High-dimensional multi-target power grid operation optimization method and system based on adaptive vector

Abstract

The invention discloses a high-dimensional multi-target power grid operation optimization method and system based on an adaptive vector. The method comprises the following steps: collecting power grid operation data; determining an optimization target, and constructing a power grid optimization model; determining a multi-objective function of a multi-objective optimization algorithm according to the demand of the power production scene; and solving an optimization problem by using a high-dimensional multi-objective optimization algorithm based on an adaptive reference vector. The method is based on a high-dimensional multi-objective optimization method for balancing power grid supply and demand, operation cost, environmental friendliness and the like, and aims at achieving unification of economical efficiency, stability and environmental friendliness of power grid operation. Effective operation of the power grid is achieved, the utilization efficiency of energy is improved, the operation target of the power grid is jointly optimized, and the overall utility is maximized. The target weight and the scheduling strategy are dynamically adjusted to ensure the flexibility and adaptability of power grid operation; important support is provided for efficient operation of an intelligent power grid, and an electric power system is promoted to develop towards the economic, environment-friendly and reliable direction.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a high-dimensional multi-objective grid operation optimization method and system based on an adaptive vector. Background Art

[0002] In recent years, the construction of intelligent power systems has been gradually accelerated, and the operating efficiency of power systems has also been significantly improved. However, with the progress and development of society, the demand for industrial and domestic electricity is continuing to rise, which has brought huge challenges to the grid dispatching of power systems. At the same time, the addition of various new energy equipment has also made the grid dispatching work more complicated. The emergence of the above factors has put forward higher requirements for the operation mode of the power grid. In summary, the operation of the power grid needs to meet the requirements of low operating cost, environmental friendliness, high operating reliability, strong power supply stability, etc. However, the existing single-objective power grid operation mode optimization method can only optimize a certain aspect, and most of the multi-objective power grid operation mode optimization methods can only optimize the operation mode on 2 to 3 objectives, and it is difficult to optimize the above four aspects at the same time. Therefore, it is necessary to provide a power grid operation method optimization method that takes into account 4 or more objectives. In solving the problem of intelligent coordinated operation optimization in smart grids, power grid optimization has the characteristics of multiple optimization objectives, high conflict and large scale, so it is necessary to consider multiple optimization objectives to balance resource coordination. High-dimensional multi-objective optimization has become a research focus. To address this challenge, researchers need to design innovative algorithms and methods to effectively solve resource allocation and intelligent computing problems in smart grids, achieve efficient utilization of grid resources and optimized management of system operations.

[0003] It is necessary to comprehensively consider the operation characteristics of the power grid and the application of smart grid technology in optimized operation to find effective solutions to optimize the operation efficiency and effect. Although many optimization methods have been applied in the fields of microgrids and new energy power grids, the existing single-objective optimization methods cannot simultaneously optimize four high-dimensional objectives. It is impossible to take into account cost, environmental pollution, reliability and stability. Therefore, a high-dimensional optimization algorithm is needed to optimize the operation methods of the power grid. Improve the reliability and stability of the power grid. At the same time, develop new energy and environmentally friendly power grid power operation methods. Improve the efficiency of power grid operation and save operating costs. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing single-objective optimization method cannot optimize four high-dimensional objectives at the same time, and cannot take into account cost, environmental pollution, reliability and stability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a high-dimensional multi-objective power grid operation optimization method based on adaptive vectors, comprising:

[0007] Collecting grid operation data;

[0008] Determine the optimization target and construct the power grid optimization model;

[0009] Determine the multi-objective function of the multi-objective optimization algorithm according to the needs of the power production scenario;

[0010] A high-dimensional multi-objective optimization algorithm based on adaptive reference vector is used to solve the optimization problem.

[0011] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, wherein: the determination of the optimization target includes, the optimization target formula is expressed as:

[0012] Min:F(x)=[f1(x),f2(x),...,f m (x)]

[0013] Max:R(x)=[r1(x),r2(x),...,r s (x)]

[0014] Subject to:g i (x)≤0,i=1,2,...,p

[0015] h j (x)=0,j=1,2,...,q

[0016] Where x=(x1,x2,...,x n ) represents n-dimensional decision variables; F(x) and R(x) contain m+s optimization objective functions, representing different aspects of grid coordinated control; g i (x) represents an inequality constraint; h j (x) represents an equality constraint, which limits the value range of the optimization variable.

