-node temperature prediction formula, the influence sub-node set and the influence prediction value set, calculate the prediction error based on the control point prediction value and the extracted real control node, and compare the prediction error with a preset prediction deviation threshold;

[0063] If the prediction error is less than or equal to the prediction deviation threshold, confirming that the control point prediction value is the optimal prediction value of the extracted real control node;

[0064] Otherwise, the control point prediction value is corrected using the pre-constructed correction coefficient to obtain the optimal prediction value;

[0065] Aggregating multiple optimal prediction values, and performing a calibration operation on the initial node network based on the multiple optimal prediction values.

[0066] Optionally, the calculation formula of the prediction error is as follows:

[0067] ;

[0068] in, represents the prediction error of the extracted real control node, Indicates the sequence number of the extracted real control node, Indicates the serial number is The control point prediction value of the real control node, Indicates the serial number is The true measurement value of the true control node.

[0069] Optionally, obtaining the predicted temperature supply value includes:

[0070] Obtain a historical heating data set, divide the historical heating data set using a pre-built time period division method to obtain multiple heating time periods, extract heating time periods from the multiple heating time periods in sequence, and perform the following operations on the extracted heating time periods:

[0071] Based on the extracted heating period, a heating period data set is obtained, user use nodes are sequentially extracted from the plurality of user use nodes, and the following operations are performed on the extracted user use nodes:

[0072] Acquire a heating data set based on the extracted user control nodes, acquire a heating mean and a heating variance based on the heating data set, construct a heating interval according to the heating mean and the heating variance, and acquire a maximum heating value of the extracted user use node based on the heating interval;

[0073] A plurality of maximum heating values ​​are aggregated to obtain a maximum heating value set, and a predicted heating value is obtained based on the maximum heating value set.

[0074] To achieve the above object, the present invention also provides a heat supply control device for a medium-deep geothermal unit based on temperature node network analysis, comprising:

[0075] The initial node network construction module is used to obtain multiple control nodes, obtain control coordinates corresponding to each control node in the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates, wherein the acquisition of multiple control nodes includes: obtaining a heat exchange unit, obtaining a heat source unit, a first water supply unit, a first water return unit, and multiple compression heat supply units based on the heat exchange unit, constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit, constructing a heat source return water node and a first return water node based on the heat source unit and the first water return unit, extracting compression heat supply units from the multiple compression heat supply units in sequence, and performing the following operations on the extracted compression heat supply units Operation: based on the extracted compression heat supply unit, obtain the heat exchange unit, the second water supply unit and the second water return unit, construct the compression water supply node according to the heat exchange unit unit and the first water supply unit, construct the compression water return node based on the heat exchange unit unit and the first water return unit, use the heat exchange unit unit and the second water supply unit to construct the second water supply node, use the heat exchange unit unit and the second water return unit to construct the second water return node, obtain the user use node according to the second water supply node and the second water return node, summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compression water supply nodes, multiple compression water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user use nodes to obtain multiple control nodes;

[0076] The directed edge network set construction module is used to extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain the directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges using a preset prediction step to obtain multiple child nodes, obtain the child node coordinates of each child node in the multiple child nodes, obtain the child node coordinate set, and construct a directed edge network based on the child node coordinate set and the extracted directed edges. A directed edge network is constructed, and subnodes are sequentially extracted from the plurality of subnodes, and the following operations are performed on the extracted subnodes: a first endpoint temperature and a second endpoint temperature are obtained based on the directed edge network, and a subnode temperature of the extracted subnode is calculated based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and after the subnode temperature is imported into the directed edge network, the construction of the directed edge network is completed, and a plurality of directed edge networks corresponding to the directed edge set are aggregated to obtain a directed edge network set, and the directed edge network set is imported into the initial node network;

[0077] A temperature node network correction module is used to obtain a plurality of network nodes based on an initial node network, extract network nodes from the plurality of network nodes in sequence, obtain node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-built prediction value correction method to obtain a temperature node network;

[0078] The heating control module is used to obtain the predicted temperature supply value. After the predicted temperature supply value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating control of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

[0079] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0080] a memory storing at least one instruction; and

[0081] The processor executes the instructions stored in the memory to implement the above-mentioned method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis.

[0082] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for heating control of medium-deep geothermal units based on temperature node network analysis.

[0083] The present invention solves the problem described in the background technology. The initial node network construction module of the embodiment of the present invention is used to obtain multiple control nodes, obtain control coordinates corresponding to each control node in the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates. Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain a directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges by using a preset prediction step to obtain multiple child nodes, obtain child node coordinates of each child node in the multiple child nodes to obtain a child node coordinate set, construct a directed edge network based on the child node coordinate set and the extracted directed edges, extract child nodes from the multiple child nodes in sequence, and perform the following operations on the extracted child nodes: obtain a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculate the child node temperature of the extracted child node based on the first endpoint temperature, the second endpoint temperature and the extracted child node, import the child node temperature into the directed edge network, complete the construction of the directed edge network, summarize the multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and import the directed edge network set into the initial node network. It can be seen that in the embodiment of the present invention, since different user usage units correspond to different spatial coordinates, the control coordinates are different, and the longer the distance, the more losses there are in the transmission process, and the lower the heat transfer efficiency. Since multiple sub-nodes are deeply buried underground, it is difficult to measure them using sensors, so it is necessary to predict the temperatures of multiple sub-nodes to achieve the purpose of building a temperature node network. Based on the initial node network, multiple network nodes are obtained, and network nodes are extracted from the multiple network nodes in sequence, and node temperature data of the extracted network nodes are obtained. After performing an identification operation on the extracted network nodes based on the node temperature data, a calibration operation is performed on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network. After obtaining the predicted temperature supply value and inputting the predicted temperature supply value into the temperature node network, a control strategy for multiple control nodes is obtained based on the temperature node network, and based on the control strategy, the heating regulation of the deep-layer geothermal unit based on the temperature node network analysis is completed. It can be seen that the embodiment of the present invention constructs a temperature node network based on existing data, and is intended to predict the temperature of other control nodes and the temperature of each node in the heat transmission process when the temperature of the control node corresponding to the user water unit changes, which is used as a reference for temperature control, and thus, the heat supply control of the medium-deep geothermal unit can be completed with less loss. Therefore, the present invention can solve the construction of the temperature node network of the geothermal unit, and use the temperature node network to predict the temperature values ​​corresponding to the changes of different nodes, thereby realizing a control strategy for low-loss regulation of the geothermal unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A schematic flow chart of a method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis provided in one embodiment of the present invention;

[0085] Figure 2 A functional module diagram of a heat supply control device for a mid-deep geothermal unit based on temperature node network analysis provided by an embodiment of the present invention;

[0086] Figure 3 A schematic diagram of the structure of an electronic device for implementing the method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis provided in one embodiment of the present invention.

