Multi-energy-flow comprehensive energy management decision-making method for industrial park

Abstract

The invention relates to the technical field of energy management, in particular to an industrial park multi-energy-flow comprehensive energy management decision-making method. The method comprises the following steps: collecting industrial waste heat data of a plurality of industrial waste heat generation sources in an industrial park, carrying out quality classification processing on the industrial waste heat data by using a K-means algorithm, and determining an industrial waste heat quality category corresponding to each industrial waste heat generation source; constructing an energy transfer network model based on the industrial waste heat generation sources of the same quality category, and selecting to-be-selected path nodes for generating energy transfer paths from the energy transfer network model by using a random walk path generation algorithm; generating an energy transfer path of the industrial waste heat by adopting a rough combination mode on the to-be-selected path nodes; the utilization path of the industrial residual and waste heat is determined based on the energy transfer path, and the multi-energy collaborative combined cooling, heating and power system is formed based on the utilization path, so that the residual and waste heat utilization efficiency can be improved, the energy management efficiency can be improved, and the energy consumption can be reduced.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, specifically to a multi-energy flow integrated energy management decision-making method for industrial parks. Background Technology

[0002] Industrial production processes generate a large amount of waste heat, such as waste heat from sewage source heat pumps, steam / exhaust gas waste heat, and high-temperature flue gas waste heat. This waste heat contains enormous energy, and if effectively utilized, it can not only reduce the park's energy consumption and dependence on traditional energy sources, but also significantly reduce greenhouse gas emissions, achieving the goal of energy conservation and emission reduction.

[0003] In existing technologies, industrial parks face numerous problems in the utilization of waste heat. On the one hand, the inconsistent quality of waste heat, with significant differences in temperature, flow rate, and other parameters from different sources, leads to traditional, often simplistic, methods of waste heat utilization. This lack of precise classification and targeted utilization of waste heat quality results in some waste heat not being fully utilized, or even being directly discharged, causing energy waste. On the other hand, the lack of rational planning of energy transfer paths for waste heat further contributes to its low utilization rate.

[0004] Therefore, there is an urgent need for a multi-energy flow integrated energy management decision-making method for industrial parks to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-energy flow integrated energy management decision-making method for industrial parks, aiming to solve the technical problem of low utilization efficiency of waste heat in industrial parks.

[0006] A multi-energy flow integrated energy management decision-making method for industrial parks, including:

[0007] Industrial waste heat data from multiple sources of industrial waste heat generation within the industrial park were collected. The K-means algorithm was used to classify the industrial waste heat data to determine the quality category of each source of industrial waste heat generation.

[0008] An energy transfer network model is constructed based on industrial waste heat generation sources of the same quality category. A random walk path generation algorithm is used to select candidate path nodes for generating energy transfer paths from the energy transfer network model.

[0009] The energy transfer paths for industrial waste heat are generated by coarse combination of the selected path nodes.

[0010] The utilization path of industrial waste heat is determined based on the energy transfer path, and a multi-energy synergistic combined heat, power and cooling system is formed based on the utilization path.

[0011] Furthermore, industrial waste heat data includes waste heat temperature, waste heat medium pressure, waste heat medium flow rate, and the amount of heat available for use.

[0012] Furthermore, the K-means algorithm is used to classify the industrial waste heat data to determine the quality category of each industrial waste heat generation source. This process includes the following steps:

[0013] Step 1: Record each industrial waste heat data point as a sample. , The value is n is the number of industrial waste heat generation sources, and k cluster centers are randomly initialized. k is the pre-set number of cluster centers, and its value is set according to the quality category of industrial waste heat. The value is ;

[0014] Step 2, calculate the sample Cluster center to which it should belong: Calculate its Euclidean distance to the k cluster centers. The calculation formula is: ;in, Representing the The value of the m-th dimension feature of a sample. Indicates the first The value of the m-th dimension feature of each cluster center is given, where M represents the total number of features. After calculating the distance between each sample and each cluster center, each sample is classified into the nearest corresponding cluster, where the cluster is the cluster center.

