New energy system capacity configuration method and device, and regional power grid system

Abstract

The application discloses a new energy system capacity configuration method and device, and a regional power grid system. The new energy system capacity configuration method comprises the following steps: establishing an individual gene sequence according to a regional power grid network topology structure; wherein the individual gene sequence is a sequence of each load branch connected with a main road of a network frame in each region in the region, and a new energy configuration capacity of a new energy power generation branch in the load branch is taken as a gene of an individual; a plurality of populations are generated; the population comprises a plurality of individuals, and an individual gene sequence of which gene assignment is completed is taken as an individual; according to an environmental constraint condition and a predicted power trajectory of each load branch of each individual in a preset time period, the plurality of populations are subjected to optimization calculation to obtain a plurality of target individuals; and a configuration capacity result of one target individual is selected as a new energy system capacity configuration scheme in the regional power grid. The application solves the capacity planning problem of the new energy system in each region from the perspective of the whole region and in consideration of regional collaborative control and consumption.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a method and apparatus for configuring the capacity of a new energy system and a regional power grid system. Background Technology

[0002] Currently, global energy shortages and environmental pollution are becoming increasingly serious. With the development of the energy revolution, the proportion of clean energy (such as wind power and photovoltaic power) used by the load is becoming increasingly important. However, the electricity consumption scenarios in different regions within the same area are different, and the load in different regions may have the following differences: large peak-valley electricity consumption difference, large dynamic fluctuations in electricity consumption, periodic fluctuations in electricity consumption, large differences in electricity demand at different times, and uncertainty in the expansion of the original load capacity.

[0003] The above factors need to be fully considered when planning new energy power supply to ensure that the planned system can adapt to load changes and that clean electricity can be supplied to the load in a reasonable and stable manner. However, due to differences in regional climate conditions, the power generation and consumption of new energy systems vary. Specifically, this is reflected in the large differences in power generation, absorption, and the functions provided by new energy systems in different regions. Therefore, system coordinated control and absorption technology has become crucial for new energy system planning. However, existing new energy system planning only considers system capacity design from the perspective of single power plant grid connection, which cannot meet the needs of regional coordinated control and absorption. Summary of the Invention

[0004] This invention provides a method and apparatus for configuring the capacity of a new energy system and a regional power grid system, which takes into account regional coordinated control and absorption from a regional global perspective, and solves the capacity planning problem of new energy systems in various regions.

[0005] In a first aspect, embodiments of the present invention provide a method for configuring the capacity of a new energy system, comprising:

[0006] Individual gene sequences are established based on the regional power grid topology; wherein, the individual gene sequence is the sequence of each load branch connected to the main grid line of each region in the region, the load branch includes the new energy power generation branch, and the new energy configuration capacity of the new energy power generation branch is used as the individual gene;

[0007] Multiple populations are generated; wherein each population comprises multiple individuals, and the gene sequence of an individual after gene assignment is completed is considered as an individual;

[0008] Based on environmental constraints and the predicted power trajectories of the load branches of each individual within a preset time period, optimization calculations are performed on multiple populations to obtain multiple target individuals.

[0009] The renewable energy configuration capacity results of each renewable energy power generation branch in a target individual are selected as the renewable energy system capacity configuration scheme in the regional power grid.

[0010] Optionally, the population is the main population, and the individual genes of the main population are assigned values ​​according to the regional power grid power constraints.

[0011] The optimization calculation of multiple populations to obtain multiple target individuals includes:

[0012] Based on the aforementioned environmental constraints, gene cross-linking and screening of individuals within the main population are performed to obtain the main populations after each treatment.

[0013] Based on the aforementioned environmental constraints, gene crossover and screening of individuals in each of the treated main populations are performed, and the resulting individuals are grouped to form multiple new main populations.

[0014] Based on the aforementioned environmental constraints, gene cross-linking and screening processes are performed on individuals within and between each of the newly formed main populations to obtain multiple target individuals.

[0015] Optionally, gene crossover and screening are performed on individuals within the main population to obtain different treated main populations, including:

[0016] Gene crossover is performed on individuals within the main population a predetermined number of times to obtain crossover individuals within the population. These crossover individuals and the individuals before the crossover process constitute a fused main population.

[0017] The behavioral trajectory of an individual is updated based on the genes of the individuals in the fusion main population; wherein, the behavioral trajectory of an individual includes the predicted new energy power generation trajectory of each of the new energy power generation branches;

[0018] The recessive genes of each individual are assigned values ​​based on the regional power grid power hard constraint condition; wherein, the recessive genes include the energy storage capacity of each load branch in the individual;

[0019] Based on the predicted power trajectory of each load branch within the preset time period, individuals in the fusion main population that do not meet the environmental constraints are eliminated; wherein, the predicted power trajectory is calculated based on the predicted load trajectory of the load branch within the preset time period, the predicted non-new energy power generation trajectory, the energy storage capacity, and the updated predicted new energy power generation trajectory.

[0020] The merged main population after elimination is subjected to iterative processing of individual gene crossover and screening within the population until the number of iterations reaches the first threshold, thus obtaining the processed main population.

