A multi-objective power supply planning method and related device based on Pareto front shape optimization

Abstract

The application provides a multi-objective power supply planning method based on Pareto front shape optimization and a related device, including obtaining a multi-objective power supply planning model of a project to be planned, and extracting investment decision variables and operation variables from the multi-objective power supply planning model; continuously optimizing solutions composed of the investment decision variables and the operation variables by using a genetic algorithm until the optimization is stopped after a stop condition is met, and a solution set is obtained; selecting a compromise solution meeting a requirement based on a Pareto front shape of the solution set, so as to determine a final multi-objective power supply planning scheme. The application optimizes the investment decision variables and the operation variables by using the genetic algorithm, minimizes conflict relationships between different objectives, selects a balanced compromise solution, and finally determines the multi-objective power supply planning scheme. The method not only considers uniformity and convergence of the Pareto front, but also particularly focuses on influences of the power supply planning on conflict relationships of operation objectives, and improves accuracy and reliability of decision-making.

Description

Technical Field

[0001] The present invention belongs to the technical field of power supply planning, and in particular relates to a multi-objective power supply planning method and related devices based on Pareto front shape optimization. Background Art

[0002] Under the "dual carbon" goals, carbon emission targets urgently need to be factored into power generation planning. However, new power sources with lower carbon emissions may have excessively high construction or operating costs. Balancing carbon emissions and costs is becoming an increasingly important issue in power generation planning. Furthermore, different power generation types have varying unit construction and operating costs. For example, wind power and photovoltaic power primarily incur construction costs, but operating costs are relatively low. In contrast, gas-fired power has lower construction costs but higher operating costs. How to arrange the capacity and location of various power sources to balance the three objectives of construction cost, operating cost, and carbon emissions is a key issue in power generation structure planning.

[0003] Power structure planning, balancing construction costs, operating costs, and carbon emissions, is a typical multi-objective optimization problem. Currently, there are three mainstream approaches: the first is to weight the three objectives (referred to as the "weight method"), thereby constructing a single-objective problem and solving it directly; the second is to embed two of the objectives into the model as constraints (referred to as the "constraint method"), thereby constructing a single-objective problem and solving it directly; and the third is to directly construct the problem as a multi-objective optimization problem (referred to as the "multi-objective method"), solving the Pareto front and finding a compromise solution on the Pareto front as the optimal solution.

[0004] While weighted and constraint methods are computationally simple, both the weight coefficients and constraint coefficients are difficult to determine, which can easily lead to decision-making bias. In contrast, the multi-objective approach characterizes the conflicting relationships between objectives through the Pareto front, which facilitates obtaining a more balanced compromise solution. However, existing multi-objective approaches focus on finding a more uniform, comprehensive, and convergent Pareto front, but overlook a key feature of multi-objective power planning problems: both operating costs and carbon emissions are objective functions generated during operation, but power planning essentially modifies the right-hand side of the constraints of the power system operation problem. Therefore, different planning schemes may structurally affect the conflicting relationships between different operational objectives. Summary of the Invention

[0005] In view of this, the present invention provides a multi-objective power supply planning method and related devices based on Pareto front shape optimization. By leveraging the mathematical feature that "the planning scheme may structurally affect the conflict relationship between different operating objectives", an indicator is proposed to measure the conflict relationship between two different objectives reflected by the shape of the Pareto front, and based on this indicator, a multi-objective power supply planning scheme with a balance of "construction cost-operating cost-carbon emissions" is obtained.

[0006] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0007] In a first aspect, the present invention provides a multi-objective power supply planning method based on Pareto front shape optimization, comprising the following steps:

[0008] Obtain a multi-objective power planning model for the project to be planned, and extract investment decision variables and operation variables from the multi-objective power planning model; investment decision variables are variables that affect the structure of the power system, and operation variables are variables that affect the cost of the power system;

[0009] A genetic algorithm is used to continuously optimize the solutions composed of investment decision variables and operating variables until the stopping condition is met, and a set of solutions is obtained. During the optimization process, the next generation of population is selected with the goal of minimizing the conflict between different objectives reflected by the shape of the Pareto front.