[0015] Step 3: Calculate the deviation between the sample and the center of its cluster. The calculation formula is:

[0016] ;

[0017] Step 4: Update the cluster centers and reassign the clusters of each sample:

[0018] ;in, This indicates the updated location of the l-th cluster center. Indicates belonging to a cluster The sample, Represents clusters The number of samples included; Steps two and three are performed to calculate the new cluster partitioning results and the new bias. ;

[0019] Step 5: Repeat steps 2 to 4 to iteratively update the clustering of the samples until the clustering bias converges, i.e., the difference in bias before and after the iterative update. Less than a given deviation threshold The process involves identifying the cluster corresponding to the industrial waste heat data for each industrial waste heat generation source. This cluster represents the quality category. The iteration termination condition is as follows: ;in, For the first iteration This is the deviation threshold for terminating the iteration.

[0020] Furthermore, constructing an energy transfer network model based on industrial waste heat generation sources of the same quality category specifically includes the following processes:

[0021] Define the energy delivery network model as ,in, A node set consists of industrial waste heat generation sources of the same quality category, where each industrial waste heat generation source is a node. , Let be the set of edges, where each edge is represented as a directed tuple, i.e. .

[0022] Furthermore, the process of selecting candidate path nodes for generating energy transfer paths from the energy transfer network model using a random walk path generation algorithm includes the following steps:

[0023] Initialize the random walk parameters and determine the starting node of the random walk. The starting node is selected from the node set V. The random walk parameters include the walk step threshold and the update period of the walk probability transition matrix. The starting node is determined from the node set V by random sampling or by specifying a node.

[0024] Using a random walk path generation algorithm, starting from the initial node, a random walk is performed according to the directed connection relationship of the edges. At each step of the walk, the next node to be reached is selected with a preset probability based on the outgoing edges of the current node.

[0025] During the random walk, the sequence of nodes traversed by the walk is recorded, and the node sequence is determined as the candidate path node sequence for energy transfer, thus completing the selection of candidate path nodes.

[0026] Furthermore, the calculation method for the preset probability specifically includes the following process:

[0027] For the current node Traverse all its edges and count them. Total number of connected edges Calculate from Transfer to probability , ;in, For the edge The weight, For the edge The weights are pre-assigned based on the historical flow and heat loss factors during the transfer of industrial waste heat at the corresponding edge.

[0028] Furthermore, the process of generating energy transfer paths for industrial waste heat using a coarse combination method for the selected path nodes specifically includes the following steps:

[0029] Step 1: Settings For coarse combination parameters, for each The candidate path nodes are coarsely combined according to the sampling order of the sampling interval values ​​to obtain several coarse combination groups;

[0030] Step 2: Combine the first and second nodes of each coarse group to form a reference vector. , and the remaining first The node and the first The vector consists of nodes. ,in, Calculate separately and Angle between Among them, angle The calculation formula is as follows: ;

[0031] Step 3: Put With threshold angle Compare, if the first points Angle greater than the threshold Then it will be arranged in the th order. The nodes preceding each node are subdivided into groups, and the nodes are arranged in order. Repeat steps two and three for the nodes preceding each node to subdivide the coarse combination, and record each subdivided group as a segmented path;

[0032] Step 4: Combine the segmented paths according to the sampling order to form the energy transfer path for industrial waste heat.

[0033] Furthermore, determining the utilization path of industrial waste heat based on the energy transfer path, and forming a multi-energy coordinated combined heat and power system based on the utilization path, specifically includes the following processes:

[0034] Integrating multiple energy inputs, including grid electricity, natural gas, wind power, photovoltaic power, and renewable energy sources such as molten salt thermal energy storage and energy storage methods, a multi-energy synergistic cogeneration system is formed. This multi-energy synergistic cogeneration system includes:

[0035] Heat supply section: The converted heat energy is delivered to the customer through a heat network to meet the user's heat demand;

[0036] Cold supply section: Absorption chillers are used to convert heat energy into cold energy and provide it to customers to meet their cooling needs;

[0037] Electricity supply section: Heat energy is converted into electrical energy through combined heat and power units, and combined with power input from the power grid, wind power generation, and photovoltaic power generation to ensure a stable power supply;

[0038] Steam supply section: Steam is generated through evaporator equipment to meet the customer's steam demand.