[0021] Optionally, the regional power grid power constraints include: the lower limit of the green electricity rate of each of the aforementioned new energy power generation branches;

[0022] After updating the individual's behavioral trajectory, the method further includes: performing evolutionary mutation processing on at least some of the individual's genes based on the lower limit of the branch green electricity rate.

[0023] Optionally, evolutionary mutation treatment of the gene includes:

[0024] The branch green electricity rate of the new energy power generation branch is calculated based on the predicted load trajectory of the new energy power generation branch corresponding to the gene and the updated predicted new energy power generation trajectory.

[0025] If the green electricity rate of the branch is lower than the lower limit of the green electricity rate of the branch, the updated predicted new energy power generation trajectory is corrected based on the green electricity rate of the branch and the lower limit of the green electricity rate of the branch.

[0026] Optionally, the population further includes: a perturbed population, wherein the individual genes of the perturbed population are randomly assigned values;

[0027] The perturbed population is used to perturb the main population during the cross-selection process of the main population.

[0028] Optionally, the perturbed population performs perturbation processing on the main population, including:

[0029] In the process of gene crossover between individuals within at least some secondary dominant populations, and / or, in the process of gene crossover between individuals in at least some secondary dominant populations, gene crossover is performed between individuals in the perturbed population and individuals in the dominant population.

[0030] Optionally, the regional power grid power constraints include: the operating capacity constraint value and the green electricity rate constraint value of each of the new energy power generation branches;

[0031] The individual genes of the main population are assigned values ​​according to the regional power grid power constraints, including:

[0032] For the genes of the first type of individuals in the main population, random values ​​are assigned within a first capacity range, where the first capacity range is from 0 to the working capacity constraint value of the new energy power generation branch.

[0033] For the genes of the second type of individuals in the main population, random values ​​are assigned within a second capacity range, where the second capacity range is the product of the load power of the new energy power generation branch and the green electricity rate constraint value of the branch to the working capacity constraint value of the new energy power generation branch.

[0034] For the genes of the third type of individuals in the main population, random values ​​are assigned within a third capacity range, where the third capacity range is from the working capacity constraint value of the new energy power generation branch to G times the working capacity constraint value of the new energy power generation branch, and G>1.

[0035] Optionally, before establishing the individual gene sequence based on the regional power grid topology, the process also includes:

[0036] The environmental constraints, the regional power grid topology, the predicted load trajectory of each load branch in the preset time period, the predicted non-new energy power generation trajectory of each load branch in the preset time period, and regional climate and weather data are obtained.

[0037] The regional climate and weather data are used to calculate the predicted new energy power generation trajectory of each of the new energy power generation branches in each individual within the preset time period during the optimization calculation process; the predicted load trajectory, the predicted non-new energy power generation trajectory, and the predicted new energy power generation trajectory are used to calculate the predicted power trajectory of each load branch.

[0038] Optionally, the environmental constraints include: regional power grid stability constraints and regional power grid green electricity rate limits.

[0039] Optionally, the regional power grid stability constraints include: regional power grid frequency stability constraints, regional power grid voltage stability constraints, and regional power grid fault occurrence transition stability constraints.

[0040] Optionally, the renewable energy configuration capacity results of each renewable energy power generation branch in a target individual are selected as the renewable energy system capacity configuration scheme in the regional power grid, including:

[0041] Multiple target individuals are classified; the classification criteria include at least one of the following: the location of the new energy power generation branch with a capacity not equal to 0 in the individual, the energy type of the new energy power generation branch, and the configuration capacity range of the new energy power generation branch.

[0042] Based on the search criteria, the renewable energy configuration capacity result of one target individual in a category is selected as the renewable energy system capacity configuration scheme in the regional power grid.

[0043] Secondly, embodiments of the present invention also provide a new energy system capacity configuration device, comprising:

[0044] An individual gene sequence construction module is used to establish individual gene sequences based on the regional power grid topology; wherein, the individual gene sequence is the sequence of each load branch connected to the main network of each region in the region, the load branch includes new energy power generation branches, and the new energy configuration capacity of the new energy power generation branches is used as the individual's gene;

[0045] A population generation module is used to generate multiple populations; wherein, each population includes multiple individuals, and the gene sequence of an individual after gene assignment is completed is considered as an individual;

[0046] The individual screening module is used to perform optimization calculations on multiple populations based on environmental constraints and the predicted power trajectories of each load branch of each individual within a preset time period, to obtain multiple target individuals.

[0047] The scheme selection module is used to select the new energy configuration capacity results of each new energy power generation branch in a target individual as the new energy system capacity configuration scheme in the regional power grid.

[0048] Thirdly, embodiments of the present invention also provide a regional power grid system, including: multiple regional power grids, each of the regional power grids being connected to multiple load branches, at least some of the load branches being equipped with new energy systems, and the capacity of each new energy system being configured according to the configuration method provided in any embodiment of the present invention.