[0010] Based on the Pareto front shape of the solution set, a compromise solution that meets the requirements is selected, and the final multi-objective power supply planning scheme of the project to be planned is determined according to the investment decision variables and operation variables reflected by the compromise solution.

[0011] Furthermore, in selecting the next generation population with the goal of minimizing the conflict relationship between different goals reflected by the shape of the Pareto front, the conflict relationship between different goals is represented by the indicator To measure, the calculation expression of this indicator is as follows:

[0012]

[0013]

[0014] Where, To measure the objective reflected by the shape of the Pareto front and goals indicators of conflictual relationships between them; is the Pearson correlation coefficient; Represents a single optimization objective The obtained standardized objective function value is elements;

[0015] represents the number of points on the Pareto front; represents the i-th Pareto optimal solution The value of the objective function, Indicates the The average value of the objective function on the Pareto front, represents the first Pareto optimal solution of the i-th The value of the objective function, Indicates the The average value of the objective function on the Pareto front; represents the variance of the mth objective function on the Pareto front, Indicates the The variance of the objective function on the Pareto front.

[0016] Furthermore, the calculation expression of the standardized objective function value is as follows:

[0017]

[0018] Where, For a single optimization goal The obtained standardized objective function value, To make the objective function Get the minimum solution, To solve Next, the objective function The true value of Represents the objective function The minimum value of Represents the objective function The maximum acceptable value.

[0019] Furthermore, for the multi-objective power planning model considering construction cost, operation cost and carbon emissions, its expression is as follows:

[0020]

[0021]

[0022] Where, represents the investment decision variable; Represents running variables; Represents the investment cost of building a power source, Represents the operating cost of a power supply, Represents the unit carbon emissions of building a power source, 、 and They represent the investment decision variable coefficient matrix, operation variable coefficient matrix and constraint restriction matrix respectively.

[0023] Furthermore, the genetic algorithm is used to continuously optimize the solutions composed of investment decision variables and operating variables until the stopping condition is met, and a set of solutions is obtained, including:

[0024] Generate the initial population V t , the initial population contains N initial individuals, each individual represents a solution;

[0025] Generate the candidate offspring V' of the current population through crossover and mutation t+1 ;

[0026] With the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, starting from the parent V t and candidate offspring V' t+1 Select the real offspring V t+1 ;

[0027] Determine whether the stopping condition is met;

[0028] If not, continue to generate new candidate offspring through crossover and mutation and re-screen the real offspring;

[0029] If so, use the current child V t+1 As a solution set.

[0030] Furthermore, with the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, t and candidate offspring V' t+1 Select the real offspring V t+1 ,include:

[0031] By comparing the objective function values ​​of any two individuals, the dominance relationship between individuals is obtained, and all individuals are sorted and graded according to the dominance relationship to obtain the individual sets F1, F2 from the best to the second best. 2, ..., F K ;

[0032] Find the kth layer so that from F1 to F k Layer, the sum of the number of individuals exceeds N, and from F1 to F k-1 Layer, the sum of the number of individuals is less than N, from F1 to F k-1 The individuals in the layer are included in the real offspring V t+1 ;

[0033] The number of individuals in the kth layer is Q, and the number of individuals from F1 to F k-1 The total number of individuals in the kth layer is counted as N', and the conflict relationship between different goals reflected by the Pareto front shape of the Q individuals in the kth layer is determined, and N-N' individuals are screened from the Q individuals to the real offspring V with the goal of minimizing the conflict relationship. t+1.

[0034] Furthermore, the stopping condition is that the number of individuals in the F1 layer is N.