[0087] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0088] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0089] The embodiment of the present application provides a method for regulating and controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis. The execution subject of the method for regulating and controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for regulating and controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0090] Reference Figure 1 FIG. 1 is a flow chart of a method for controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis according to an embodiment of the present invention. In this embodiment, the method for controlling the heat supply of a medium-deep geothermal unit based on temperature node network analysis includes:

[0091] S1. Acquire multiple control nodes, acquire control coordinates corresponding to each of the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates.

[0092] Further, the obtaining of multiple control nodes includes:

[0093] Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit;

[0094] Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit;

[0095] Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit;

[0096] Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units:

[0097] Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit;

[0098] Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit;

[0099] Constructing a compression water return node based on the heat exchange unit and the first water return unit;

[0100] A second water supply node is constructed by using a heat exchange unit and a second water supply unit;

[0101] The second water return node is constructed by using the heat exchange unit and the second water return unit;

[0102] Obtaining a user usage node according to the second water supply node and the second water return node;

[0103] The heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user use nodes are summarized to obtain multiple control nodes.

[0104] It can be understood that the control node is a node that can detect and control the temperature, the control coordinates are coordinates obtained in the geodetic coordinate system, and the initial node network is a network constructed by scaling down multiple control nodes in the geodetic coordinate system and multiple control node coordinates corresponding to the multiple control nodes and adding temperature data.

[0105] It should be noted that the heat source unit is a unit where the deep geothermal unit is located. In the embodiment of the present invention, the heat source unit receives low-temperature return water and outputs high-temperature supply water, and finally provides heat for the user node. The first water supply unit is a unit for water supply directly connected to the heat source unit, and hot water flows from the heat source unit to the first water supply unit. The first return water unit is a unit for return water directly connected to the heat source unit.

[0106] Specifically, the first water supply unit is directly connected to the heat source unit, and each of the multiple compression heat supply units is directly connected to the first water supply unit and the first water return unit, and is not connected to the heat source unit. The functions of the second water supply unit and the second water return unit are similar to those of the first water supply unit and the first water return unit, and are not repeated here. The second water supply unit and the second water return unit are directly connected to the user unit and the heat exchange unit unit, that is, the second water supply unit provides hot water to the user unit, and the second water return unit receives water used by the user unit and transfers it to the heat exchange unit unit. The heat exchange unit unit includes a heat exchange compressor.

[0107] It can be understood that the heat source water supply node and the heat source water return node are the nodes at the water supply and water return of the heat source unit, respectively, and the heat source water supply node is arranged at the output end of the heat source unit, and the heat source water return node is arranged at the input end of the heat source unit. The first water supply node and the first water return node are the nodes in the first water supply unit and the first water return unit, respectively, the compression water supply node and the compression water return node are the nodes at the connection between the heat exchange unit unit and the first water supply unit, and the compression water supply node is arranged at the input end of the heat exchange unit connected to the first water supply node, the compression water return node is arranged at the output end of the heat exchange unit connected to the first water return node, the first water supply node is arranged at the output end of the first water supply unit connected to the heat exchange unit unit, and the first water return node is arranged at the input end of the first water supply unit connected to the heat exchange unit unit.

[0108] Specifically, the second water supply node and the second water return node are both nodes between the heat exchanger unit and the second water supply unit, and the second water supply node is arranged at the input end of the heat exchanger unit connected to the second water supply node, and the second water return node is arranged at the output end of the heat exchanger unit connected to the second water supply node, and the user use node is arranged at the place where the user uses it, and is used to indicate the heat consumption of the user.

[0109] It should be noted that the control node can regulate the temperature, but in the embodiment of the present invention, multiple control nodes are provided, and each of the multiple control nodes corresponds to multiple devices. If the temperature of each of the multiple control nodes is regulated every time the heating amount corresponding to the user unit is regulated, a lot of resources will be wasted, and multiple control nodes are buried deep underground, which is more time-consuming and labor-intensive. At the same time, in the process of regulation, the regulation cannot be successful in one go. Therefore, the embodiment of the present invention constructs a temperature node network based on existing data, aiming at predicting the temperature of other control nodes and the temperature of each node in the heat transmission process when the temperature of the control node corresponding to the user water unit changes, which is used as a reference for temperature regulation, and thus, the heat regulation of the medium and deep geothermal units can be completed with less loss.

[0110] S2. Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain a directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges using a preset prediction step size to obtain multiple child nodes, obtain the child node coordinates of each child node in the multiple child nodes, and obtain a child node coordinate set.

[0111] It should be noted that in the heating process, the function between control nodes is to transfer heat by water, so in a pipeline, there is a water flow inlet and a water flow outlet. Therefore, according to the flow direction of the water flow and the pipeline corresponding to the water flow, the embodiment of the present invention constructs a directed edge to represent the above heating process. A control node includes multiple directed edges.

[0112] Exemplarily, in the first water supply unit, after the heat source water supply node supplies water to the first water supply unit, the water flows out through the first water supply node in the first water supply unit. At this time, the first water supply node includes two directed edges, one of which is from the heat source water supply node to the first water supply node, and the other is from the first water supply node to the compression water supply node. In the embodiment of the present invention, the first water supply node is connected to multiple heat source water supply nodes, so there are multiple directed edges.

[0113] It should be noted that the prediction step length is a preset length for dividing directed edges. The shorter the prediction step length, the finer the division, the more sub-nodes there are, and the greater the amount of calculation. In the embodiment of the present invention, the temperature network of the geothermal unit is constructed, and different user units correspond to different spatial coordinates, so the control coordinates are different, and the longer the distance, the more losses there are in the transmission process, and the lower the heat transfer efficiency. Since multiple sub-nodes are deeply buried underground, it is difficult to measure them using sensors, so it is necessary to predict the temperature of multiple sub-nodes. The sub-node coordinates are the coordinates of the sub-nodes in the initial node network.