[0049] In the new energy system capacity configuration method provided by this invention, individual gene sequences are constructed, treating all new energy power generation branches within a region as individuals within the region as a whole. The configuration capacity value of each new energy power generation branch is used as the individual's gene. Based on environmental constraints, evolutionary screening is performed on an individual basis. This is equivalent to considering the energy interaction between power grids in different regions within the region, comprehensively considering the global functional effect of each new energy power generation branch in the overall region, focusing on the optimal cooperation between new energy systems, rather than just considering the optimality of a single system. Furthermore, during the optimization process, the time dimension of the actual system operation is considered. A predicted power trajectory within a preset time period is introduced into the population optimization process. The evolutionary selection process of individuals is quantitatively analyzed through the power trajectory curve, which is beneficial for finding a pool of target individuals that meet the environmental constraints. In summary, this embodiment takes the capacity of each new energy system as the optimization target, and the individual evolution process within a preset time period as the basis. Through global optimization of population evolution, it provides a new energy system capacity optimization strategy that takes into account the overall regional power grid perspective and comprehensively considers regional coordinated control and absorption. This strategy can achieve new energy capacity planning that satisfies both the requirements between systems and the system itself while ensuring the stable operation of the regional power grid.

[0050] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a new energy system capacity configuration method provided in an embodiment of the present invention;

[0053] Figure 2 This is a flowchart illustrating another method for configuring the capacity of a new energy system provided in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of a new energy system capacity configuration method provided in an embodiment of the present invention;

[0055] Figure 4 This is a schematic diagram of the process of gene crossover and screening within a main population provided by an embodiment of the present invention;

[0056] Figure 5 This is a schematic diagram illustrating the process of individual gene crossover and screening between main populations provided in an embodiment of the present invention;

[0057] Figure 6 This is a schematic diagram of the structure of a new energy system capacity configuration device provided in an embodiment of the present invention. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0059] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0060] This invention provides a method for configuring the capacity of a new energy system, applicable to the capacity planning and design of a new energy system with the goal of improving the absorption of new energy, taking into account the interconnection of power grids in different regions. This method can be executed by a new energy system capacity configuration device, which can be implemented in hardware and / or software. The device can be integrated into the equipment of the power grid system to achieve local optimization, or deployed on a cloud platform of the network for remote optimization. Figure 1 This is a flowchart illustrating a new energy system capacity configuration method provided in an embodiment of the present invention. See also... Figure 1 The capacity configuration method for this new energy system includes the following steps:

[0061] S110. Establish individual gene sequences based on the regional power grid topology; wherein, the individual gene sequence is the sequence of each load branch connected to the main grid line of each region in the region, the load branch includes the new energy power generation branch, and the new energy configuration capacity of the new energy power generation branch is used as the individual gene.

[0062] The grid topology of a regional power grid system can be understood as follows: a regional power grid system includes multiple regional power grids, and each regional power grid may include at least one main grid line, each main grid line connecting at least one load branch; at least some of the main grid lines can transmit energy to each other, forming the global topology of the regional power grid. At least some load branches are equipped with new energy power generation systems, such as wind power or photovoltaic systems; at least some load branches are equipped with non-new energy power generation systems, such as traditional fossil fuel systems like thermal power.

[0063] Once the order of genes in an individual gene sequence is determined, it remains unchanged. The optimization process targets the configuration capacity value of each gene in the individual gene sequence. For example, the individual gene sequence can be formed by arranging all new energy power generation branches in a region according to a preset order; wherein, new energy power generation branches include both planned load branches capable of installing new energy systems and load branches that are expected to have new energy systems added based on predictions of load expansion due to economic development and the anticipated withdrawal of fossil fuel power generation systems. Alternatively, the individual gene sequence can also be formed by arranging all load branches in a region according to a preset order, with the new energy configuration capacity of each load branch as a gene; wherein, the gene value of load branches without new energy systems can always remain 0.

[0064] S120. Generate multiple populations; where each population includes multiple individuals, and the gene sequence of an individual after gene assignment is completed is considered as an individual.

[0065] This step is equivalent to generating an initial population. The population size and the number of individuals in each population can be selected according to actual needs, and there is no limitation here. When generating the initial individuals, each gene can be randomly assigned a value, or the value can be selected according to the initial planned capacity range of each new energy power generation branch.

[0066] For each individual, the gene values ​​within the individual are used as optimization variables; the non-new energy power generation and load power of each load branch can be obtained in advance before optimization calculation, but they are not used as variables, but rather as environmental factors affecting the individual's evolution process within a preset time period.

[0067] S130. Based on environmental constraints and the predicted power trajectories of each load branch of each individual within a preset time period, optimize calculations are performed on multiple populations to obtain multiple target individuals.

[0068] This step can be based on a genetic algorithm framework, performing individual gene crossover and mutation selection on the various populations generated in S120 to obtain target individuals whose individuals and genes both meet environmental constraints.

[0069] For example, environmental constraints may include regional power grid stability constraints and regional power grid green electricity rate limits, in order to maximize the installed capacity of new energy sources while ensuring the stable operation of the regional power grid's new energy system, load system, and power grid system, thereby maximizing the overall green electricity rate within the region.

