Mass air conditioner multi-target day-ahead optimization scheduling method and system considering carbon emission flow

Abstract

The invention relates to the technical field of air conditioner dispatching, in particular to a mass air conditioner multi-target day-ahead optimal dispatching method and system considering carbon emission flow. The method comprises the steps that a multi-target optimization model of air conditioner load day-ahead scheduling is constructed with the minimum temperature comfort deviation and the minimum comprehensive cost as targets; wherein the optimal solution of the multi-objective optimization model comprises the minimum temperature comfort deviation and the minimum comprehensive cost, and the comprehensive cost comprises the electricity cost and the carbon emission cost; determining a constraint condition in the multi-objective optimization model, and converting the constraint condition into a penalty function; the constraint conditions comprise a temperature constraint, a power constraint, a load balance constraint, a switch state constraint, a carbon emission constraint and an electric power cost constraint; solving an optimal solution of the multi-objective optimization model by adopting a parrot optimization algorithm, and controlling the operation of each air conditioner according to the optimal solution of the multi-objective optimization model; according to the method, dual-objective rapid optimization scheduling of the power consumption cost and the carbon emission cost of the mass air conditioners is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning scheduling, and in particular to a method and system for multi-objective day-ahead optimization scheduling of massive air conditioners taking carbon emission flows into consideration. Background Art

[0002] Summer air conditioning load is critical to the operation of buildings and power systems. Due to the high temperatures in summer, air conditioning load accounts for a significant proportion of the total energy consumption of buildings. Especially in hot weather, the demand for air conditioning systems may increase significantly, leading to peak loads in the power system. This not only affects energy consumption and electricity bills, but also affects the stability of the power grid and the comfort inside the building. Therefore, managing and optimizing summer air conditioning loads is of great significance for improving energy efficiency, reducing costs and ensuring power supply security. Summary of the invention

[0003] In view of this, an object of an embodiment of the present invention is to provide a method and system for multi-objective day-ahead optimization scheduling of massive air conditioners taking into account carbon emission flows, so as to improve energy efficiency, reduce costs and ensure power supply security.

[0004] In a first aspect, an embodiment of the present invention provides a multi-objective day-ahead optimization scheduling method for massive air conditioners considering carbon emission flows, comprising:

[0005] A multi-objective optimization model for day-ahead scheduling of air-conditioning load is constructed with the goal of minimizing temperature comfort deviation and minimizing comprehensive cost; wherein the optimal solution of the multi-objective optimization model includes minimizing temperature comfort deviation and minimizing comprehensive cost, and the comprehensive cost includes electricity cost and carbon emission cost;

[0006] Determine the constraints in the multi-objective optimization model, and convert the constraints into penalty functions; wherein the constraints include temperature constraints, power constraints, load balance constraints, switch state constraints, carbon emission constraints, and electricity cost constraints;

[0007] The Parrot optimization algorithm is used to solve the optimal solution of the multi-objective optimization model, and the operation of each air conditioner is controlled according to the optimal solution of the multi-objective optimization model.

[0008] Optionally, the expression of the multi-objective optimization model is as follows:

[0009]

[0010] Among them, f1 represents the temperature comfort deviation function; f2 represents the comprehensive electricity cost function of electricity cost and carbon emission cost; Z is the number of users; ω z (t) is the indoor temperature demand weight of the zth user at the tth moment; T z，avg (t) and T z，set(t) are the average indoor temperature and preset indoor temperature of the zth user at time t, respectively; is the on / off state of the air conditioning load of the zth user; Δt represents the duration of the zth user turning on at the tth moment; P z (t) represents the rated power of the user's air conditioning load; S represents the number of hours in a day; σ z (t) is the carbon emission factor of electricity of the zth user at the tth moment; e (t) and λ c (t) are the electricity price and carbon price at the tth moment respectively.

