Dynamic economic emission scheduling optimization method and system based on regional collaboration

Abstract

The invention discloses a dynamic economic emission scheduling optimization method and system based on regional collaboration, and belongs to the technical field of dynamic economic emission scheduling. Comprising the following steps of: constructing a dynamic economic emission scheduling model by taking minimization of fuel cost and pollution emission as targets and taking load demand and power loss as constraints; solving the dynamic economic emission scheduling model through a multi-objective evolutionary algorithm to obtain a scheduling optimization scheme; according to the multi-objective evolutionary algorithm, an individual adaptive evolutionary strategy is utilized to construct a main population and an auxiliary population, and a regional co-evolutionary strategy is utilized to carry out collaborative optimization on the main population and the auxiliary population. Individual information can be fully utilized to assist evolution, each region of a target space is searched, and the difficulty of dynamic economic emission scheduling optimization is reduced; the problems that an existing algorithm is insufficient in optimal capability and prone to falling into a local optimal solution, and various planning schemes cannot be provided are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic economic emission scheduling, and in particular to a dynamic economic emission scheduling optimization method and system based on regional collaboration. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] Fossil fuel-based power plants emit large amounts of sulfur oxides (SO x ), nitrogen oxides (NO x ) and carbon dioxide (CO 2 ) and other pollutants, which lead to reduced air visibility and increased global warming. In recent years, society's demand for electricity has not only required low cost and sufficient and safe supply, but also emphasized the need to minimize environmental pollution.

[0004] In this context, a variety of strategies have been proposed to reduce air pollution. These strategies include installing pollutant purification devices, using low-emission fuels, replacing old equipment with clean fuel burners, and implementing dynamic economic emissions dispatch (DEED). Among them, the first three options require the installation of new equipment or the transformation of existing equipment, which usually involves higher capital investment and is therefore more suitable as a long-term solution. Compared with these methods, dynamic economic emissions dispatch is more attractive as a short-term alternative. DEED optimizes resource allocation by dispatching the output of online generators according to predicted load demand, aiming to minimize costs and emissions while ensuring power supply.

[0005] With the rapid development and widespread application of artificial intelligence technology, evolutionary algorithms have begun to be used to solve the dynamic economic emission dispatch (DEED) problem and have achieved initial results. However, existing methods are insufficient in optimization ability, easily fall into local optimal solutions, and cannot provide a variety of planning schemes for selection. Summary of the invention

[0006] In order to address the shortcomings of the prior art, the present invention provides a dynamic economic emission scheduling optimization method, system, electronic device, computer-readable storage medium and computer program product based on regional collaboration, which effectively utilizes individual information through individual adaptive evolution strategy to identify a better solution area; improves the distribution of the population through regional collaborative evolution strategy to provide decision makers with more options.

[0007] In a first aspect, the present invention provides a method for optimizing dynamic economic emission scheduling based on regional collaboration;

[0008] A dynamic economic emission scheduling optimization method based on regional coordination, comprising:

[0009] A dynamic economic emission dispatch model is constructed with the goal of minimizing fuel costs and pollution emissions and with load demand and power loss as constraints;

[0010] The dynamic economic emission scheduling model is solved by a multi-objective evolutionary algorithm to obtain a scheduling optimization solution;

[0011] The multi-objective evolutionary algorithm uses an individual adaptive evolutionary strategy to construct a main population and an auxiliary population, and uses a regional collaborative evolutionary strategy to collaboratively optimize the main population and the auxiliary population.

[0012] In some embodiments, the use of individual adaptive evolution strategy to construct the main population and the auxiliary population is specifically: using the individual adaptive evolution strategy to optimize each individual in the target space and output a population; and constructing the main population and the auxiliary population based on the population.

[0013] In some embodiments, the optimization of each individual in the target space using the individual adaptive evolution strategy and the output population specifically include:

[0014] Determine the neighborhood of each individual in the target space, optimize each individual in the neighborhood according to the preset decision variable grouping, generate offspring and compare them with the corresponding individuals, and save individuals with smaller target values ​​until each individual enters the stagnation stage;

[0015] Determine whether the convergence-related variable set and the diversity variable set are both not empty. If so, optimize the diversity variable set; if not, output the population.

[0016] In some embodiments, constructing a main population and an auxiliary population according to the population specifically includes:

[0017] Assign the population to the main population and the auxiliary population, and normalize the target vector of the individuals in the auxiliary population according to the minimum value of each target of the individuals in the pre-stored auxiliary population;

[0018] Generate multiple reference vectors in the target space, calculate the angles between all reference vectors and the normalized target vector, and select the individual with the smallest angle to form a subpopulation of the auxiliary population.