[0035] In a second aspect, the present invention provides a multi-objective power supply planning device based on Pareto front shape optimization, comprising:

[0036] The parameter acquisition module is used to obtain the multi-objective power planning model of the project to be planned and extract investment decision variables and operation variables from the multi-objective power planning model; investment decision variables are variables that affect the power system structure, and operation variables are variables that affect the power system cost;

[0037] The optimization module is used to continuously optimize the solutions composed of investment decision variables and operating variables using a genetic algorithm until the stopping condition is met and a set of solutions is obtained. During the optimization process, the next generation of population is selected with the goal of minimizing the conflict between different objectives reflected by the shape of the Pareto front.

[0038] The planning module is used to select a compromise solution that meets the requirements based on the Pareto front shape of the solution set, and to determine the final multi-objective power supply planning scheme for the project to be planned based on the investment decision variables and operation variables reflected in the compromise solution.

[0039] In a third aspect, the present invention provides a computer device, comprising a processor and a memory:

[0040] The memory is used to store computer programs and send instructions of the computer programs to the processor;

[0041] The processor executes the multi-objective power planning method based on Pareto front shape optimization according to the instructions of the computer program.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a multi-objective power supply planning method based on Pareto front shape optimization as in the first aspect is implemented.

[0043] In summary, the present invention provides a multi-objective power planning method and related device based on Pareto front shape optimization, including obtaining a multi-objective power planning model for a project to be planned, and extracting investment decision variables and operating variables from the multi-objective power planning model; the investment decision variables are variables that affect the structure of the power system, and the operating variables are variables that affect the cost of the power system; using a genetic algorithm to continuously optimize the solutions composed of the investment decision variables and operating variables until a stopping condition is met, thereby obtaining a set of solutions; during the optimization process, the next generation population is selected with the goal of minimizing the conflict relationship between different objectives reflected by the Pareto front shape; based on the Pareto front shape of the solution set, a compromise solution that meets the requirements is selected, and the final multi-objective power planning scheme for the project to be planned is determined based on the investment decision variables and operating variables reflected in the compromise solution. The present invention uses a genetic algorithm to optimize the investment decision variables and operating variables to minimize the conflict relationship between different objectives, thereby selecting a balanced compromise solution and ultimately determining the multi-objective power planning scheme. This method not only considers the uniformity and convergence of the Pareto front, but also pays special attention to the impact of power planning on the conflict relationship between operating objectives, thereby improving the accuracy and reliability of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0045] Figure 1 A flowchart of a multi-objective power planning method based on Pareto front shape optimization provided by an embodiment of the present invention;

[0046] Figure 2 A block diagram of a multi-objective power planning device based on Pareto front shape optimization provided by an embodiment of the present invention;

[0047] Figure 3 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 The embodiment of the present invention provides a multi-objective power supply planning method based on Pareto front shape optimization, comprising the following steps:

[0050] S1: Obtain a multi-objective power planning model for the project to be planned, and extract investment decision variables and operation variables from the multi-objective power planning model; investment decision variables are variables that affect the power system structure, and operation variables are variables that affect the power system cost.

[0051] It should be noted that the project to be planned refers to a power planning project involving the construction, expansion or transformation of the power supply system, and the multi-objective power planning model is a mathematical model used to describe multiple objectives (such as cost, environmental impact, reliability, etc.) in power planning problems.

[0052] Investment decision variables are those that influence the structure of the power system, such as the type, capacity, location, and construction time of the generator sets. Operational variables are those that influence the cost of the power system, such as fuel usage, generator output, transmission losses, and carbon emission costs.

[0053] This step clarifies the boundary conditions and objectives of the planning problem by obtaining a multi-objective power planning model. Investment decision variables and operational variables are extracted to further refine the problem and facilitate subsequent optimization.

[0054] S2: Use genetic algorithms to continuously optimize the solutions composed of investment decision variables and operating variables until the stopping conditions are met and a set of solutions is obtained. During the optimization process, the next generation population is selected with the goal of minimizing the conflict relationship between different objectives reflected by the Pareto front shape.