[0070] For example, the preset time period can be a typical cycle that reflects the power generation and consumption characteristics during the operation of the regional power grid, such as one year. The predicted power trajectory of a load branch within the preset time period can be calculated from the power generation trajectory and load power trajectory of that load branch within the preset time period. The power generation trajectory and load power trajectory of the load branch can be predicted based on historical power records or empirical formulas of the regional power grid. Among them, the non-new energy power generation trajectory and load trajectory of the load branch can be used continuously in the optimization iteration process; while the new energy power generation trajectory of the load branch can be updated accordingly after each gene value update to ensure the accuracy of the optimization calculation.

[0071] S140. Select the new energy configuration capacity results of each new energy power generation branch in a target individual as the new energy system capacity configuration scheme in the regional power grid.

[0072] After optimization and screening by S130, a candidate pool of results consisting of multiple target individuals can be obtained. Users can select a target individual from the candidate pool as the capacity configuration scheme for the new energy system in the regional power grid based on screening conditions such as capacity range, location of the new energy system, or type of new energy system. The specific screening process is not limited here.

[0073] In the new energy system capacity configuration method provided in this embodiment of the invention, by constructing individual gene sequences, all new energy power generation branches within a region are treated as individuals within the region as a whole, and the configuration capacity value of each new energy power generation branch is treated as the individual's gene. Based on environmental constraints, evolutionary selection is performed on an individual basis, which is equivalent to considering the energy interaction between power grids in different regions within the region, comprehensively considering the global functional effect of each new energy power generation branch in the overall region, focusing on the optimal cooperation between new energy systems, rather than just considering the optimality of a single system. Furthermore, during the optimization process, the time dimension of the actual system operation is considered, and a predicted power trajectory within a preset time period is introduced into the population optimization process. The evolutionary selection process of individuals is quantitatively analyzed through the power trajectory curve, which is beneficial for finding a candidate pool of target individuals that meet the environmental constraints. In summary, this embodiment takes the capacity of each new energy system as the optimization target, and through global optimization via population evolution, provides a new energy system capacity optimization strategy that comprehensively considers regional coordinated control and absorption from the perspective of the overall regional power grid. This strategy can achieve new energy capacity planning that satisfies both the requirements between systems and the requirements of the system itself while ensuring the stable operation of the regional power grid.

[0074] The following is a detailed explanation of the capacity configuration method for new energy systems.

[0075] First, the system parameters and controlled objects used in this application are described. Each system parameter and controlled object can be represented in matrix form, specifically including:

[0076] Regional power grid architecture matrix SD n×m This matrix represents a regional power grid consisting of n main grid lines and m load branches on each main grid line. In this matrix, 1 indicates the presence of a load branch, and 0 indicates its absence.

[0077] Regional power grid input-output constraint matrix SDTP n×m The element sdtp in this matrix ij This indicates the power input and output constraints of the system on each load branch.

[0078] Regional power grid load matrix SDLDP n×m The elements sdldp in this matrix ij This represents the load power on each load branch. Introducing the time dimension yields the load time-domain power curve matrix SDLDP for each load branch. n×m * The elements sdldp in this matrix ij * This represents the predicted load trajectory curve for each load branch within a preset time period.

[0079] Regional power grid renewable energy system power generation matrix SDSWP n×m The element sdswp in this matrix ij This indicates the capacity and power of the new energy power generation system in each load branch of the system.

[0080] Regional power grid non-new energy system power generation matrix SDFP k This matrix represents the number of non-new energy power generation branches configured within the region, and the element sdfp in this matrix... i This represents the output power of each non-renewable energy generation branch. Over time, some fossil fuel power systems will be phased out. Introducing the time dimension yields the time-domain power curve matrix SDFP for each non-renewable energy generation branch. k * The elements in this matrix are sdfp i * This represents the predicted non-renewable energy generation trajectory curves for each non-renewable energy generation branch within a preset time period. To align the non-renewable energy system power generation matrix with other matrices, this matrix can also be represented as an n x m matrix, where elements corresponding to load branches without non-renewable energy generation systems can be assigned a value of 0.

[0081] In addition, the optimization process may also utilize the regional power grid's renewable energy system energy storage capacity power matrix SDBP. n×m The element sdbp in this matrix ij This represents the energy storage capacity of the new energy system in each load branch of the system. Thus, by using the total installed capacity comprised of the power generation capacity and energy storage capacity of the new energy system as the optimization target, and by introducing the peak-shaving and valley-filling functions of the energy storage system, the margin and flexibility of system power flow regulation can be increased, and the range of selectable power generation capacities for the new energy system can be expanded.

[0082] Then, the constraints involved in the optimization process will be explained:

[0083] For the entire regional power grid, the overall power flow, including active and reactive power, can be divided into three cases: regional power output, regional power input, and regional power generation and consumption balance. For the entire regional power grid, the regional power requirement is between [stap_min, stap_max]. The hard constraint condition for the regional power grid is shown in formula (1), which is used to ensure the stability of the regional power grid system.