[0017] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, the power grid optimization model includes the maximum and minimum output power limits of each generator set, which are expressed as:

[0018] P min <P<P max

[0019] Assuming the total demand of the power grid is D, considering the loss, the supply and demand balance is expressed as:

[0020]

[0021] The total cost of grid operation is composed of all generators. The efficiency of the generator set decreases as the output power increases. The objective function is expressed as:

[0022]

[0023] Where f1(x) represents the grid operation cost; P i represents the output power of the i-th generator set; establish the cost minimization grid optimization problem; a i , b i 、c i represents a constant coefficient;

[0024] Considering the output power, volatility of renewable energy, safe and stable operation of the power grid, and spare capacity; establish a power grid optimization problem to minimize carbon emissions; the carbon emission function is expressed as the sum of the carbon emissions of each power source, where the carbon emissions of each power source are expressed as the sum of the products of its output power and the carbon emission coefficient per unit of power generation. The carbon emission function formula is expressed as:

[0025]

[0026] Where f2(x) represents the carbon emissions during the operation of the power grid; e i It represents the carbon emission coefficient per unit of electricity generated by each power generation source; by solving the optimization problem, the optimal control parameters are found to minimize the carbon emissions of the power grid.

[0027] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, the requirements of the power production scenario include establishing a reliability index for power grid operation and establishing a reliability maximization objective function, which is expressed as follows:

[0028]

[0029] Among them, R Pi represents the spare capacity of generator set i; R Rj represents the reserve ratio of transmission line j; establish the stability maximization objective function, and simplify the frequency regulation control of the generator set into a linear relationship, that is, when the grid frequency f deviates from the reference value f ref When the generator set adjusts the power output P i ;

[0030] The power adjustment formula is expressed as:

[0031] ΔP i =K pfi (f rgf -f)

[0032] The voltage control of the transmission line is simplified to a linear relationship, that is, when the voltage V j Deviates from its reference value V ref When the voltage is adjusted, the voltage adjustment formula is expressed as:

[0033] ΔV j =K pfi (V ref -V)

[0034] The stability of the power grid is measured by a comprehensive indicator that includes the weighted sum of frequency deviation and voltage deviation.

[0035] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, the multi-objective function of the multi-objective optimization algorithm includes: establishing a power grid optimization problem with maximum stability; optimizing the stability of the power grid by adjusting the frequency modulation control of the generator set and the voltage control of the transmission line; the stability objective function formula is expressed as:

[0036]

[0037] A multi-objective power grid operation mode optimization problem model is constructed for minimizing costs, minimizing carbon emissions, and maximizing reliability and stability. The formula is expressed as follows:

[0038]

[0039] P min <P<P max

[0040] P res (t)+P cdg (t)+P es (t)+P pcc (t) = P load (t)

[0041] Among them, P res (t) represents the power of renewable energy at time t; P cdg (t) represents the power of the controllable distributed generation at time t, P es (t) represents the power of the energy storage system at time t; P pcc (t) represents the exchange power with the large power grid.

[0042] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, wherein: the adaptive reference vector includes generating a descendant population set O by using a population reproduction operation of a parent population P;

[0043] Generate a descendant population O containing N individuals by using simulated binomial crossover SBX and polynomial mutation cycles; perform N / 2 rounds of the following operations to generate N descendant individuals to form a descendant set O:

[0044] Randomly select individuals from 2 parent populations p and Generate two crossover offspring c1 and c2 by crossover. The crossover offspring c1 and c2 change the value of the decision variable of the crossover offspring within the mutation range according to the given probability. The crossover offspring o1 and o2 that have undergone polynomial mutation enter the offspring population O.

