Comprehensive energy system polymorphic simulation method, system, equipment and medium

Abstract

The invention belongs to the technical field of integrated energy system simulation, and particularly relates to an integrated energy system polymorphic simulation method, system and device and a medium. Aiming at the defects of an existing comprehensive energy system simulation method in model accuracy and calculation efficiency, the invention adopts the following technical scheme: the multi-state simulation method for the comprehensive energy system comprises the following steps: S1, according to physical characteristics and flow rules of various forms of energy in the comprehensive energy system, establishing a multi-state simulation model for the comprehensive energy system; constructing an integrated energy system polymorphic model; s2, constructing a polymorphic model library of the integrated energy system based on the polymorphic model of the integrated energy system; and S3, based on the polymorphic model library, in combination with multi-scene topology analysis, performing simulation calculation. The multi-state simulation method of the integrated energy system has the beneficial effects that the modeling method based on mechanism and data dual-drive improves the simulation accuracy by performing dynamic modeling on the integrated energy system.

Description

Technical Field

[0001] The present invention belongs to the technical field of integrated energy system simulation, and specifically relates to a method, system, equipment and medium for multi-state simulation of an integrated energy system. Background Art

[0002] As the complexity of energy systems continues to increase, integrated energy systems are increasingly becoming the key to promoting efficient energy utilization and sustainable development. Integrated energy systems can integrate multiple energy forms and energy conversion methods to achieve efficient utilization of energy resources and meet energy needs in different application scenarios. It is crucial to manage and operate integrated energy systems intelligently, efficiently and reliably.

[0003] Simulation modeling of integrated energy systems is a very effective means. However, current simulation technology has many limitations in dealing with multi-energy flow coupling, interdisciplinary topological structures, and multi-application scenarios with dynamic characteristics, especially in the balance between model accuracy and computational efficiency. Accurate modeling and efficient simulation of integrated energy systems in multiple application scenarios still face challenges.

[0004] In addition, existing integrated energy system simulation technologies generally focus on data-driven or physical mechanism-based simulation methods, and rarely truly consider "mechanism-data dual drive". The new idea of ​​"mechanism-data dual drive" combines the real-time feedback capability of data-driven with the accuracy based on physical mechanisms to improve the accuracy and efficiency of simulation. At the same time, traditional energy system simulation is often limited to a single field and cannot effectively reveal the complex mutual influence caused by the interconnection of multiple energy sources; there is also a lack of comprehensive and efficient solutions for data integration in different fields, coordination and interaction of various equipment models, and interface communication in different programming languages.

[0005] Therefore, simulation technology based on integrated energy systems must overcome multiple problems, including but not limited to challenges such as cross-disciplinary data integration, equipment model polymorphism and multi-language interaction. For example, data format differences from different fields, data quality standardization, difficulty in data acquisition, and difficulty in large-scale data management; it involves a large number of equipment types, model changes caused by uncertain working conditions, and complex coupling relationships between equipment; equipment model communication using different programming languages ​​requires overcoming language conversion errors, data transmission efficiency issues, and interface stability. Summary of the invention

[0006] In view of the shortcomings of existing integrated energy system simulation methods in terms of model accuracy and computational efficiency, the present invention proposes a multi-application-oriented integrated energy system polymorphic simulation method, which improves the accuracy and efficiency of simulation by a mechanism-data dual-driven method, and supports the collaborative work of various energy devices in different application scenarios. The present invention also proposes an integrated energy system polymorphic simulation system, equipment and medium based on the integrated energy system polymorphic simulation method.

[0007] To achieve the above object, the present invention adopts the following technical solution: a polymorphic simulation method for an integrated energy system, the polymorphic simulation method for an integrated energy system comprising:

[0008] S1. Construct a multi-state model of the integrated energy system based on the physical characteristics and flow laws of various forms of energy in the integrated energy system;

[0009] S2. Based on the polymorphic model of the integrated energy system, a polymorphic model library of the integrated energy system is constructed;

[0010] S3. Based on the polymorphic model library and combined with multi-scenario topology analysis, simulation solutions are performed.

[0011] Step S1 includes:

[0012] Step S11: For key equipment and energy supply pipelines in the integrated energy system, a generalized impedance model is constructed according to the mechanism of energy transmission, conversion and storage. The generalized impedance model is expressed by a mathematical formula as follows:

[0013] Z i =f(P i ,Q i ,T i ,...) (1)

[0014] In the formula, Z i is the impedance of the ith device or pipeline, P i , Q i , T i Etc. are key parameters related to active power, reactive power, and temperature.

[0015] Step S12: By analogy with the resistance-capacitance circuit of electricity, a dynamic transmission model of key equipment and energy supply pipelines is constructed. The dynamic transmission model is expressed by a mathematical formula as follows:

[0016] F j =g(Z1,Z2,...,Z n ,P j ,Q j ,...) (2)

[0017] In the formula, F j is the flow rate of the jth energy source, Z1 to Z nis the impedance of relevant key equipment or pipelines, P j , Q j etc. are the relevant key parameters.

[0018] Step S13 includes:

[0019] Step S131: Establishing steady-state and dynamic mechanism models of various energy flows, including:

[0020] Step S1311: For the power flow, a steady-state model based on power grid flow analysis and a multi-state model of the integrated energy system based on transient stability analysis are established. The power flow equation in the steady-state model is expressed as:

[0021]

[0022] Where P ij represents the power flow from node i to node j; V i and V j represents the voltage at nodes i and j; θ i and θ j represents the voltage phase angle between nodes i and j, θ ij =θ i -θ j ;X ij represents the reactance between nodes i and j;

[0023] The comprehensive energy system polymorphic model of power flow is expressed as follows:

[0024]

[0025] V j =I j ·R j (5)

[0026] In the formula, I i is the current of the ith branch; V j is the voltage across the jth element; R j is the resistance of the jth element;

[0027] Step S1312: For thermal energy flow, a steady-state thermal network model based on the first and second laws of thermodynamics and a multi-state model of a comprehensive energy system considering thermal inertia are established. The thermal network equation in the steady-state model is expressed as:

[0028]

[0029] Q ij represents the thermal energy flow (heat) from node i to node j; T i and T j represents the temperature of nodes i and j; R ijrepresents the thermal resistance between nodes i and j;

[0030] The comprehensive energy system polymorphic model of thermal energy flow is as follows:

[0031]

[0032] Q in =η heat ·P heat (8)

[0033]

[0034] In the formula, is the rate of change of thermal energy with time; Q in is the heat provided by the heat source; Q out is the amount of heat flowing to the heat load;