[0039] Compared to existing solutions, the beneficial effects achieved by this invention are:

[0040] Improving the efficiency of waste heat utilization: By using the K-means algorithm to classify industrial waste heat data by quality, the quality category corresponding to each industrial waste heat generation source can be accurately determined. This allows waste heat of different qualities to be utilized in a targeted manner, avoiding the problem of insufficient utilization caused by differences in waste heat quality in traditional methods. This greatly improves the overall utilization efficiency of waste heat, converting potentially wasted energy into usable forms such as heat, cooling, and electricity, and reducing the energy procurement costs of industrial parks.

[0041] Optimizing energy transfer paths: An energy transfer network model is constructed based on industrial waste heat generation sources of the same quality category. A random walk path generation algorithm is used to select candidate path nodes for generating energy transfer paths, generating energy transfer paths through a coarse combination. This approach can scientifically and rationally determine the transfer paths of waste heat according to the actual structure and characteristics of the energy transfer network, reducing energy loss during the transfer process and enabling waste heat to reach the utilization end more efficiently, further improving the systematic nature of energy utilization.

[0042] Achieving Multi-Energy Coordinated Operation: This method establishes a multi-energy coordinated combined heat, power, and cooling system based on the utilization path of waste heat, integrating various energy inputs such as grid electricity, natural gas, wind power, photovoltaic power, and molten salt thermal storage. Through intelligent control and optimized scheduling, synergistic complementarity among multiple energy sources is achieved. The operating status of each energy input and conversion equipment is dynamically adjusted according to changes in the client's demand for heat, cooling, steam, and electricity. This not only improves the stability and reliability of energy supply but also allows for the selection of the optimal energy combination under different energy price and supply conditions, thereby reducing energy costs. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0044] Figure 1 This is a flowchart illustrating a multi-energy flow integrated energy management decision-making method for industrial parks, according to an embodiment of the present invention.

[0045] Figure 2 This is a flowchart of another industrial park multi-energy flow integrated energy management decision-making method according to an embodiment of the present invention;

[0046] Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more exemplary embodiments. Numerous specific details are provided in the following description to give a full understanding of exemplary embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, steps, etc., can be employed. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0049] This embodiment provides a multi-energy flow integrated energy management decision-making method for industrial parks. Figure 1 This is a flowchart illustrating a multi-energy flow integrated energy management decision-making method for industrial parks, as described in an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0050] Step S101: Collect industrial waste heat data from multiple industrial waste heat generation sources in the industrial park, and use the K-means algorithm to classify the industrial waste heat data to determine the industrial waste heat quality category corresponding to each industrial waste heat generation source.

[0051] It is worth noting that industrial waste heat data includes waste heat temperature, waste heat medium pressure, waste heat medium flow rate, and the amount of usable heat in the waste heat. Specifically, this includes the waste heat temperature range (e.g., low-temperature waste heat <100℃, medium-temperature waste heat 100-300℃, high-temperature waste heat >300℃), the flow rate of the waste heat medium (e.g., steam, flue gas, cooling water), the pressure of the waste heat medium (e.g., steam pressure), and the amount of usable heat in the waste heat.

[0052] Step S102: Construct an energy transfer network model based on industrial waste heat generation sources of the same quality category, and use a random walk path generation algorithm to select candidate path nodes for generating energy transfer paths from the energy transfer network model;

[0053] Step S103: Generate energy transfer paths for industrial waste heat by using a coarse combination method for the selected path nodes;

[0054] Step S104: Determine the utilization path of industrial waste heat based on the energy transfer path, and form a multi-energy coordinated combined heat, power and cooling system based on the utilization path.