[0045] The SBX operator simulates the crossover operator of single-point binary crossover, selecting a total of N parent individuals to generate N crossover offspring c:

[0046]

[0047] Among them, β satisfies the Beta distribution and is dynamically determined by the environmental factor η according to the following formula: η represents a custom parameter; the decision variables of each bit in c1 and c2 formed after the crossover operation are mutated within a given range based on the probability ω, and the formula is expressed as:

[0048] x1 c =x1 c +Δ j

[0049]

[0050] in, represents the decision variable in the crossover offspring c, Δ j Indicates that after polynomial mutation, the mutation value is increased based on a certain probability, μ j Represents a random number;

[0051] The APD distance is defined as:

[0052] d t,i,j =(1+P(θ t,i,j ))·||f′ t,i ||

[0053] P is the penalty function formula about θ:

[0054]

[0055] Among them, α represents the user-defined parameter, γ represents the t ,j forms the angle of other reference vectors with the smallest angle.

[0056] As a preferred solution of the high-dimensional multi-objective power grid operation optimization method based on adaptive vectors described in the present invention, wherein: the high-dimensional multi-objective optimization algorithm includes performing an initialization operation, taking cost minimization, carbon emission minimization, and reliability and stability maximization as optimization objective functions;

[0057] Initialize the population p = [x1, x2, ..., x N ], where x i Represents individuals in the population, N is the number of individuals in the population; generate N reference vector sets V that are uniformly distributed in the target space.

[0058] Cyclic population reproduction operation: The purpose of the population reproduction operation is to use the parent population P to generate the offspring population set O;

[0059] Merge population operation: The merge population operation merges the parent population p with the child population O to generate a merged population Q;

[0060] The environmental selection operation selects N high-quality individuals from the merged population Q to form the next generation population p;

[0061] Reference vector adaptive operation uses the selected high-quality solution set to guide the reference vector generation, realize dynamic adaptive adjustment of the reference vector, and improve optimization efficiency;

[0062] Iterate the loop until the termination condition, and repeat the cycle of population reproduction to environment selection until the termination condition is met and the number of fitness evaluations reaches the threshold.

[0063] A high-dimensional multi-objective power grid operation optimization system based on an adaptive vector using any method described in the present invention comprises:

[0064] Data input module, collects and pre-processes power grid operation data;

[0065] The optimization problem construction module constructs multi-objective optimization problems based on preprocessed data and grid requirements;

[0066] The optimization algorithm execution module executes the optimization algorithm, generates and optimizes the population, iterates until the optimal solution set is obtained, and solves the high-dimensional multi-objective power grid operation optimization problem;

[0067] The result analysis and decision support module analyzes the optimization results, provides decision support, and visualizes the results.

[0068] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0069] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0070] Beneficial effects of the present invention: A high-dimensional multi-objective optimization method based on balancing the supply and demand of the power grid, operating costs, environmental friendliness and other multiple requirements is intended to achieve the unity of economy, stability and environmental protection of power grid operation. By designing a collaborative optimization algorithm, the effective operation of the power grid is achieved to improve the efficiency of energy utilization, and the operation goals of the power grid are jointly optimized to maximize the overall utility. At the same time, a dynamic adaptive mechanism is introduced to enable the system to dynamically adjust the target weights and scheduling strategies according to dynamic changes such as the operating status of the power grid, market demand, and fluctuations in renewable energy, so as to ensure the flexibility and adaptability of the power grid operation; provide important support for the efficient operation of the smart grid, and promote the development of the power system in an economical, environmentally friendly and reliable direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0072] Figure 1 An overall flow chart of a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector provided by the first embodiment of the present invention;

[0073] Figure 2 An explanation diagram of high-dimensional solution space correlation vector operations for the same task request in a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector provided by the first embodiment of the present invention;

[0074] Figure 3 A schematic flow chart of a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector provided in the first embodiment of the present invention;

[0075] Figure 4 A reliability comparison diagram of a multi-objective method of a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector provided by a second embodiment of the present invention;

[0076] Figure 5 A stability comparison diagram of a multi-objective method of a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector provided by a second embodiment of the present invention;

[0077] Figure 6A cost comparison diagram of a multi-objective method for optimizing power grid operation based on an adaptive vector in a high-dimensional multi-objective manner provided by a second embodiment of the present invention;

[0078] Figure 7 A carbon emission comparison chart of a multi-objective method for optimizing power grid operation in a high-dimensional multi-objective manner based on an adaptive vector is provided in accordance with the second embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0080] Example 1

[0081] Reference Figure 1-Figure 3 , is an embodiment of the present invention, and provides a high-dimensional multi-objective power grid operation optimization method based on an adaptive vector, comprising:

[0082] S1: Collect grid operation data.