[0035] Q loss is the heat lost by the system; η heat is the conversion efficiency of the heat source; P heat is the power of the heat source; T source and T sink are the temperatures of the heat source and heat load, respectively; R is the thermal resistance, which describes the resistance to heat flow;

[0036] Step S1313: For gas energy flow, a steady-state and integrated energy system multi-state model based on fluid mechanics and pipeline transmission is established. The gas energy flow equation in the steady-state model is expressed as:

[0037]

[0038] G ij represents the gas energy flow from node i to node j; K represents the pipeline constant; p i and p j represents the gas pressure at nodes i and j; ρ represents the gas density; Z represents the gas compressibility factor; T represents the gas temperature;

[0039] The comprehensive energy system polymorphic model of gas energy flow is as follows:

[0040]

[0041] m in =ρ·Q gas,in (12)

[0042] m out =ρ·Q gas,out (13)

[0043] In the formula, is the rate of change of natural gas mass over time; m in and mout are the mass of natural gas entering and leaving the pipeline respectively; m loss is the mass of natural gas lost in the system; ρ is the density of natural gas; Q gas,in and Q gas,out are the volume flow rates of gas entering and leaving the pipeline, respectively;

[0044] The electric heat conversion equation is expressed as:

[0045] Q=η eh ·P (14)

[0046] Where, Q represents thermal power; η eh represents the electric-thermal conversion efficiency; P represents the electric power.

[0047] Step S13 also includes:

[0048] The training process of the mechanism model includes:

[0049] Assume that there are historical data of n nodes in the integrated energy system, and the historical data of n nodes are taken as input, denoted as x = [x1, x2, ..., x n ], substitute into the mechanism model to calculate the key node parameters, and get the calculated value y c , the historical measurement data of the key nodes is recorded as y r , construct the deviation function f(θ) of the two as follows:

[0050]

[0051]

[0052] In the formula, θ represents the model parameters to be verified and optimized in the comprehensive energy mechanism model, θ=[θ1,θ2,...,θ m ]; n represents the node data in the integrated energy system; and are the historical measured values ​​and calculated values ​​of the i-th node respectively;

[0053] During training, the parameters θ are optimized by minimizing the bias function.

[0054] Step S13 also includes:

[0055] Step S134: on the basis of the mechanism-data fusion model, construct a multi-energy flow equivalent model, including: coupling models of different energy forms to describe the conversion and interaction between them, introducing energy conversion coefficient and energy loss coefficient parameters to describe the conversion efficiency and loss between different energy forms, and optimizing the multi-energy flow equivalent model through an optimization algorithm;

[0056] Step S135: On the basis of the multi-energy flow equivalent model, time variables and dynamic control equations are introduced to construct a multi-state model of the integrated energy system, which describes the dynamic behavior and response characteristics of the system at different time scales;

[0057] Step S136: Use real-time data to verify and evaluate the comprehensive energy system polymorphic model to check the accuracy and reliability of the comprehensive energy system polymorphic model.

[0058] Step S2 includes:

[0059] Step S21: standardize the multi-state model of the integrated energy system, expressed as:

[0060] Standardize(Model i )=Model std (17)

[0061] In the formula, Model i Represents the original integrated energy system polymorphic model; Model std It is the standardized model;

[0062] Step S22: Develop a multi-language interactive platform interface, and use an application program interface to implement data interaction of a multi-state model of an integrated energy system between different programming languages;

[0063] Step S23: Based on the above steps, further construct a polymorphic model library:

[0064] Step S231, classifying and abstracting standardized polymorphic models of different integrated energy systems;

[0065] Step S232: determine the input and output interfaces and parameters of the integrated energy system multi-state model, and further clearly define the input and output interfaces and parameter formats required for each integrated energy system multi-state model;

[0066] Step S233: Use an open source language to write the model library code to ensure that the integrated energy system polymorphic model can be called and integrated by multiple programming languages.

[0067] Step S3 includes:

[0068] Step S31: construct a topological structure based on the energy flow graph. The energy flow graph structure is expressed as follows:

[0069] A·x=b (18)

[0070] Where A is the coefficient matrix based on the energy flow diagram; x is the unknown variable vector; b is the known condition vector; A, x and b are determined by topological analysis, reflecting the structure and energy flow distribution of the integrated energy system.

[0071] Step S32: Use parallel computing solver Solver parallel The decomposed simulation subtasks are processed to generate the final simulation result set Results, which is expressed as follows:

[0072] Solver parallel (Subtasks)→Results (19)

[0073] Step S33, based on step S31 and step S32, performing collaborative simulation solution;

[0074] Step S331: Divide the simulation boundary according to the specific application scenario, and determine the appropriate simulation step size to ensure the accuracy and efficiency of the simulation;

[0075] Step S332: construct a collaborative simulation solution library under multiple application scenarios to provide customized simulation solutions for different scenarios;

[0076] Step S333: using the distributed average consensus algorithm to perform collaborative simulation, as shown below:

[0077]

[0078] In the formula, Represents the value of node i at the kth iteration; is the neighbor set of node i, representing all nodes connected to node i; w ij is the weight between node i and node j;

[0079] Furthermore, each node continuously updates its own value and exchanges information with adjacent nodes, ultimately achieving global information consistency. The information exchange between nodes is completed by the message passing protocol, which is expressed as:

[0080]

[0081] In the formula, function f(·) represents the information aggregation method; function g(·) represents the information processing function.

[0082] The integrated energy system polymorphic simulation system adopts the aforementioned integrated energy system polymorphic simulation method, and the integrated energy system polymorphic simulation system comprises:

[0083] A comprehensive energy system multi-state model building module is used to build a comprehensive energy system multi-state model based on the physical characteristics and flow laws of various forms of energy in the comprehensive energy system;

[0084] A polymorphic model library construction module is used to construct a polymorphic model library for integrated energy systems;

[0085] The analytical solution module is used to perform simulation solutions based on the polymorphic model library and combined with multi-scenario topology analysis.

[0086] A computer device includes a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, the aforementioned polymorphic simulation method of the integrated energy system is implemented.

[0087] A computer-readable storage medium stores a computer program, which, when executed, implements the aforementioned integrated energy system polymorphic simulation method.

