A heat pump and central heating complementary optimization operation method in a random fuzzy environment

Abstract

The application discloses a heat pump and central heating complementary optimal operation method in a random fuzzy environment, which comprises the following steps: collecting system historical operation data, weather data and historical building load, and establishing a time-of-day building load prediction model; based on building load prediction values of each time period, combining a heat distribution index between the heat pump and the central heating heat network, and designing a time-of-day combined heat supply operation mode of the heat pump and the central heating heat network; establishing a system time-of-day regular complementary optimal operation model with the minimum system comprehensive cost and the minimum carbon emission as objective functions; based on the fuzzy randomness of heat pump energy output and the system time-of-day regular complementary optimal operation model, a time-of-day heat pump and central heating complementary optimal operation model is established by using a fuzzy random chance constraint theory; a mixed intelligent algorithm combining a random fuzzy simulation algorithm and an intelligent optimization algorithm is used to solve the model, and a time-of-day heat pump and central heating complementary optimal operation strategy is obtained.

Description

Technical Field

[0001] This invention belongs to the field of smart heating technology, specifically relating to a method for complementary and optimized operation of heat pumps and centralized heating under random fuzzy environments. Background Technology

[0002] Currently, my country's heating systems primarily rely on traditional centralized coal-fired heating. With energy shortages and increasing heating demand, existing heating networks are generally unable to meet the heating needs of residential areas. Ground source heat pump systems are a highly efficient, energy-saving, and environmentally friendly new energy supply system; however, they require significant initial investment, and long-term operation can lead to a decrease in soil temperature and insufficient heating capacity of the heat pump units. Solar energy has enormous potential, but it lacks continuity and is significantly affected by climate.

[0003] In recent years, research on combined heating systems using heat pumps of different energy forms has attracted considerable attention from scholars. However, studies on complementary heating systems combining heat pumps and heating networks are relatively few. Furthermore, when heat pumps of different energy forms are connected to the heating network of a centralized heating system, the output of the heat pumps is correlated with some random fuzzy variables, posing challenges to the optimal operation of the system. For the complementary optimal operation of heat pumps and the heating network of a centralized heating system, how to effectively reduce the disturbances caused by the uncertainty of heat pump energy output to the optimal operation of the complementary heating system, and improve the accuracy of the system's optimal heating operation, are urgent problems to be solved.

[0004] Based on the above technical problems, it is necessary to design a new method for complementary optimization of heat pump and centralized heating operation under random fuzzy environment. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method for complementary optimization operation of heat pump and centralized heating under random fuzzy environment. This method can effectively reduce the disturbance caused by the uncertainty of heat pump energy output to the optimized operation of complementary heating system, improve the accuracy of system heating optimization operation, and improve the utilization rate of heat pump energy and the operational flexibility of the system.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0007] This invention provides a method for optimizing the complementary operation of heat pumps and centralized heating under random fuzzy environments. The method includes:

[0008] Step S1: Establish a digital twin model of the heat pump and centralized heating complementary system;

[0009] Step S2: Based on the digital twin model of the heat pump and centralized heating complementary system, collect historical system operation data, weather data and historical building load, and establish a time-segmented building load prediction model;

[0010] Step S3: Based on the time-sharing building load prediction model, obtain the predicted building load values ​​for each time period, and combine the proposed heat pump and centralized heating network heat distribution index to design the time-sharing heat pump and centralized heating network joint heating operation mode.

[0011] Step S4: Based on the digital twin model of the heat pump and centralized heating complementary system and the time-sharing joint heating operation mode, establish a system time-sharing conventional complementary optimization operation model with the objective functions of minimizing the overall system cost and minimizing carbon emissions;

[0012] Step S5: Based on the fuzzy randomness of the heat pump energy output and the time-sharing conventional complementary optimization operation model of the system, a time-sharing complementary optimization operation model of heat pump and centralized heating is established using fuzzy random chance constraint theory.

[0013] Step S6: Use a hybrid intelligent algorithm that combines random fuzzy simulation algorithm and intelligent optimization algorithm to solve the time-sharing heat pump and centralized heating complementary optimization operation model to obtain the optimal operation strategy of time-sharing heat pump and centralized heating complementary.

[0014] Furthermore, in step S1, establishing a digital twin model of the heat pump and centralized heating complementary system includes:

[0015] Step S101: Construct a virtual entity for the heat pump and centralized heating complementary system, and establish a digital twin model of the heat pump and centralized heating complementary system after connecting the virtual and physical data, including:

[0016] A structural model, physical equipment entity model, behavioral model, and rule model of a heat pump and centralized heating complementary system are constructed. The physical equipment entity model is obtained by adding physical attributes of the equipment. Based on the basic functional theory, a behavioral model is constructed to establish a virtual simulation system of a multi-heat source networked heating system with renewable energy, which has interactive functions and simulates a real operating environment. Finally, a rule model of the virtual entity is established to formulate the control strategy of the virtual entity.

[0017] By collecting actual operating data of physical equipment in the heat pump and centralized heating complementary system, corresponding virtual equipment is driven to establish a mapping relationship between virtual and physical data, forming an operation strategy for the heat pump and centralized heating complementary system; 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 space are realized, and a digital twin model of the heat pump and centralized heating complementary system is established.