[0114] S3. Construct a directed edge network based on the child node coordinate set and the extracted directed edges, extract child nodes from the multiple child nodes in sequence, and perform the following operations on the extracted child nodes: obtain the first endpoint temperature and the second endpoint temperature based on the directed edge network, calculate the child node temperature of the extracted child node based on the first endpoint temperature, the second endpoint temperature and the extracted child nodes, import the child node temperature into the directed edge network, and complete the construction of the directed edge network.

[0115] Furthermore, the directed edge network is a network obtained by dividing the extracted directed edges according to the prediction step size. The embodiment of the present invention first obtains an initial directed edge network, and then imports multiple child node temperatures into the directed edge network through a series of calculations below, thereby completing the construction of the directed edge network.

[0116] It can be understood that the two ends of the directed edge are respectively connected to the control nodes, and the two control nodes corresponding to the extracted directed edge are the first end and the second end respectively. The first end and the second end have and only have one control node connected to them. For example, if the extracted directed edge is a directed edge between the compressed water supply node and the first water supply node, then the first end and the second end of the extracted directed edge are the compressed water supply node and the first water supply node, and the first end and the second end are not in a one-to-one correspondence with the compressed water supply node and the first water supply node, that is, if the first end is the compressed water supply node, the second end is the first water supply node, and if the first end is the first water supply node, the second end is the compressed water supply node.

[0117] It should be noted that the first endpoint temperature is the temperature of the first endpoint obtained by measurement, and the second endpoint temperature is the temperature of the second endpoint obtained by measurement. The child node temperature is the temperature of the child node predicted by calculation in the extracted directed edge.

[0118] Further, the calculating the sub-node temperature of the extracted sub-node based on the first endpoint temperature, the second endpoint temperature and the extracted sub-node includes:

[0119] Constructing a prediction node set based on the child node coordinate set, wherein the prediction node set includes a plurality of prediction nodes;

[0120] Prediction nodes are extracted from the prediction node set in sequence, and the following operations are performed on the extracted prediction nodes:

[0121] Obtain the directed edge corresponding to the extracted prediction node to obtain the target edge, obtain the first end and the second end of the target edge based on the target edge, and obtain a real point coordinate set and a real value set based on the first end and the second end, wherein the real point coordinate set includes: a first point coordinate corresponding to the first end and a second point coordinate corresponding to the second end, and the real value set includes: a first temperature corresponding to the first end and a second temperature corresponding to the second end;

[0122] Obtaining the child node coordinates of the extracted prediction node to obtain the prediction node coordinates, calculating the distance influence weight of the extracted prediction node using a pre-constructed distance influence formula and a real point coordinate set, and calculating the node prediction value of the extracted prediction node based on the distance influence weight and the real value set;

[0123] Eliminate the prediction node coordinates of the prediction nodes extracted from the prediction node set to obtain an updated prediction set;

[0124] After confirming that the updated prediction set is a prediction node set, the node prediction value is input into the real value set, and the prediction node coordinate is input into the real point coordinate set, thereby obtaining an updated real value set and an updated real point coordinate set;

[0125] After confirming that the updated true value set is the true value set and the updated true point coordinate set is the true point coordinate set, return to the step of extracting prediction nodes from the prediction node set in sequence, and perform the following operations on the extracted prediction nodes until the updated prediction set is an empty set.

[0126] It can be understood that the prediction node set is a set of child nodes that need to be predicted.

[0127] It should be noted that the embodiment of the present invention is a process of continuously using predicted values ​​as known values ​​to predict unknown values. For example, in the first calculation, all nodes in the prediction node set are multiple nodes corresponding to the child node coordinate set. After the prediction calculation, the extracted child nodes correspond to the node prediction values, and then the node prediction values ​​corresponding to the extracted child nodes are used as known values, that is, the true values ​​in the embodiment of the present invention, and the child node prediction values ​​are input into the true set, and the extracted child nodes are input into the true point coordinate set, and the extracted child nodes in the prediction node set are eliminated, so that the extracted child nodes that were originally required to be predicted are converted into known nodes, and the temperature prediction of the unknown child nodes is then performed.

[0128] Specifically, the real point coordinate set is a set of coordinates of nodes that do not need to be predicted and whose temperature values ​​are known. For example, when the extracted sub-nodes are predicted, the sub-node coordinates corresponding to the extracted sub-nodes are input into the real point coordinate set. Therefore, the sub-nodes included in the real point coordinate set also include control nodes, and the real point coordinate set corresponding to each extracted sub-node is different. The real value set is a set of known temperature values ​​corresponding to the coordinates in the real point coordinate set. The first point coordinates and the second point coordinates are the coordinates of the first end in the initial node network and the coordinates of the second end in the initial node network. The first temperature is the temperature of the first end, and the second temperature is the temperature of the second end. The predicted node is the sub-node extracted from the predicted node set. The predicted node coordinates are the coordinates of the predicted node. The distance influence weight is the influence weight of each real value corresponding to the real point coordinates in the other real point coordinate sets in the target edge on the extracted prediction node, and in the embodiment of the present invention, it is considered that the farther the distance from the extracted prediction node is, the smaller the influence on the extracted prediction node is, and prediction is only performed in the target edge. This is because the temperature difference is large during the water supply and return process, and the water supply and return are two parallel lines. In the embodiment of the present invention, the water supply and return pipes are located underground, and they are all long-distance heat transport, so the influence of distance on temperature should be considered.

[0129] Further, the node prediction value is the temperature prediction value of the extracted prediction node calculated by the formula. When the updated prediction set is an empty set, it means that all the prediction nodes in the original prediction nodes have been predicted and finally all converted into known values.

[0130] Specifically, the distance influence formula is as follows:

[0131] ;

[0132] in, Indicates that the sequence number of the real point coordinate set is The distance influence weight of the real point coordinates on the extracted prediction node, represents the predicted node coordinates of the extracted predicted node, and the predicted node coordinates are the coordinates in the corresponding spatial coordinate system in the initial node network, Indicates that the sequence number of the real point coordinate set is The label corresponding to the real point coordinates, Indicates that the sequence number of the real point coordinate set is The distance between the real point coordinates and the predicted node coordinates, represents the weight control coefficient, Indicates the total number of influence point coordinates in the influence point coordinate set.