[0088] The beneficial effects of the integrated energy system polymorphic simulation method of the present invention are: improving the accuracy of simulation by dynamically modeling the integrated energy system according to the physical characteristics and flow laws of various forms of energy in the integrated energy system; solving the language interaction challenge. Furthermore, under the premise of ensuring accuracy, the efficiency of simulation calculation is improved to adapt to the complex calculation requirements under multi-energy flow coupling and multi-application scenarios; with the help of key parameter identification technology, the accuracy of simulation is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a flow chart of a polymorphic simulation method for an integrated energy system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0090] The technical solutions of the embodiments of the present invention are explained and described below, but the following embodiments are only preferred embodiments of the present invention, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the protection scope of the present invention.

[0091] See also Figure 1 , a multi-state simulation method for an integrated energy system according to an embodiment of the present invention, the multi-state simulation method for an integrated energy system comprising:

[0092] S1. Construct a multi-state model of the integrated energy system based on the physical characteristics and flow laws of various forms of energy in the integrated energy system;

[0093] S2. Based on the polymorphic model of the integrated energy system, build a polymorphic model library of the integrated energy system and develop a simulation platform with multi-language interaction capabilities;

[0094] S3. Based on the polymorphic model library and combined with multi-scenario topology analysis, simulation solutions are performed.

[0095] Step S1 includes:

[0096] Step S11: For key equipment and energy supply pipelines in the integrated energy system, a generalized impedance model is constructed according to the mechanism of energy transmission, conversion and storage. The generalized impedance model is expressed by a mathematical formula as follows:

[0097] Z i =f(P i ,Q i ,T i ,...) (1)

[0098] In the formula, Z i is the impedance of the ith device or pipeline, P i , Q i , T i Etc. are key parameters related to active power, reactive power, and temperature.

[0099] Step S12: By analogy with the resistance-capacitance circuit of electricity, a dynamic transmission model of key equipment and energy supply pipelines is constructed, wherein the multi-energy flow equivalent model is expressed by a mathematical formula as follows:

[0100] F j =g(Z1,Z2,...,Z n ,P j ,Q j ,...) (2)

[0101] In the formula, F j is the flow rate of the jth energy source, Z1 to Z n is the impedance of relevant key equipment or pipelines, P j , Q j etc. are the relevant key parameters.

[0102] Step S13: Based on the dynamic transmission model, establish steady-state and dynamic mechanism models of each energy flow, combine historical data and real-time data, and build a multi-state model of the comprehensive energy system based on mechanism-data dual drive. The dynamic transmission model is a general expression of the mechanism model, and each specific development is carried out according to the specific energy flow.

[0103] Step S13 includes:

[0104] Step S131: Establishing steady-state and dynamic mechanism models of various energy flows, including:

[0105] Step S1311: For the power flow, a steady-state model based on power grid flow analysis and a multi-state model of the integrated energy system based on transient stability analysis are established. The power flow equation in the steady-state model is expressed as:

[0106]

[0107] Where P ijrepresents the power flow from node i to node j; V i and V j represents the voltage at nodes i and j; θ i and θ j represents the voltage phase angle between nodes i and j, θ ij =θ i -θ j ;X ij represents the reactance between nodes i and j;

[0108] The comprehensive energy system polymorphic model of power flow is expressed as follows:

[0109]

[0110] V j =I j ·R j (5)

[0111] In the formula, I i is the current of the ith branch; V j is the voltage across the jth element; R j is the resistance of the jth element;

[0112] Step S1312: For thermal energy flow, a steady-state thermal network model based on the first and second laws of thermodynamics and a multi-state model of a comprehensive energy system considering thermal inertia are established. The thermal network equation in the steady-state model is expressed as:

[0113]

[0114] Q ij represents the thermal energy flow (heat) from node i to node j; T i and T j represents the temperature of nodes i and j; R ij represents the thermal resistance between nodes i and j;

[0115] The comprehensive energy system polymorphic model of thermal energy flow is as follows:

[0116]

[0117] Q in =η heat ·P heat (8)

[0118]

[0119] In the formula, is the rate of change of thermal energy with time; Q in is the heat provided by the heat source; Q out is the amount of heat flowing to the heat load;

[0120] Q loss is the heat lost by the system; η heat is the conversion efficiency of the heat source; P heat is the power of the heat source; T source and T sink are the temperatures of the heat source and heat load, respectively; R is the thermal resistance, which describes the resistance to heat flow;

[0121] Step S1313: For gas energy flow, a steady-state and integrated energy system multi-state model based on fluid mechanics and pipeline transmission is established. The gas energy flow equation in the steady-state model is expressed as:

[0122]

[0123] G ij represents the gas energy flow from node i to node j; K represents the pipeline constant; p i and p j represents the gas pressure at nodes i and j; ρ represents the gas density; Z represents the gas compressibility factor; T represents the gas temperature;

[0124] The comprehensive energy system polymorphic model of gas energy flow is as follows:

[0125]

[0126] m in =ρ·Q gas,in (12)

[0127] m out =ρ·Q gas,out (13)

[0128] In the formula, is the rate of change of natural gas mass over time; m in and m out are the mass of natural gas entering and leaving the pipeline respectively; m loss is the mass of natural gas lost in the system; ρ is the density of natural gas; Q gas,in and Q gas,out are the volume flow rates of gas entering and leaving the pipeline, respectively;

[0129] The electric heat conversion equation is expressed as:

[0130] Q=η eh ·P (14)

[0131] Where, Q represents thermal power; η eh represents the electric-thermal conversion efficiency; P represents the electric power.

[0132] Step S13 also includes:

[0133] Step S132: Collect historical data and real-time data, including flow, pressure, temperature, concentration and other parameters of various energy forms. Preprocess the data, including data cleaning, outlier processing, data interpolation, etc. Perform feature extraction and selection on the data to extract the features required for modeling.

[0134] Step S133, combine the mechanism model with the data-driven model, train the mechanism model, use historical data to verify and optimize the parameters of the mechanism model, and obtain a mechanism-data fusion model. In the fusion model, the mechanism model provides constraints on physical laws, and the data-driven model provides an approximation to the actual system behavior.

[0135] The training process of the mechanism model includes:

[0136] Assume that there are historical data of n nodes in the integrated energy system, and the historical data of n nodes are taken as input, denoted as x = [x1, x2, ..., x n ], substitute into the mechanism model to calculate the key node parameters, and get the calculated value y c , the historical measurement data of the key nodes is recorded as y r , construct the deviation function f(θ) of the two as follows:

[0137]

[0138]

[0139] In the formula, θ represents the model parameters to be verified and optimized in the comprehensive energy mechanism model, θ=[θ1,θ2,...,θ m ]; n represents the node data in the integrated energy system; and are the historical measured values ​​and calculated values ​​of the i-th node respectively;

[0140] During the training process, the parameter θ is optimized by minimizing the deviation function, such as by minimizing the error between the calculated value y of the mechanism model and the true value (such as mean square error, cross entropy, etc.). This can be achieved through optimization algorithms such as back propagation algorithm and gradient descent.