[0018] Step S102: Identify the digital twin model, including:

[0019] The real-time operating data of the heat pump and centralized heating complementary system 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 heat pump and centralized heating complementary system.

[0020] Further, in step S2, based on the digital twin model of the heat pump and centralized heating complementary system, historical system operation data, weather data, and historical building loads are collected to establish a time-segmented building load prediction model, including:

[0021] Based on the digital twin model of the heat pump and centralized heating complementary system, the actual system operation is simulated, and historical load data of the system are collected in different time and weather dimensions.

[0022] Based on the differences in heat load changes at different times of the day, the correlation coefficient between target time periods is calculated between two days to generate a behavior matrix. Then, time periods are divided into partitions, and the similarity of heat load behavior within the target time periods is calculated.

[0023] By combining historical load data of the system with heat load behavior similarity from different time and weather dimensions, the data is input into a neural network model for learning and training, and a time-segmented building load prediction model is established.

[0024] Furthermore, the calculation of the similarity of heat load behavior within the target time period includes:

[0025] The Pearson correlation coefficient r between the load state sequences every two days within the m-th target time period is calculated to obtain the correlation matrix P of the building load for D days within the m-th target time period. m , is represented as:

[0026]

[0027] The Pearson correlation coefficient between the load state sequences of building load on day i and day j within the m-th target time period. The larger the value, the higher the similarity between the two.

[0028] Similarity of heat load behavior in the m-th target time period

[0029] Further, in step S3, based on the time-segmented building load prediction model, the predicted building load values ​​for each time period are obtained. Combined with the proposed heat distribution indicators between the heat pump and the centralized heating network, a time-segmented joint heating operation mode for the heat pump and the centralized heating network is designed, including:

[0030] Based on the time-segmented building load prediction model, the predicted building load values ​​for different time periods within a day are obtained. The predicted building load values ​​are divided into multiple load data intervals. The heat distribution index between the heat pump and the centralized heating network in the multiple load data intervals is proposed, and the corresponding heat distribution index is completed by the heat pump and the centralized heating network.

[0031] The principle of prioritizing heat pump heating is adopted. When the load data range is low, the heat pump heating operation mode is used alone for heating. When the load data range is medium, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be lower. When the load data range is high, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be higher.

[0032] Further, in step S4, based on the digital twin model of the heat pump and centralized heating complementary system and the combined heating operation mode, a system time-sharing conventional complementary optimization operation model is established with the objective functions of minimizing overall system cost and minimizing carbon emissions, including:

[0033] Based on the digital twin model of the heat pump and centralized heating complementary system and the joint heating operation mode, the system is simulated and analyzed. After obtaining the operating characteristics of each equipment in the system and the heating demand analysis, a system time-sharing conventional complementary optimization operation model is established with a multi-objective function that minimizes the overall system cost and carbon emissions and sets relevant system constraints.

[0034] The objective function, which aims to minimize the overall system cost, is expressed as:

[0035]

[0036] Where T is the total scheduling time; C 1,t C 2,t C 3,t These are the initial investment cost, operation and maintenance cost, and pollution treatment cost for time period t, respectively; the initial investment cost includes at least the investment cost of each component of the system and the cost of system piping accessories and water pumps; the operation and maintenance cost includes at least the electricity cost consumed by the heat pump and water pumps, system operation and management cost, and equipment repair and depreciation costs;

[0037] The objective function, which aims to minimize carbon emissions, is expressed as:

[0038]

[0039] Where N is the number of devices that generate carbon emissions; P i,t Let α be the heating power of the i-th device during time period t; iCarbon emission coefficient for heating the i-th device; g u,t Electricity purchased for the power grid; β u For power supply emission coefficient;

[0040] Set system-related constraints, including:

[0041] Energy balance constraint: Q rb (t)+Q rw (t)-Q loss (t)-Q sx (t)=Q h (t); Q rb (t) represents the heat supplied by the heat pump at time t; Q rw (t) represents the heat supplied by the heating network at time t; Q loss (t) represents the heat lost by the hot water storage tank to the outside at time t; Q sx (t) represents the amount of heat stored in the hot water tank at time t; Q h (t) represents the heating demand at time t;

[0042] Output constraint: P i,min ≤P i,t ≤P i,max ;P i,max P i,min These are the upper and lower limits of the output of the i-th device, respectively;

[0043] Capacity constraint: L i,min ≤L i,t ≤L i,max L i,t L represents the capacity of the i-th device during time period t; i,max L i,min These are the upper and lower limits of the capacity of the i-th device, respectively.

[0044] Further, step S5, based on the fuzzy randomness of the heat pump energy output and the system's time-sharing conventional complementary optimization operation model, utilizes fuzzy random chance constraint theory to establish a time-sharing heat pump and centralized heating complementary optimization operation model, including:

[0045] A stochastic fuzzy model of heat pump output is established using stochastic fuzzy variables related to the output of heat pumps from different energy sources. Specifically, when the heat pump is a solar heat pump, solar radiation intensity is strongly correlated with the heat pump output, and a stochastic fuzzy model of solar heat pump is established using solar radiation intensity as a stochastic fuzzy variable. When the heat pump is an air source heat pump, ambient air temperature, inlet and outlet water temperature of the heat pump, and condenser flow rate are strongly correlated with the heat pump heating efficiency, and a stochastic fuzzy model of air source heat pump is established using ambient air temperature as a stochastic fuzzy variable. When the heat pump is a ground source heat pump, ground source parameters, including soil temperature, soil thermal properties, and buried pipe flow velocity, are strongly correlated with the heat transfer performance of the ground source heat pump, and a stochastic fuzzy model of ground source heat pump is established using ground source parameters as stochastic fuzzy variables.

