Multi-region collaborative heating scheduling method based on multi-agent adjustment cost consistency

Abstract

The application discloses a multi-region collaborative heating scheduling method based on multi-agent adjustment cost consistency, and comprises the following steps: a mechanism modeling and data identification method is used to establish a digital twin model of a multi-region collaborative heating system; one region in the multi-region collaborative heating system is responsible for tracking a total heating scheduling instruction, and each region exchanges information with adjacent regions; the multi-region collaborative heating system is set as a corresponding agent, and a consistency collaborative communication topology graph of a multi-agent system is established; a low-carbon economic scheduling model of the multi-region collaborative heating system is established; when total load demand changes result in heating output power changes, a multi-agent consistency algorithm is used to solve the low-carbon economic scheduling model of the multi-region collaborative heating system, and optimal incremental cost and heating output power are obtained; the multi-agent consistency algorithm is used to realize optimal power distribution, and low-carbon economic operation of the multi-region collaborative heating system is ensured.

Description

Technical Field

[0001] This invention belongs to the field of smart heating technology, specifically relating to a multi-regional collaborative heating scheduling method based on the consistency of multi-agent adjustment costs. Background Technology

[0002] As the interconnection of regional heating systems continues to strengthen, smart heating systems are showing a trend towards more complex coupling. Since multi-regional interconnection facilitates resource allocation across the entire network, achieving coordinated cooperation among multiple regions and improving system reliability has become a development trend for heating systems both domestically and internationally.

[0003] The functional structure and behavioral characteristics of multi-agent systems are expressed based on the mutual understanding, cooperation, coordination, communication, scheduling, control, and management among agents. Multi-agent systems not only possess the characteristics of distribution, autonomy, and coordination, but also have learning, self-organizing, and reasoning abilities. When solving practical problems, using multi-agent system methods can significantly improve problem-solving efficiency and also provide high reliability and robustness.

[0004] However, the ideal safe and stable operation of a heating system requires a fixed network structure and minimal changes in network topology. In reality, however, a multi-regional coordinated heating system is a dynamically changing network. The topology of the heating network can change due to load variations, faults, and other reasons. Finding the optimal scheduling scheme for multi-regional coordinated heating to minimize costs and achieve low-carbon and economical scheduling of multi-regional coordinated heating systems under varying load conditions and while meeting system constraints is an urgent problem to be solved.

[0005] Based on the above technical problems, a new multi-regional collaborative heating scheduling method based on the consistency of multi-agent adjustment costs needs to be designed. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a multi-regional collaborative heating scheduling method based on the consistency of multi-agent adjustment costs.

[0007] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0008] This invention provides a multi-regional collaborative heating scheduling method based on the consistency of adjustment costs among multiple agents, comprising:

[0009] Step S1: Establish a digital twin model of the multi-regional collaborative heating system using mechanism modeling and data identification methods; in the multi-regional collaborative heating system, one region is responsible for tracking the overall heating dispatch instructions, and each region exchanges information with its neighboring regions;

[0010] Step S2: Set the multi-regional collaborative heating system as a corresponding intelligent agent and establish a consistent collaborative communication topology diagram of the multi-agent system;

[0011] Step S3: Establish a low-carbon economic dispatch model for a multi-regional coordinated heating system;

[0012] Step S4: When changes in total load demand lead to changes in heating output power, the optimal incremental cost and heating output power are obtained by solving the low-carbon economic scheduling model of the multi-regional coordinated heating system based on the digital twin model of the multi-regional coordinated heating system and using the multi-agent consensus algorithm; and the feasibility of the optimal incremental cost and heating output power is verified based on the digital twin model of the multi-regional coordinated heating system.

[0013] Furthermore, in step S1, a digital twin model of the multi-regional coordinated heating system is established using mechanism modeling and data identification methods, specifically including:

[0014] Step S101: Construct a virtual entity for a multi-regional collaborative heating system, including:

[0015] The process involves constructing physical device entity models, behavioral models, and rule models. First, a structural mechanism model of the multi-regional collaborative heating system is built and imported into a visualization platform, adding physical attributes to the equipment. Then, a behavioral model is constructed based on the fundamental thermodynamic theory of multi-regional collaborative heating systems, establishing a virtual simulation system for the multi-regional collaborative heating system with interactive functions and a simulated real-world operating environment. Finally, a rule model for the virtual entities is established to formulate control strategies for the virtual entities.