[0141] Step S134: on the basis of the mechanism-data fusion model, construct a multi-energy flow equivalent model, including: coupling models of different energy forms to describe the conversion and interaction between them, introducing energy conversion coefficient and energy loss coefficient parameters to describe the conversion efficiency and loss between different energy forms, and optimizing the multi-energy flow equivalent model through an optimization algorithm;

[0142] Step S135: On the basis of the multi-energy flow equivalent model, time variables and dynamic control equations are introduced to construct a multi-state model of the integrated energy system, which describes the dynamic behavior and response characteristics of the system at different time scales;

[0143] Step S136: Use real-time data to verify and evaluate the multi-state model of the integrated energy system to check the accuracy and reliability of the multi-state model of the integrated energy system.

[0144] Step S2 includes:

[0145] Step S21: standardize the multi-state model of the integrated energy system, expressed as:

[0146] Standardize(Model i )=Model std (17

[0147] In the formula, Model i Represents the original integrated energy system polymorphic model; Model std is the standardized model;

[0148] Standardization includes data standardization, feature standardization, model parameter standardization, etc.

[0149] Data standardization includes:

[0150] Data preprocessing, including: Missing value processing: use mean, median, mode, interpolation or machine learning algorithms (such as K nearest neighbor, decision tree, etc.) to fill missing values; Outlier processing: identify and process outliers based on business logic or statistical methods (such as IQR rule, Z-score, etc.);

[0151] Data normalization: converting data to the same scale. Common methods include maximum-minimum normalization (scaling data to the [0,1] interval) and Z-score normalization (converting data to a standard normal distribution). For example, the maximum-minimum normalization formula is: (x_{\text{norm}}=\frac{x-x_{\text{min}}}{x_{\text{max}}-x_{\text{min}}})

[0152] Feature normalization includes:

[0153] Feature selection: Select features that have a greater impact on model performance based on correlation analysis, information gain, mutual information, and other methods.

[0154] Feature transformation: Transform the original features, such as logarithmic transformation, polynomial transformation, Box-Cox transformation, etc., to meet the model requirements.

[0155] Feature scaling: For example, scaling features to unit variance (such as Z-score standardization) or scaling to a specific range (such as [0,1]).

[0156] Model parameter standardization includes:

[0157] Parameter initialization: Use a unified parameter initialization method, such as random initialization, He initialization, Xavier initialization, etc.

[0158] Hyperparameter settings: For hyperparameters such as learning rate, number of iterations, batch size, etc., make sure to use the same settings during training and validation.

[0159] Optimization algorithm: Choose a suitable optimization algorithm (such as gradient descent, Adam, RMSprop, etc.) and ensure the consistency of algorithm parameters (such as learning rate decay, momentum, etc.).

[0160] Step S22: Develop a multi-language interactive platform interface, and use an application program interface to implement data interaction of a multi-state model of an integrated energy system between different programming languages;

[0161] Step S23: Based on the above steps, further construct a polymorphic model library:

[0162] Step S231, classifying and abstracting standardized polymorphic models of different integrated energy systems;

[0163] Step S232: determine the input and output interfaces and parameters of the integrated energy system multi-state model, and further clearly define the input and output interfaces and parameter formats required for each integrated energy system multi-state model;

[0164] Step S233: Use an open source language to write the model library code to ensure that the integrated energy system polymorphic model can be called and integrated by multiple programming languages.

[0165] Step S3 includes:

[0166] Step S31: construct a topological structure based on the energy flow graph. The energy flow graph structure is expressed as follows:

[0167] A·x=b (18)

[0168] Where A is the coefficient matrix based on the energy flow diagram; x is the unknown variable vector; b is the known condition vector; A, x and b are determined by topological analysis, reflecting the structure and energy flow distribution of the integrated energy system.

[0169] Step S32: Use parallel computing solver Solver parallel The decomposed simulation subtasks are processed to generate the final simulation result set Results, which is expressed as follows:

[0170] Solver parallel (Subtasks)→Results (19)

[0171] Step S33, based on step S31 and step S32, performing collaborative simulation solution;

[0172] Step S331: Divide the simulation boundary according to the specific application scenario, and determine the appropriate simulation step size to ensure the accuracy and efficiency of the simulation;

[0173] Step S332: construct a collaborative simulation solution library under multiple application scenarios to provide customized simulation solutions for different scenarios;

[0174] Step S333: using the distributed average consensus algorithm to perform collaborative simulation, as shown below:

[0175]

[0176] In the formula, Represents the value of node i at the kth iteration; is the neighbor set of node i, representing all nodes connected to node i; w ij is the weight between node i and node j;

[0177] Furthermore, each node continuously updates its own value and exchanges information with adjacent nodes, ultimately achieving global information consistency. The information exchange between nodes is completed by the message passing protocol, which is expressed as:

[0178]

[0179] In the formula, function f(·) represents the information aggregation method; function g(·) represents the information processing function.

[0180] The comprehensive energy system polymorphic simulation method of this embodiment mainly includes the following steps: first, according to the physical characteristics and flow laws of various forms of energy in the comprehensive energy system, steady-state and dynamic mechanism models of various energy flows are established; then, the mechanism model is combined with the data-driven model, and the historical data is used to perform parameter verification and optimization on the mechanism model, and the mechanism model is trained to obtain a mechanism-data fusion model; then, based on the mechanism-data fusion model, a multi-energy flow equivalent model is constructed; finally, based on the multi-energy flow equivalent model, time variables and dynamic control equations are introduced to construct a comprehensive energy system polymorphic model, which describes the dynamic behavior and response characteristics of the system at different time scales.

[0181] Theoretical Application Examples

[0182] There is a regional multi-energy system, which includes multiple energy forms such as electricity, heat, and natural gas. It is composed of gas turbines, generators, photovoltaic power generation (PV), wind power generation (WT), energy storage system (ES), control system, etc., and realizes efficient utilization and conversion of energy through energy hubs. The simulation process of this multi-energy system includes:

[0183] Step S1, modeling the energy hub. Although the multi-energy system includes multiple energy forms such as electricity, heat, and natural gas, the energy forms are abstracted into two basic needs: electricity and heat.