[0083] Furthermore, by rationally dispatching power generation units, optimizing transmission line configuration, and increasing the proportion of renewable energy, costs can be reduced, stability can be improved, and greenhouse gas emissions can be reduced, thereby achieving efficient, stable, and environmentally friendly grid operation.

[0084] Furthermore, the optimization objective is determined, and the optimization objective formula is expressed as:

[0085] Min:F(x)=[f1(x),f2(x),...,f m (x)]

[0086] Max:R(x)=[r1(x),r2(x),...,r s (x)]

[0087] Subject to:g i (x)≤0,i=1,2,...,p

[0088] h j (x)=0,j=1,2,...,q

[0089] Where x=(x1,x2,...,x n ) represents n-dimensional decision variables; F(x) and R(x) contain m+s optimization objective functions, representing different aspects of grid coordinated control; gi (x) represents an inequality constraint; h j (x) represents an equality constraint, which limits the value range of the optimization variable.

[0090] It should be noted that the inequality constraints may include capacity limits of transmission lines, maximum output limits of generator sets, etc. These equality constraints may include node voltage balance equations, power balance equations, etc.

[0091] S2: Determine the optimization target and construct the power grid optimization model.

[0092] Furthermore, the grid optimization model includes the maximum and minimum output power limits of each generator set, expressed as:

[0093] P min <P<P max

[0094] Furthermore, assuming that the total demand of the power grid is D, considering the loss, the supply and demand balance is expressed as:

[0095]

[0096] Furthermore, the total cost of grid operation is composed of all generators, and the efficiency of the generator sets decreases as the output power increases. The objective function is expressed as:

[0097]

[0098] Where f1(x) represents the grid operation cost; P i represents the output power of the i-th generator set; establish the cost minimization grid optimization problem; a i , b i 、c i represents a constant coefficient.

[0099] Furthermore, considering the output power, volatility of renewable energy, safe and stable operation of the power grid, and spare capacity, a power grid optimization problem with carbon emission minimization is established; the carbon emission function is expressed as the sum of the carbon emissions of each power source, where the carbon emission of each power source is expressed as the sum of the product of its output power and the carbon emission coefficient per unit of power generation. The carbon emission function formula is expressed as:

[0100]

[0101] Where f2(x) represents the carbon emissions during the operation of the power grid; e i It represents the carbon emission coefficient per unit of electricity generated by each power generation source; by solving the optimization problem, the optimal control parameters are found to minimize the carbon emissions of the power grid.

[0102] It should be noted that the multi-objective optimization grid operation method is modeled by comprehensively considering multiple objectives. Grid operation involves multiple stakeholders, such as power companies, consumers, environmental protection agencies, etc. These interests may conflict, for example, reducing costs may increase environmental pollution.

[0103] S3: Determine the multi-objective function of the multi-objective optimization algorithm according to the requirements of the power production scenario.

[0104] Furthermore, the requirements of the power production scenario include establishing reliability indicators for power grid operation and establishing a reliability maximization objective function, which is expressed as follows:

[0105]

[0106] Among them, R Pi represents the spare capacity of generator set i; R Rj Represents the reserve ratio of transmission line j. Establishing the stability maximization objective function, the frequency regulation control of the generator set is simplified to a linear relationship, that is, when the grid frequency f deviates from the reference value f ref When the generator set adjusts the power output P i .