[0046] Based on the heat pump output stochastic fuzzy model and the system's time-segmented conventional complementary optimization operation model, the deterministic model is transformed into a stochastic fuzzy chance constraint model. The constraints that do not contain stochastic fuzzy variables are still in deterministic form. It is assumed that the confidence level and probability level of the comprehensive system cost that the decision-maker can accept are α and β, respectively, and the confidence level and probability level of carbon emissions are χ and γ.

[0047] For any given confidence levels α, β, χ, γ, σ, and ψ, the pessimistic values ​​of the overall system cost and carbon emissions, under chance constraints, are expressed by the stochastic fuzzy chance-constrained model as follows:

[0048]

[0049] in, The pessimistic value for (α,β); Let be the pessimistic value of (χ,γ); Ch{·} is the chance measure.

[0050] Further, in step S6, a hybrid intelligent algorithm combining stochastic fuzzy simulation and intelligent optimization is used to solve the time-sharing heat pump and centralized heating complementary optimal operation model to obtain the optimal operation strategy for the time-sharing heat pump and centralized heating complementarity, including:

[0051] Initialize the population size and maximum number of iterations for the genetic optimization algorithm;

[0052] Chromosomes are constructed using a natural coding method. After chromosome coding, given a confidence level, the feasibility of chromosomes is tested using chance-constrained random simulation. If the constraints are still not met after the maximum number of simulations, chromosomes are regenerated until multiple valid chromosomes that meet the population size requirements are generated as the initial population.

[0053] For each individual in the population, a pessimistic value is calculated using stochastic fuzzy simulation. The reciprocal of the normalized result is used as the fitness value, and the fitness values ​​are sorted to calculate the average fitness and maximum fitness of the individuals in the population. The fitness value is calculated using the reciprocal of the overall system cost and carbon emissions as the fitness function.

[0054] Based on the individual fitness value, the selection of the next generation population is completed by using a random sampling mechanism and a dynamic addition strategy, and chromosome updates are completed through adaptive crossover and mutation genetic operations.

[0055] By continuously iterating, it is determined whether the maximum number of iterations has been reached. If it has, the calculation stops and the optimal operation strategy of time-sharing heat pump and centralized heating is output; otherwise, the pessimistic value and fitness value are recalculated.

[0056] Furthermore, the selection of the next generation population using a random sampling mechanism and a dynamic individual addition strategy includes:

[0057] Given a population size of N and the fitness of the i-th individual as f(i), calculate the expected number of offspring that this individual will have.

[0058] For the expected quantity N (i) Round down to the nearest integer. As the number of surviving offspring for each individual, selection Individual offspring;

[0059] Parent individuals are sorted by fitness and selected. A new individual is added to the offspring, while individuals with better fitness from the parent generation are retained;

[0060] The adaptive crossover and mutation genetic operations are represented as follows:

[0061]

[0062]

[0063] Among them, P c P m These are the crossover probability and the mutation probability, respectively; f max f is the maximum fitness value in the population. ave f is the average fitness value of the population; f′ is the value with higher fitness among the two crossover individuals; f is the fitness value of the mutated individual; k1, k2, k3 and k4 take values ​​in the interval (0,1).

[0064] Furthermore, the optimized operation method for the complementary operation of heat pumps and centralized heating also includes:

[0065] Based on the digital twin model of the heat pump and centralized heating complementary system, the optimal operation strategy of the time-sharing heat pump and centralized heating complementary system is verified. If the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values ​​after the operation strategy is executed, the operation strategy is issued; otherwise, the operation strategy is readjusted and optimized until the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values.

[0066] The beneficial effects of this invention are:

[0067] This invention establishes a time-segmented building load prediction model; based on this model, it obtains predicted building load values ​​for each time period, and combines these with the proposed heat distribution indicators between the heat pump and the centralized heating network to design a time-segmented joint heating operation mode for the heat pump and centralized heating network; based on the digital twin model of the heat pump and centralized heating complementary system and the time-segmented joint heating operation mode, it establishes a time-segmented conventional complementary optimization operation model for the system with the objective functions of minimizing overall system cost and carbon emissions; based on the fuzzy randomness of heat pump energy output and the aforementioned time-segmented conventional complementary optimization operation model, it establishes a time-segmented heat pump and centralized heating complementary optimization operation model using fuzzy random chance constraint theory; and it solves the time-segmented heat pump and centralized heating complementary optimization operation model using a hybrid intelligent algorithm combining stochastic fuzzy simulation algorithm and intelligent optimization algorithm to obtain the optimal operation strategy for time-segmented heat pump and centralized heating complementarity. This effectively reduces the disturbance caused by the uncertainty of heat pump energy output to the optimized operation of the complementary heating system, improves the accuracy of the system's optimized heating operation, and enhances the utilization rate of heat pump energy and the operational flexibility of the system. It has the advantages of being scientifically sound and highly applicable.