[0184] Step S131: construct a steady-state and dynamic mechanism model, wherein the steady-state and dynamic mechanism model includes:

[0185] Step S1311: For the power flow, a steady-state model based on power grid flow analysis and a multi-state model of the integrated energy system based on transient stability analysis are established. The power flow equation in the steady-state model is expressed as:

[0186]

[0187] Where P ij represents the power flow from node i to node j; V i and V j represents the voltage at nodes i and j; θ i and θ j represents the voltage phase angle between nodes i and j, θ ij =θ i -θ j ;X ij represents the reactance between nodes i and j;

[0188] The comprehensive energy system polymorphic model of power flow is expressed as follows:

[0189]

[0190] V j =I j ·R j (5)

[0191] In the formula, I i is the current of the ith branch; V j is the voltage across the jth element; R j is the resistance of the jth element;

[0192] Step S1312: For thermal energy flow, a steady-state thermal network model based on the first and second laws of thermodynamics and a multi-state model of a comprehensive energy system considering thermal inertia are established. The thermal network equation in the steady-state model is expressed as:

[0193]

[0194] Q ij represents the thermal energy flow (heat) from node i to node j; T i and T j represents the temperature of nodes i and j; R ij represents the thermal resistance between nodes i and j;

[0195] The comprehensive energy system polymorphic model of thermal energy flow is as follows:

[0196]

[0197] Q in =η heat ·P heat (8)

[0198]

[0199] In the formula, is the rate of change of thermal energy with time; Q in is the heat provided by the heat source; Q out is the amount of heat flowing to the heat load;

[0200] Q loss is the heat lost by the system; η heat is the conversion efficiency of the heat source; P heat is the power of the heat source; T source and T sink are the temperatures of the heat source and heat load, respectively; R is the thermal resistance, which describes the resistance to heat flow;

[0201] Step S1313: For gas energy flow, a steady-state and integrated energy system multi-state model based on fluid mechanics and pipeline transmission is established. The gas energy flow equation in the steady-state model is expressed as:

[0202]

[0203] G ij represents the gas energy flow from node i to node j; K represents the pipeline constant; p i and p j represents the gas pressure at nodes i and j; ρ represents the gas density; Z represents the gas compressibility factor; T represents the gas temperature;

[0204] The comprehensive energy system polymorphic model of gas energy flow is as follows:

[0205]

[0206] m in =ρ·Q gas,in (12)

[0207] m out =ρ·Q gas,out (13)

[0208] In the formula, is the rate of change of natural gas mass over time; m in and m out are the mass of natural gas entering and leaving the pipeline respectively; m loss is the mass of natural gas lost in the system; ρ is the density of natural gas; Q gas,in and Q gas,out are the volume flow rates of gas entering and leaving the pipeline, respectively;

[0209] The electric heat conversion equation is expressed as:

[0210] Q=η eh ·P (14)

[0211] Where, Q represents thermal power; η eh represents the electric-thermal conversion efficiency; P represents the electric power.

[0212] More specifically, the speed dynamic equation of the gas turbine is expressed as:

[0213]

[0214] Where N turbine (t) represents the gas turbine speed at time t (rpm); T mech is the mechanical time constant; f fuel is the conversion function from fuel flow to mechanical power; m fuel (t) represents the natural gas fuel flow rate at time t (kg / s); f loss is the mechanical power loss function; T exhaust (t) represents the gas turbine exhaust temperature at time t (K).

[0215] The power output equation of a gas turbine is expressed as:

[0216] P turbine,elec (t) = η turbine ·f mech-elec (N turbine (t)) (23)

[0217] Where P turbine,elec (t) represents the power output of the gas turbine at time t (kW); η turbine The efficiency of the gas turbine; f mech-elec is the conversion function from mechanical power to electrical output.

[0218] The state equation of the energy storage system (using battery energy storage) is expressed as:

[0219]

[0220] In the formula, E ES (t) is the energy level of the energy storage system at time t (kWh); η ES,ch and η ES,dis Respectively represent the charging and discharging efficiency of the energy storage system; P ES,ch (t) represents the charging power of the energy storage system at time t (kW); P ES,dis (t) represents the discharge power of the energy storage system at time t (kW).

[0221] The power output equation of the CHP (Cogeneration, combined heat and power) system is expressed as:

[0222] P CHP,elec (t) = η CHP ·F gas,CHP (t)(25)

[0223] Where P CHP,elec (t) represents the power output of the CHP system at time t; η CHP Indicates the power conversion efficiency of the combined heating and power supply system; F gas,CHP (t) is the natural gas flow rate supplied to the CHP system (m 3 / h).

[0224] The thermal output equation of the CHP system is expressed as:

[0225] Q CHP,heat (t) = η heat ·F gas,CHP (t) (26)

[0226] In the formula, Q CHP,heat (t) represents the thermal output of the CHP system at time t; η heat Indicates the thermal conversion efficiency of CHP.

[0227] The thermal output equation of the boiler is expressed as:

[0228] Q boiler (t) = η boiler ·F gas,boiler (t) (27)

[0229] In the formula, Q boiler (t) represents the thermal output of the boiler at time t; η boiler Indicates the thermal conversion efficiency of the boiler; F gas,boiler (t) represents the natural gas flow rate supplied to the boiler (m3 / h).

[0230] The energy demand balance equation is expressed as:

[0231] P elec (t)+P ES,ch (t)+P loss (t) = P CHP,elec (t)+P grid (t)+P turbine,elec (t)+P PV (t)+P WT (t)+P ES,dis (t) (28)

[0232] Q heat (t) = Q CHP,heat (t)+Q boiler (t) (29)

[0233] Where P elec (t) represents the power demand of the region at time t (kW); Q heat (t) represents the heat demand of the region at time t (kW); P grid (t) is the electricity obtained from the grid; P loss (t) is the loss in the process of power transmission and conversion; P PV (t) represents the photovoltaic power generation power at time t (kW); P WT (t) represents the wind power generation power at time t (kW); P ES,ch (t) and P ES,dis (t) represent the charging and discharging power (kW) of the energy storage system at time t, respectively.

[0234] Step S132: Utilize historical meteorological data, equipment operation data, load demand data, etc. to predict and verify energy demand such as electricity and heat, and then optimize and verify parameters of the dynamic mechanism model of the energy hub.

[0235] 1) Data source collection

[0236] Meteorological data: Collect historical and real-time meteorological data, including temperature, humidity, wind speed, wind direction, sunshine duration, etc., to predict the output of renewable energy such as photovoltaic power generation and wind power generation.

[0237] Equipment status data: Collect operating status data such as temperature, pressure, speed, current, voltage, etc. from various energy equipment (such as gas turbines, generators, photovoltaic panels, wind turbines, etc.) to monitor the health of the equipment and predict maintenance needs.