[0055] It should be noted that a genetic algorithm is a global optimization algorithm that uses operations such as selection, crossover, and mutation to generate new generations of solutions, gradually approaching the optimal solution. A genetic algorithm solution is a specific combination of investment decision variables and operating variables, representing a possible power supply planning scenario. Optimization refers to the process of continuously searching and optimizing solutions using a genetic algorithm, aiming to find a set of optimal solutions that simultaneously meet multiple objectives. After multiple iterations, a series of solutions is generated, which typically lie on the Pareto front. In multi-objective optimization, the Pareto front is the set of solutions that cannot further improve any one objective without degrading the others. The geometry of the Pareto front reflects the conflicting relationships between different objectives.

[0056] This step uses a genetic algorithm for optimization, which can find a set of Pareto optimal solutions in complex multi-objective optimization problems. At the same time, minimizing the conflict between different objectives reflected by the shape of the Pareto front during the optimization process helps to find a more balanced solution and avoid excessive bias towards a certain goal.

[0057] S3: Select a compromise solution that meets the requirements based on the Pareto front shape of the solution set, and determine the final multi-objective power supply planning scheme for the project to be planned based on the investment decision variables and operation variables reflected by the compromise solution.

[0058] It should be noted that a compromise solution refers to one or more solutions selected on the Pareto front that achieve the best balance between multiple objectives. When choosing a compromise solution, you can decide based on your actual needs and preferences, for example, you can choose the solution with the lowest total cost or the solution with the lowest carbon emissions.

[0059] This step selects a compromise solution based on the shape of the Pareto front, ensuring the final solution strikes an optimal balance between multiple objectives and avoiding the bias inherent in single-objective optimization. The resulting multi-objective power planning solution provides a concrete basis for implementation in actual power planning projects, helping to achieve both economic and environmental benefits.

[0060] This embodiment provides a multi-objective power planning method based on Pareto front shape optimization. This method clarifies the relationship between the power system structure and operating costs by extracting investment decision variables and operating variables. It then uses a genetic algorithm for global optimization, avoiding the problem of local optimal solutions and ensuring that a better solution set can be found. During the optimization process, the goal is to minimize the conflict relationship between different objectives reflected by the Pareto front shape, ensuring that the generated solution set can better reflect the balance relationship between different objectives. By selecting a compromise solution on the Pareto front, the impact of different planning schemes on the conflict relationship between operating objectives is taken into account, thereby improving the accuracy and reliability of decision-making.

[0061] The method proposed in this paper implements multi-objective power planning based on Pareto front shape optimization. The Pareto front is defined in an M-dimensional standardized objective function space, where M represents the number of objective functions, which can be expressed as:

[0062] (1)

[0063] in, and Represents for any variable , the true value and standardized value of the mth objective function. It can be seen that . represents the minimum value of the mth objective function, Represents the acceptable maximum value of the mth objective function.

[0064] In this paper, the shape of the Pareto front refers to how the Pareto front spreads out in the M-dimensional normalized objective function space. It's worth noting that the Pareto front doesn't spread out evenly across all objective function dimensions. However, the Pareto shape directly influences the selection of the final compromise solution (e.g., the classic method for selecting compromise solutions, the Top-of-Search Order by Approximately Ideal Solutions (TOPSIS)).

[0065] In one embodiment of the present invention, a multi-objective power planning model for the balance of “construction cost-operation cost-carbon emission” can be expressed in a concise form as follows:

[0066] (2)

[0067] (3)

[0068] Where, Represents a 0-1 investment decision variable, including whether to choose to build a new power source at a set of preset locations (i.e., pre-determined geographical locations where power facilities can be built), and what type of power source to choose; Represents operating variables, including generator output, line flow, etc. Represents the investment cost of building a power source, Represents the operating cost of a power supply, Represents the unit carbon emissions of building a power source. 、 and They represent the investment decision variable coefficient matrix, operation variable coefficient matrix and constraint restriction matrix respectively.

[0069] It can be seen that the model is a multi-objective mixed integer programming model. At the same time, if the investment decision variables are given , then the model is simplified to a linear programming model. This means that the decision variables Determines the running variables The feasible domain of 、 The optimal region and spatial distribution of the optimal value affect the shape of the Pareto front and the final compromise solution. In other words, different decisions can alter the conflicting relationships among various objective functions. This means that by changing decisions, it is possible to mitigate conflicts between different objectives, thereby systematically achieving a balanced power planning solution among construction costs, operating costs, and carbon emissions.