[0133] Further, the node prediction value of the extracted prediction node is calculated based on the distance influence weight and the true value set, including:

[0134] Construct a sub-node temperature prediction formula, and calculate the node prediction value of the extracted prediction node according to the sub-node temperature prediction formula and the distance influence weight, wherein the sub-node temperature prediction formula is:

[0135] ;

[0136] in, represents the node prediction value of the extracted child node, Represents the sequence number of the real point coordinates in the real point coordinate set, Indicates that the sequence number of the real point coordinate set corresponding to the extracted prediction node is The distance influence weight of the real point coordinates on the extracted prediction node, Indicates the serial number is The real value corresponding to the real point coordinates.

[0137] S4. Aggregate multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and import the directed edge network set into the initial node network.

[0138] It can be understood that after obtaining the directed edge network corresponding to the extracted directed edge according to the above operation, the node prediction temperature corresponding to each of the multiple sub-nodes in the directed edge is imported into the directed edge, and then the multiple directed edge networks are imported into the initial node network, then the predictions corresponding to the multiple sub-nodes can be completed.

[0139] S5. Acquire multiple network nodes based on the initial node network, extract network nodes from the multiple network nodes in sequence, acquire node temperature data of the extracted network nodes, and perform identification operations on the extracted network nodes based on the node temperature data.

[0140] It is understandable that the embodiment of the present invention constructs a directed edge network for the directed edges corresponding to the extracted control nodes, but one directed edge corresponds to two control nodes. That is to say, in the embodiment of the present invention, when the coordinates of the child nodes do not change, the node prediction value of the extracted child nodes will be calculated twice through the above calculation. Therefore, the temperature data corresponding to the child nodes not only has a unique node prediction value, but when constructing the final temperature node network, a unique output value is required, so the initial node network needs to be processed again as described below.

[0141] Further, the step of acquiring the node temperature data of the extracted network node and performing an identification operation on the extracted network node based on the node temperature data comprises:

[0142] Based on the extracted network node, determine whether the network node is a control node, if the extracted network node is a control node, remove the extracted network node, otherwise, retain the extracted network node to obtain a network sub-node;

[0143] Aggregate multiple network sub-nodes to obtain a network sub-node set, extract network sub-nodes from the network sub-node set in sequence, and perform the following operations on the extracted network sub-nodes:

[0144] Node temperature data is obtained based on the extracted network sub-nodes, multiple initial predicted temperature values ​​are obtained based on the node temperature data, the average of the multiple initial predicted temperature values ​​is calculated to obtain the node prediction average, and the node prediction average is used to perform an identification operation on the extracted network sub-nodes.

[0145] It can be understood that the network node is a node in the initial node network. In the embodiment of the present invention, according to the above, the initial node network includes multiple control nodes and multiple sub-nodes, wherein the control nodes are controllable and the values ​​are detectable, and the sub-nodes are completely predicted values, so it is necessary to process the node temperature data corresponding to the sub-nodes.

[0146] Specifically, the network sub-node is a collection of all nodes that are not control nodes. The node temperature data is data used to represent the content stored corresponding to the network sub-node. Optionally, the data stored in the node temperature data includes but is not limited to: the coordinates of the network sub-node, multiple node prediction values ​​of the network sub-node, the directed edge corresponding to the network sub-node, and the distance influence weight of all other sub-nodes in the directed edge network corresponding to the network sub-node.

[0147] Furthermore, the node prediction mean is used to perform a labeling operation on the extracted network sub-nodes, so that in the final temperature node network, the node prediction mean is the final temperature output value of the network sub-nodes extracted from the temperature node network.

[0148] S6. Utilize a pre-constructed prediction value correction method to perform a calibration operation on the initial node network to obtain a temperature node network.

[0149] Furthermore, the use of the pre-built prediction value correction method to perform a calibration operation on the initial node network includes:

[0150] Based on the initial node network, multiple real control nodes are obtained, real control nodes are extracted from the multiple real control nodes in sequence, and the following operations are performed on the extracted real control nodes:

[0151] Obtaining an influence sub-node set of the extracted real control node, and obtaining an influence prediction value set based on the extracted influence sub-node set, wherein the influence sub-nodes in the influence sub-node set correspond one-to-one to the influence prediction values ​​in the influence prediction value set;

[0152] Calculate the control point prediction value of the extracted real control node using the distance influence formula, the sub-node temperature prediction formula, the influence sub-node set and the influence prediction value set, calculate the prediction error based on the control point prediction value and the extracted real control node, and compare the prediction error with a preset prediction deviation threshold;

[0153] If the prediction error is less than or equal to the prediction deviation threshold, confirming that the control point prediction value is the optimal prediction value of the extracted real control node;

[0154] Otherwise, the control point prediction value is corrected using the pre-constructed correction coefficient to obtain the optimal prediction value;

[0155] Aggregating multiple optimal prediction values, and performing a calibration operation on the initial node network based on the multiple optimal prediction values.

[0156] It should be noted that the above content is intended to use multiple nodes adjacent to the real control node to calculate the predicted value of the real control node, which is used to detect the reliability of the prediction method in the embodiment of the present invention. This is because, in the temperature node network, after the predicted temperature supply value is input, the temperature of the real control node will also change accordingly, which is used to predict the heating status of the entire deep geothermal unit. Therefore, in order to be able to predict the real control node, it is necessary to calibrate the initial node network.

[0157] It is understandable that the temperature node network is a modified initial node network. The real control node is a node connected to the unit in the embodiment of the present invention and can directly control the temperature, for example, the heat source water supply node and the heat source water return node corresponding to the heat source unit. In the embodiment of the present invention, the multiple control nodes mentioned above are all real control nodes. The impact prediction value set is a set of temperature values ​​of each of the multiple impact sub-nodes in the temperature node network.

[0158] Furthermore, the influencing sub-node set is a collection of sub-nodes that have an impact on the real control node. For example, the first return node corresponds to multiple directed edges. The first sub-node and the second sub-node adjacent to the first return node in each of 50% of the directed edges are randomly selected as influencing sub-nodes, and then the first sub-node adjacent to the first return node in each of the remaining 50% of the directed edges is selected as the influencing sub-node. Multiple influencing sub-nodes are summarized to obtain the influencing sub-node set.