[0011] Optionally, the penalty function of the constraint conditions in the multi-objective optimization model includes:

[0012] Constraint 1: Penalty function for temperature constraint;

[0013]

[0014] Constraint 2: Penalty function of power constraint;

[0015]

[0016] Constraint 3: Penalty function for load balancing constraints;

[0017]

[0018]

[0019] Constraint 4: Penalty function for switch state constraint;

[0020]

[0021] Constraint 5: penalty function for carbon emission constraints;

[0022]

[0023] Constraint 6: Penalty function for electricity cost constraint;

[0024]

[0025] Among them, T min , T max They represent the minimum and maximum indoor temperatures respectively, P min and P max Respectively represent the minimum rated power value and the maximum rated power value, P d (t) represents the rated power value that meets the total load demand at each moment, C max and E max Represent the maximum allowable values ​​of carbon emissions and electricity costs, βk represents the penalty coefficient of the corresponding constraint condition, M k represents the penalty cost of the corresponding constraint, k=1,2,3,4,5.

[0026] Optionally, the using the Parrot optimization algorithm to solve the optimal solution of the multi-objective optimization model includes:

[0027] Under the constraints, the parameters of the multi-objective optimization model are solved to obtain a set of solutions as the initialization population, and each solution is an individual in the population; wherein the solution is a vector including the user's temperature setting, the air conditioner on state and the power;

[0028] Iteratively calculate the parameters of the multi-objective optimization model, and in each iteration, calculate the fitness function of each individual to minimize the solution, and obtain multiple fitness function values; wherein the fitness function includes a temperature comfort deviation function and a comprehensive electricity cost function;

[0029] A set of Pareto optimal frontier solutions is determined from the multiple fitness function values ​​as a leader; the position of each individual is updated according to the position of the leader and the remaining fitness function values, until the number of iterative calculations reaches a preset maximum number of iterations, and it is determined that the population gradually converges to the Pareto optimal solution, thereby obtaining the optimal solution of the multi-objective optimization model.

[0030] Optionally, controlling the operation of each air conditioner according to the optimal solution of the multi-objective optimization model includes:

[0031] Acquire control parameters of each air conditioner, and cluster each air conditioner into multiple groups of air conditioner sets based on the control parameters;

[0032] Determine the optimal solution corresponding to each air conditioner in the air conditioner set, and determine the cluster center of the optimal solution corresponding to each air conditioner;

[0033] The cluster center is used as a cluster parameter of the corresponding air-conditioning set, and the operation of each air-conditioning in the air-conditioning set is controlled according to the cluster parameter.

[0034] Optionally, the fitness function is expressed as:

[0035]

[0036] Among them, X i represents the i-th individual, ω1 and ω2 represent the temperature comfort deviation function f1(X i ) and the comprehensive electricity cost function f2(X i ), and K represents the total number of constraint adjustments.

[0037] In a second aspect, an embodiment of the present invention provides a multi-objective day-ahead optimization scheduling system for massive air conditioners considering carbon emission flows, including a memory and a processor.

[0038] The memory is used to store computer programs;

[0039] The processor is used to implement the method according to the first aspect of the present invention when executing the computer program.

[0040] According to a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing a program executable by a processor, wherein the executable program is used to execute the method according to the first aspect of the present invention when executed by the processor.