[0068] 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.

[0069] 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

[0070] 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.

[0071] Figure 1 This is a flowchart of an optimized operation method for heat pumps and centralized heating in a random fuzzy environment according to the present invention.

[0072] Figure 2 This is a flowchart illustrating how the present invention uses a hybrid intelligent algorithm to solve the complementary optimization operation model of time-sharing heat pumps and centralized heating. Detailed Implementation

[0073] 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.

[0074] Example 1

[0075] Figure 1 This invention relates to a method for optimizing the operation of heat pumps and centralized heating systems in a stochastic fuzzy environment.

[0076] like Figure 1 As shown, this embodiment 1 provides a method for optimizing the complementary operation of heat pumps and centralized heating under random fuzzy environments. The method includes:

[0077] Step S1: Establish a digital twin model of the heat pump and centralized heating complementary system;

[0078] Step S2: Based on the digital twin model of the heat pump and centralized heating complementary system, collect historical system operation data, weather data and historical building load, and establish a time-segmented building load prediction model;

[0079] Step S3: Based on the time-sharing building load prediction model, obtain the predicted building load values ​​for each time period, and combine the proposed heat pump and centralized heating network heat distribution index to design the time-sharing heat pump and centralized heating network joint heating operation mode.

[0080] Step S4: Based on the digital twin model of the heat pump and centralized heating complementary system and the time-sharing joint heating operation mode, establish a system time-sharing conventional complementary optimization operation model with the objective functions of minimizing the overall system cost and minimizing carbon emissions;

[0081] Step S5: Based on the fuzzy randomness of the heat pump energy output and the time-sharing conventional complementary optimization operation model of the system, a time-sharing complementary optimization operation model of heat pump and centralized heating is established using fuzzy random chance constraint theory.

[0082] Step S6: Use a hybrid intelligent algorithm that combines random fuzzy simulation algorithm and intelligent optimization algorithm to solve the time-sharing heat pump and centralized heating complementary optimization operation model to obtain the optimal operation strategy of time-sharing heat pump and centralized heating complementary.

[0083] In this embodiment, step S1, establishing a digital twin model of the heat pump and centralized heating complementary system, includes:

[0084] Step S101: Construct a virtual entity for the heat pump and centralized heating complementary system, and establish a digital twin model of the heat pump and centralized heating complementary system after connecting the virtual and physical data, including:

[0085] A structural model, physical equipment entity model, behavioral model, and rule model of a heat pump and centralized heating complementary system are constructed. The physical equipment entity model is obtained by adding physical attributes of the equipment. Based on the basic functional theory, a behavioral model is constructed to establish a virtual simulation system of a multi-heat source networked heating system with renewable energy, which has interactive functions and simulates a real operating environment. Finally, a rule model of the virtual entity is established to formulate the control strategy of the virtual entity.

[0086] By collecting actual operating data of physical equipment in the heat pump and centralized heating complementary system, corresponding virtual equipment is driven to establish a mapping relationship between virtual and physical data, forming an operation strategy for the heat pump and centralized heating complementary system; 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 space are realized, and a digital twin model of the heat pump and centralized heating complementary system is established.

[0087] Step S102: Identify the digital twin model, including:

[0088] The real-time operating data of the heat pump and centralized heating complementary system 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 heat pump and centralized heating complementary system.

[0089] In this embodiment, step S2, based on the digital twin model of the heat pump and centralized heating complementary system, collects historical system operation data, weather data, and historical building loads to establish a time-segmented building load prediction model, including:

[0090] Based on the digital twin model of the heat pump and centralized heating complementary system, the actual system operation is simulated, and historical load data of the system are collected in different time and weather dimensions.

[0091] Based on the differences in heat load changes at different times of the day, the correlation coefficient between target time periods is calculated between two days to generate a behavior matrix. Then, time periods are divided into partitions, and the similarity of heat load behavior within the target time periods is calculated.

[0092] By combining historical load data of the system with heat load behavior similarity from different time and weather dimensions, the data is input into a neural network model for learning and training, and a time-segmented building load prediction model is established.

[0093] In this embodiment, calculating the similarity of heat load behavior within the target time period includes:

[0094] The Pearson correlation coefficient r between the load state sequences every two days within the m-th target time period is calculated to obtain the correlation matrix P of the building load for D days within the m-th target time period. m , is represented as:

[0095]

[0096]

[0097] The Pearson correlation coefficient between the load state sequences of building load on day i and day j within the m-th target time period. The larger the value, the higher the similarity between the two.

[0098] Similarity of heat load behavior in the m-th target time period

[0099] In this embodiment, step S3, based on the time-segmented building load prediction model, obtains the predicted building load values ​​for each time period, and combines this with the proposed heat distribution index between the heat pump and the centralized heating network to design a time-segmented joint heating operation mode for the heat pump and the centralized heating network, including:

[0100] Based on the time-segmented building load prediction model, the predicted building load values ​​for different time periods within a day are obtained. The predicted building load values ​​are divided into multiple load data intervals. The heat distribution index between the heat pump and the centralized heating network in the multiple load data intervals is proposed, and the corresponding heat distribution index is completed by the heat pump and the centralized heating network.