[0159] It should be noted that the calculation method of the control point prediction value is consistent with the method of calculating the node prediction value in the previous article, which will not be repeated here. The optimal prediction value is the output value of the extracted real control node in the temperature node network after optimization. The prediction deviation threshold is the maximum value that considers the prediction error to be a negligible error.

[0160] Furthermore, the calculation formula of the prediction error is as follows:

[0161] ;

[0162] in, represents the prediction error of the extracted real control node, Indicates the sequence number of the extracted real control node, Indicates the serial number is The control point prediction value of the real control node, Indicates the serial number is The true measurement value of the true control node.

[0163] It is understandable that when the prediction error is greater than the prediction deviation threshold, it indicates that the prediction of multiple influencing sub-nodes corresponding to the real control node in the embodiment of the present invention is inaccurate, and further, the prediction of multiple node prediction values ​​is inaccurate.

[0164] Furthermore, the use of a pre-constructed correction coefficient to correct the control point prediction value to obtain an optimal prediction value includes:

[0165] Obtain a weight adjustment coefficient, construct a modified distance influence formula based on the weight adjustment coefficient and the distance influence formula, and after confirming that the modified distance influence formula is the distance influence formula, return to the step of calculating the sub-node temperature of the extracted sub-node based on the first endpoint temperature, the second endpoint temperature and the extracted sub-node, until the prediction error is less than or equal to the prediction deviation threshold.

[0166] It is understandable that the weight adjustment coefficient is a coefficient used for the node prediction value. The modified distance influence formula is a formula after the distance influence formula is modified using the weight adjustment coefficient.

[0167] S7. Obtain predicted heating value, input the predicted heating value into the temperature node network, obtain control strategies of multiple control nodes based on the temperature node network, and complete heating regulation of the deep geothermal unit based on the temperature node network analysis based on the control strategy.

[0168] Further, obtaining the predicted temperature supply value includes:

[0169] Obtain a historical heating data set, divide the historical heating data set using a pre-built time period division method to obtain multiple heating time periods, extract heating time periods from the multiple heating time periods in sequence, and perform the following operations on the extracted heating time periods:

[0170] Based on the extracted heating period, a heating period data set is obtained, user use nodes are sequentially extracted from the plurality of user use nodes, and the following operations are performed on the extracted user use nodes:

[0171] Acquire a heating data set based on the extracted user control nodes, acquire a heating mean and a heating variance based on the heating data set, construct a heating interval according to the heating mean and the heating variance, and acquire a maximum heating value of the extracted user use node based on the heating interval;

[0172] A plurality of maximum heating values ​​are aggregated to obtain a maximum heating value set, and a predicted heating value is obtained based on the maximum heating value set.

[0173] Furthermore, the predicted temperature supply value is the temperature that each user-use node in the multiple user-use nodes needs to be heated. The embodiment of the present invention has constructed a temperature node network. Therefore, after the predicted temperature supply value is input into the multiple user-use nodes, all nodes in the temperature node network except the user-use nodes will predict the temperature values ​​corresponding to all other nodes, and the predicted temperature value corresponding to each control node in the multiple control nodes in the temperature node network is a reference control strategy. For example, the predicted temperature supply value of each user-use node in the multiple user-use nodes in the temperature node network is 50°C, so each maximum heating value in the maximum heating value set is 50°C. 50°C is imported into the temperature node network, and the heat source water supply node therefore undergoes a value change, and the corresponding predicted reference value is 80°C, then the control strategy corresponding to the heat source water supply node can be set to 80°C.

[0174] It should be noted that the historical heating data set is a data set of heating conditions of all nodes in the temperature node network in the embodiment of the present invention in the past period of time. The heating period is a different heating period. For example, in daily life, there is more heating during the day, and fewer families choose heating at night. Therefore, the amount of heat required in different heating periods is different. For example, a day is divided into: Beijing time 0:00 to Beijing time 8:00, Beijing time 8:00 to 22:00, and Beijing time 22:00 to Beijing time 24:00. The period heating data set is a data set of heating conditions of all nodes in the temperature node network extracted during the heating period in the past period of time. The heating data set is a data set of heating conditions of multiple user-used nodes extracted in the past period of time. The heating mean and heating variance are the mean and variance of the heat supplied to the user-used nodes.

[0175] It is understandable that the heating interval is used to remove abnormal values ​​and retain representative heating data. For example, hail suddenly falls on a summer day in June, and heating is needed at this time, but hail in summer is a rare event and not representative, so it is necessary to remove abnormal values ​​to find a representative control strategy. The maximum heating value is used to ensure the maximum value of the heating amount of the user's node.

[0176] The present invention solves the problem described in the background technology. The initial node network construction module of the embodiment of the present invention is used to obtain multiple control nodes, obtain control coordinates corresponding to each control node in the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates. Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain a directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges by using a preset prediction step to obtain multiple child nodes, obtain child node coordinates of each child node in the multiple child nodes to obtain a child node coordinate set, construct a directed edge network based on the child node coordinate set and the extracted directed edges, extract child nodes from the multiple child nodes in sequence, and perform the following operations on the extracted child nodes: obtain a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculate the child node temperature of the extracted child node based on the first endpoint temperature, the second endpoint temperature and the extracted child node, import the child node temperature into the directed edge network, complete the construction of the directed edge network, summarize the multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and import the directed edge network set into the initial node network. It can be seen that in the embodiment of the present invention, since different user usage units correspond to different spatial coordinates, the control coordinates are different, and the longer the distance, the more losses there are in the transmission process, and the lower the heat transfer efficiency. Since multiple sub-nodes are deeply buried underground, it is difficult to measure them using sensors, so it is necessary to predict the temperatures of multiple sub-nodes to achieve the purpose of building a temperature node network. Based on the initial node network, multiple network nodes are obtained, and network nodes are extracted from the multiple network nodes in sequence, and node temperature data of the extracted network nodes are obtained. After performing an identification operation on the extracted network nodes based on the node temperature data, a calibration operation is performed on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network. After obtaining the predicted temperature supply value and inputting the predicted temperature supply value into the temperature node network, a control strategy for multiple control nodes is obtained based on the temperature node network, and based on the control strategy, the heating regulation of the deep-layer geothermal unit based on the temperature node network analysis is completed. It can be seen that the embodiment of the present invention constructs a temperature node network based on existing data, and is intended to predict the temperature of other control nodes and the temperature of each node in the heat transmission process when the temperature of the control node corresponding to the user water unit changes, which is used as a reference for temperature control, and thus, the heat supply control of the medium-deep geothermal unit can be completed with less loss. Therefore, the present invention can solve the construction of the temperature node network of the geothermal unit, and use the temperature node network to predict the temperature values ​​corresponding to the changes of different nodes, thereby realizing a control strategy for low-loss regulation of the geothermal unit.