[0019] In some embodiments, the collaborative optimization of the main population and the auxiliary population using the regional collaborative evolution strategy specifically includes:

[0020] The main population produces multiple offspring, and each subpopulation in the auxiliary population produces multiple offspring to form the offspring population;

[0021] Based on the offspring population, the next generation population of the main population is selected according to the constraint dominance principle; each individual in the offspring population is reallocated to the reference vector, and the next generation population of the auxiliary population is selected according to the constraint relaxation dominance principle.

[0022] In some embodiments, before constructing the main population and the auxiliary population using the individual adaptive evolution strategy, the method further includes:

[0023] Initialize the overall population, preprocess the decision variables in the overall population, and divide the decision variables into a convergence-related variable set and a diversity variable set using the K-means clustering method.

[0024] In a second aspect, the present invention provides a dynamic economic emission scheduling optimization system based on regional collaboration;

[0025] A dynamic economic emission scheduling optimization system based on regional coordination, comprising:

[0026] The building module is configured to: construct a dynamic economic emission dispatch model with the goal of minimizing fuel cost and pollution emission and with load demand and power loss as constraints;

[0027] The scheduling optimization module is configured to: solve the dynamic economic emission scheduling model through a multi-objective evolutionary algorithm to obtain a scheduling optimization solution;

[0028] The multi-objective evolutionary algorithm uses an individual adaptive evolutionary strategy to construct a main population and an auxiliary population, and uses a regional collaborative evolutionary strategy to collaboratively optimize the main population and the auxiliary population.

[0029] In a third aspect, the present invention provides an electronic device;

[0030] An electronic device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned dynamic economic emission scheduling optimization method based on regional collaboration.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium;

[0032] A computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the steps of the above-mentioned regional collaboration-based dynamic economic emission scheduling optimization method claimed.

[0033] In a fifth aspect, the present invention provides a computer program product;

[0034] A computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned dynamic economic emission scheduling optimization method based on regional collaboration.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The technical solution provided by the present invention makes full use of individual information through individual adaptive evolution strategy, dynamically allocates computing resources to each individual, reduces resource waste and leaves more resources for subsequent evolution; through regional collaborative evolution strategy, it simultaneously searches for constrained Pareto fronts in multiple sub-regions, explores each region of the target space, improves the distribution of the population, and provides more scheduling optimization solutions.

[0037] 2. The technical solution provided by the present invention decouples complex decision variables and reduces the difficulty of optimization. It has strong robustness and can be applied to a variety of dynamic economic emission scheduling problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0039] Figure 1 A schematic diagram of a flow chart provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0040] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0043] Embodiment 1

[0044] The existing methods are insufficient in optimization ability and are prone to fall into local optimal solutions, and cannot provide a variety of scheduling optimization solutions for selection; and because the DEED problem is non-convex, nonlinear and highly coupled, the existing methods have insufficient reasoning for individual information and cannot identify a better solution; therefore, the present invention provides a dynamic economic emission scheduling optimization method based on regional collaboration, which utilizes individual adaptive evolution strategies to construct main populations and auxiliary populations, and utilizes regional collaborative evolution strategies to collaboratively optimize the main population and auxiliary populations.

[0045] Next, combine Figure 1 , a dynamic economic emission scheduling optimization method based on regional collaboration disclosed in this embodiment is described in detail. The dynamic economic emission scheduling optimization method based on regional collaboration includes the following steps:

[0046] S1. With the goal of minimizing fuel costs and pollution emissions, and with capacity, ramp rate, and power balance as constraints, a dynamic economic emission scheduling model is constructed.

[0047] Among them, the objective function is expressed as follows:

[0048]

[0049] Among them, F(x) represents the total fuel cost of N power generation units within T scheduling time intervals, E(x) represents the total pollution emissions of N power generation units in the entire scheduling period, and x i,t represents the output active power of the i-th generating unit in the scheduling time interval t, x i,min represents the lower limit of the output of the active power of the i-th generating unit in the scheduling time interval t, A i , B i , C i , D i 、E i , H i and G i Represents the correlation coefficient.

[0050] The constraints are expressed as follows:

[0051]

[0052] The first formula represents the capacity constraint of the power generation unit, x i,min and x i,max They represent the minimum and maximum output of the i-th power generation unit respectively; the second formula is the ramp rate constraint of the power generation unit, U Ri and D Ri They represent the ramp-up and ramp-down rate limits of the i-th generating unit, respectively, and ΔT is the length of each scheduling time interval. The third formula is the actual power balance constraint, x LD,t and xPL,t They represent the load demand and power loss in the time interval t respectively.