[0101] The principle of prioritizing heat pump heating is adopted. When the load data range is low, the heat pump heating operation mode is used alone for heating. When the load data range is medium, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be lower. When the load data range is high, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be higher.

[0102] It should be noted that the principle of combining heat pumps and existing centralized heating systems for complementary heating is to prioritize heat pump heating and supplement centralized heating. Various types of energy heat pumps can be used, including ground source heat pumps, air source heat pumps, solar heat pumps, sewage source heat pumps, seawater source heat pumps, etc. The heat pumps can be planned according to the geographical location and environmental conditions, and the heating load of the heat pumps and centralized heating systems can be allocated proportionally to achieve complementary heating and make full use of the heating advantages of energy.

[0103] In this embodiment, step S4, based on the digital twin model of the heat pump and centralized heating complementary system and the combined heating operation mode, establishes a system time-sharing conventional complementary optimization operation model with the objective functions of minimizing overall system cost and minimizing carbon emissions, including:

[0104] Based on the digital twin model of the heat pump and centralized heating complementary system and the joint heating operation mode, the system is simulated and analyzed. After obtaining the operating characteristics of each equipment in the system and the heating demand analysis, a system time-sharing conventional complementary optimization operation model is established with a multi-objective function that minimizes the overall system cost and carbon emissions and sets relevant system constraints.

[0105] The objective function, which aims to minimize the overall system cost, is expressed as:

[0106]

[0107] Where T is the total scheduling time; C 1,t C 2,t C 3,t These are the initial investment cost, operation and maintenance cost, and pollution treatment cost for time period t, respectively; the initial investment cost includes at least the investment cost of each component of the system and the cost of system piping accessories and water pumps; the operation and maintenance cost includes at least the electricity cost consumed by the heat pump and water pumps, system operation and management cost, and equipment repair and depreciation costs;

[0108] The objective function, which aims to minimize carbon emissions, is expressed as:

[0109]

[0110] Where N is the number of devices that generate carbon emissions; P i,t Let α be the heating power of the i-th device during time period t; i Carbon emission coefficient for heating the i-th device; g u,t Electricity purchased for the power grid; β u For power supply emission coefficient;

[0111] Set system-related constraints, including:

[0112] Energy balance constraint: Q rb (t)+Q rw (t)-Q loss (t)-Q sx (t)=Q h (t); Q rb (t) represents the heat supplied by the heat pump at time t; Q rw (t) represents the heat supplied by the heating network at time t; Q loss (t) represents the heat lost by the hot water storage tank to the outside at time t; Q sx (t) represents the amount of heat stored in the hot water tank at time t; Q h (t) represents the heating demand at time t;

[0113] Output constraint: P i,min ≤P i,t ≤P i,max ;P i,max P i,min These are the upper and lower limits of the output of the i-th device, respectively;

[0114] Capacity constraint: L i,min ≤L i,t ≤L i,max L i,t L represents the capacity of the i-th device during time period t; i,max L i,min These are the upper and lower limits of the capacity of the i-th device, respectively.

[0115] In this embodiment, step S5, based on the fuzzy randomness of the heat pump energy output and the system's time-sharing conventional complementary optimization operation model, utilizes fuzzy random chance constraint theory to establish a time-sharing heat pump and centralized heating complementary optimization operation model, including:

[0116] A stochastic fuzzy model of heat pump output is established using stochastic fuzzy variables related to the output of heat pumps from different energy sources. Specifically, when the heat pump is a solar heat pump, solar radiation intensity is strongly correlated with the heat pump output, and a stochastic fuzzy model of solar heat pump is established using solar radiation intensity as a stochastic fuzzy variable. When the heat pump is an air source heat pump, ambient air temperature, inlet and outlet water temperature of the heat pump, and condenser flow rate are strongly correlated with the heat pump heating efficiency, and a stochastic fuzzy model of air source heat pump is established using ambient air temperature as a stochastic fuzzy variable. When the heat pump is a ground source heat pump, ground source parameters, including soil temperature, soil thermal properties, and buried pipe flow velocity, are strongly correlated with the heat transfer performance of the ground source heat pump, and a stochastic fuzzy model of ground source heat pump is established using ground source parameters as stochastic fuzzy variables.

[0117] Based on the heat pump output stochastic fuzzy model and the system's time-segmented conventional complementary optimization operation model, the deterministic model is transformed into a stochastic fuzzy chance constraint model. The constraints that do not contain stochastic fuzzy variables are still in deterministic form. It is assumed that the confidence level and probability level of the comprehensive system cost that the decision-maker can accept are α and β, respectively, and the confidence level and probability level of carbon emissions are χ and γ.

[0118] For any given confidence levels α, β, χ, γ, σ, and ψ, the pessimistic values ​​of the overall system cost and carbon emissions, under chance constraints, are expressed by the stochastic fuzzy chance-constrained model as follows:

[0119]

[0120] in, The pessimistic value for (α,β); Let be the pessimistic value of (χ,γ); Ch{·} is the chance measure.

[0121] Figure 2 This is a flowchart illustrating how the present invention uses a hybrid intelligent algorithm to solve the complementary optimization operation model of time-sharing heat pumps and centralized heating.