[0016] Step S102: Establish virtual and physical data connections for the multi-regional coordinated heating system, including:

[0017] First, sensor detection points are set up on the physical equipment of the multi-regional collaborative heating system. The actual operation data of the physical equipment of the multi-regional collaborative heating system is collected through Internet of Things technology, and corresponding detection points are set up on the virtual equipment to collect simulation data at the corresponding locations.

[0018] Then, by calling the collected actual operating data to drive the corresponding model in the virtual space, a mapping relationship is established with the simulation data formed by the virtual equipment of the multi-regional collaborative heating system, thus forming the operation strategy of the multi-regional collaborative heating system;

[0019] Finally, by continuously iterating and optimizing the data acquisition and control process, the connection and dynamic interaction of real-time data between physical entities and virtual spaces are realized, and the establishment of a digital twin model of a multi-regional collaborative heating system is completed.

[0020] Step S103: Identify the digital twin model, including:

[0021] The real-time operating data of the multi-regional coordinated heating system equipment under multiple operating conditions are integrated into the established digital twin model. The simulation results of the digital twin model are adaptively identified and corrected using the reverse identification method to obtain the identified and corrected digital twin model of the multi-regional coordinated heating system.

[0022] Furthermore, in step S2, the multi-regional coordinated heating system is configured as a corresponding intelligent agent, and a consistent coordinated communication topology diagram of the multi-agent system is established, specifically including:

[0023] Based on the digital twin model of a multi-regional coordinated heating system, the set of intelligent agent systems is determined as x = {x1, x2, ..., x}. n};

[0024] The communication topology of the multi-agent system is described as a graph G = (V, E, A); where the set of agents V = {v1, v2, ..., v...} n}; E represents the communication edge set between agents. (v i ,v j ) = e ij ∈E indicates that information is exchanged between the i-th agent and the j-th agent;

[0025] The communication connections are described by a weighted adjacency matrix A, a diagonal matrix D, and a Laplacian matrix L; where... w ij Yes (v) i ,v j The weight of ); d ij The elements are in the diagonal matrix D.

[0026] Furthermore, in step S3, a low-carbon economic dispatch model for a multi-regional coordinated heating system is established, specifically including:

[0027] Set the heating cost C for each regional heating unit. i And carbon emission costs E i , is represented as:

[0028]

[0029]

[0030] The objective function for low-carbon economic scheduling of a multi-regional coordinated heating system is defined as follows:

[0031]

[0032] Among them, a i b i c iLet u and u represent the fuel consumption coefficients of the i-th heating unit, respectively. i v i w i Let P represent the carbon emission coefficients of the i-th heating unit; Gi The output power of the i-th heating unit is calculated differently depending on the type of heating unit. When it is a combined heat and power unit, P is... Gi =P ei +γ i h i P ei For the electrical output of the i-th heating unit, h i Let γ be the heating power of the i-th heating unit. i ε is the thermoelectric conversion coefficient; T is the dispatch cycle; ε is the carbon emission cost coefficient; N is the number of regions;

[0033] The constraints of the multi-regional coordinated heating system shall be set, including at least: power balance constraints, electrical balance constraints, thermal balance constraints, and heating unit capacity constraints.

[0034] Furthermore, in step S4, when changes in total load demand lead to changes in heating output power, a multi-agent consensus algorithm is used to solve the low-carbon economic scheduling model of the multi-regional coordinated heating system to obtain the optimal incremental cost and heating output power. Specifically, this includes:

[0035] The low-carbon economic dispatch model of a multi-regional coordinated heating system is transformed using the Lagrange multiplier method:

[0036]

[0037] Among them, the load demand P D The difference in change is denoted as ΔP D The change in output power in each region is denoted as ΔP. Gi The change in load demand is related to the output power of all district heating systems; λ is the Lagrange multiplier corresponding to the power balance constraint, representing the incremental cost in the low-carbon economic dispatch model;