[0107] Furthermore, the power adjustment formula is expressed as:

[0108] ΔP i =K pfi (f rgf -f)

[0109] Furthermore, the voltage control of the transmission line is simplified to a linear relationship, that is, when the voltage V j Deviates from its reference value V ref When the voltage is adjusted, the voltage adjustment formula is expressed as:

[0110] ΔV j =K pfi (V ref -V)

[0111] Furthermore, the stability of the power grid is measured by a comprehensive indicator that includes the weighted sum of frequency deviation and voltage deviation.

[0112] Furthermore, the multi-objective function of the multi-objective optimization algorithm includes establishing a power grid optimization problem that maximizes stability; optimizing the stability of the power grid by adjusting the frequency control of the generator set and the voltage control of the transmission line; the stability objective function formula is expressed as:

[0113]

[0114] Furthermore, a multi-objective power grid operation mode optimization problem model is constructed for minimizing costs, minimizing carbon emissions, and maximizing reliability and stability. The formula is expressed as follows:

[0115]

[0116] P min <P<P max

[0117] P res (t)+P cdg (t)+P es (t)+P pcc (t) = P load (t)

[0118] Among them, P res (t) represents the power of renewable energy at time t; P cdg (t) represents the power of the controllable distributed generation at time t, P es (t) represents the power of the energy storage system at time t; P pcc (t) represents the exchange power with the large power grid.

[0119] It should be noted that through multi-objective optimization, a balance can be achieved between different stakeholders to maximize the overall benefits. Multi-objective optimization can better reflect the complexity and dynamics of the power grid system, thereby improving the robustness of the system. When the power grid faces uncertainty and changes, multi-objective optimization can help the system better adapt to and respond to changes in the external environment.

[0120] S4: Use a high-dimensional multi-objective optimization algorithm based on adaptive reference vector to solve the optimization problem.

[0121] For further reference, Figure 2 , Figure 2 It is to improve the high-dimensional optimization algorithm in the high-dimensional solution space correlation vector operation explanation diagram. Figure 1 It can be seen that the algorithm proposed in the present invention associates individuals with reference vectors by calculating the angular distance. If Θ2 is less than Θ1, the individual is associated with vector V3. The adaptive reference vector includes generating a descendant population set O by using a population reproduction operation on a parent population P.

[0122] Furthermore, a simulated binomial crossover SBX and a polynomial mutation cycle are used to generate a descendant population O containing N individuals; the following operations are performed N / 2 rounds to generate N descendant individuals to form an descendant set O.

[0123] Furthermore, we randomly select two individuals from the parent population p. and Two crossover offspring c1 and c2 are generated by crossover. The crossover offspring c1 and c2 change the values ​​of the decision variables of the crossover offspring within the mutation range according to the given probability. The crossover offspring o1 and o2 that have undergone polynomial mutation enter the offspring population O.

[0124] Furthermore, the SBX operator simulates the crossover operator of single-point binary crossover, selecting a total of N parent individuals to generate N crossover offspring c:

[0125]

[0126] Among them, β satisfies the Beta distribution and is dynamically determined by the environmental factor η according to the following formula: η represents a custom parameter; the decision variables of each bit in c1 and c2 formed after the crossover operation are mutated within a given range based on the probability ω, and the formula is expressed as:

[0127] x1 c =x1 c +Δ j

[0128]

[0129] in, represents the decision variable in the crossover offspring c, Δ j Indicates that after polynomial mutation, the mutation value is increased based on a certain probability, μ j Represents a random number.

[0130] Furthermore, the APD distance is defined as:

[0131] d t,i,j＝ (1+P(θ t,i,j ))·||f′ t,i ||

[0132] Furthermore, P is the penalty function formula for θ:

[0133]

[0134] Among them, α represents the user-defined parameter, γ represents the t ,j forms the angle of other reference vectors with the smallest angle.

[0135] Furthermore, high-dimensional multi-objective optimization algorithms include, for example Figure 3 As shown, an initialization operation is performed, with cost minimization, carbon emission minimization, and reliability and stability maximization as the optimization objective function.