[0070] Based on the above analysis, in one embodiment of the present application, an indicator is proposed to measure the conflict relationship between the objectives m and m' reflected by the shape of the Pareto front, as follows:

[0071] (4)

[0072] (5)

[0073] wherein, is the Pearson correlation coefficient; denotes the number of points on the Pareto front; denotes the value of the mth objective function of the ith Pareto optimal solution, denotes the average value of the mth objective function on the Pareto front; denotes the variance of the mth objective function on the Pareto front. If is larger, the positive correlation between the objectives m and m' is stronger, i.e. the conflict is smaller; on the contrary, if is smaller, the negative correlation between the objectives m and m' is stronger, i.e. the conflict is larger. denotes the mth element of the normalized objective function values (i.e. ) obtained by optimizing the objective m individually.

[0074] In a further embodiment of the present application, the normalized objective function values can be expressed as:

[0075] (6)

[0076] It can be seen that, since , the smaller is (the closer to 0), the smaller the conflict between the objectives m and m' is; on the contrary, the larger is (the closer to 1), the larger the conflict between the objectives m and m' is. In summary, the larger is, the larger the conflict between the objectives m and m' is. On the contrary, the smaller is, the smaller the conflict between the objectives m and m' is.

[0077] The indicator about the decision variables is highly nonlinear. Therefore, in one embodiment of the present application, a brand new heuristic multi-objective optimization method, Pareto front shape-incorporated non-dominated sorting genetic algorithm (PFS-NSGA), is proposed to obtain a multi-objective power system planning scheme (e.g., a multi-objective power system planning scheme balancing the construction cost, operation cost, and carbon emission). The PFS-NSGA method generates a new generation of optimization individuals (denoted as V t ) continuously, and mainly achieves the following two objectives:

[0078] 1) making the objective value set (denoted as Ft) constituted by each generation closer to the real Pareto front;

[0079] 2) making the index smaller, thereby systematically optimizing the conflict relationship among multiple objectives;

[0080] The specific steps are as follows:

[0081] Step 1: generating N initial individuals, denoted as V t (t = 1), each individual representing a solution, i.e., Accordingly, the objective function value corresponding to each individual can be obtained according to formula (2). It is worth noting that if each individual does not satisfy the constraint condition listed in formula (3), a penalty term is added to the objective function; then, the standardized objective function value is obtained according to formula (1).

[0082] Step 2: generating the selected offspring V' t+1 of the current population through crossover and mutation;

[0083] Step 3: selecting the real offspring V t+1 from the parent V t and the selected offspring V' t+1 , aiming to minimize the conflict relationship between different objectives reflected by the Pareto front shape;

[0084] Step 4: judging whether the stopping condition is met, if yes, ending the iteration and entering Step 5; otherwise, jumping to Step 2;

[0085] Step 5: taking the objective value set corresponding to the current offspring V t+1 as the final Pareto front obtained, and selecting the final compromise solution according to the preference of the decision maker.

[0086] The prior art solves the multi-objective power source planning problem based on a complicated mass of mixed integer linear sub-problems. The embodiment greatly reduces the number and complexity of the sub-problems to be solved through steps 2-4, thereby improving the solving efficiency and shortening the calculation time.

[0087] In a further embodiment of the application, the basis for screening the offspring in step 3 comprises the following sub-steps:

[0088] (1) By comparing the objective function values of any two individuals, the dominance relationship of the two individuals can be obtained. Further, all individuals are sorted according to their dominance, thereby being divided into different levels, denoted as: F1, F 2, ..., F K . Among them, F1 is the optimal individual set found so far, F2 is the sub-optimal individual set found so far, and so on;

[0089] (2) Find the kth level, such that the sum of the number of individuals from F1 to F k layer is greater than N, and the sum of the number of individuals from F1 to F k-1 layer is less than N, and all individuals from F1 to F k-1 layer are included in the real offspring V t+1 .