[0177] like Figure 2, which is a functional module diagram of a heat supply control device for a medium-deep geothermal unit based on temperature node network analysis provided by an embodiment of the present invention.

[0178] The medium-deep geothermal unit heat supply control device 100 based on temperature node network analysis of the present invention can be installed in an electronic device. According to the functions to be implemented, the medium-deep geothermal unit heat supply control device 100 based on temperature node network analysis can include an initial node network construction module 101, a directed edge network set construction module 102, a temperature node network correction module 103 and a heat supply control module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0179] The initial node network construction module 101 is used to obtain multiple control nodes, obtain control coordinates corresponding to each control node in the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates, wherein the obtaining of multiple control nodes includes: obtaining a heat exchange unit, obtaining a heat source unit, a first water supply unit, a first water return unit, and multiple compression heat supply units based on the heat exchange unit, constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit, constructing a heat source return water node and a first return water node based on the heat source unit and the first water return unit, extracting compression heat supply units from the multiple compression heat supply units in sequence, and executing the following steps on the extracted compression heat supply units: The following operations are performed: based on the extracted compression heat supply unit, a heat exchanger unit, a second water supply unit and a second water return unit are obtained; a compression water supply node is constructed according to the heat exchanger unit and the first water supply unit; a compression water return node is constructed based on the heat exchanger unit and the first water return unit; a second water supply node is constructed using the heat exchanger unit and the second water supply unit; a second water return node is constructed using the heat exchanger unit and the second water return unit; a user use node is obtained according to the second water supply node and the second water return node; a heat source water supply node, a heat source water return node, a first water supply node, a first water return node, a plurality of compression water supply nodes, a plurality of compression water return nodes, a plurality of second water supply nodes, a plurality of second water return nodes and a plurality of user use nodes are summarized to obtain a plurality of control nodes;

[0180] The directed edge network set construction module 102 is used to extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain the directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges using a preset prediction step to obtain multiple child nodes, obtain the child node coordinates of each child node in the multiple child nodes to obtain a child node coordinate set, and construct a directed network set based on the child node coordinate set and the extracted directed edges. edge network, extracting subnodes from the multiple subnodes in sequence, and performing the following operations on the extracted subnodes: obtaining a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculating the subnode temperature of the extracted subnode based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, importing the subnode temperature into the directed edge network, completing the construction of the directed edge network, summarizing multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and importing the directed edge network set into the initial node network;

[0181] The temperature node network correction module 103 obtains a plurality of network nodes based on the initial node network, extracts network nodes from the plurality of network nodes in sequence, obtains node temperature data of the extracted network nodes, performs an identification operation on the extracted network nodes based on the node temperature data, and then performs a calibration operation on the initial node network using a pre-built prediction value correction method to obtain a temperature node network;

[0182] The heat supply control module 104 obtains the predicted temperature supply value, inputs the predicted temperature supply value into the temperature node network, obtains the control strategy of multiple control nodes based on the temperature node network, and completes the heat supply control of the deep geothermal unit based on the temperature node network analysis based on the control strategy.

[0183] In detail, each module in the medium-deep geothermal unit heat supply control device 100 based on temperature node network analysis in the embodiment of the present invention is used in the same manner as above. Figure 1 The same technical means are used as the heating control method of the medium-deep geothermal unit based on temperature node network analysis described in, and can produce the same technical effects, so I will not go into details here.

[0184] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis provided by an embodiment of the present invention.

[0185] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis.

[0186] The memory 11 includes at least one type of readable storage medium, including flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program of the heating control method of the deep geothermal unit based on the temperature node network analysis, but also can be used to temporarily store the data that has been output or is to be output.

[0187] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a method program for controlling heating of a deep geothermal unit based on temperature node network analysis, etc.), and calls data stored in the memory 11, so as to execute various functions of the electronic device 1 and process data.

[0188] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0189] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0190] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0191] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0192] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0193] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0194] The program of the method for controlling the heating supply of a medium-deep geothermal unit based on the temperature node network analysis stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, the following can be achieved:

[0195] Acquire multiple control nodes, acquire control coordinates corresponding to each of the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates;

[0196] Wherein, the obtaining of multiple control nodes includes:

[0197] Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit;

[0198] Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit;

[0199] Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit;

[0200] Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units:

[0201] Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit;

[0202] Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit;

[0203] Constructing a compression water return node based on the heat exchange unit and the first water return unit;

[0204] A second water supply node is constructed by using a heat exchange unit and a second water supply unit;

[0205] The second water return node is constructed by using the heat exchange unit and the second water return unit;

[0206] Obtaining a user usage node according to the second water supply node and the second water return node;

[0207] Summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user nodes to obtain multiple control nodes;

[0208] Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes:

[0209] Obtain the directed edge set of the extracted control node, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges:

[0210] Dividing the extracted directed edges by using a preset prediction step length to obtain a plurality of child nodes, obtaining the child node coordinates of each child node in the plurality of child nodes to obtain a child node coordinate set, and constructing a directed edge network based on the child node coordinate set and the extracted directed edges;

[0211] Subnodes are extracted from the multiple subnodes in sequence, and the following operations are performed on the extracted subnodes:

[0212] Acquiring a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculating a subnode temperature of the extracted subnode based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and importing the subnode temperature into the directed edge network to complete the construction of the directed edge network;

[0213] Aggregating multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and importing the directed edge network set into the initial node network;

[0214] Acquire multiple network nodes based on an initial node network, extract network nodes from the multiple network nodes in sequence, acquire node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network;

[0215] The predicted heating value is obtained, and after the predicted heating value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating regulation of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

[0216] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0217] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0218] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0219] Acquire multiple control nodes, acquire control coordinates corresponding to each of the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates;

[0220] Wherein, the obtaining of multiple control nodes includes:

[0221] Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit;

[0222] Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit;

[0223] Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit;

[0224] Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units:

[0225] Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit;

[0226] Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit;