[0053] S2. Solving the dynamic economic emission scheduling model through a multi-objective evolutionary algorithm to obtain a scheduling optimization solution; specifically including:

[0054] S201. Initialize a population P of size NP.

[0055] S202: Preprocess the decision variable set.

[0056] In order to reduce the difficulty of optimization, in this embodiment, the complex decision variable set is decoupled. As an implementation method, the specific process is as follows:

[0057] S2021. Randomly select nSel candidate solutions from the total population P, perform nPer perturbations on all decision variables of the candidate solutions, and generate perturbation solutions.

[0058] Specifically, when a decision variable is perturbed, the other decision variables remain unchanged. The sample solutions are normalized, and the perturbation solutions generated by each decision variable are used for fitting to generate a straight line L, so that the number of straight lines corresponding to each decision variable is nSel. The angles between these straight lines and the normal of the hyperplane are calculated respectively. Similarly, each decision variable obtains nSel angles. Among them, the normal line represents the convergence direction, and the angle value is used to measure the contribution of the decision variable to convergence and diversity. The larger the angle, the greater the contribution of the decision variable to diversity, and the smaller the angle, the greater the contribution of the decision variable to convergence. The K-means clustering method is used to divide the decision variables into two categories according to the average angle of each variable, namely, the convergence-related variable set CV and the diversity variable set DV.

[0059] In this embodiment, the K-means clustering method is used to divide the decision variables into two categories according to the angle average value of each variable. Specifically, first, two angle values ​​are selected as the initial cluster centers, the difference between the remaining angle and the two cluster centers is calculated, and the decision variable is assigned to the cluster center with the smallest interpolation value. For each cluster, its cluster center, that is, the mean of all data points, is recalculated, and finally the assignment and update steps are repeated until the cluster center no longer changes, that is, the variable with a smaller angle average value is related to convergence, and the other variable is related to diversity.

[0060] S2022. Determine whether the convergence-related variable set is empty. If not, use formula (2) to divide CV into multiple subgroups SubV 1-n Otherwise, use formula (2) to divide all decision variables into multiple subgroups SubV 1-n , the variables between subgroups are interrelated; formula (2) is expressed as follows:

[0061] |(f s (x)|x i =a 2 , x j =b 1 -f s (x)|x i =a 1 , x j =b 1

[0062] -(f s (x)|x i =a 2 , x j =b 2 -f s (x)|x i =a 1 , x j =b 2 )|>∈ (2)

[0063] Among them, ∈ is a small positive value, D is the number of decision variables.

[0064] Given a multi-objective optimization problem: minF(x)=(f 1 (x),f 2 (x),…,f M (x)) T , assuming and is the decision variable X=(x 1 ,…,x D ), namely If there is a 1 , a 2 , b 1 , b 2 , x i ∈X i , x j ∈X j and at least one f s (x)(1≤s≤M), if the above conditions are met, then X i and X j are interrelated.

[0065] Here, after the variables are divided, there are two situations: one is that they can be clearly divided into CV and DV, and the other is that the CV set is empty, that is, all variables are DV

[0066] S203, using individual adaptive evolution strategy to optimize and output population P. Specifically including:

[0067] S2031. Calculate each individual A in the target space i The Euclidean distance between (i∈[1,NP]) and the remaining individuals, and obtain the neighborhood B of each individual i .

[0068] S2032. For each individual A i , in its neighborhood B i In the above example, we group the decision variables SubV 1-n The variables belonging to the decision variable group are optimized in turn. In the optimization process of each decision variable group, the values ​​of other decision variable groups are fixed, and only the value of the current decision variable group is optimized, thus generating a descendant O i , compare A i With O i The objective function value of the two is retained, and the individual with the smaller objective value is retained.

[0069] S2033. For each individual A i According to formulas (3) and (4), it is determined whether the process has entered the stagnation stage. Individuals that are in the stagnation stage will no longer evolve, while individuals that are not in the stagnation stage will jump to S2032 to continue optimization. When all individuals are in the stagnation stage, it will jump to S2034.

[0070] Specifically, first calculate the individual A between some evolutionary generations g i The standard deviation of each target is given by equation (3), where m is the number of targets. It is believed that A i has been fully optimized. Then, A i Add to the stagnant population (SI), as shown in formula (4).

[0071]

[0072] S2034. When the convergence-related variable set CV and the diversity variable set DV are not empty sets, jump to S2035; otherwise, the optimization stage ends and the population P is output.

[0073] S2035. Optimize the DV variable set to make the population more evenly distributed on the unconstrained Pareto front.