[0090] (3) Count the number of individuals in the kth level as Q, and count the total number of individuals from F1 to F k-1 layer as N'. Calculate the index according to formulas (4) and (5) to determine the conflict relationship between different objectives reflected by the shape of the Pareto front of the Q individuals in the kth level, and select N-N' individuals from the Q individuals in the kth level to the real offspring V t+1 .

[0091] The prior art usually optimizes the obtained Pareto front first, and then finds a compromise solution to consider the balance relationship between multiple objectives. The embodiment of the application takes advantage of the mathematical feature that "the planning scheme may affect the conflict relationship between different operation objectives in structure", proposes an index for measuring the conflict relationship between objective m and objective m' reflected by the shape of the Pareto front, and creatively considers the relationship form between multiple objectives in step 3-sub-step (3) in the iteration process. Not only is it beneficial to save calculation time, but also is beneficial to coordinate the conflict relationship between multiple objectives.

[0092] In a further embodiment of the application, the stop condition is that the number of individuals in the F1 layer is N.

[0093] Based on the same inventive concept, an embodiment of the present application further provides a multi-objective power planning device based on Pareto front shape optimization for implementing the multi-objective power planning method based on Pareto front shape optimization. The solution provided by this device is similar to the solution described in the above-mentioned method. Therefore, the specific limitations of the multi-objective power planning device based on Pareto front shape optimization provided below can be found in the above-mentioned limitations of the multi-objective power planning method based on Pareto front shape optimization, and will not be repeated here.

[0094] See also Figure 2 The embodiment of the present invention provides a multi-objective power supply planning device based on Pareto front shape optimization, comprising:

[0095] The parameter acquisition module is used to obtain the multi-objective power planning model of the project to be planned and extract investment decision variables and operation variables from the multi-objective power planning model; investment decision variables are variables that affect the power system structure, and operation variables are variables that affect the power system cost;

[0096] The optimization module is used to continuously optimize the solutions composed of investment decision variables and operating variables using a genetic algorithm until the stopping condition is met and a set of solutions is obtained. During the optimization process, the next generation of population is selected with the goal of minimizing the conflict between different objectives reflected by the shape of the Pareto front.

[0097] The planning module is used to select a compromise solution that meets the requirements based on the Pareto front shape of the solution set, and to determine the final multi-objective power supply planning scheme for the project to be planned based on the investment decision variables and operation variables reflected in the compromise solution.

[0098] Furthermore, in selecting the next generation population with the goal of minimizing the conflict relationship between different goals reflected by the shape of the Pareto front, the conflict relationship between different goals is represented by the indicator To measure, the calculation expression of this indicator is as follows:

[0099]

[0100]

[0101] Where, To measure the objective reflected by the shape of the Pareto front and goals indicators of conflictual relationships between them; is the Pearson correlation coefficient; Represents a single optimization objective The obtained standardized objective function value is elements;

[0102] represents the number of points on the Pareto front; represents the i-th Pareto optimal solution The value of the objective function, Indicates the The average value of the objective function on the Pareto front, represents the i-th Pareto optimal solution The value of the objective function, Indicates the The average value of the objective function on the Pareto front; represents the variance of the mth objective function on the Pareto front, Indicates the The variance of the objective function on the Pareto front.

[0103] Furthermore, the calculation expression of the standardized objective function value is as follows:

[0104]

[0105] Where, For a single optimization goal The obtained standardized objective function value, To make the objective function Get the minimum solution, To solve Next, the objective function The true value of Represents the objective function The minimum value of Represents the objective function The maximum acceptable value.

[0106] Furthermore, for the multi-objective power planning model considering construction cost, operation cost and carbon emissions, its expression is as follows:

[0107]

[0108]

[0109] Where, represents the investment decision variable; Represents running variables; Represents the investment cost of building a power source, Represents the operating cost of a power supply, Represents the unit carbon emissions of building a power source, 、 and They represent the investment decision variable coefficient matrix, operation variable coefficient matrix and constraint restriction matrix respectively.