[0055] In summary, this invention collects industrial waste heat data from multiple industrial waste heat generation sources within an industrial park, uses the K-means algorithm to classify the data for quality, and determines the quality category of each industrial waste heat generation source. Based on industrial waste heat generation sources of the same quality category, an energy transfer network model is constructed. A random walk path generation algorithm is used to select candidate path nodes from the energy transfer network model to generate energy transfer paths. A coarse combination method is used to generate energy transfer paths for the industrial waste heat from the candidate path nodes. Based on the energy transfer paths, utilization paths for the industrial waste heat are determined, and a multi-energy coordinated combined heat, power, and cooling system is formed based on these utilization paths. This improves the efficiency of waste heat utilization, enhances energy management efficiency, and reduces energy consumption.

[0056] In some embodiments, the K-means algorithm is used to classify industrial waste heat data to determine the quality category of each industrial waste heat generation source. This process includes the following steps:

[0057] Step 1: Record each industrial waste heat data point as a sample. , The value is n is the number of industrial waste heat generation sources, and k cluster centers are randomly initialized. k is a pre-set number of cluster centers, whose value is set according to the quality category of industrial waste heat. The quality categories of industrial waste heat include unusable industrial waste heat grades, low-quality industrial waste heat grades, medium-quality industrial waste heat grades, and high-quality industrial waste heat grades. The value is , where the preferred value of k is 4.

[0058] It's worth noting that meeting the unusable industrial waste heat rating requires the following conditions: extremely low temperature, typically close to or below ambient temperature. Some cooling water discharged after multiple heat exchanges may only be a few degrees Celsius higher than ambient temperature, exhibiting highly unstable heat load with significant fluctuations in flow and temperature, making stable heat recovery difficult. For example, the emission volume and temperature of some intermittently produced process waste gases vary greatly across different time periods. Meeting the low-quality industrial waste heat rating requires the following conditions: relatively low temperature, generally below 100℃; heat load stability: the heat load fluctuates somewhat, but is relatively stable compared to the unusable rating. Meeting the medium-quality industrial waste heat rating requires the following conditions: temperature in a moderate range, typically between 100 and 300℃; heat load stability: the heat load is relatively stable, with small fluctuations in flow and temperature. For example, the flue gas from some continuously operating industrial boilers maintains a relatively stable temperature and flow rate. Meeting the high-quality industrial waste heat rating requires the following conditions: relatively high temperature, generally above 300℃. The raw gas temperature in high-temperature coking ovens can reach 650-1000℃, and the high-temperature flue gas temperature in some metal smelting processes is also in the hundreds or even thousands of degrees Celsius. Heat load stability is characterized by stable heat load and minimal fluctuations in flow rate and temperature. For example, the exhaust steam from the turbines of large thermal power plants maintains a basically constant temperature and flow rate under stable power generation conditions.

[0059] Step 2, calculate the sample Cluster center to which it should belong: Calculate its Euclidean distance to the k cluster centers. The calculation formula is: ;in, Representing the The value of the m-th dimension feature of a sample. Indicates the first The value of the m-th dimension feature of each cluster center is given, where M represents the total number of features. After calculating the distance between each sample and each cluster center, each sample is classified into the nearest corresponding cluster, where the cluster is the cluster center.

[0060] Step 3: Calculate the deviation between the sample and the center of its cluster. The calculation formula is:

[0061] ;

[0062] Step 4: Update the cluster centers and reassign the clusters of each sample:

[0063] ;in, This indicates the updated location of the l-th cluster center. Indicates belonging to a cluster The sample, Represents clusters The number of samples included; Steps two and three are performed to calculate the new cluster partitioning results and the new bias. ;

[0064] Step 5: Repeat steps 2 to 4 to iteratively update the clustering of the samples until the clustering bias converges, i.e., the difference in bias before and after the iterative update. Less than a given deviation threshold The process involves identifying the cluster corresponding to the industrial waste heat data for each industrial waste heat generation source. This cluster represents the quality category. The iteration termination condition is as follows: ; The value can be 0.01, where, For the first iteration This is the deviation threshold for terminating the iteration.