[0041] The embodiments of the present invention include the following beneficial effects: the embodiments of the present invention take the minimum temperature comfort deviation and the lowest comprehensive cost as the goal, construct a multi-objective optimization model for the day-ahead scheduling of air conditioning loads; achieve the minimum temperature comfort deviation and the lowest comprehensive cost; by determining the constraints in the multi-objective optimization model, convert the constraints into penalty functions; wherein the constraints include temperature constraints, power constraints, load balance constraints, switch state constraints, carbon emission constraints and electricity cost constraints, so that the electricity cost and the carbon emission cost based on the dynamic carbon emission factor are incorporated into the optimization goal; by using the Parrot optimization algorithm to solve the optimal solution of the multi-objective optimization model, the operation of each air conditioner is controlled according to the optimal solution of the multi-objective optimization model. The Parrot optimization algorithm is applied to the multi-objective day-ahead optimization scheduling of massive air conditioners, realizing the dynamic, real-time and precise quantification of massive air conditioners, and realizing the rapid optimization scheduling of the dual goals of electricity cost and carbon emission cost of massive air conditioners. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 A flowchart of a multi-objective day-ahead optimization scheduling method for massive air conditioners considering carbon emission flows provided by an embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of a massive air conditioning multi-objective day-ahead optimization scheduling system considering carbon emission flow according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] It should be noted that all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0047] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0048] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0049] In the related art, when performing multi-objective day-ahead optimization scheduling of massive air conditioners, the following problems exist:

[0050] 1. Traditional methods usually use average carbon emission factors at the regional or provincial level, which fails to reflect the changes in electricity sources and carbon emissions in different time periods and geographical locations. This coarse-grained calculation cannot capture the differences in carbon emissions caused by peak electricity consumption or changes in the power structure in different regions.

[0051] 2. Traditional carbon emission factors are often based on historical data and are updated infrequently, which may result in the factors used not being able to reflect the increase in the proportion of new energy in the current power structure. This lag causes carbon emission estimates to deviate from actual conditions and affects the accuracy of decision-making.

[0052] 3. Traditional methods fail to consider the impact of real-time power dispatch, which directly affects the use of different power sources in the power grid, thereby affecting actual carbon emissions. The traditional average carbon emission factor method cannot dynamically reflect this change.

[0053] 4. The traditional optimization of independent switch control strategies for large numbers of air conditioners is very time-consuming. By clustering similar air conditioner parameters, a unified control strategy can be obtained, which greatly saves time costs.

[0054] In order to solve these problems, the present invention introduces a dynamic carbon emission factor calculation method, which uses the grid spatiotemporal data model and combines the real-time analysis of power flow to increase the calculation frequency of the carbon emission factor to once per hour or once per minute, so as to more accurately reflect the carbon emission levels in different time periods and regions. The dynamic carbon emission factor can be predicted in advance and provided to users. Users can adjust their electricity consumption habits according to the expected carbon emission level and reduce carbon emissions within a feasible range, thereby better supporting the goal of green development.

[0055] Figure 1 A flowchart of a multi-objective day-ahead optimization scheduling method for massive air conditioners considering carbon emission flow is provided in an embodiment of the present invention. The method comprises the following steps:

[0056] S110, constructing a multi-objective optimization model for day-ahead scheduling of air-conditioning load with the goal of minimizing temperature comfort deviation and minimizing comprehensive cost; wherein the optimal solution of the multi-objective optimization model includes minimizing temperature comfort deviation and minimizing comprehensive cost, and the comprehensive cost includes electricity cost and carbon emission cost;

[0057] S120, determining the constraints in the multi-objective optimization model, and converting the constraints into penalty functions; wherein the constraints include temperature constraints, power constraints, load balance constraints, switch state constraints, carbon emission constraints, and power cost constraints;

[0058] S130, using the Parrot optimization algorithm to solve the optimal solution of the multi-objective optimization model, and controlling the operation of each air conditioner according to the optimal solution of the multi-objective optimization model.

[0059] In the present invention, the maximization of the multi-objective optimization model adopts temperature comfort and comprehensive cost as the optimal scheduling of the two main objectives, the comprehensive cost includes electricity cost and carbon emission cost, and the multi-objective Parrot optimization algorithm is used to solve the optimal solution of the multi-objective optimization model.