[0074] Specifically, the CV variable set is fixed, and only the DV variable set is used to generate the offspring O. The populations P and O are merged and updated, and the next generation population P is output. The condition for stopping optimization is similar to the individual stagnation judgment, as shown in formula (5).

[0075]

[0076] in, is the overall standard deviation of the population on the ωth target in generation T, when When , the optimization phase ends and the population P is output.

[0077] S204: Construct the main population MP and auxiliary population AP that need to cooperate with each other. Specifically, it includes:

[0078] S2041. Assign population P to MP and AP, where MP is the same as P and AP is a replica of population P. Perform the following operations on AP:

[0079] S2042. Calculate the minimum value of each individual in the archived AP on each target, and normalize the target vector of each individual in the AP according to these values.

[0080] S2043. Generate l reference vectors uniformly in the target space.

[0081] S2044. Calculate the angles between all reference vectors and the normalized target vector.

[0082] S2045. Select λ individuals with the smallest angle in each normalized target vector to form a subpopulation SubAP i (i∈[1,l]), ensuring that AP has candidate individuals in every sub-region of the target space.

[0083] S205, using regional co-evolution strategy for optimization. Specifically including:

[0084] S2051. The main population MP produces offspring OMP of size NP.

[0085] S2052. For AP, each subgroup SubAP i will generate a descendant SubOAP of size λ i .

[0086] S2053. The offspring produced by the two populations are combined into Oall.

[0087] S2054. For MP, select the next generation population according to the constraint dominance principle. For AP, redistribute Oall to each reference vector, and then select the next generation population according to the constraint relaxation dominance principle.

[0088] Specifically, the constraint dominance criterion first determines whether the solution satisfies all constraints, and gives priority to solutions that meet all constraints, emphasizing the feasibility of the solution. If both solutions meet the constraints, the advantages and disadvantages are compared through the Pareto dominance relationship. For solutions that do not meet the constraints, their constraint violation degrees are compared, and the one with the lower violation degree is better, guiding the solution to approach the feasible domain.

[0089] The constraint relaxation dominance principle usually sets a threshold ε to handle constraints in a more flexible way. This method determines the feasibility of a solution by comparing its constraint violation with ε. Specifically, if the constraint violation of a solution is lower than ε, its constraint violation is considered to be zero and the solution is considered feasible. This method proposes the following rules when evaluating solutions: When the constraint violations of two solutions A and B are both lower than ε, and A Pareto dominates B, A is considered better. If the constraint violation of A is lower than ε and the constraint violation of B exceeds ε, A is always better than B regardless of the objective function value. If the constraint violations of A and B both exceed ε, but the CV value of A is lower than that of B, A is considered better.

[0090] S206: Determine whether the set maximum number of evaluation times has been reached. If so, the algorithm terminates and outputs MP. Otherwise, execute S205.

[0091] Next, in order to verify the advancedness of the method described in this embodiment, two classic dynamic economic dispatch optimization cases are selected as optimization targets, called DEED1 and DEED2, and these two cases have 144 and 336 devices respectively; the output of active power of these devices can be changed during the optimization process, that is, the number of their decision variables is 144 and 336 respectively. The population P size is set to 100, the maximum number of evaluations is set to 8000×D, and the optimization method described in this embodiment is compared with four advanced evolutionary algorithms (LMOCSO, DPSEA, POCEA, CMOCSO) that have been used for dynamic economic dispatch. The obtained hypervolume index (HV) data is shown in Table 1.

[0092] Among them, the larger the HV value, the better the algorithm effect, and the more optimal solutions the algorithm can provide. If the algorithm cannot find a feasible solution during operation, the result will be represented by "NaN". According to the data analysis of Table 1, the method of the present invention achieved optimal performance in both cases, surpassing all comparison methods. This is mainly due to the proposed individual adaptive optimization strategy, which effectively promotes the rapid search of the population in the entire target space and approaches the unconstrained Pareto frontier. In addition, the regional co-evolution strategy further improves the distribution of the population, thereby obtaining more optimal feasible planning solutions. In actual production operations, users can make comprehensive use of these solutions according to their own specific circumstances to design the most satisfactory production scheduling planning guide.

[0093] Table 1 Comparison results of the HV index of the present invention and other four advanced evolutionary algorithms for dynamic economic dispatch problems

[0094]

[0095] Embodiment 2

[0096] This embodiment discloses a dynamic economic emission scheduling optimization system based on regional collaboration, including:

[0097] The building module is configured to: construct a dynamic economic emission dispatch model with the goal of minimizing fuel cost and pollution emission and with load demand and power loss as constraints;

[0098] The scheduling optimization module is configured to: solve the dynamic economic emission scheduling model through a multi-objective evolutionary algorithm to obtain a scheduling optimization solution;

[0099] The multi-objective evolutionary algorithm uses an individual adaptive evolutionary strategy to construct a main population and an auxiliary population, and uses a regional collaborative evolutionary strategy to collaboratively optimize the main population and the auxiliary population.