[0065] In some embodiments, constructing an energy transfer network model based on industrial waste heat generation sources of the same quality category specifically includes the following processes:

[0066] Define the energy delivery network model as ,in, A node set consists of industrial waste heat generation sources of the same quality category, where each industrial waste heat generation source is a node. , Let be the set of edges, where each edge is represented as a directed tuple, i.e. .

[0067] In some embodiments, Figure 2 This is a flowchart of another industrial park multi-energy flow integrated energy management decision-making method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process of selecting candidate path nodes for generating energy transfer paths from the energy transfer network model using the random walk path generation algorithm includes the following steps:

[0068] Step S201: Initialize the random walk parameters and determine the starting node of the random walk. The starting node is selected from the node set V.

[0069] The random walk parameters include the walk step threshold and the walk probability transition matrix update period. The starting node is determined from the node set V by random sampling or by specifying a node. The number of walk steps is determined based on the total number of nodes NV in the same quality energy network. If the network node density is high, the walk step threshold is set to 1.5NV. The walk probability transition matrix update period is 24 hours.

[0070] Step S202: Using a random walk path generation algorithm, starting from the starting node, perform a random walk according to the directed connection relationship of the edges. At each step of the walk, select the next node to be reached by the walk with a preset probability based on the edge situation of the current node.

[0071] The calculation method for the preset probability specifically includes the following process:

[0072] For the current node Traverse all its edges and count them. Total number of connected edges Calculate from Transfer to probability , ;in, For the edge The weight, For the edge The weights are pre-assigned based on the historical flow and heat loss factors during the transfer of industrial waste heat along the corresponding edge. The following is an example of weight assignment: Weights are determined based on the ratio of the edge's historical cumulative transmission flow to the network's average flow. Edges with higher historical flow indicate more frequent use in actual energy transfer, resulting in higher weights. A flow fluctuation correction term is also introduced to attenuate the weight of edges with flow fluctuations exceeding a preset threshold, reflecting the impact of transmission stability on path selection. The heat loss rate per unit of heat transferred along the edge is calculated by combining the physical transmission distance, pipeline insulation coefficient, and medium temperature decay characteristics. Edges with lower heat loss rates have higher weights. For high-temperature waste heat transfer scenarios, an additional temperature sensitivity coefficient is introduced to impose a higher weight penalty on edges with high temperature difference losses. The following is an example of weight calculation: Basic parameters: Edge :node (Residual heat from the reactor) → Node (Heat exchange station), the historical cumulative transmission flow of the edge is 1200GJ, the average network flow is 800GJ, and the historical flow contribution is... for: Its weight can be 1.5.

[0073] Step S203: During the random walk, record the sequence of nodes traversed by the walk, determine the node sequence as the candidate path node sequence for energy transfer, and complete the selection of candidate path nodes.

[0074] In some embodiments, generating energy transfer paths for industrial waste heat using a coarse combination approach for the selected path nodes specifically includes the following process:

[0075] Step 1: Settings For coarse combination parameters, for each The candidate path nodes are coarsely combined according to the sampling order of the sampling interval values ​​to obtain several coarse combination groups;

[0076] Step 2: Combine the first and second nodes of each coarse group to form a reference vector. , and the remaining first The node and the first The vector consists of nodes. ,in, Calculate separately and Angle between Among them, angle The calculation formula is as follows: ;

[0077] Step 3: Put With threshold angle Compare, if the first points Angle greater than the threshold Then it will be arranged in the th order. The nodes preceding each node are subdivided into groups, and the nodes are arranged in order. Repeat steps two and three for the nodes preceding each node to subdivide the coarse combination, and record each subdivided group as a segmented path;

[0078] It is worth noting that, The settings can include setting a threshold angle based on the transfer efficiency of waste heat in different directions. If the heat loss is small and the transfer efficiency is high when waste heat is transferred within a certain angle range, then the upper limit of that angle range can be used as the threshold angle. For example, if experiments or theoretical analysis show that the heat transfer efficiency remains high when the angle between the waste heat transfer direction and the reference vector direction is less than 30 degrees, then the threshold angle can be set accordingly. Set to 30 degrees.