[0038] For ΔP Gi The partial derivatives were calculated and reasoned to obtain:

[0039] λ-β i -v i =2(P Gi +ΔP Gi (a) i +u i );

[0040]

[0041] The sum of the changes in heating output power across all areas is calculated and expressed as:

[0042]

[0043] The optimal incremental cost is calculated as follows:

[0044]

[0045] Set the incremental cost λ and the allowable power difference σ for each agent, and apply a consensus algorithm to each agent to obtain the output power P of each agent under the incremental cost. Gi ;

[0046] Determine P Gi Is it within the constraints? If it is, then the new optimized output power... Otherwise, P Gi * =P Gi,max or P Gi * =P Gi,min ;

[0047] Calculate power deviation It then determines whether the absolute value of the power deviation is within the allowable range |Δp<σ|. If it is within the range, the power P is directly output. Gi * Otherwise, perform a consistency calculation again.

[0048] Furthermore, the process of applying a consensus algorithm to each agent to perform consensus calculation includes:

[0049] Establish dynamic models of leader and follower agents in a multi-regional collaborative heating system:

[0050]

[0051] Where A and B are constant matrices; x i =(x i-1 , ..., x i,n ) T The state of agent i; u i It is the input vector of agent i; f(·)=(f1,f2,...,f n ) T f i The state is x at time t. i-1 , ..., x i,n The function of time; i = 0 is the leader agent, i = 1, 2, ..., n is the follower agent;

[0052] The incremental cost for each heating zone is calculated and expressed as follows:

[0053]

[0054] The follower-consistent update process is represented as:

[0055]

[0056] The leader consistency update process introduces a power deviation, denoted as:

[0057]

[0058] in, Let be a convergence coefficient representing the convergence rate, and The leader agent satisfies the power balance constraint when updating the incremental cost of the follower agent:

[0059] Taking into account the output constraints of each district's heating system, the consistency update process is expressed as follows:

[0060]

[0061] Where, λ i,lower , λ i,upper These are the minimum and maximum values ​​of the consistency variables for agent i, respectively.

[0062] Furthermore, the output power P Gi * The output power function is expressed as:

[0063]

[0064] Furthermore, in step S2, there are multiple communication channels between the agents. When some communication lines fail, the agents can complement each other's information, and the scheduling performance of the heating system remains optimal.

[0065] The beneficial effects of this invention are:

[0066] This invention establishes a low-carbon economic scheduling model for a multi-regional collaborative heating system by setting up a multi-agent collaborative heating system and building a communication network topology model based on graph theory. It also establishes a consensus algorithm for regional incremental costs and employs a leader-follower distributed consensus algorithm for the multi-agent system to solve the low-carbon economic scheduling model. Optimal scheduling is performed based on the system response power, achieving plug-and-play functionality for each region. Real-time information interaction among the multi-agents ensures the algorithm's convergence speed and robustness, resulting in better power optimization scheduling of the multi-regional collaborative heating system and achieving optimal power allocation, thus guaranteeing the system's low-carbon economic operation.

[0067] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0068] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0069] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0070] Figure 1 This is a flowchart of a multi-regional collaborative heating scheduling method based on the consistency of adjustment costs of multiple agents according to the present invention.

[0071] Figure 2 This is a schematic diagram of the multi-region consistency collaborative scheduling framework of the present invention;

[0072] Figure 3 This is a schematic diagram of the heating system zoning model of the present invention;

[0073] Figure 4 This is a flowchart of the consistent low-carbon economic scheduling algorithm of the present invention. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions 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, 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.

[0075] Example 1

[0076] Figure 1 This is a flowchart of a multi-regional collaborative heating scheduling method based on the consistency of adjustment costs of multiple agents, which is involved in this invention.

[0077] Figure 2 This is a schematic diagram of the multi-region consistency and collaborative scheduling framework involved in this invention.

[0078] Figure 3This is a schematic diagram of the heating system zoning model involved in this invention.

[0079] Figure 4 This is a flowchart of the consistent low-carbon economic scheduling algorithm involved in this invention.