[0136] Furthermore, the population p = [x1, x2, ..., xN] is initialized, where xi represents an individual in the population and N is the number of individuals in the population; a set of N reference vectors V uniformly distributed in the target space is generated;

[0137] Furthermore, the cyclic population reproduction operation: the purpose of the population reproduction operation is to use the parent population P to generate the offspring population set O.

[0138] Furthermore, the merge population operation: the merge population operation merges the parent population p with the child population O to generate a merged population Q.

[0139] Furthermore, the environmental selection operation selects N high-quality individuals from the merged population Q to form the next generation population p.

[0140] Furthermore, the reference vector adaptive operation utilizes the selected high-quality solution set to guide the reference vector generation, realizes the dynamic adaptive adjustment of the reference vector, and improves the optimization efficiency.

[0141] Furthermore, the iteration loop is repeated until the termination condition, and the cycle of population reproduction to environment selection is repeated until the termination condition is met and the number of fitness evaluations reaches a threshold.

[0142] Furthermore, the reference vector is adaptively operated: the selected normalized Pareto quality solution set is used to guide the reference vector to be adaptively adjusted. The next reference vector generation method is calculated by the maximum and minimum values ​​of the objective function among individuals in the quality population. The formula is as follows:

[0143]

[0144] Furthermore, the reference vector is dynamically and adaptively adjusted to guide the reference vector close to the direction vector of the objective function optimization. Iteration loop until termination condition: Repeat until the termination condition is met, that is, the number of fitness evaluations reaches 200,000 times.

[0145] Furthermore, the improved high-dimensional optimization algorithm uses a reference vector to guide the evolution of individuals. The reference vector is a set of vectors orthogonal to multiple targets and is used to guide the search space. For each individual x in the population, the distance between it and the reference vector is calculated. The distance is usually expressed in terms of angle distance, etc. The smaller the distance, the closer the individual is to a certain reference vector, that is, the better the performance on a certain target. The individual is selected based on the distance between the individual and the reference vector. The individual with the smallest distance is usually selected as the candidate solution for the next generation of evolution.

[0146] It should be noted that the candidate solutions are updated through evolutionary operations such as crossover and mutation to generate the next generation of individuals. At the same time, the reference vector is also updated according to the evolution of the individuals to adapt to the changes in the search space. The selection and evolution operations are repeated until the stop condition is met, such as reaching the maximum number of iterations or reaching the convergence standard. High-dimensional optimization algorithms can effectively optimize multiple objectives and find the Pareto optimal solution set, providing a comprehensive solution for power grid optimization.

[0147] On the other hand, this embodiment also provides a high-dimensional multi-objective power grid operation optimization system based on an adaptive vector, which includes:

[0148] Data input module collects and preprocesses power grid operation data.

[0149] The optimization problem building module constructs multi-objective optimization problems based on the preprocessed data and grid requirements.

[0150] The optimization algorithm execution module executes the optimization algorithm, generates and optimizes the population, iterates until the optimal solution set is obtained, and solves the high-dimensional multi-objective power grid operation optimization problem.

[0151] The result analysis and decision support module analyzes the optimization results, provides decision support, and visualizes the results.

[0152] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0153] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0154] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0155] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0156] Example 2

[0157] Reference Figure 4-Figure 7 , which is an embodiment of the present invention, provides a high-dimensional multi-objective power grid operation optimization method based on adaptive vectors. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0158] The high-dimensional multi-objective power grid operation mode optimization method based on adaptive reference vector specifically includes the following steps: first, the population is initialized; second, the population is propagated to generate the child population O using the parent population P, the parent population and the child population are merged to generate the population Q, the environment of the population Q is selected, and the high-quality population is selected to guide the adaptive adjustment of the reference vector; and whether the termination condition is met to jump out of the cycle to obtain the Pareto solution set.

[0159] In the experiment, we compared the traditional benchmark power grid operation method and the power grid operation method optimized by the single-objective particle swarm algorithm. The high-dimensional multi-objective power grid operation mode optimization method based on adaptive reference vector proposed in this paper is superior to the collaborative optimization method and the single-objective optimization algorithm. At the same time, we also compared the multi-objective NSGA-II optimization algorithm. After experimental comparison, the high-dimensional multi-objective power grid operation mode optimization method based on adaptive reference vector proposed in this paper can better combine multiple objective functions. It is superior to the power grid operation method optimized by NSGA-II in terms of stability and reliability.