[0110] Furthermore, the genetic algorithm is used to continuously optimize the solutions composed of investment decision variables and operating variables until the stopping condition is met, and a set of solutions is obtained, including:

[0111] Generate the initial population V t , the initial population contains N initial individuals, each individual represents a solution;

[0112] Generate the candidate offspring V' of the current population through crossover and mutation t+1 ;

[0113] With the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, from the parent V t and candidate offspring V' t+1 Select the real offspring V t+1 ;

[0114] Determine whether the stopping condition is met;

[0115] If not, continue to generate new candidate offspring through crossover and mutation and re-screen the real offspring;

[0116] If so, use the current child V t+1 As a solution set.

[0117] Furthermore, with the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, t and candidate offspring V' t+1 Select the real offspring V t+1 ,include:

[0118] By comparing the objective function values ​​of any two individuals, the dominance relationship between individuals is obtained, and all individuals are sorted and graded according to the dominance relationship to obtain the individual sets F1, F2 from the best to the second best. 2, ..., F K ;

[0119] Find the kth layer so that from F1 to F k Layer, the sum of the number of individuals exceeds N, and from F1 to F k-1 Layer, the sum of the number of individuals is less than N, from F1 to F k-1 The individuals in the layer are included in the real offspring V t+1 ;

[0120] The number of individuals in the kth layer is Q, and the number of individuals from F1 to F k-1The total number of individuals in the kth layer is counted as N', and the conflict relationship between different goals reflected by the Pareto front shape of the Q individuals in the kth layer is determined, and N-N' individuals are screened from the Q individuals to the real offspring V with the goal of minimizing the conflict relationship. t+1 .

[0121] Furthermore, the stopping condition is that the number of individuals in the F1 layer is N.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0123] Reference Figure 3 An embodiment of the present invention also provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, it implements the multi-objective power planning method based on Pareto front shape optimization as described in any one of the above methods.

[0124] The computer device may be a desktop computer, notebook computer, PDA, cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 3 The computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, etc.

[0125] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0126] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the computer device. Furthermore, the memory may include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is about to be output.

[0127] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the multi-objective power supply planning method based on Pareto front shape optimization as described in any one of the above methods is implemented.

[0128] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0129] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0130] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0131] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A multi-objective power planning method based on Pareto front shape optimization, characterized in that: The steps include: Obtaining a multi-objective power planning model for the project to be planned, and extracting investment decision variables and operating variables from the multi-objective power planning model; the investment decision variables are variables that affect the structure of the power system, including the type, capacity, location, and construction time of the generator set; and the operating variables are variables that affect the cost of the power system, including fuel usage, generator output, transmission loss, and carbon emission cost; A genetic algorithm is used to continuously optimize the solutions composed of the investment decision variables and the operating variables until a stopping condition is satisfied, thereby obtaining a set of solutions. During the optimization process, the next generation population is selected with the goal of minimizing the conflict relationship between different objectives reflected by the shape of the Pareto front; Selecting a compromise solution that meets the requirements based on the Pareto front shape of the solution set, and determining a final multi-objective power supply planning scheme for the project to be planned based on the investment decision variables and the operating variables reflected by the compromise solution; In selecting the next generation population with the goal of minimizing the conflict relationship between different goals reflected by the shape of the Pareto front, the conflict relationship between different goals is adopted by the indicator To measure, the calculation expression of this indicator is as follows: ； ； Where, To measure the objective reflected by the shape of the Pareto front and goals indicators of conflictual relationships between them; is the Pearson correlation coefficient; Represents a single optimization objective The obtained standardized objective function value is elements; represents the number of points on the Pareto front; represents the first Pareto optimal solution of the i-th The value of the objective function, Indicates the The average value of the objective function on the Pareto front, represents the first Pareto optimal solution of the i-th The value of the objective function, Indicates the The average value of the objective function on the Pareto front; represents the variance of the mth objective function on the Pareto front, Indicates the The variance of the objective function on the Pareto front; The genetic algorithm is used to continuously optimize the solution composed of the investment decision variables and the operating variables until the stopping condition is met, and a set of solutions is obtained, including: Generate the initial population V t , the initial population includes N initial individuals, each individual represents a solution; Generate the candidate offspring V' of the current population through crossover and mutation t+1 ; With the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, starting from the parent V t and candidate offspring V' t+1 Select the real offspring V t+1 ; Determine whether the stopping condition is met; If not, continue to generate new candidate offspring through crossover and mutation and re-screen the real offspring; If so, use the current child V t+1 as the solution set; With the goal of minimizing the conflict between different objectives reflected by the Pareto front shape, starting from the parent V t and candidate offspring V' t+1 Select the real offspring V t+1 ,include: By comparing the objective function values ​​of any two individuals, the dominance relationship between the individuals is obtained, and all individuals are sorted and graded according to the dominance relationship to obtain the individual sets F1, F2 from the best to the second best. 2, ..., F K ; Find the kth layer so that from F1 to F k Layer, the sum of the number of individuals exceeds N, and from F1 to F k-1 Layer, the sum of the number of individuals is less than N, from F1 to F k-1 The individuals in the layer are included in the real offspring V t+1 ; The number of individuals in the kth layer is Q, and the number of individuals from F1 to F k-1 The total number of individuals in the kth layer is counted as N', and the conflict relationship between different goals reflected by the Pareto front shape of the Q individuals in the kth layer is determined, and N-N' individuals are screened from the Q individuals to the real offspring V with the goal of minimizing the conflict relationship. t+1 .