[0100] It should be noted that the above-mentioned construction modules and scheduling optimization modules correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Embodiment 1. It should be noted that the above-mentioned modules, as part of the system, can be executed in a computer system such as a set of computer executable instructions.

[0101] Embodiment 3

[0102] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned dynamic economic emission scheduling optimization method based on regional collaboration are completed.

[0103] Embodiment 4

[0104] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned dynamic economic emission scheduling optimization method based on regional collaboration are completed.

[0105] Embodiment 5

[0106] Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned dynamic economic emission scheduling optimization method based on regional collaboration.

[0107] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0110] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic economic emission scheduling optimization method based on regional coordination, characterized in that: include: A dynamic economic emission dispatch model is constructed with the goal of minimizing fuel costs and pollution emissions and with load demand and power loss as constraints; The dynamic economic emission scheduling model is solved by a multi-objective evolutionary algorithm to obtain a scheduling optimization solution; The multi-objective evolutionary algorithm uses an individual adaptive evolutionary strategy to construct a main population and an auxiliary population, and uses a regional collaborative evolutionary strategy to collaboratively optimize the main population and the auxiliary population.

2. The method for optimizing dynamic economic emission scheduling based on regional coordination according to claim 1, characterized in that: The method of using the individual adaptive evolutionary strategy to construct the main population and the auxiliary population specifically includes: using the individual adaptive evolutionary strategy to optimize each individual in the target space and output the population; and constructing the main population and the auxiliary population according to the population.

3. The method for optimizing dynamic economic emission scheduling based on regional coordination according to claim 2, characterized in that: The individual adaptive evolution strategy is used to optimize each individual in the target space, and the output population specifically includes: Determine the neighborhood of each individual in the target space, optimize each individual in the neighborhood according to the preset decision variable grouping, generate offspring and compare them with the corresponding individuals, and save individuals with smaller target values ​​until each individual enters the stagnation stage; Determine whether the convergence-related variable set and the diversity variable set are both not empty. If so, optimize the diversity variable set; if not, output the population.

4. The method for optimizing dynamic economic emission scheduling based on regional coordination according to claim 2, characterized in that: The construction of the main population and the auxiliary population according to the population specifically includes: Assign the population to the main population and the auxiliary population, and normalize the target vector of the individuals in the auxiliary population according to the minimum value of each target of the individuals in the pre-stored auxiliary population; Multiple reference vectors are generated in the target space, the angles between all reference vectors and the normalized target vector are calculated, and the individuals with the smallest angles are selected to form a subpopulation of the auxiliary population.

5. The method for optimizing dynamic economic emission scheduling based on regional coordination according to claim 1, characterized in that: The method of using the regional co-evolution strategy to coordinately optimize the main population and the auxiliary population specifically includes: The main population produces multiple offspring, and each subpopulation in the auxiliary population produces multiple offspring to form the offspring population; Based on the offspring population, the next generation population of the main population is selected according to the constraint dominance principle; each individual in the offspring population is reallocated to the reference vector, and the next generation population of the auxiliary population is selected according to the constraint relaxation dominance principle.

6. The method for optimizing dynamic economic emission scheduling based on regional coordination according to claim 1, characterized in that: Before using the individual adaptive evolution strategy to construct the main population and auxiliary population, it also includes: Initialize the overall population, preprocess the decision variables in the overall population, and divide the decision variables into a convergence-related variable set and a diversity variable set using the K-means clustering method.

7. A dynamic economic emission scheduling optimization system based on regional coordination, characterized by: include: The building module is configured to: construct a dynamic economic emission dispatch model with the goal of minimizing fuel cost and pollution emission and with load demand and power loss as constraints; The scheduling optimization module is configured to: solve the dynamic economic emission scheduling model through a multi-objective evolutionary algorithm to obtain a scheduling optimization solution; The multi-objective evolutionary algorithm uses an individual adaptive evolutionary strategy to construct a main population and an auxiliary population, and uses a regional collaborative evolutionary strategy to collaboratively optimize the main population and the auxiliary population.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the dynamic economic emission scheduling optimization method based on regional collaboration as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the dynamic economic emission scheduling optimization method based on regional collaboration as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the dynamic economic emission scheduling optimization method based on regional collaboration as described in any one of claims 1 to 6 are implemented.

Images