[0227] Constructing a compression water return node based on the heat exchange unit and the first water return unit;

[0228] A second water supply node is constructed by using a heat exchange unit and a second water supply unit;

[0229] The second water return node is constructed by using the heat exchange unit and the second water return unit;

[0230] Obtaining a user usage node according to the second water supply node and the second water return node;

[0231] Summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user nodes to obtain multiple control nodes;

[0232] Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes:

[0233] Obtain the directed edge set of the extracted control node, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges:

[0234] Dividing the extracted directed edges by using a preset prediction step length to obtain a plurality of child nodes, obtaining the child node coordinates of each child node in the plurality of child nodes to obtain a child node coordinate set, and constructing a directed edge network based on the child node coordinate set and the extracted directed edges;

[0235] Subnodes are extracted from the multiple subnodes in sequence, and the following operations are performed on the extracted subnodes:

[0236] Acquiring a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculating a subnode temperature of the extracted subnode based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and importing the subnode temperature into the directed edge network to complete the construction of the directed edge network;

[0237] Aggregating multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and importing the directed edge network set into the initial node network;

[0238] Acquire multiple network nodes based on an initial node network, extract network nodes from the multiple network nodes in sequence, acquire node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network;

[0239] The predicted heating value is obtained, and after the predicted heating value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating regulation of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

[0240] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, and actual implementation may have other division methods.

[0241] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0242] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0243] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0244] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0245] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis, characterized in that: The method comprises: Acquire multiple control nodes, acquire control coordinates corresponding to each of the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates; Wherein, the obtaining of multiple control nodes includes: Acquire a heat exchange unit, and acquire a heat source unit, a first water supply unit, a first water return unit, and a plurality of compression heat supply units based on the heat exchange unit; Constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit; Constructing a heat source return water node and a first return water node based on the heat source unit and the first return water unit; Extract compression heat supply units from the plurality of compression heat supply units in sequence, and perform the following operations on the extracted compression heat supply units: Acquire a heat exchange unit, a second water supply unit and a second water return unit based on the extracted compression heat supply unit; Constructing a compressed water supply node according to the heat exchange unit and the first water supply unit; Constructing a compression water return node based on the heat exchange unit and the first water return unit; A second water supply node is constructed by using a heat exchange unit and a second water supply unit; The second water return node is constructed by using the heat exchange unit and the second water return unit; Obtaining a user usage node according to the second water supply node and the second water return node; Summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compressed water supply nodes, multiple compressed water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user nodes to obtain multiple control nodes; Extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: Obtain the directed edge set of the extracted control node, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: Dividing the extracted directed edges by using a preset prediction step length to obtain a plurality of child nodes, obtaining the child node coordinates of each child node in the plurality of child nodes to obtain a child node coordinate set, and constructing a directed edge network based on the child node coordinate set and the extracted directed edges; Subnodes are extracted from the multiple subnodes in sequence, and the following operations are performed on the extracted subnodes: Acquiring a first endpoint temperature and a second endpoint temperature based on the directed edge network, calculating a subnode temperature of the extracted subnode based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and importing the subnode temperature into the directed edge network to complete the construction of the directed edge network; Aggregating multiple directed edge networks corresponding to the directed edge set to obtain a directed edge network set, and importing the directed edge network set into the initial node network; Acquire multiple network nodes based on an initial node network, extract network nodes from the multiple network nodes in sequence, acquire node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-constructed prediction value correction method to obtain a temperature node network; The predicted heating value is obtained, and after the predicted heating value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating regulation of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

2. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 1, characterized in that: The step of calculating the sub-node temperature of the extracted sub-node based on the first endpoint temperature, the second endpoint temperature and the extracted sub-node comprises: Constructing a prediction node set based on the child node coordinate set, wherein the prediction node set includes a plurality of prediction nodes; Prediction nodes are extracted from the prediction node set in sequence, and the following operations are performed on the extracted prediction nodes: Obtain the directed edge corresponding to the extracted prediction node to obtain the target edge, obtain the first end and the second end of the target edge based on the target edge, and obtain a real point coordinate set and a real value set based on the first end and the second end, wherein the real point coordinate set includes: a first point coordinate corresponding to the first end and a second point coordinate corresponding to the second end, and the real value set includes: a first temperature corresponding to the first end and a second temperature corresponding to the second end; Obtaining the child node coordinates of the extracted prediction node to obtain the prediction node coordinates, calculating the distance influence weight of the extracted prediction node using a pre-constructed distance influence formula and a real point coordinate set, and calculating the node prediction value of the extracted prediction node based on the distance influence weight and the real value set; Eliminate the prediction node coordinates of the prediction nodes extracted from the prediction node set to obtain an updated prediction set; After confirming that the updated prediction set is a prediction node set, the node prediction value is input into the real value set, and the prediction node coordinate is input into the real point coordinate set, thereby obtaining an updated real value set and an updated real point coordinate set; After confirming that the updated true value set is the true value set and the updated true point coordinate set is the true point coordinate set, return to the step of extracting prediction nodes from the prediction node set in sequence, and perform the following operations on the extracted prediction nodes until the updated prediction set is an empty set.

3. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 2, characterized in that: The distance affects the formula as follows: ； in, Indicates that the sequence number of the real point coordinate set is The distance influence weight of the real point coordinates on the extracted prediction node, represents the predicted node coordinates of the extracted predicted node, and the predicted node coordinates are the coordinates in the corresponding spatial coordinate system in the initial node network, Indicates that the sequence number of the real point coordinate set is The label corresponding to the real point coordinates, Indicates that the sequence number of the real point coordinate set is The distance between the real point coordinates and the predicted node coordinates, represents the weight control coefficient, Indicates the total number of influence point coordinates in the influence point coordinate set.

4. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 3, characterized in that: The node prediction value of the extracted prediction node is calculated based on the distance influence weight and the true value set, including: Construct a sub-node temperature prediction formula, and calculate the node prediction value of the extracted prediction node according to the sub-node temperature prediction formula and the distance influence weight, wherein the sub-node temperature prediction formula is: ； in, represents the node prediction value of the extracted child node, Represents the sequence number of the real point coordinates in the real point coordinate set, Indicates that the sequence number of the real point coordinate set corresponding to the extracted prediction node is The distance influence weight of the real point coordinates on the extracted prediction node, Indicates the serial number is The real value corresponding to the real point coordinates.

5. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 4, characterized in that: The step of acquiring the node temperature data of the extracted network node and performing a marking operation on the extracted network node based on the node temperature data comprises: Based on the extracted network node, determine whether the network node is a control node, if the extracted network node is a control node, remove the extracted network node, otherwise, retain the extracted network node to obtain a network sub-node; Aggregate multiple network sub-nodes to obtain a network sub-node set, extract network sub-nodes from the network sub-node set in sequence, and perform the following operations on the extracted network sub-nodes: Node temperature data is obtained based on the extracted network sub-nodes, multiple initial predicted temperature values ​​are obtained based on the node temperature data, the average of the multiple initial predicted temperature values ​​is calculated to obtain the node prediction average, and the node prediction average is used to perform an identification operation on the extracted network sub-nodes.

6. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 5, characterized in that: The method of using a pre-built prediction value correction method to perform a calibration operation on the initial node network includes: Based on the initial node network, multiple real control nodes are obtained, real control nodes are extracted from the multiple real control nodes in sequence, and the following operations are performed on the extracted real control nodes: Obtaining an influence sub-node set of the extracted real control node, and obtaining an influence prediction value set based on the extracted influence sub-node set, wherein the influence sub-nodes in the influence sub-node set correspond one-to-one to the influence prediction values ​​in the influence prediction value set; Calculate the control point prediction value of the extracted real control node using the distance influence formula, the sub-node temperature prediction formula, the influence sub-node set and the influence prediction value set, calculate the prediction error based on the control point prediction value and the extracted real control node, and compare the prediction error with a preset prediction deviation threshold; If the prediction error is less than or equal to the prediction deviation threshold, confirming that the control point prediction value is the optimal prediction value of the extracted real control node; Otherwise, the control point prediction value is corrected using the pre-constructed correction coefficient to obtain the optimal prediction value; Aggregating multiple optimal prediction values, and performing a calibration operation on the initial node network based on the multiple optimal prediction values.

7. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 6, characterized in that: The calculation formula of the prediction error is as follows: ； in, represents the prediction error of the extracted real control node, Indicates the sequence number of the extracted real control node, Indicates the serial number is The control point prediction value of the real control node, Indicates the serial number is The true measurement value of the true control node.

8. The method for controlling heating supply of a medium-deep geothermal unit based on temperature node network analysis according to claim 1, characterized in that: The step of obtaining the predicted heating value comprises: Obtain a historical heating data set, divide the historical heating data set using a pre-built time period division method to obtain multiple heating time periods, extract heating time periods from the multiple heating time periods in sequence, and perform the following operations on the extracted heating time periods: Based on the extracted heating period, a heating period data set is obtained, user use nodes are sequentially extracted from the plurality of user use nodes, and the following operations are performed on the extracted user use nodes: Acquire a heating data set based on the extracted user control nodes, acquire a heating mean and a heating variance based on the heating data set, construct a heating interval according to the heating mean and the heating variance, and acquire a maximum heating value of the extracted user use node based on the heating interval; A plurality of maximum heating values ​​are aggregated to obtain a maximum heating value set, and a predicted heating value is obtained based on the maximum heating value set.

9. A heating control device for a mid-deep geothermal unit based on temperature node network analysis, characterized in that: The device comprises: The initial node network construction module is used to obtain multiple control nodes, obtain control coordinates corresponding to each control node in the multiple control nodes based on the multiple control nodes, obtain multiple control coordinates, and construct an initial node network based on the multiple control coordinates, wherein the acquisition of multiple control nodes includes: obtaining a heat exchange unit, obtaining a heat source unit, a first water supply unit, a first water return unit, and multiple compression heat supply units based on the heat exchange unit, constructing a heat source water supply node and a first water supply node based on the heat source unit and the first water supply unit, constructing a heat source return water node and a first return water node based on the heat source unit and the first water return unit, extracting compression heat supply units from the multiple compression heat supply units in sequence, and performing the following operations on the extracted compression heat supply units Operation: based on the extracted compression heat supply unit, obtain the heat exchange unit, the second water supply unit and the second water return unit, construct the compression water supply node according to the heat exchange unit unit and the first water supply unit, construct the compression water return node based on the heat exchange unit unit and the first water return unit, use the heat exchange unit unit and the second water supply unit to construct the second water supply node, use the heat exchange unit unit and the second water return unit to construct the second water return node, obtain the user use node according to the second water supply node and the second water return node, summarize the heat source water supply node, the heat source water return node, the first water supply node, the first water return node, multiple compression water supply nodes, multiple compression water return nodes, multiple second water supply nodes, multiple second water return nodes and multiple user use nodes to obtain multiple control nodes; The directed edge network set construction module is used to extract control nodes from multiple control nodes in sequence, and perform the following operations on the extracted control nodes: obtain the directed edge set of the extracted control nodes, extract directed edges from the directed edge set in sequence, and perform the following operations on the extracted directed edges: divide the extracted directed edges using a preset prediction step to obtain multiple child nodes, obtain the child node coordinates of each child node in the multiple child nodes, obtain the child node coordinate set, and construct a directed edge network based on the child node coordinate set and the extracted directed edges. A directed edge network is constructed, and subnodes are sequentially extracted from the plurality of subnodes, and the following operations are performed on the extracted subnodes: a first endpoint temperature and a second endpoint temperature are obtained based on the directed edge network, and a subnode temperature of the extracted subnode is calculated based on the first endpoint temperature, the second endpoint temperature and the extracted subnode, and after the subnode temperature is imported into the directed edge network, the construction of the directed edge network is completed, and a plurality of directed edge networks corresponding to the directed edge set are aggregated to obtain a directed edge network set, and the directed edge network set is imported into the initial node network; A temperature node network correction module is used to obtain a plurality of network nodes based on an initial node network, extract network nodes from the plurality of network nodes in sequence, obtain node temperature data of the extracted network nodes, perform an identification operation on the extracted network nodes based on the node temperature data, and then perform a calibration operation on the initial node network using a pre-built prediction value correction method to obtain a temperature node network; The heating control module is used to obtain the predicted temperature supply value. After the predicted temperature supply value is input into the temperature node network, the control strategy of multiple control nodes is obtained based on the temperature node network, and the heating control of the medium and deep geothermal units based on the temperature node network analysis is completed based on the control strategy.

Images