[0122] like Figure 2 As shown, in this embodiment, step S6 employs a hybrid intelligent algorithm combining stochastic fuzzy simulation and intelligent optimization to solve the time-sharing heat pump and centralized heating complementary optimal operation model, obtaining the optimal operation strategy for the time-sharing heat pump and centralized heating complementarity, including:

[0123] Initialize the population size and maximum number of iterations for the genetic optimization algorithm;

[0124] Chromosomes are constructed using a natural coding method. After chromosome coding, given a confidence level, the feasibility of chromosomes is tested using chance-constrained random simulation. If the constraints are still not met after the maximum number of simulations, chromosomes are regenerated until multiple valid chromosomes that meet the population size requirements are generated as the initial population.

[0125] For each individual in the population, a pessimistic value is calculated using stochastic fuzzy simulation. The reciprocal of the normalized result is used as the fitness value, and the fitness values ​​are sorted to calculate the average fitness and maximum fitness of the individuals in the population. The fitness value is calculated using the reciprocal of the overall system cost and carbon emissions as the fitness function.

[0126] Based on the individual fitness value, the selection of the next generation population is completed by using a random sampling mechanism and a dynamic addition strategy, and chromosome updates are completed through adaptive crossover and mutation genetic operations.

[0127] By continuously iterating, it is determined whether the maximum number of iterations has been reached. If it has, the calculation stops and the optimal operation strategy of time-sharing heat pump and centralized heating is output; otherwise, the pessimistic value and fitness value are recalculated.

[0128] It should be noted that for multi-objective stochastic fuzzy decision-making problems, the model is established as follows:

[0129]

[0130] x is the decision variable, ξ is the random fuzzy vector, and f i (x,ξ) is the objective function, g j (x,ξ) are constraint functions, γ i and δ i For a pre-defined confidence level, α j and β j Given a pre-defined confidence level, find a minimum decision variable x such that the probability measure and confidence measure of the objective function being lower than f reach δ and γ, respectively, while simultaneously applying the constraint g. j α of (x,ξ) j Opportunity value greater than β j .

[0131] The feasibility of using chance-constrained random simulations to test chromosomes includes:

[0132] Considering the stochastic nature of the constraint parameters, a stochastic simulation technique is introduced to verify whether the constraints hold. Assuming the probability distribution of the random fuzzy variables is ψ(ξ(θ0)), N independent random variables ξ are uniformly generated. i (θ0), i = 1, 2, ..., N;

[0133] Let N′ be the number of trials that satisfy the constraints. If N′ / N≥δ, then the chromosome decision vector is feasible. If, after a predetermined number of simulations, no clear vector θ0 that satisfies the constraints is generated, then the chromosome decision vector is not feasible.

[0134] Pessimulation of the objective function using stochastic fuzzy models, including:

[0135] Design a pessimistic value operator for minimizing confidence levels α, β, χ, and γ using stochastic fuzzy simulation. Constrain the objective function. and With the goal of minimizing the overall system cost f1 and carbon emissions f2, for given decision variables, we seek the minimum value that minimizes the constraints of the objective function.

[0136] In this embodiment, the selection of the next generation population using a random sampling mechanism and a dynamic individual addition strategy includes:

[0137] Given a population size of N and the fitness of the i-th individual as f(i), calculate the expected number of offspring that this individual will have.

[0138] For the expected quantity N (i Round down to the nearest integer. As the number of surviving offspring for each individual, selection Individual offspring;

[0139] Parent individuals are sorted by fitness and selected. A new individual is added to the offspring, while individuals with better fitness from the parent generation are retained;

[0140] The adaptive crossover and mutation genetic operations are represented as follows:

[0141]

[0142]

[0143] Among them, P c P m These are the crossover probability and the mutation probability, respectively; f max f is the maximum fitness value in the population. ave f is the average fitness value of the population; f′ is the value with higher fitness among the two crossover individuals; f is the fitness value of the mutated individual; k1, k2, k3 and k4 take values ​​in the interval (0,1).

[0144] It should be noted that an improved adaptive genetic algorithm based on a residual random sampling mechanism and a dynamic introduction of new individuals is proposed. By introducing a residual random sampling mechanism, the algorithm ensures that individuals with fitness greater than the average fitness are preferentially inherited into the next generation, thus significantly reducing the algorithm's error. Simultaneously, the algorithm's dynamic introduction of new individuals ensures that while maintaining the population size, the individuals added to the next generation are all from individuals with high fitness in the previous generation.

[0145] In this embodiment, the optimized operation method of heat pump and centralized heating complementarity further includes:

[0146] Based on the digital twin model of the heat pump and centralized heating complementary system, the optimal operation strategy of the time-sharing heat pump and centralized heating complementary system is verified. If the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values ​​after the operation strategy is executed, the operation strategy is issued; otherwise, the operation strategy is readjusted and optimized until the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 method for complementary and optimized operation of heat pumps and centralized heating under random fuzzy environments, characterized in that, The optimized operation method that combines heat pumps and centralized heating includes: Step S1: Establish a digital twin model of the heat pump and centralized heating complementary system; Step S2: Based on the digital twin model of the heat pump and centralized heating complementary system, collect historical system operation data, weather data and historical building load, and establish a time-segmented building load prediction model; Step S3: Based on the time-sharing building load prediction model, obtain the predicted building load values ​​for each time period, and combine the proposed heat pump and centralized heating network heat distribution index to design the time-sharing heat pump and centralized heating network joint heating operation mode. Step S4: Based on the digital twin model of the heat pump and centralized heating complementary system and the time-sharing joint heating operation mode, establish a system time-sharing conventional complementary optimization operation model with the objective functions of minimizing the overall system cost and minimizing carbon emissions; Step S5: Based on the fuzzy stochasticity of the heat pump energy output and the time-sharing conventional complementary optimization operation model of the system, a time-sharing complementary optimization operation model of the heat pump and centralized heating is established using fuzzy stochastic chance constraint theory, including: A stochastic fuzzy model of heat pump output is established using stochastic fuzzy variables related to the output of heat pumps from different energy sources. Specifically, when the heat pump is a solar heat pump, solar radiation intensity is strongly correlated with the heat pump output, and a stochastic fuzzy model of solar heat pump is established using solar radiation intensity as a stochastic fuzzy variable. When the heat pump is an air source heat pump, ambient air temperature, inlet and outlet water temperature of the heat pump, and condenser flow rate are strongly correlated with the heat pump heating efficiency, and a stochastic fuzzy model of air source heat pump is established using ambient air temperature as a stochastic fuzzy variable. When the heat pump is a ground source heat pump, ground source parameters, including soil temperature, soil thermal properties, and buried pipe flow velocity, are strongly correlated with the heat transfer performance of the ground source heat pump, and a stochastic fuzzy model of ground source heat pump is established using ground source parameters as stochastic fuzzy variables. Based on the stochastic fuzzy model of heat pump output and the system's time-segmented conventional complementary optimization operation model, the system's time-segmented conventional complementary optimization operation model is transformed into a stochastic fuzzy chance constraint model. The constraints, which do not contain stochastic fuzzy variables, still adopt a deterministic form. It is assumed that the confidence level and probability level of the overall system cost acceptable to the decision-maker are respectively... and The credibility and probability levels of carbon emissions are: and ; For any given confidence level , , , , and To minimize the pessimistic values ​​of the overall system cost and carbon emissions under opportunity constraints, the stochastic fuzzy opportunity-constrained model is expressed as: ； in, for The pessimistic value; for The pessimistic value; For chance measurement; The overall system cost target; The target for system carbon emissions; The heat supplied by the heat pump at time t; The heat supplied to the heating network at time t; The heat lost by the hot water tank to the outside at time t; The amount of heat stored in the hot water tank at time t; Let be the heating demand at time t; Let be the heating power of the i-th device during time period t; , These are the upper and lower limits of the output of the i-th device, respectively; Let be the capacity of the i-th device during time period t; , These are the upper and lower limits of the capacity of the i-th device, respectively; Step S6: A hybrid intelligent algorithm combining stochastic fuzzy simulation and intelligent optimization is used to solve the time-sharing heat pump and centralized heating complementary optimal operation model to obtain the optimal operation strategy for the time-sharing heat pump and centralized heating complementarity, including: Initialize the population size and maximum number of iterations for the genetic optimization algorithm; Chromosomes are constructed using a natural coding method. After chromosome coding, given a confidence level, the feasibility of chromosomes is tested using chance-constrained random simulation. If the constraints are still not met after the maximum number of simulations, chromosomes are regenerated until multiple valid chromosomes that meet the population size requirements are generated as the initial population. For each individual in the population, a pessimistic value is calculated using stochastic fuzzy simulation. The reciprocal of the normalized result is used as the fitness value, and the fitness values ​​are sorted to calculate the average fitness and maximum fitness of the individuals in the population. The fitness value is calculated using the reciprocal of the overall system cost and carbon emissions as the fitness function. Based on the individual fitness value, the selection of the next generation population is completed by using a random sampling mechanism and a dynamic addition strategy, and chromosome updates are completed through adaptive crossover and mutation genetic operations. By continuously iterating, it is determined whether the maximum number of iterations has been reached. If it has, the calculation stops and the optimal operation strategy of time-sharing heat pump and centralized heating is output; otherwise, the pessimistic value and fitness value are recalculated.

2. The optimized operation method of heat pump and centralized heating complementarity according to claim 1, characterized in that, In step S1, establishing a digital twin model of the heat pump and centralized heating complementary system includes: Step S101: Construct a virtual entity for the heat pump and centralized heating complementary system, and establish a digital twin model of the heat pump and centralized heating complementary system after connecting the virtual and physical data, including: A structural model, physical equipment entity model, behavioral model, and rule model of a heat pump and centralized heating complementary system are constructed. The physical equipment entity model is obtained by adding physical attributes of the equipment. Based on the basic functional theory, a behavioral model is constructed to establish a virtual simulation system of a multi-heat source networked heating system with renewable energy, which has interactive functions and simulates a real operating environment. Finally, a rule model of the virtual entity is established to formulate the control strategy of the virtual entity. By collecting actual operating data of physical equipment in the heat pump and centralized heating complementary system, corresponding virtual equipment is driven to establish a mapping relationship between virtual and physical data, forming an operation strategy for the heat pump and centralized heating complementary system; 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 space are realized, and a digital twin model of the heat pump and centralized heating complementary system is established. Step S102: Identify the digital twin model, including: The real-time operating data of the heat pump and centralized heating complementary system 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 heat pump and centralized heating complementary system.