[0080] like Figure 1-4 As shown, this embodiment 1 provides a multi-regional collaborative heating scheduling method based on the consistency of multi-agent adjustment costs, which includes:

[0081] Step S1: Establish a digital twin model of the multi-regional collaborative heating system using mechanism modeling and data identification methods; in the multi-regional collaborative heating system, one region is responsible for tracking the overall heating dispatch instructions, and each region exchanges information with its neighboring regions;

[0082] Step S2: Set the multi-regional collaborative heating system as a corresponding intelligent agent and establish a consistent collaborative communication topology diagram of the multi-agent system;

[0083] Step S3: Establish a low-carbon economic dispatch model for a multi-regional coordinated heating system;

[0084] Step S4: When changes in total load demand lead to changes in heating output power, the optimal incremental cost and heating output power are obtained by solving the low-carbon economic scheduling model of the multi-regional coordinated heating system based on the digital twin model of the multi-regional coordinated heating system and using the multi-agent consensus algorithm; and the feasibility of the optimal incremental cost and heating output power is verified based on the digital twin model of the multi-regional coordinated heating system.

[0085] It should be noted that, on the one hand, the digital twin model of the multi-regional coordinated heating system is used to predict scheduling strategies (optimal incremental cost and output power): by simulating and predicting multiple scheduling strategies using the digital twin model, schemes that do not meet the constraints, boundary conditions, and relevant system parameters of the scheduling model can be eliminated. On the other hand, the digital twin model of the multi-regional coordinated heating system is used to make decisions on scheduling strategies: after obtaining the scheduling strategy, the relevant scheduling schemes of the optimal strategy are derived based on the digital twin model of the multi-regional coordinated heating system to verify the feasibility of the strategy. If the strategy is verified and passed, it is executed to achieve multi-regional coordinated heating scheduling; otherwise, the scheduling strategy is recalculated and obtained. By using the digital twin model to verify the feasibility of the scheduling strategy, check the parameters, and visualize the results, the scientific verification of the scheme is achieved, making the scheduling strategy more in line with expectations.

[0086] In this embodiment, step S1 involves establishing a digital twin model of a multi-regional coordinated heating system using mechanistic modeling and data identification methods, specifically including:

[0087] Step S101: Construct a virtual entity for a multi-regional collaborative heating system, including:

[0088] The process involves constructing physical device entity models, behavioral models, and rule models. First, a structural mechanism model of the multi-regional collaborative heating system is built and imported into a visualization platform, adding physical attributes to the equipment. Then, a behavioral model is constructed based on the fundamental thermodynamic theory of multi-regional collaborative heating systems, establishing a virtual simulation system for the multi-regional collaborative heating system with interactive functions and a simulated real-world operating environment. Finally, a rule model for the virtual entities is established to formulate control strategies for the virtual entities.

[0089] Step S102: Establish virtual and physical data connections for the multi-regional coordinated heating system, including:

[0090] First, sensor detection points are set up on the physical equipment of the multi-regional collaborative heating system. The actual operation data of the physical equipment of the multi-regional collaborative heating system is collected through Internet of Things technology, and corresponding detection points are set up on the virtual equipment to collect simulation data at the corresponding locations.

[0091] Then, by calling the collected actual operating data to drive the corresponding model in the virtual space, a mapping relationship is established with the simulation data formed by the virtual equipment of the multi-regional collaborative heating system, thus forming the operation strategy of the multi-regional collaborative heating system;

[0092] Finally, by continuously iterating and optimizing the data acquisition and control process, the connection and dynamic interaction of real-time data between physical entities and virtual spaces are realized, and the establishment of a digital twin model of a multi-regional collaborative heating system is completed.

[0093] Step S103: Identify the digital twin model, including:

[0094] The real-time operating data of the multi-regional coordinated heating system equipment under multiple operating conditions are integrated into the established digital twin model. The simulation results of the digital twin model are adaptively identified and corrected using the reverse identification method to obtain the identified and corrected digital twin model of the multi-regional coordinated heating system.