[0060] The present invention proposes a multi-objective day-ahead optimization scheduling method for massive air conditioners based on the Parrot optimization algorithm, and at the same time incorporates electricity cost and carbon emission cost based on dynamic carbon emission factors into the optimization objectives. The present invention adopts the Kmeans clustering method to cluster similar parameters of air conditioners into a large category, and then uses the cluster center of the cluster as the clustering parameter of the air conditioner to obtain a unified air conditioner switch control strategy, which greatly saves time. The Parrot optimization algorithm adopted realizes dynamic and real-time scheduling of massive air conditioners, and accurately quantifies carbon emission costs, thereby obtaining rapid optimal decisions for the dual objectives of electricity cost and carbon emission cost of massive air conditioners.

[0061] In some embodiments, the expression of the multi-objective optimization model is as follows:

[0062]

[0063] Among them, f1 represents the temperature comfort deviation function; f2 represents the comprehensive electricity cost function of electricity cost and carbon emission cost; Z is the number of users; ω z (t) is the indoor temperature demand weight of the zth user at the tth moment; T z，avg (t) and T z，set (t) are the average indoor temperature and preset indoor temperature of the zth user at time t, respectively; is the on / off state of the air conditioning load of the zth user; Δt represents the duration of the zth user turning on at the tth moment; P z (t) represents the rated power of the user's air conditioning load; S represents the number of hours in a day; σ z (t) is the carbon emission factor of electricity of the zth user at the tth moment; e (t) and λ c (t) are the electricity price and carbon price at the tth moment respectively.

[0064] In some embodiments, the penalty function of the constraint conditions in the multi-objective optimization model includes:

[0065] Constraint 1: Penalty function for temperature constraint;

[0066]

[0067] Constraint 2: Penalty function of power constraint;

[0068]

[0069] Constraint 3: Penalty function for load balancing constraints;

[0070]

[0071] Constraint 4: Penalty function for switch state constraint;

[0072]

[0073] Constraint 5: penalty function for carbon emission constraints;

[0074]

[0075] Constraint 6: Penalty function for electricity cost constraint;

[0076]

[0077] Among them, T min , T max They represent the minimum and maximum indoor temperatures respectively, P min and Pmax Respectively represent the minimum rated power value and the maximum rated power value, P d (t) represents the rated power value that meets the total load demand at each moment, C max and E max Represent the maximum allowable values ​​of carbon emissions and electricity costs, β k represents the penalty coefficient of the corresponding constraint condition, M k represents the penalty cost of the corresponding constraint, k=1,2,3,4,5.

[0078] In some embodiments, the using of the Parrot optimization algorithm to solve the optimal solution of the multi-objective optimization model includes:

[0079] S131, under constraints, solving the parameters of the multi-objective optimization model to obtain a set of solutions as an initialization population, and treating each solution as an individual in the population; wherein the solution is a vector including the user's temperature setting, the air conditioner on state, and the power;

[0080] S132, iteratively calculating the parameters of the multi-objective optimization model, and in each iteration, calculating the fitness function of each individual to minimize the fitness function, and obtaining multiple fitness function values; wherein the fitness function includes a temperature comfort deviation function and a comprehensive electricity cost function;

[0081] S133, determining a group of Pareto optimal frontier solutions from the multiple fitness function values ​​as a leader; updating the position of each individual according to the position of the leader and the remaining fitness function values, until the number of iterative calculations reaches a preset maximum number of iterations, determining that the population gradually converges to the Pareto optimal solution, and obtaining the optimal solution of the multi-objective optimization model.

[0082] Specifically, it is determined whether the number of iterative calculations reaches the maximum number of iterations. If it is lower than the maximum number of iterations, S132 is continued to be executed for iterative calculations. Through multiple iterations, the population will gradually converge to the Pareto optimal solution as the optimal solution of the multi-objective optimization model.