[0084] stap_min<{∑sdldp ij +∑sdswp ij +∑sdfp k} <stap_max (1)

[0085] For each load branch, the branch power must first satisfy the regional power grid output-input constraint matrix SDTP. n×m The power range for each load branch is given in the documentation. In addition, each load branch is subject to the branch equipment capacity (or operating capacity constraint value) zcap_max. ij The hard constraints (such as Equation 2, must be met) and the green electricity rate constraint value swrat of the load branch on the branch must also be met. ij The soft constraint conditions (such as Equation 3) can be satisfied. Among them, the branch equipment capacity zcap_max ij This can be understood as the rated capacity of the transformers equipped in the load branch.

[0086] sdldp ij +sdswp ij <zcap_max ij (2)

[0087]

[0088] In the power flow calculation during the optimization process, the regional power grid stability constraints include at least: regional power grid frequency stability constraints, regional power grid voltage stability constraints (for each characteristic node in the region), and regional power grid fault occurrence transition stability constraints.

[0089] Based on the aforementioned regional principle constraints, this invention employs a global optimization process to screen and identify the renewable energy capacity configuration for each load branch. This configured capacity represents the capacity that can be effectively absorbed by the region. With the advancement of the 3060 dual-carbon target, the overall electricity consumption environment is gradually changing, and the price difference between load and electricity is widening. As long as renewable energy can be absorbed, revenue can be generated. The installed capacity and absorption rate of renewable energy are gradually becoming the dominant factors influencing the system's economic benefits. Therefore, during the optimization process, the optimization direction for the capacity configuration of all renewable energy generation branches within the region is: maximizing the installed capacity of renewable energy while satisfying the constraints, thereby maximizing the overall green electricity rate of the region.

[0090] The following is combined with Figure 2 The optimization process is explained in detail. Figure 2 This is a flowchart illustrating another method for configuring the capacity of a new energy system provided in an embodiment of the present invention. See also... Figure 2 The capacity configuration method for this new energy system includes the following steps:

[0091] S210. Determine the boundary conditions of the regional power grid.

[0092] Specifically, this step can be used as a preparatory step for optimization processing; see [link to relevant documentation]. Figure 3This step specifically involves acquiring regional climate and weather data, power grid architecture data, load data for each branch of the power grid, and renewable energy data for each branch of the power grid. Specifically, the regional climate and weather data is used to update the predicted renewable energy generation trajectory of each renewable energy generation branch within a preset time period during the optimization calculation process; the regional power grid topology can be extracted from the power grid architecture data; the load data for each branch of the power grid may include historical load data for each load branch; and the renewable energy data for each branch of the power grid may include information such as renewable energy planning status and energy type of the renewable energy system for each load branch.

[0093] After obtaining the above data, based on the power grid structure, load, and existing renewable energy systems, the grid's carrying capacity, the load and trends of each branch, and the status and trends of renewable energy generation can be analyzed and calculated. Specifically, based on the above data, the predicted load trajectory of each load branch, the predicted non-renewable energy generation trajectory, and the prediction method for the renewable energy generation trajectory of each load branch can be calculated. In addition, this step also requires obtaining the regional power grid stability constraints and the regional power grid output-input constraints. These predicted trajectories and constraints are applied to the subsequent global capacity optimization process between systems to obtain the final capacity configuration scheme for each system.

[0094] For example, in this step, the constraint on the configuration capacity range of each new energy power generation branch prioritizes [sdldp] ij ×swrat ij zcap_max ij ], and then consider [0, zcap_max ij That is, to meet the green electricity rate constraints of branch lines as much as possible.

[0095] S220. Determine the individual's gene sequence.

[0096] S230, generating multiple main populations.

[0097] This step is equivalent to generating the initial population. For example, X1 main populations can be generated, each containing Y individuals; X1>1, and Y>1. The individual genes in the main populations are assigned values ​​according to the regional power grid power constraints, and the individual genes in the main populations undergo selective evolution according to the constraints.

[0098] Specifically, the main population includes three types of individuals: Type 1, Type 2, and Type 3, generated in a certain proportion. For Type 1 individuals, their genes are distributed according to a first capacity range [0, zcap_max]. ij Constraints are applied, and the corresponding new energy power generation branch capacity power values ​​are generated randomly with uniform probability; for the second type of individual, the individual gene is determined according to the second capacity range [sdldp]. ij ×swrat ijzcap_max ij Constraints are applied, and the corresponding new energy power generation branch capacity power values ​​are generated randomly with uniform probability; for the third type of individual, the individual gene is determined according to the third capacity range [zcap_max]. ij ,G*zcap_max ij The constraint is that the capacity and power values ​​of the corresponding new energy power generation branches are randomly generated with uniform probability, and G>1, meaning that the boundary constraint of the third type of individual is amplified by a factor of G. This setting can effectively improve the ergodicity of individual gene values ​​and reduce the risk of the optimization results entering local convergence. Preferably, the individual gene generation function of each population can be set to be different to improve the randomness and ergodicity of the individual gene generation method, further reducing the risk of the optimization results entering local convergence.