[0095] In this embodiment, step S2 involves setting the multi-regional coordinated heating system as corresponding intelligent agents and establishing a consistent coordinated communication topology diagram for the multi-agent system, specifically including:

[0096] Based on the digital twin model of a multi-regional coordinated heating system, the set of intelligent agent systems is determined as x = {x1, x2, ..., x}. n};

[0097] The communication topology of the multi-agent system is described as a graph G = (V, E, A); where the set of agents V = {v1, v2, ..., v...} n}; E represents the communication edge set between agents. (v i ,v j) = e ij ∈E indicates that information is exchanged between the i-th agent and the j-th agent;

[0098] The communication connections are described by a weighted adjacency matrix A, a diagonal matrix D, and a Laplacian matrix L; where... w ij Yes (v) i ,v j The weight of ); d ij The elements are in the diagonal matrix D.

[0099] In this embodiment, step S3, establishing a low-carbon economic dispatch model for a multi-regional coordinated heating system, specifically includes:

[0100] Set the heating cost C for each regional heating unit. i And carbon emission costs E i , is represented as:

[0101]

[0102]

[0103] The objective function for low-carbon economic scheduling of a multi-regional coordinated heating system is defined as follows:

[0104]

[0105] Among them, a i b i c i Let u and u represent the fuel consumption coefficients of the i-th heating unit, respectively. i v i w i Let P represent the carbon emission coefficients of the i-th heating unit; Gi The output power of the i-th heating unit is calculated differently depending on the type of heating unit. When it is a combined heat and power unit, P is... Gi =P ei +γ i h i P ei For the electrical output of the i-th heating unit, h i Let γ be the heating power of the i-th heating unit. i ε is the thermoelectric conversion coefficient; T is the dispatch cycle; ε is the carbon emission cost coefficient; N is the number of regions;

[0106] The constraints of the multi-regional coordinated heating system shall be set, including at least: power balance constraints, electrical balance constraints, thermal balance constraints, and heating unit capacity constraints.

[0107] In this embodiment, in step S4, when changes in total load demand lead to changes in heating output power, a multi-agent consensus algorithm is used to solve the low-carbon economic scheduling model of the multi-regional coordinated heating system to obtain the optimal incremental cost and heating output power. Specifically, this includes:

[0108] The low-carbon economic dispatch model of a multi-regional coordinated heating system is transformed using the Lagrange multiplier method:

[0109]

[0110] Among them, the load demand P D The difference in change is denoted as ΔP D The change in output power in each region is denoted as ΔP. Gi The change in load demand is related to the output power of all district heating systems; λ is the Lagrange multiplier corresponding to the power balance constraint, representing the incremental cost in the low-carbon economic dispatch model;

[0111] For ΔP Gi The partial derivatives were calculated and reasoned to obtain:

[0112] λ-β i -v i =2(P Gi +ΔP Gi (a) i +u i );

[0113]

[0114] The sum of the changes in heating output power across all areas is calculated and expressed as:

[0115]

[0116] The optimal incremental cost is calculated as follows:

[0117]

[0118] Set the incremental cost λ and the allowable power difference σ for each agent, and apply a consensus algorithm to each agent to obtain the output power P of each agent under the incremental cost. Gi ;

[0119] Determine P Gi Is it within the constraints? If it is, then the new optimized output power... Otherwise, P Gi * =P Gi,max or P Gi * =PGi,min ;

[0120] Calculate power deviation It then determines whether the absolute value of the power deviation is within the allowable range |Δp<σ|. If it is within the range, the power P is directly output. Gi * Otherwise, perform a consistency calculation again.

[0121] In this embodiment, the process of applying a consensus algorithm to each agent to perform consensus calculation includes:

[0122] Establish dynamic models of leader and follower agents in a multi-regional collaborative heating system:

[0123]

[0124] Where A and B are constant matrices; x i =(x i-1 , ..., x i,n ) T The state of agent i; u i It is the input vector of agent i; f(·)=(f1,f2,...,f n ) T f i The state is x at time t. i-1 , ..., x i,n The function of time; i = 0 is the leader agent, i = 1, 2, ..., n is the follower agent;

[0125] The incremental cost for each heating zone is calculated and expressed as follows:

[0126]

[0127] The follower-consistent update process is represented as:

[0128]

[0129] The leader consistency update process introduces a power deviation, denoted as:

[0130]

[0131] in, Let be a convergence coefficient representing the convergence rate, and The leader agent satisfies the power balance constraint when updating the incremental cost of the follower agent:

[0132] Taking into account the output constraints of each district's heating system, the consistency update process is expressed as follows:

[0133]

[0134] Where, λ i,lower , λ i,upper These are the minimum and maximum values ​​of the consistency variables for agent i, respectively.