[0160] Figure 4 It shows that the reliability of the multi-objective method considered in this invention is better than that of the single-objective optimization methods, the greedy algorithm and the particle swarm algorithm, and the multi-objective optimization algorithm proposed in this paper is also better than the multi-objective NSGA-II algorithm and the traditional collaborative optimization method; Figure 5 It shows that the stability of the multi-objective method considered in this invention is better than that of the single-objective optimization methods, the greedy algorithm and the particle swarm algorithm, and the multi-objective optimization algorithm proposed in this paper is also better than the multi-objective NSGA-II algorithm and the traditional collaborative optimization method; Figure 6 and Figure 7 It shows that the method proposed in the present invention is lower than other comparative algorithms including single-objective particle swarm algorithm and greedy algorithm in terms of cost and carbon emission indicators. It is also lower than the multi-objective optimization NSGA-II algorithm in terms of cost and carbon emission indicators, and is better than the traditional collaborative optimization method.

[0161] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A high-dimensional multi-objective power grid operation optimization method based on adaptive vectors, characterized in that: include: Collecting grid operation data; Determine the optimization target and construct the power grid optimization model; Determine the multi-objective function of the multi-objective optimization algorithm according to the needs of the power production scenario; A high-dimensional multi-objective optimization algorithm based on adaptive reference vector is used to solve the optimization problem.

2. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 1, characterized in that: Determining the optimization target includes, the optimization target formula is expressed as: Min:F(x)=[f1(x),f2(x),...,f m (x)] Max:R(x)=[r1(x),r2(x),...,r s (x)] Subject to:g i (x)≤0,i=1,2,...,p h j (x)=0,j=1,2,...,q Where x=(x1,x2,...,x n ) represents n-dimensional decision variables; F(x) and R(x) contain m+s optimization objective functions, representing different aspects of grid coordinated control; g i (x) represents an inequality constraint; h j (x) represents an equality constraint, which limits the value range of the optimization variable.

3. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 2, characterized in that: The grid optimization model includes the maximum and minimum output power limits of each generator set, expressed as: P min <P<P max Assuming the total demand of the power grid is D, considering the loss, the supply and demand balance is expressed as: The total cost of grid operation is composed of all generators. The efficiency of the generator set decreases as the output power increases. The objective function is expressed as: Where f1(x) represents the grid operation cost; P i represents the output power of the i-th generator set; establish the cost minimization grid optimization problem; a i , b i 、c i represents a constant coefficient; Considering the output power, volatility of renewable energy, safe and stable operation of the power grid, and spare capacity; establish a power grid optimization problem to minimize carbon emissions; the carbon emission function is expressed as the sum of the carbon emissions of each power source, where the carbon emissions of each power source are expressed as the sum of the products of its output power and the carbon emission coefficient per unit of power generation. The carbon emission function formula is expressed as: Where f2(x) represents the carbon emissions during the operation of the power grid; e i It represents the carbon emission coefficient per unit of electricity generated by each power generation source; by solving the optimization problem, the optimal control parameters are found to minimize the carbon emissions of the power grid.

4. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 3, characterized in that: The requirements of the power production scenario include establishing reliability indicators for power grid operation and establishing a reliability maximization objective function, which is expressed as follows: Among them, R Pi represents the spare capacity of generator set i; R Rj represents the reserve ratio of transmission line j; establish the stability maximization objective function, and simplify the frequency regulation control of the generator set into a linear relationship, that is, when the grid frequency f deviates from the reference value f ref When the generator set adjusts the power output P i ; The power adjustment formula is expressed as: ΔP i =K pfi (f rgf -f) The voltage control of the transmission line is simplified to a linear relationship, that is, when the voltage V j Deviates from its reference value V ref When the voltage is adjusted, the voltage adjustment formula is expressed as: ΔV j =K pfi (V ref -V) The stability of the power grid is measured by a comprehensive indicator that includes the weighted sum of frequency deviation and voltage deviation.

5. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 4, characterized in that: The multi-objective function of the multi-objective optimization algorithm includes: establishing a power grid optimization problem for maximizing stability; optimizing the stability of the power grid by adjusting the frequency control of the generator set and the voltage control of the transmission line; The stability objective function formula is expressed as: A multi-objective power grid operation mode optimization problem model is constructed for minimizing costs, minimizing carbon emissions, and maximizing reliability and stability. The formula is expressed as follows: subject: P min <P<P max P res (t)+P cdg (t)+P es (t)+P pcc (t)=P load (t) Among them, P res (t) represents the power of renewable energy at time t; P cdg (t) represents the power of the controllable distributed generation at time t, P es (t) represents the power of the energy storage system at time t; P pcc (t) represents the exchange power with the large power grid.

6. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 5, characterized in that: The adaptive reference vector includes generating a descendant population set O by using a population reproduction operation on a parent population P; Generate a descendant population O containing N individuals by using simulated binomial crossover SBX and polynomial mutation cycles; perform N / 2 rounds of the following operations to generate N descendant individuals to form a descendant set O: Randomly select individuals from 2 parent populations p and Generate two crossover offspring c1 and c2 by crossover. The crossover offspring c1 and c2 change the value of the decision variable of the crossover offspring within the mutation range according to the given probability. The crossover offspring o1 and o2 that have undergone polynomial mutation enter the offspring population O. The SBX operator simulates the crossover operator of single-point binary crossover, selecting a total of N parent individuals to generate N crossover offspring c: Among them, β satisfies the Beta distribution and is dynamically determined by the environmental factor η according to the following formula: η represents a custom parameter; the decision variables of each bit in c1 and c2 formed after the crossover operation are mutated within a given range based on the probability ω, and the formula is expressed as: x1 c =x1 c +Δ j in, represents the decision variable in the crossover offspring c, Δ j Indicates that after polynomial mutation, the mutation value is increased based on a certain probability, μ j Represents a random number; The APD distance is defined as: d t,i,j =(1+P(θ t,i,j ))·||f′ t,i || P is the penalty function formula about θ: Among them, α represents the user-defined parameter, and γ represents the t ,j forms the angle of other reference vectors with the smallest angle.

7. The high-dimensional multi-objective power grid operation optimization method based on adaptive vector according to claim 6, characterized in that: The high-dimensional multi-objective optimization algorithm includes performing an initialization operation, taking cost minimization, carbon emission minimization, and reliability and stability maximization as optimization objective functions; Initialize the population p = [x1, x2, ..., x N ], where x i represents the individuals in the population, and N is the number of individuals in the population; generate N reference vector sets V that are evenly distributed in the target space; Cyclic population reproduction operation: The purpose of the population reproduction operation is to use the parent population P to generate the offspring population set O; Merge population operation: The merge population operation merges the parent population p with the child population O to generate a merged population Q; The environmental selection operation selects N high-quality individuals from the merged population Q to form the next generation population p; Reference vector adaptive operation uses the selected high-quality solution set to guide the reference vector generation, realize dynamic adaptive adjustment of the reference vector, and improve optimization efficiency; Iterate the loop until the termination condition, and repeat the cycle of population reproduction to environment selection until the termination condition is met and the number of fitness evaluations reaches the threshold.

8. A high-dimensional multi-objective power grid operation optimization system based on an adaptive vector using the method according to any one of claims 1 to 7, characterized in that: Data input module, collects and pre-processes power grid operation data; The optimization problem construction module constructs multi-objective optimization problems based on preprocessed data and grid requirements; The optimization algorithm execution module executes the optimization algorithm, generates and optimizes the population, iterates until the optimal solution set is obtained, and solves the high-dimensional multi-objective power grid operation optimization problem; The result analysis and decision support module analyzes the optimization results, provides decision support, and visualizes the results.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the high-dimensional multi-objective power grid operation optimization method based on an adaptive vector are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the high-dimensional multi-objective power grid operation optimization method based on an adaptive vector are implemented.

Images