[0083] The Parrot optimization algorithm combines the multi-objective process as follows:

[0084] 1. Population initialization;

[0085] Initialize a set of solutions, and define each solution as a vector containing the user's temperature setting, air conditioning on status, and power. i , define the states it contains as:

[0086]

[0087] 2. Fitness assessment;

[0088] In each iteration, for each individual X i Calculate the fitness function value. The fitness function includes two objective functions in the following form:

[0089]

[0090]

[0091] Next, calculate each solution X i The objective function value f1(X i ) and f2(X i ), the goal is to minimize the fitness function f(X i ):

[0092]

[0093] Among them, X i represents the i-th individual, ω1 and ω2 represent the temperature comfort deviation function f1(X i ) and the comprehensive electricity cost function f2(X i ) is the weight coefficient of .

[0094] 3. Selecting a leader;

[0095] To select a leader, the concept of Pareto optimal solution is used. For two solutions X a and X b ,definition:

[0096] If the following formula is satisfied, then X is determined a Priority X b :

[0097]

[0098] If X a Priority X b , then X a is considered as a non-inferior solution. In this way, a set of Pareto optimal frontier solutions can be found, which are called leaders.

[0099] 4. Location update;

[0100] In the parrot optimization algorithm, the parrot will update its position according to the position of the leader and other solutions. The specific update rules are as follows:

[0101] X i (t+1)=X i (t)+r1·(L(t)-X i (t))+r2·(X j (t)-X i (t))(21);

[0102] In the formula, X i (t+1) represents the solution of the ith parrot in the t+1th generation, L(t) represents the leader solution in the current iteration (i.e., one of the Pareto optimal solutions), X j (t) is another randomly selected solution to increase the diversity of solutions. r1 and r2 are random numbers in the interval [0, 1], which control the degree to which the parrot learns from the leader solution and the random solution, respectively.

[0103] 5. Iteration and Convergence

[0104] After multiple iterations, the population will gradually converge to the Pareto optimal solution. Set the maximum number of iterations Tmax as the convergence criterion, and the final solution will be in the form of:

[0105]

[0106] Among them, X* is the Pareto optimal solution set, T * z,avg (t) is the optimal indoor temperature of the zth user at the tth moment, is the optimal switching state of the air conditioning load of the zth user, P * z (t) is the optimal rated power of the user's air conditioning load.

[0107] In some embodiments, controlling the operation of each air conditioner according to the optimal solution of the multi-objective optimization model includes:

[0108] S134, obtaining control parameters of each air conditioner, and clustering the air conditioners into a plurality of air conditioner sets based on the control parameters;

[0109] S135, determining an optimal solution corresponding to each air conditioner in the air conditioner set, and determining a cluster center of the optimal solution corresponding to each air conditioner;

[0110] S136: Using the cluster center as a cluster parameter of the corresponding air-conditioning set, and controlling the operation of each air-conditioning in the air-conditioning set according to the cluster parameter.

[0111] The Kmeans clustering method is used to cluster similar parameters of each air conditioner in the scheduling multi-objective optimization model into a large category, and then the cluster center of the cluster is used as the clustering parameter of the air conditioner to obtain a unified air conditioner switch control strategy.

[0112] It should be noted that the K-means algorithm is an iterative clustering analysis algorithm. Its core idea is to divide the n objects in the data set into K clusters so that the sum of the distances from each object to the center (or mean point, centroid) of its cluster is minimized. The distance mentioned here usually refers to the Euclidean distance, but it can also be other types of distance metrics.

[0113] Divide the n objects in the data set into K clusters,

[0114] 1. Initialization: Select K initial cluster centers;

[0115] At the beginning of the algorithm, K data points need to be randomly selected as the initial cluster centers. The selection of these initial cluster centers has a certain impact on the final clustering results.

[0116] 2. Assignment: Assign each data point to the nearest cluster center;

[0117] For each data point in the data set, calculate its distance from each cluster center and assign it to the cluster center closest to it. This step usually uses Euclidean distance as the distance metric, and the calculation formula is as follows:

[0118]

[0119] In the formula, x is the data point, c is i is the i-th cluster center, d is the dimension of the data, x j and c ij are x and c respectively i The value in the jth dimension.