[0099] S240. Based on environmental constraints, perform gene cross-linking and screening of individuals within the main population to obtain the main populations after each treatment.

[0100] For each main population, individuals within the population exchange genes according to certain rules, which is equivalent to the regional power grid new energy system power generation matrix SDSWP. n×m The power values ​​of the corresponding new energy power generation branches are exchanged to generate new individuals. The new individuals are merged with the initial individuals to form a new main population; after eliminating individuals in the new main population that do not meet the environmental constraints, the main population after elimination is obtained. For example, after the number of iterations of the cross-selection step in this population reaches the first threshold d, each main population after treatment is obtained, where d>1.

[0101] S250. Based on environmental constraints, gene cross-linking and screening of individuals in each treated main population are performed, and the treated individuals are grouped to form multiple new main populations.

[0102] This step includes: cross-pollinating individuals from different main populations to generate multiple new individuals; eliminating and screening all new individuals according to environmental constraints; and grouping the new individuals that meet the evolutionary requirements into groups of Y individuals per population to obtain new main populations.

[0103] S260. Based on environmental constraints, gene cross-linking and screening of individuals within and between populations are performed on each new main population to obtain multiple target individuals.

[0104] This step is equivalent to performing S240 and S250 iterative processing on each new main population. After tag generation iterations, if the stopping condition is met, the iteration stops, resulting in multiple target individuals that satisfy the environmental constraints.

[0105] The stopping condition can be that the number of iterations of the new main population reaches the second threshold; or that the number of individuals meeting the environmental constraints is sufficient, and the probability distribution analysis results of the regional green electricity rate of the individuals meeting the conditions meet the requirements. The probability distribution analysis results can include the probability distribution type and probability distribution function coefficients, etc.

[0106] S270. Classify the optimization results for multiple target individuals.

[0107] The classification criteria include at least one of the following: the location of the new energy power generation branch with a capacity of non-zero in the individual, the energy type of the new energy power generation branch, and the configuration capacity range of the new energy power generation branch; the classification results can also be combined with the weather conditions of the area where the new energy power generation branch is located.

[0108] S280. Based on the search criteria, select the renewable energy configuration capacity result of one of the target individuals in a category as the renewable energy system capacity configuration scheme in the regional power grid.

[0109] This embodiment realizes the capacity configuration planning of each new energy power generation branch in the regional power grid through S210-S280.

[0110] Based on the above embodiments, optionally, in S230, when generating X1 main populations, X2 perturbation populations can also be generated simultaneously, where X2 > 1; the number of individuals in a perturbation population can be the same as the number of individuals in a main population. The genes of individuals in the perturbation populations are randomly assigned using a random function, and the individual genes are not subject to constraints, evolving randomly. The perturbation populations are used to perturb the main populations during the cross-selection process. In this embodiment, by introducing perturbation populations and randomly perturbing the main populations during the selection and evolution process, complex environments can be better simulated, the population search space can be increased, and individuals more adapted to the environment can be selected, avoiding local convergence.

[0111] Specifically, perturbing the main population by disturbing the existing population includes:

[0112] In S240, during the process of gene crossover within the main population, the perturbation population also undergoes gene crossover within the population to obtain a sufficiently rich number of perturbation individuals.

[0113] In S240-S260, during gene crossover of individuals within at least some of the secondary primary populations, and / or, during gene crossover of individuals between at least some of the secondary primary populations, some individuals from the perturbed population are used to perform perturbed mutation crossover gene exchange on individuals in the primary population.

[0114] Below, in conjunction with Figure 4This paper explains the evolutionary process within the main population of S240. Figure 4 This is a schematic diagram illustrating the process of gene crossover and selection within a main population, provided by an embodiment of the present invention. See also... Figure 4 The process of gene crossover and selection within a population includes:

[0115] S310. Perform a preset number of gene crossovers on individuals within the main population to obtain crossover individuals within the population. These crossover individuals and the individuals before the crossover process constitute the fused main population.

[0116] In this step, a preset number of gene crossovers are performed between individuals in each main population to obtain a sufficient number of crossover individuals, thereby increasing the richness and diversity of individuals in the fused main population. For example, the preset number of crossovers can be three.

[0117] S320. Update the behavioral trajectory of individuals based on the genes of individuals in the fusion main population; wherein, the behavioral trajectory of individuals includes the predicted new energy power generation trajectory of each new energy power generation branch.

[0118] Based on various system environments (including but not limited to the power grid, loads, renewable energy generation, non-renewable energy generation, and climate and weather) and empirical data within the regional power grid, the time-domain operating "trajectory" of each renewable energy generation branch—its generation curve trend or function—can be obtained. Therefore, when the renewable energy system capacity (genetic value) changes, the predicted renewable energy generation trajectory of each renewable energy generation branch changes accordingly. After cross-processing in S310, based on the climate and weather information of each region and the genetic values, the predicted renewable energy generation trajectories in each entity are updated, ensuring the accuracy of the power flow calculation results.