[0079] Step 4: Combine the segmented paths according to the sampling order to form the energy transfer path for industrial waste heat.

[0080] In some embodiments, determining the utilization path of industrial waste heat based on the energy transfer path and forming a multi-energy coordinated combined heat and power system based on the utilization path specifically includes the following processes:

[0081] Based on the different energy demand types of users (heat, cooling, electricity, steam), the utilization path of industrial waste heat is determined. For example, for users with heat demand, the converted heat energy is directly transmitted through the heat network; for users with cooling demand, absorption chillers are used to convert heat energy into cooling energy for supply; for electricity users, a stable power supply is provided through a combination of combined heat and power units and renewable energy generation; and for users who need steam, steam is supplied through steam generated by evaporators.

[0082] Integrating multiple energy inputs, including grid electricity, natural gas, wind power, photovoltaic power, and renewable energy sources such as molten salt thermal energy storage and energy storage methods, a multi-energy synergistic cogeneration system is formed. This multi-energy synergistic cogeneration system includes:

[0083] Heat supply section: The converted heat energy is delivered to the customer through a heat network to meet the user's heat demand;

[0084] Cold supply section: Absorption chillers are used to convert heat energy into cold energy and provide it to customers to meet their cooling needs;

[0085] Electricity supply section: Heat energy is converted into electrical energy through combined heat and power units, and combined with power input from the power grid, wind power generation, and photovoltaic power generation to ensure a stable power supply;

[0086] Steam supply section: Steam is generated through evaporator equipment to meet the customer's steam demand.

[0087] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0088] In some embodiments, Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention, such as... Figure 3 As shown, the electronic device includes a memory 301 and a processor 302. The memory 301 stores a computer program. When the computer program is executed by the processor 302, the processor 302 executes the industrial park multi-energy flow integrated energy management decision-making method as described in any of the above embodiments.

[0089] The memory 301 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. The memory 301 has storage space 303 for program code 313 for performing any of the method steps described above. For example, the storage space 303 for program code may include individual program codes 313 for implementing the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When run by a computing processing device, this code causes the computing processing device to perform the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When these codes are run by a computing processing device, the device causes it to execute the steps of the multi-energy flow integrated energy management decision-making method for industrial parks described above.

[0090] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0091] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0092] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0094] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A multi-energy flow integrated energy management decision-making method for industrial parks, characterized in that the method... include: Industrial waste heat data from multiple sources of industrial waste heat generation within the industrial park were collected. The K-means algorithm was used to classify the industrial waste heat data to determine the quality category of each source of industrial waste heat generation. An energy transfer network model is constructed based on industrial waste heat generation sources of the same quality category. A random walk path generation algorithm is used to select candidate path nodes for generating energy transfer paths from the energy transfer network model. The energy transfer paths for industrial waste heat are generated by coarse combination of the selected path nodes. The utilization path of industrial waste heat is determined based on the energy transfer path, and a multi-energy synergistic combined heat, power and cooling system is formed based on the utilization path.

2. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 1, characterized in that, Industrial waste heat data includes waste heat temperature, waste heat medium pressure, waste heat medium flow rate, and the amount of heat available for use.

3. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 1, characterized in that, The K-means algorithm is used to classify the quality of industrial waste heat data to determine the quality category of each industrial waste heat generation source. The specific process includes the following steps: Step 1: Record each industrial waste heat data point as a sample. , The value is n is the number of industrial waste heat generation sources, and k cluster centers are randomly initialized. k is the pre-set number of cluster centers, and its value is set according to the quality category of industrial waste heat. The value is ; Step 2, calculate the sample Cluster center to which it should belong: Calculate its Euclidean distance to the k cluster centers. The calculation formula is: ;in, Representing the The value of the m-th dimension feature of a sample. Indicates the first The value of the m-th dimension feature of each cluster center is given, where M represents the total number of features. After calculating the distance between each sample and each cluster center, each sample is classified into the nearest corresponding cluster, where the cluster is the cluster center. Step 3: Calculate the deviation between the sample and the center of its cluster. The calculation formula is: ； Step 4: Update the cluster centers and reassign the clusters of each sample: ;in, This indicates the updated location of the l-th cluster center. Indicates belonging to a cluster The sample, Represents clusters The number of samples included; Steps two and three are performed to calculate the new cluster partitioning results and the new bias. ; Step 5: Repeat steps 2 to 4 to iteratively update the clustering of the samples until the clustering bias converges, i.e., the difference in bias before and after the iterative update. Less than a given deviation threshold The process involves identifying the cluster corresponding to the industrial waste heat data for each industrial waste heat generation source. This cluster represents the quality category. The iteration termination condition is as follows: ;in, For the first iteration This is the deviation threshold for terminating the iteration.

4. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 1, characterized in that, The specific process of constructing an energy transfer network model based on industrial waste heat generation sources of the same quality category includes the following steps: Define the energy delivery network model as ,in, A node set consists of industrial waste heat generation sources of the same quality category, where each industrial waste heat generation source is a node. , Let be the set of edges, where each edge is represented as a directed tuple, i.e. .

5. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 4, characterized in that, The process of selecting candidate path nodes for generating energy transfer paths from an energy transfer network model using a random walk path generation algorithm includes the following steps: Initialize the random walk parameters and determine the starting node of the random walk. The starting node is selected from the node set V. The random walk parameters include the number of steps threshold and the update period of the walk probability transition matrix. The starting node is determined from the node set V by random sampling or by specifying a node. Using a random walk path generation algorithm, starting from the initial node, a random walk is performed according to the directed connection relationship of the edges. At each step of the walk, the next node to be reached is selected with a preset probability based on the edge situation of the current node. During the random walk, the sequence of nodes traversed by the walk is recorded, and the node sequence is determined as the candidate path node sequence for energy transfer, thus completing the selection of candidate path nodes.

6. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 5, characterized in that, The calculation method for the preset probability specifically includes the following process: For the current node Traverse all its edges and count them. Total number of connected edges Calculate from Transfer to probability , ;in, For the edge The weight, For the edge The weights are pre-assigned based on the historical flow and heat loss factors during the transfer of industrial waste heat at the corresponding edge.

7. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 1, characterized in that, The process of generating energy transfer paths for industrial waste heat using a coarse combination method for selecting path nodes includes the following steps: Step 1: Settings For coarse combination parameters, for each The candidate path nodes are coarsely combined according to the sampling order of the sampling interval values ​​to obtain several coarse combination groups; Step 2: Combine the first and second nodes of each coarse group to form a reference vector. , and the remaining first The node and the first The vector consists of nodes. ,in, Calculate separately and Angle between Among them, angle The calculation formula is as follows: ; Step 3: Put With threshold angle Compare, if the first points Angle greater than the threshold Then it will be arranged in the th order. The nodes preceding each node are subdivided into groups, and the nodes are arranged in order. Repeat steps two and three for the nodes preceding each node to subdivide the coarse combination, and record each subdivided group as a segmented path; Step 4: Combine the segmented paths according to the sampling order to form the energy transfer path for industrial waste heat.

8. The multi-energy flow integrated energy management decision-making method for industrial parks according to claim 1, characterized in that, Based on the energy transfer path, the utilization path of industrial waste heat is determined, and based on the utilization path, a multi-energy coordinated combined heat and power (CHP) system is specifically constructed. Includes the following processes: Integrating multiple energy inputs, including grid electricity, natural gas, wind power, photovoltaic power, and renewable energy sources such as molten salt thermal energy storage and energy storage methods, a multi-energy synergistic cogeneration system is formed. This multi-energy synergistic cogeneration system includes: Heat supply section: The converted heat energy is delivered to the customer through a heat network to meet the user's heat demand; Cold supply section: Absorption chillers are used to convert heat energy into cold energy and provide it to customers to meet their cooling needs; Electricity supply section: Heat energy is converted into electrical energy through combined heat and power units, and combined with power input from the power grid, wind power generation, and photovoltaic power generation to ensure a stable power supply; Steam supply section: Steam is generated through evaporator equipment to meet the customer's steam demand.

Images