[0120] 3. Update: recalculate the center of each cluster;

[0121] For each cluster, recalculate its cluster center. The new cluster center is the mean of all data points in the cluster, and the calculation formula is as follows:

[0122]

[0123] Among them, S i is the set of data points of the ith cluster, |S i | is the number of data points in the set.

[0124] 4. Iteration: Repeat the allocation and update steps until the termination condition is met;

[0125] Repeat the allocation and update steps until some termination condition is met. Common termination conditions include:

[0126] Reaching the maximum number of iterations: In order to prevent the algorithm from falling into an infinite loop, the present invention sets a maximum number of iterations as a termination condition.

[0127] Compared with the prior art, the present invention has the following advantages:

[0128] 1. The present invention adopts the parrot optimization algorithm to apply to the multi-objective optimal scheduling of massive air-conditioning operation. Each parrot individual chooses to forage in a small group with abundant food. They can take advantage of the position of the owner and the existence of the group, and walk towards the food so that the parrots can stay, communicate, and be more random in the process of position optimization. The traversal ability is more superior, and the optimization process is more efficient. Its convergence speed and accuracy are well presented in multi-objective optimization scheduling, and the objective function can obtain the optimal solution with good performance more quickly. In the present invention, good decision-making balance ability is shown under the dual-objective optimization of electricity cost and carbon emission cost. These advantages do not exist in single-objective optimization algorithms.

[0129] 2. On the one hand, with the rapid development of renewable energy (such as wind energy and solar energy), the energy structure in the power system has become more complex and changeable. The traditional electric carbon factor cannot reflect these changes in real time, especially when the mixed ratio of fossil energy and new energy fluctuates continuously in different time periods; on the other hand, the real-time scheduling of the power grid directly affects the usage ratio of different power sources, thereby affecting carbon emissions. The traditional static electric carbon factor cannot capture these instantaneous changes. The dynamic electric carbon factor adopted in the present invention is combined with the real-time data of power scheduling, which can more accurately reflect the actual carbon emission level and support the optimization scheduling and emission reduction strategies of the power system.

[0130] 3. Individually controlling each air conditioner requires a lot of computing resources and time, especially when dealing with large-scale air conditioning systems. The present invention can significantly reduce the cost of computing and optimization by clustering and merging similar devices for processing; at the same time, a unified control strategy can ensure that the same type of air-conditioning equipment has consistent operating performance under the same environmental conditions, thereby providing a more stable and predictable user experience, especially in scenarios of large buildings or regional centralized control.

[0131] like Figure 2 As shown, an embodiment of the present invention provides a massive air conditioning multi-objective day-ahead optimization scheduling system considering carbon emission flow, the massive air conditioning multi-objective day-ahead optimization scheduling system considering carbon emission flow includes a memory 220 and a processor 210, the memory 220 is used to store a computer program; the processor 210 is used to implement when executing the computer program Figure 1 The method described in S110-S130.

[0132] One embodiment of the present invention provides a computer-readable storage medium, wherein a program executable by a processor is stored, and when the executable program is executed by the processor, it is used to implement Figure 1 The method described in S110-S130.

[0133] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0135] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A multi-objective day-ahead optimization scheduling method for massive air conditioners considering carbon emission flow, characterized in that: include: A multi-objective optimization model for day-ahead scheduling of air-conditioning load is constructed with the goal of minimizing temperature comfort deviation and minimizing comprehensive cost; wherein the optimal solution of the multi-objective optimization model includes minimizing temperature comfort deviation and minimizing comprehensive cost, and the comprehensive cost includes electricity cost and carbon emission cost; Determine the constraints in the multi-objective optimization model, and convert the constraints into penalty functions; wherein the constraints include temperature constraints, power constraints, load balance constraints, switch state constraints, carbon emission constraints, and electricity cost constraints; The Parrot optimization algorithm is used to solve the optimal solution of the multi-objective optimization model, and the operation of each air conditioner is controlled according to the optimal solution of the multi-objective optimization model.