[0238] Load data: Collect load data of energy sources such as electricity, heat, and natural gas, including historical load, real-time load, and predicted load, to assess energy demand and optimize energy distribution.

[0239] 2) Data preprocessing

[0240] Data cleaning: Remove duplicate, erroneous or abnormal data to ensure data accuracy and reliability.

[0241] Data conversion: Convert data into a unified format and unit for data analysis and model building.

[0242] Data interpolation: For missing data, interpolation, regression and other methods are used to fill them.

[0243] Step S133: Combine the mechanism model with the data-driven model, use historical data to verify and optimize the parameters of the mechanism model, train the mechanism model, and obtain a mechanism-data fusion model. The training process of the mechanism model includes:

[0244] Assume that there are historical data of n nodes in the integrated energy system, and the historical data of n nodes are taken as input, denoted as x = [x1, x2, ..., x n ], substitute into the mechanism model to calculate the key node parameters, and get the calculated value y c , the historical measurement data of the key nodes is recorded as y r , construct the deviation function f(θ) of the two as follows:

[0245]

[0246]

[0247] In the formula, θ represents the model parameters to be verified and optimized in the comprehensive energy mechanism model, θ=[θ1,θ2,...,θ m ]; n represents the node data in the integrated energy system; and are the historical measured values ​​and calculated values ​​of the i-th node respectively;

[0248] During the training process, the parameter θ is optimized by minimizing the deviation function. This can be achieved through optimization algorithms such as back propagation and gradient descent.

[0249] Ideally, minf(θ)=0 should be satisfied. In this example, the error range is controlled within a given minimum value ∈ according to engineering requirements, so that minf(θ)≤ε, and the resistance characteristic identification and calibration problem is transformed into a nonlinear function optimization problem.

[0250] Furthermore, with the goal of minimizing the deviation function, the Levenberg-Marquarelt (LM) algorithm is used to solve the mechanism model parameter θ. The i-th update iteration is expressed as:

[0251] θ i+1 =θ i +Δθ i (30)

[0252]

[0253] Where Δθ is the update iteration variable; J is the Jacobian matrix of f(θ); I is the identity matrix; ξ i Ι is the damping term, ξ i is a positive parameter to prevent When approaching singularity, Δθ i Too large.

[0254] The process of identifying the parameter θ of the mechanism model by the data-driven model is as follows:

[0255] (1) Randomly assign an initial value θ0 and an allowable error ∈ according to the engineering requirement reference value θ;

[0256] (2) Calculate the state parameter y according to the mechanism model c (θ);

[0257] (3) Calculate the objective function f(θ);

[0258] (4) Calculate the Jacobian matrix J and perform iterative updates;

[0259] (5) If f(θ)≤ε, stop and output the result, otherwise return to step (2).

[0260] Step S134: on the basis of the mechanism-data fusion model, construct a multi-energy flow equivalent model, including: coupling models of different energy forms to describe the conversion and interaction between them, introducing energy conversion coefficient and energy loss coefficient parameters to describe the conversion efficiency and loss between different energy forms, and optimizing the multi-energy flow equivalent model through an optimization algorithm;

[0261] Step S135: On the basis of the multi-energy flow equivalent model, time variables and dynamic control equations are introduced to construct a multi-state model of the integrated energy system, which describes the dynamic behavior and response characteristics of the system at different time scales;

[0262] Step S136: Use real-time data to verify and evaluate the comprehensive energy system polymorphic model to check the accuracy and reliability of the comprehensive energy system polymorphic model.

[0263] Step S2 includes:

[0264] Step S21: standardize the multi-state model of the integrated energy system, expressed as:

[0265] Standardize(Model i )=Model std (17)

[0266] In the formula, Model i Represents the original integrated energy system polymorphic model; Model std It is the standardized model;

[0267] Step S22: Develop a multi-language interactive platform interface, and use an application program interface to implement data interaction of a multi-state model of an integrated energy system between different programming languages;

[0268] Step S23: Based on the above steps, further construct a polymorphic model library:

[0269] Step S231: classify and abstract the standardized polymorphic models of different integrated energy systems to more effectively manage and organize a large number of integrated energy system models; classify solar photovoltaics, wind turbines, energy storage devices, etc. according to their functional characteristics, and establish a hierarchical model library based on this; take the photovoltaic model as an example, input includes light intensity Φ, ambient temperature T ambient , photovoltaic area, etc. PV , Photovoltaic conversion efficiency η PV , output includes voltage, current, etc.;

[0270] Step S232: determine the input and output interfaces and parameters of the integrated energy system multi-state model, and further clearly define the input and output interfaces and parameter formats required for each integrated energy system multi-state model;

[0271] Step S233: Use an open source language to write the model library code to ensure that the integrated energy system polymorphic model can be called and integrated by multiple programming languages.

[0272] Step S3 includes:

[0273] Step S31: construct a topological structure based on the energy flow graph. The energy flow graph structure is expressed as follows:

[0274] A·x=b (18)

[0275] Where A is the coefficient matrix based on the energy flow diagram; x is the unknown variable vector; b is the known condition vector; A, x and b are determined by topological analysis, reflecting the structure and energy flow distribution of the integrated energy system; the power generated by CHP, GT, PV, WT and ES flows to the power load and ES (when charging); the heat flows from GT and CHP to the thermal load;

[0276] Step S32: Use parallel computing solver Solver parallel The decomposed simulation subtasks are processed to generate the final simulation result set Results, which is expressed as follows:

[0277] Solver parallel (Subtasks)→Results (19)

[0278] Each subtask can be simulated and calculated independently, and the output simulation of CHP, GT, PV, and WT can be processed in parallel as subtasks.

[0279] Step S33: Based on step S31 and step S32, collaborative simulation is performed, including:

[0280] Step S331: Divide the simulation boundary according to the specific application scenario, and determine the appropriate simulation step size to ensure the accuracy and efficiency of the simulation; determine the simulation scope according to the system components and energy flow diagram, and consider the simulation of the power part or the joint simulation of power and heat. Determine the simulation step size according to the system dynamic characteristics and simulation accuracy requirements, and select a simulation iteration every 15 minutes;

[0281] Step S332: construct a collaborative simulation solution library under multiple application scenarios to provide customized simulation solutions for different scenarios;

[0282] Step S333: using the distributed average consensus algorithm to perform collaborative simulation, as shown below:

[0283]

[0284] In the formula, Represents the value of node i at the kth iteration; is the neighbor set of node i, representing all nodes connected to node i; w ij is the weight between node i and node j;

[0285] Furthermore, each node continuously updates its own value and exchanges information with adjacent nodes, ultimately achieving global information consistency. The information exchange between nodes is completed by the message passing protocol, which is expressed as:

[0286]

[0287] In the formula, function f(·) represents the information aggregation method, and the weighted average function is selected; function g(·) represents the information processing function.