[0119] S330. Assign values ​​to the recessive genes of each individual based on the hard constraints of regional power grid power; wherein, the recessive genes include the energy storage capacity of each load branch in the individual.

[0120] For each individual, a regional power grid new energy system energy storage capacity power matrix (SDBP) can be established first. n×m And assign 0 to each element in the matrix. After completing S310, calculate whether the individual meets the regional power grid hard constraint condition based on formula (1). If the constraint is met, then the matrix SDBP n×m All elements in the matrix remain zero. If the constraint is not met, the matrix SDBP needs to be updated. n×m The values ​​of each element in the matrix. Specifically, when the constraints are not met, the individual regional power grid renewable energy system power generation matrix SDSWP is first selected. n×m The gene value in the middle exceeds sdldp ij The load branch is then determined, and the energy storage capacity power range of that load branch is defined as [0, zcap_max].ij -sdldp ij Finally, a recessive gene pool for each individual is generated based on the energy storage capacity power range of each load branch.

[0121] S340. Based on the predicted power trajectory of each load branch within a preset time period, eliminate individuals in the fusion main population that do not meet the environmental constraints.

[0122] In this step, it is necessary to calculate the degree to which individuals in the fusion master population meet the environmental constraints. Specifically, this means whether the regional power grid stability constraints, such as frequency stability, voltage stability, and fault transition stability, are met throughout the entire preset time period, and whether the environmental adaptability condition, such as the regional power grid green electricity rate limit, is met.

[0123] Among them, the regional green electricity rate (GrenR) of an individual is based on the individual's behavioral trajectory and the load time-domain power curve matrix (SDLDP) of each load branch. n×m * Time-domain power curve matrix of each non-new energy power generation branch (SDFP) k * And the calculation of individual recessive gene energy storage capacity. For example, according to formula (4):

[0124]

[0125] For each individual in the merged main population, the regional green power rate (GrenR) is calculated. Individuals with a regional green power rate (GrenR) lower than the minimum regional green power rate (GrenR_Min) are eliminated and no longer participate in the subsequent evolutionary process; other individuals are retained. For example, a probability distribution analysis can be performed on the green power rate of the main population after population selection to understand the degree of population evolution.

[0126] S350. Continue iterative processing of individual gene crossover, updating and screening within the population for the eliminated fusion main population.

[0127] That is, repeat steps S310-S340.

[0128] S360. Determine if the number of iterations has reached the threshold for the first iteration. If yes, proceed to S370. If no, return to S350.

[0129] S370, the main population after processing.

[0130] In this embodiment, selective evolution within the main population was completed through S310-S370.

[0131] Below, in conjunction with Figure 5 This paper explains the evolutionary process among the main populations in S250. Figure 5This is a schematic diagram illustrating the process of gene crossover and selection between individual populations provided in an embodiment of the present invention. See also... Figure 5 The process of gene crossover and selection between individuals in a population includes:

[0132] S410. Gene crossover is performed on individuals in the main population after different treatments to obtain multiple new individuals.

[0133] S420. Based on the genes of the newborn individuals, update the predicted new energy power generation trajectory of each new energy power generation branch in the newborn individuals within a preset time period.

[0134] This step can be found in the detailed explanation of S320, and will not be repeated here.

[0135] S430, update the recessive genes of each newborn individual based on the hard constraint condition of regional power grid power.

[0136] Among these, recessive genes include the energy storage capacity of each load branch in the newborn individual. This step can be found in the detailed explanation of S330, and will not be repeated here.

[0137] S440. Retain newly born individuals that meet the environmental constraints as treated individuals.

[0138] This step can be found in the detailed explanation of S340, and will not be repeated here.

[0139] S450. After treatment, individuals are grouped into new parent populations according to each population, which includes Y individuals.

[0140] In this embodiment, the selection evolution process between the main populations is completed through S410-S450. The newly formed main populations can continue to undergo selection evolution iteration within and between populations until the stopping condition is met.

[0141] Based on the above embodiments, optionally, in at least one step of the main population selection evolution process, i.e., intra-population selection evolution and inter-population selection evolution, the lower limit of branch green electricity rate GrenR can also be used. ij _min, which involves evolutionary mutation treatment of at least a portion of the genes of at least some individuals.

[0142] Individual genetic evolution variation refers to the selective modification of the configuration capacity of renewable energy power generation branches within an individual, with the modification direction being to increase the green electricity rate of the branches. Specific steps include:

[0143] Using formula (5), the branch green electricity rate (GrenR) of the new energy power generation branch is calculated based on the predicted load trajectory of the corresponding new energy power generation branch and the updated predicted new energy power generation trajectory. ij .

[0144]

[0145] Determining the green electricity rate of branch circuits (GrenR) ij Is it below the lower limit of branch green electricity rate? (GrenR) ij _min; if so, then use formula (6), based on the branch green electricity rate GrenR ij and the lower limit of green electricity rate of branch lines GrenR ij _min Corrected and updated predicted renewable energy generation trajectory sdswp ij * The corrected trajectory sdswp is obtained. ij *′ This will increase the new energy configuration capacity of this new energy power generation branch.