[0135] In this embodiment, the output power P Gi * The output power function is expressed as:

[0136]

[0137] In this embodiment, the agents in step S2 have multiple communication channels. When some communication lines fail, the agents can complement each other's information, and the heating system's scheduling performance remains optimal.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0139] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0140] If the functionality is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0141] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A multi-regional collaborative heating scheduling method based on multi-agent adjustment cost consistency, characterized in that, It includes: Step S1: Establish a digital twin model of the multi-regional collaborative heating system using mechanism modeling and data identification methods; in the multi-regional collaborative heating system, one region is responsible for tracking the overall heating dispatch instructions, and each region exchanges information with its neighboring regions; Step S2: Set the multi-regional collaborative heating system as a corresponding intelligent agent and establish a consistent collaborative communication topology diagram of the multi-agent system; Step S3: Establish a low-carbon economic dispatch model for a multi-regional coordinated heating system; Step S4: When changes in total load demand lead to changes in heating output power, the optimal incremental cost and heating output power are obtained by solving the low-carbon economic scheduling model of the multi-regional coordinated heating system based on the digital twin model of the multi-regional coordinated heating system and using the multi-agent consensus algorithm; and the feasibility of the optimal incremental cost and heating output power is verified based on the digital twin model of the multi-regional coordinated heating system. In step S4, when changes in total load demand lead to changes in heating output power, a multi-agent consensus algorithm is used to solve the low-carbon economic scheduling model of the multi-regional coordinated heating system to obtain the optimal incremental cost and heating output power. Specifically, this includes: The low-carbon economic dispatch model of a multi-regional coordinated heating system is transformed using the Lagrange multiplier method: where the change difference of load demand P D is denoted as ΔP D , the change of each regional output power is denoted as ΔP Gi , the change of load demand is related to the output power of all regional heating systems; λ is the Lagrange multiplier corresponding to the power balance constraint, representing the incremental cost in the low-carbon economic dispatching model; For ΔP Gi The partial derivatives were calculated and reasoned to obtain: λ-β i -v i =2(P Gi +ΔP Gi (a) i +u i ); The sum of the changes in heating output power across all areas is calculated and expressed as: The optimal incremental cost is calculated as follows: Set the incremental cost λ and the allowable power difference σ for each agent, and apply a consensus algorithm to each agent to obtain the output power P of each agent under the incremental cost. Gi ; Determine P Gi Is it within the constraints? If it is, then the new optimized output power... Otherwise, P Gi * =P Gi,max or P Gi * =P Gi,min ; Calculate power deviation It then determines whether the absolute value of the power deviation is within the allowable range |Δp<σ|. If it is within the range, the power P is directly output. Gi * Otherwise, perform a consistency calculation again.

2. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, In step S1, a digital twin model of the multi-regional coordinated heating system is established using mechanism modeling and data identification methods, specifically including: Step S101: Construct a virtual entity for a multi-regional collaborative heating system, including: The process involves constructing physical device entity models, behavioral models, and rule models. First, a structural mechanism model of the multi-regional collaborative heating system is built and imported into a visualization platform, adding physical attributes to the equipment. Then, a behavioral model is constructed based on the fundamental thermodynamic theory of multi-regional collaborative heating systems, establishing a virtual simulation system for the multi-regional collaborative heating system with interactive functions and a simulated real-world operating environment. Finally, a rule model for the virtual entities is established to formulate control strategies for the virtual entities. Step S102: Establish virtual and physical data connections for the multi-regional coordinated heating system, including: First, sensor detection points are set up on the physical equipment of the multi-regional collaborative heating system. The actual operation data of the physical equipment of the multi-regional collaborative heating system is collected through Internet of Things technology, and corresponding detection points are set up on the virtual equipment to collect simulation data at the corresponding locations. Then, by calling the collected actual operating data to drive the corresponding model in the virtual space, a mapping relationship is established with the simulation data formed by the virtual equipment of the multi-regional collaborative heating system, thus forming the operation strategy of the multi-regional collaborative heating system; Finally, by continuously iterating and optimizing the data acquisition and control process, the connection and dynamic interaction of real-time data between physical entities and virtual spaces are realized, and the establishment of a digital twin model of a multi-regional collaborative heating system is completed. Step S103: Identify the digital twin model, including: The real-time operating data of the multi-regional coordinated heating system equipment under multiple operating conditions are integrated into the established digital twin model. The simulation results of the digital twin model are adaptively identified and corrected using the reverse identification method to obtain the identified and corrected digital twin model of the multi-regional coordinated heating system.

3. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, In step S2, the multi-regional coordinated heating system is configured as a corresponding intelligent agent, and a consistent coordinated communication topology diagram of the multi-agent system is established, specifically including: Based on the digital twin model of a multi-regional coordinated heating system, the set of intelligent agent systems is determined as x = {x1, x2, ..., x}. n }; The communication topology of the multi-agent system is described as a graph G = (V, E, A); where the set of agents V = {v1, v2, ..., v...} n }; E represents the communication edge set between agents. (v i ,v j ) = e ij ∈E indicates that information is exchanged between the i-th agent and the j-th agent; The communication connections are described by a weighted adjacency matrix A, a diagonal matrix D, and a Laplacian matrix L; where... w ij Yes (v) i ,v j The weight of ); d ij The elements are in the diagonal matrix D.

4. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, In step S3, a low-carbon economic dispatch model for a multi-regional coordinated heating system is established, specifically including: Set the heating cost C for each regional heating unit. i And carbon emission costs E i , is represented as: The objective function for low-carbon economic scheduling of a multi-regional coordinated heating system is defined as follows: Among them, a i b i c i Let u and u represent the fuel consumption coefficients of the i-th heating unit, respectively. i v i w i Let P represent the carbon emission coefficients of the i-th heating unit; Gi The output power of the i-th heating unit is calculated differently depending on the type of heating unit. When it is a combined heat and power unit, P is... Gi =P ei +γ i h i P ei For the electrical output of the i-th heating unit, h i Let γ be the heating power of the i-th heating unit. i ε is the thermoelectric conversion coefficient; T is the dispatch cycle; ε is the carbon emission cost coefficient; N is the number of regions; The constraints of the multi-regional coordinated heating system shall be set, including at least: power balance constraints, electrical balance constraints, thermal balance constraints, and heating unit capacity constraints.

5. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, The process of applying a consensus algorithm to each agent to perform consensus calculation includes: Establish dynamic models of leader and follower agents in a multi-regional collaborative heating system: Where A and B are constant matrices; x i =(x i-1 , ..., x i,n ) T The state of agent i; u i It is the input vector of agent i; f(·)=(f1,f2,…,f n ) T f i The state is x at time t. i-1 , ..., x i,n The function of time; i = 0 is the leader agent, i = 1, 2, ..., n is the follower agent; The incremental cost for each heating zone is calculated and expressed as follows: The follower-consistent update process is represented as: The leader consistency update process introduces a power deviation, denoted as: in, Let be a convergence coefficient representing the convergence rate, and The leader agent satisfies the power balance constraint when updating the incremental cost of the follower agent: Taking into account the output constraints of each district's heating system, the consistency update process is expressed as follows: Where, λ i,lower , λ i,upper These are the minimum and maximum values ​​of the consistency variables for agent i, respectively.

6. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, The output power P Gi * The output power function is expressed as:

7. The multi-regional coordinated heating scheduling method according to claim 1, characterized in that, In step S2, the agents communicate with each other through multiple channels. When some communication lines fail, the agents complement each other's information, and the heating system's scheduling performance remains optimal.

Images