3. The optimized operation method of heat pump and centralized heating complementarity according to claim 1, characterized in that, Step S2, based on the digital twin model of the heat pump and centralized heating complementary system, collects historical system operation data, weather data, and historical building loads to establish a time-segmented building load prediction model, including: Based on the digital twin model of the heat pump and centralized heating complementary system, the actual system operation is simulated, and historical load data of the system are collected in different time and weather dimensions. Based on the differences in heat load changes at different times of the day, the correlation coefficient between target time periods is calculated between two days to generate a behavior matrix. Then, time periods are divided into partitions, and the similarity of heat load behavior within the target time periods is calculated. By combining historical load data of the system with heat load behavior similarity from different time and weather dimensions, the data is input into a neural network model for learning and training, and a time-segmented building load prediction model is established.

4. The optimized operation method of heat pump and centralized heating complementarity according to claim 3, characterized in that, The calculation of heat load behavior similarity within the target time period includes: The Pearson correlation coefficient r between the load state sequences every two days within the m-th target time period is calculated to obtain the correlation matrix of the building load for D days within the m-th target time period. , is represented as: ； ； The Pearson correlation coefficient between the load state sequences of building load on day i and day j within the m-th target time period. The larger the value, the higher the similarity between the two. Similarity of heat load behavior in the m-th target time period .

5. The optimized operation method of heat pump and centralized heating complementarity according to claim 1, characterized in that, Step S3 involves obtaining the predicted building load values ​​for each time period based on the time-segmented building load prediction model, and designing a time-segmented joint heating operation mode for the heat pump and the centralized heating network, in conjunction with the proposed heating distribution indicators between the heat pump and the centralized heating network. This includes: Based on the time-segmented building load prediction model, the predicted building load values ​​for different time periods within a day are obtained. The predicted building load values ​​are divided into multiple load data intervals. The heat distribution index between the heat pump and the centralized heating network in the multiple load data intervals is proposed, and the corresponding heat distribution index is completed by the heat pump and the centralized heating network. The principle of prioritizing heat pump heating is adopted. When the load data range is low, the heat pump heating operation mode is used alone for heating. When the load data range is medium, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be lower. When the load data range is high, the heat pump and centralized heating network combined heating operation mode is adopted, and the heat pump heating allocation index is set to be higher and the heating network heating allocation index is set to be higher.

6. The method for complementary and optimized operation of heat pump and centralized heating according to claim 1, characterized in that, Step S4, based on the digital twin model of the heat pump and centralized heating complementary system and the combined heating operation mode, establishes a system time-sharing conventional complementary optimization operation model with the objective functions of minimizing overall system cost and minimizing carbon emissions, including: Based on the digital twin model of the heat pump and centralized heating complementary system and the joint heating operation mode, the system is simulated and analyzed. After obtaining the operating characteristics of each equipment in the system and the heating demand analysis, a system time-sharing conventional complementary optimization operation model is established with a multi-objective function that minimizes the overall system cost and carbon emissions and sets relevant system constraints. The objective function, which is to minimize the overall system cost, is expressed as: ； in, Total scheduling time; , , These are the initial investment cost, operation and maintenance cost, and pollution treatment cost for time period t, respectively; the initial investment cost includes at least the investment cost of each component of the system and the cost of system piping accessories and water pumps; the operation and maintenance cost includes at least the electricity cost consumed by the heat pump and water pumps, system operation and management cost, and equipment repair and depreciation costs; The objective function, which aims to minimize carbon emissions, is expressed as: ； in, The number of devices that generate carbon emissions; The carbon emission coefficient for heating the i-th device; Electricity purchased for the power grid; For power supply emission coefficient; Set system-related constraints, including: Energy balance constraints: ; Output constraints: ; Capacity constraints: .

7. The optimized operation method of heat pump and centralized heating as described in claim 1, characterized in that, The selection of the next generation population using a random sampling mechanism and a dynamic individual addition strategy includes: Given a population size of N and the fitness of the i-th individual as f(i), calculate the expected number of offspring that this individual will have. ; For the expected quantity Round down to the nearest integer. As the number of surviving offspring for each individual, selection Individual offspring; Parent individuals are sorted by fitness and selected. A new individual is added to the offspring, while individuals with better fitness from the parent generation are retained; The adaptive crossover and mutation genetic operations are represented as follows: ； ； in, , These are the crossover probability and the mutation probability, respectively. This represents the maximum fitness value in the population. This represents the average fitness value of the population. The value with the higher fitness among the two crossover individuals; This represents the fitness value of the mutated individual. , , and Take the values ​​in the interval (0,1) respectively.

8. The method for complementary and optimized operation of heat pump and centralized heating according to claim 1, characterized in that, The optimized operation method for the complementary operation of heat pumps and centralized heating also includes: Based on the digital twin model of the heat pump and centralized heating complementary system, the optimal operation strategy of the time-sharing heat pump and centralized heating complementary system is verified. If the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values ​​after the operation strategy is executed, the operation strategy is issued; otherwise, the operation strategy is readjusted and optimized until the primary energy utilization rate of the heat pump and the primary energy utilization rate of the centralized heating system both meet the preset values.

Images