[0288] Among them, each component such as CHP, GT, PV, WT, etc. is regarded as a node, and the components with energy flow with it constitute its neighbor set.

[0289] Heuristic algorithms can include particle swarm algorithm, ant colony algorithm, and simulated return algorithm.

[0290] Based on the dynamic mechanism model of the energy hub, an optimization control strategy can be formulated, such as adjusting the natural gas supply to the CHP system and boiler, as well as the electricity obtained from the grid, according to the predicted power and heat demand, to achieve efficient energy utilization and stable operation of the system. The detailed steps of the optimization control strategy based on the energy hub are as follows.

[0291] According to the dynamic mechanism model established in the previous steps, the power and heat demand forecast is carried out, and the historical data D hist and prediction model M pred Make predictions:

[0292] P elec ,Q heat =M pred (D hist ,t) (32)

[0293] Furthermore, an optimization control strategy is formulated, and the optimization goal is to minimize the cost. The objective function is expressed as:

[0294]

[0295] In the formula, C nat is the natural gas price, C grid It is the time-of-use electricity price of the power grid. Penalty terms include penalties for violating demand and system constraints.

[0296] Based on the balance constraints in the energy hub modeling step, the objective function is solved by combining optimization algorithms such as predictive control, dynamic programming, and genetic algorithms to obtain the optimal decision variable values.

[0297] Furthermore, according to the output of the optimization algorithm, the natural gas supply to the gas turbine and CHP units, as well as the electricity obtained from the power grid, are adjusted. Iteration and optimization are performed based on real-time data and system operation conditions to achieve efficient energy utilization and stable system operation.

[0298] The beneficial effects of the polymorphic simulation method of the integrated energy system of the embodiment of the present invention are: using genetic algorithms and the like to identify key parameters, and using forward and backward methods and the like to solve the power flow analysis model, so as to achieve more accurate modeling of the dynamic behavior of the integrated energy system; through sophisticated calculation methods and combining the operating characteristics of each energy supply equipment with data-driven key parameter identification, the system dynamic behavior simulation is made more realistic and credible; a polymorphic model library construction method is proposed to standardize the original equipment models into a unified format to ensure that these models can seamlessly collaborate and effectively integrate; a multi-language interactive platform interface is developed to exchange model data across programming languages ​​through an application program interface to achieve high flexibility and interoperability of collaborative work of models in different fields; finally, based on multi-scenario topology analysis technology, a parallel computing solver is used to process the decomposed simulation subtasks to achieve collaborative simulation solution; parallel computing has high computing efficiency and fast speed.

[0299] The embodiment of the present invention also provides a comprehensive energy system polymorphic simulation system, which adopts the above-mentioned comprehensive energy system polymorphic simulation method. The comprehensive energy system polymorphic simulation system includes:

[0300] A comprehensive energy system multi-state model building module is used to build a comprehensive energy system multi-state model based on the physical characteristics and flow laws of various forms of energy in the comprehensive energy system;

[0301] A polymorphic model library construction module is used to construct a polymorphic model library for integrated energy systems;

[0302] Simulation platform development module, used to develop a simulation platform with multi-language interaction capabilities for multi-state models of integrated energy systems;

[0303] The analytical solution module is used to perform simulation solutions based on the polymorphic model library and combined with multi-scenario topology analysis.

[0304] An embodiment of the present invention also provides a computer device, including a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, the aforementioned integrated energy system polymorphic simulation method is implemented.

[0305] The embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, the aforementioned integrated energy system polymorphic simulation method is implemented.

[0306] The above is only a specific implementation of the invention, but the protection scope of the invention is not limited thereto. Those skilled in the art should understand that the invention includes but is not limited to the contents described in the above specific implementation. Any modification that does not deviate from the functional and structural principles of the invention will be included in the scope of the claims.

Claims

1. A polymorphic simulation method for an integrated energy system, characterized in that: include: S1. Construct a multi-state model of the integrated energy system based on the physical characteristics and flow laws of various forms of energy in the integrated energy system; S2. Based on the polymorphic model of the integrated energy system, a polymorphic model library of the integrated energy system is constructed; S3. Based on the polymorphic model library and combined with multi-scenario topology analysis, simulation solutions are performed.

2. The method for multi-state simulation of an integrated energy system according to claim 1, characterized in that: Step S1 includes: Step S11: For key equipment and energy supply pipelines in the integrated energy system, a universal impedance model is constructed according to the mechanism of energy transmission, conversion and storage. The universal impedance model of a single energy flow is expressed by a mathematical formula: Z i = f(P i , Q i , T i , ...) (1) In the formula, Z i is the impedance of the ith device or pipeline, P i , Q i , T i are the relevant key parameters; Step S12: Based on the generalized impedance model, a dynamic transmission model of key equipment and energy supply pipelines is constructed. The dynamic transmission model is expressed by a mathematical formula: F j = g(Z1, Z2, ..., Z n , P j , Q j , ...) (2) In the formula, F j is the flow rate of the jth energy source, Z1 to Z n is the impedance of relevant key equipment or pipelines, P j , Q j are the relevant key parameters; Step S13: Based on the dynamic transmission model, steady-state and dynamic mechanism models of each energy flow are established, and historical data and real-time data are combined to construct a multi-state model of the integrated energy system based on mechanism-data dual drive.