2. The multi-objective power supply planning method based on Pareto front shape optimization according to claim 1 is characterized in that: The calculation expression of the standardized objective function value is as follows: ； Where, For a single optimization goal The obtained standardized objective function value, To make the objective function Get the minimum solution, To solve Next, the objective function The true value of Represents the objective function The minimum value of Represents the objective function The maximum acceptable value.

3. The multi-objective power supply planning method based on Pareto front shape optimization according to claim 1, characterized in that: The multi-objective power planning model considering construction cost, operation cost and carbon emission is expressed as follows: ； ； Where, represents the investment decision variable; Represents running variables; Represents the investment cost of building a power source, Represents the operating cost of a power supply, Represents the unit carbon emissions of building a power source, 、 and They represent the investment decision variable coefficient matrix, operation variable coefficient matrix and constraint restriction matrix respectively.

4. The multi-objective power supply planning method based on Pareto front shape optimization according to claim 1, characterized in that: The stopping condition is that the number of individuals in the F1 layer is N.

5. A multi-objective power planning device based on Pareto front shape optimization, characterized in that: A multi-objective power supply planning method based on Pareto front shape optimization according to any one of claims 1 to 4 is implemented, comprising: A parameter acquisition module is used to obtain a multi-objective power planning model for the project to be planned, and to extract investment decision variables and operating variables from the multi-objective power planning model; the investment decision variables are variables that affect the structure of the power system, and the operating variables are variables that affect the cost of the power system; An optimization module is used to continuously optimize the solutions composed of the investment decision variables and the operating variables using a genetic algorithm until a stopping condition is met, thereby obtaining a set of solutions; during the optimization process, the next generation population is selected with the goal of minimizing the conflict relationship between different objectives reflected by the shape of the Pareto front; A planning module is used to select a compromise solution that meets the requirements based on the Pareto front shape of the solution set, and to determine the final multi-objective power supply planning scheme for the project to be planned based on the investment decision variables and the operating variables reflected by the compromise solution.

6. A computer device, characterized in that: The device includes a processor and a memory: The memory is used to store the computer program and send instructions of the computer program to the processor; The processor executes the multi-objective power supply planning method based on Pareto front shape optimization according to any one of claims 1 to 4 according to the instructions of the computer program.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a multi-objective power supply planning method based on Pareto front shape optimization according to any one of claims 1 to 4.

Images