2. The method according to claim 1, characterized in that: The expression of the multi-objective optimization model is as follows: Among them, f1 represents the temperature comfort deviation function; f2 represents the comprehensive electricity cost function of electricity cost and carbon emission cost; Z is the number of users; ω z (t) is the indoor temperature demand weight of the zth user at the tth moment; T z，avg (t) and T z，set (t) are the average indoor temperature and preset indoor temperature of the zth user at time t, respectively; is the on / off state of the air conditioning load of the zth user; Δt represents the duration of the zth user turning on at the tth moment; P z (t) represents the rated power of the user's air conditioning load; S represents the number of hours in a day; σ z (t) is the carbon emission factor of electricity of the zth user at the tth moment; e (t) and λ c (t) are the electricity price and carbon price at the tth moment respectively.

3. The method according to claim 2, characterized in that The penalty function of the constraint conditions in the multi-objective optimization model includes: Constraint 1: Penalty function for temperature constraint; Constraint 2: Penalty function of power constraint; Constraint 3: Penalty function for load balancing constraints; Constraint 4: Penalty function for switch state constraint; Constraint 5: penalty function for carbon emission constraints; Constraint 6: Penalty function for electricity cost constraint; Among them, T min , T max They represent the minimum and maximum indoor temperatures respectively, P min and P max Respectively represent the minimum rated power value and the maximum rated power value, P d (t) represents the rated power value that meets the total load demand at each moment, C max and E max Represent the maximum allowable values ​​of carbon emissions and electricity costs, β k represents the penalty coefficient of the corresponding constraint condition, M k represents the penalty cost of the corresponding constraint, k=1,2,3,4,5.

4. The method according to claim 2, characterized in that: The method of using the Parrot optimization algorithm to solve the optimal solution of the multi-objective optimization model includes: Under the constraints, the parameters of the multi-objective optimization model are solved to obtain a set of solutions as the initialization population, and each solution is an individual in the population; wherein the solution is a vector including the user's temperature setting, the air conditioner on state and the power; Iteratively calculate the parameters of the multi-objective optimization model, and in each iteration, calculate the fitness function of each individual to minimize the solution, and obtain multiple fitness function values; wherein the fitness function includes a temperature comfort deviation function and a comprehensive electricity cost function; A set of Pareto optimal frontier solutions is determined from the multiple fitness function values ​​as a leader; the position of each individual is updated according to the position of the leader and the remaining fitness function values, until the number of iterative calculations reaches a preset maximum number of iterations, and it is determined that the population gradually converges to the Pareto optimal solution, thereby obtaining the optimal solution of the multi-objective optimization model.

5. The method according to claim 4, characterized in that The controlling the operation of each air conditioner according to the optimal solution of the multi-objective optimization model includes: Acquire control parameters of each air conditioner, and cluster each air conditioner into multiple groups of air conditioner sets based on the control parameters; Determine the optimal solution corresponding to each air conditioner in the air conditioner set, and determine the cluster center of the optimal solution corresponding to each air conditioner; The cluster center is used as a cluster parameter of the corresponding air-conditioning set, and the operation of each air-conditioning in the air-conditioning set is controlled according to the cluster parameter.

6. The method according to claim 5, characterized in that The expression of the fitness function is: Among them, X i represents the i-th individual, ω1 and ω2 represent the temperature comfort deviation function f1(X i ) and the comprehensive electricity cost function f2(X i ), and K represents the total number of constraint adjustments.

7. A multi-objective day-ahead optimization scheduling system for massive air conditioning considering carbon emission flow, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 6 when executing the computer program.

8. A computer-readable storage medium storing a program executable by a processor, characterized in that: The executable program is used to perform the method according to any one of claims 1 to 6 when executed by a processor.

Images