3. The method for multi-state simulation of an integrated energy system according to claim 2, characterized in that: Step S13 includes: Step S131: Establishing steady-state and dynamic mechanism models of various energy flows, including: Step S1311: For the power flow, a steady-state model based on power grid flow analysis and a dynamic model based on transient stability analysis are established. The power flow equation in the steady-state model is expressed as: Where P ij represents the power flow from node i to node j; V i and V j represents the voltage at nodes i and j; θ i and θ j represents the voltage phase angle between nodes i and j, θ ij =θ i -θ j ;X ij represents the reactance between nodes i and j; The dynamic model of power flow is expressed as follows: V j =I j ·R j (5) In the formula, I i is the current of the ith branch; V j is the voltage across the jth element; R j is the resistance of the jth element; Step S1312: For thermal energy flow, a steady-state thermal network model based on the first and second laws of thermodynamics and a dynamic model considering thermal inertia are established. The thermal network equation in the steady-state model is expressed as: Q ij represents the thermal energy flow (heat) from node i to node j; T i and T j represents the temperature of nodes i and j; R ij represents the thermal resistance between nodes i and j; The dynamic model of thermal energy flow is as follows: Q in =η heat ·P heat (8) In the formula, is the rate of change of thermal energy with time; Q in is the heat provided by the heat source; Q out is the amount of heat flowing to the heat load; Q loss is the heat lost by the system; η heat is the conversion efficiency of the heat source; P heat is the power of the heat source; T source and T sink are the temperatures of the heat source and heat load, respectively; R is the thermal resistance, which describes the resistance to heat flow; Step S1313: For the gas energy flow, a steady-state and dynamic model based on fluid mechanics and pipeline transmission is established. The gas energy flow equation in the steady-state model is expressed as: G ij represents the gas energy flow from node i to node j; K represents the pipeline constant; p i and p j represents the gas pressure at nodes i and j; ρ represents the gas density; Z represents the gas compressibility factor; T represents the gas temperature; The dynamic model of gas energy flow is as follows: m in =ρ·Q gas,in (12) m out =ρ·Q gas,out (13) In the formula, is the rate of change of natural gas mass over time; m in and m out are the mass of natural gas entering and leaving the pipeline respectively; m loss is the mass of natural gas lost in the system; ρ is the density of natural gas; Q gas,in and Q gas,out are the volume flow rates of gas entering and leaving the pipeline, respectively; The electrothermal conversion equation is expressed as: Q=η eh ·P (14) Where, Q represents thermal power; η eh represents the electric-thermal conversion efficiency; P represents the electric power.

4. The method for multi-state simulation of an integrated energy system according to claim 3, characterized in that: Step S13 also includes: Step S132: collect historical data and real-time data, pre-process the data, extract and select features of the data, and obtain a data-driven model; Step S133: Combine the mechanism model with the data-driven model, use historical data to verify and optimize the parameters of the mechanism model, train the mechanism model, and obtain a mechanism-data fusion model. The training process of the mechanism model includes: Assume that there are historical data of n nodes in the integrated energy system, and the historical data of n nodes are taken as input, denoted as x = [x1, x2, ..., x n ], substitute into the mechanism model to calculate the key node parameters, and get the calculated value y c , the historical measurement data of the key nodes is recorded as y r , construct the deviation function f(θ) of the two as follows: In the formula, θ represents the model parameters to be verified and optimized in the comprehensive energy mechanism model, θ=[θ1,θ2,...,θ m ]; n represents the node data in the integrated energy system; and are the historical measured values ​​and calculated values ​​of the i-th node respectively; During training, the parameters θ are optimized by minimizing the bias function.

5. The method for multi-state simulation of an integrated energy system according to claim 4, characterized in that: Step S13 also includes: Step S134: on the basis of the mechanism-data fusion model, construct a multi-energy flow equivalent model, including: coupling models of different energy forms to describe the conversion and interaction between them, introducing energy conversion coefficient and energy loss coefficient parameters to describe the conversion efficiency and loss between different energy forms, and optimizing the multi-energy flow equivalent model through an optimization algorithm; Step S135: On the basis of the multi-energy flow equivalent model, time variables and dynamic control equations are introduced to construct a multi-state model of the integrated energy system, which describes the dynamic behavior and response characteristics of the system at different time scales; Step S136: Use real-time data to verify and evaluate the comprehensive energy system polymorphic model to check the accuracy and reliability of the comprehensive energy system polymorphic model.

6. The method for multi-state simulation of an integrated energy system according to any one of claims 1 to 5, characterized in that: Step S2 includes: Step S21, standardizing the integrated energy system polymorphic model; Step S22: Develop a multi-language interactive platform interface, and use an application program interface to implement dynamic model data interaction between different programming languages; Step S23: Based on the above steps, further construct a polymorphic model library: Step S231, classifying and abstracting standardized polymorphic models of different integrated energy systems; Step S232: determine the input and output interfaces and parameters of the integrated energy system multi-state model, and further clearly define the input and output interfaces and parameter formats required for each integrated energy system multi-state model; Step S233: Use open source language to write model library code.

7. The method for multi-state simulation of an integrated energy system according to any one of claims 1 to 5, characterized in that: Step S3 includes: Step S31: construct a topological structure based on the energy flow graph. The energy flow graph structure is expressed as follows: A·x=b (17) Where A is the coefficient matrix based on the energy flow diagram; x is the unknown variable vector; b is the known condition vector; A, x and b are determined by topological analysis, reflecting the structure and energy flow distribution of the integrated energy system; Step S32: Use parallel computing solver Solver parallel The decomposed simulation subtasks are processed to generate the final simulation result set Results, which is expressed as follows: Solver parallel (Subtasks)→Results (18) Step S33: Based on step S31 and step S32, collaborative simulation is performed, including: Step S331: Divide the simulation boundary according to the specific application scenario, and determine the appropriate simulation step size to ensure the accuracy and efficiency of the simulation; Step S332: construct a collaborative simulation solution library under multiple application scenarios to provide customized simulation solutions for different scenarios; Step S333: using the distributed average consensus algorithm to perform collaborative simulation, as shown below: In the formula, Represents the value of node i at the kth iteration; is the neighbor set of node i, representing all nodes connected to node i; w ij is the weight between node i and node j; Furthermore, each node continuously updates its own value and exchanges information with adjacent nodes, ultimately achieving global information consistency. The information exchange between nodes is completed by the message passing protocol, which is expressed as: In the formula, function f(·) represents the information aggregation method; function g(·) represents the information processing function.

8. An integrated energy system polymorphic simulation system, adopting the integrated energy system polymorphic simulation method according to any one of claims 1 to 7, characterized in that: The comprehensive energy system polymorphic simulation system comprises: A comprehensive energy system multi-state model building module is used to build a comprehensive energy system multi-state model based on the physical characteristics and flow laws of various forms of energy in the comprehensive energy system; A polymorphic model library construction module is used to construct a polymorphic model library for integrated energy systems; The analytical solution module is used to perform simulation solutions based on the polymorphic model library and combined with multi-scenario topology analysis.

9. A computer device comprising a processor and a storage medium, wherein the storage medium stores a computer program, wherein: When the computer program is executed by a processor, the polymorphic simulation method of the integrated energy system as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the polymorphic simulation method of the integrated energy system as described in any one of claims 1 to 7 is implemented.

Images