[0146]

[0147] In summary, the new energy system capacity configuration method provided by this invention comprehensively considers the overall stability and green electricity rate of the regional power grid, and through a global optimization strategy, provides configuration schemes for the power generation capacity and energy storage capacity of each new energy power generation branch with a preset time period as the evolution cycle. Furthermore, the result obtained from the global optimization of the entire region in this invention is not a single-point result, but a pool of results that meets the optimization objective. This pool contains optimized new energy configuration capacities under various on-site combination scenarios, effectively avoiding the incompleteness of the optimization solution.

[0148] This invention also provides a new energy system capacity configuration device, which is used to implement the new energy system capacity configuration method provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method. Figure 6 This is a schematic diagram of the structure of a new energy system capacity configuration device provided in an embodiment of the present invention. See also... Figure 6 The capacity configuration device of the new energy system includes: an individual gene sequence construction module 510, a population generation module 520, an individual screening module 530, and a scheme selection module 540.

[0149] The individual gene sequence construction module 510 is used to establish individual gene sequences based on the regional power grid topology. The individual gene sequence is the sequence of each load branch connected to the main grid line in each region. Load branches include new energy power generation branches, and the new energy configuration capacity of each new energy power generation branch serves as the individual's gene. The population generation module 520 is used to generate multiple populations. Each population includes multiple individuals, and the gene sequence of an individual after gene assignment is considered as one individual. The individual screening module 530 is used to optimize multiple populations based on environmental constraints and the predicted power trajectories of each load branch of each individual within a preset time period, obtaining multiple target individuals. The scheme selection module 540 is used to select the new energy configuration capacity results of each new energy power generation branch in a target individual as the new energy system capacity configuration scheme in the regional power grid.

[0150] Based on the above embodiments, optionally, the population is the main population, and the individual genes of the main population are assigned values ​​according to the regional power grid power constraints. The individual screening module 530 specifically includes: an intra-population screening unit, an inter-population screening unit, and a new main population screening unit. The intra-population screening unit is used to perform gene cross-linking and screening of individuals within the main population based on environmental constraints to obtain various treated main populations. The inter-population screening unit is used to perform gene cross-linking and screening of individuals between different treated main populations based on environmental constraints, and group the resulting individuals into multiple new main populations. The new main population screening unit is used to perform gene cross-linking and screening of individuals within and between different new main populations based on environmental constraints to obtain multiple target individuals.

[0151] Based on the above embodiments, optionally, the intra-population screening unit is specifically used for: performing a preset number of gene crossover processes on individuals within the main population to obtain crossover individuals, which, together with the individuals before the crossover process, constitute a fused main population. The behavioral trajectory of individuals in the fused main population is updated based on their genes; wherein, the behavioral trajectory of an individual includes the predicted new energy power generation trajectory of each new energy power generation branch. Recessive genes of each individual are assigned values ​​based on the regional power grid power hard constraint conditions; wherein, the recessive genes include the energy storage capacity of each load branch within the individual. Individuals in the fused main population that do not meet the environmental constraint conditions are eliminated based on the predicted load trajectory, predicted non-new energy power generation trajectory, energy storage capacity, and updated predicted new energy power generation trajectory of each load branch within the preset time period; wherein, the predicted power trajectory is calculated based on the predicted load trajectory, predicted non-new energy power generation trajectory, energy storage capacity, and updated predicted new energy power generation trajectory of the load branch within the preset time period. The eliminated fused main population undergoes iterative processing of intra-population individual gene crossover and screening until the number of iterations reaches the first threshold, resulting in a processed main population.

[0152] Based on the above embodiments, optionally, the regional power grid power constraint includes: a lower limit of the branch green electricity rate for each new energy power generation branch. The new energy system capacity configuration device further includes: an evolutionary mutation module, used to perform evolutionary mutation processing on at least some genes of an individual based on the lower limit of the branch green electricity rate after updating the individual's behavioral trajectory.

[0153] Specifically, the evolutionary mutation module is used to calculate the branch green electricity rate of the new energy power generation branch based on the predicted load trajectory of the new energy power generation branch corresponding to the gene and the updated predicted new energy power generation trajectory; if the branch green electricity rate is lower than the lower limit of the branch green electricity rate, the updated predicted new energy power generation trajectory is corrected based on the branch green electricity rate and the lower limit of the branch green electricity rate.

[0154] Based on the above embodiments, optionally, the multiple populations generated by the population generation module 520 further include a perturbation population, wherein the individual genes of the perturbation population are randomly assigned. The new energy system capacity configuration device further includes a perturbation module, used to perturb the main population using the perturbation population during the cross-selection process of the main population.

[0155] The perturbation module is specifically used to perform gene crossover between individuals in the perturbation population and individuals in the main population during gene crossover between individuals in at least some secondary main populations.

[0156] Based on the above embodiments, optionally, the regional power grid power constraint conditions include: the working capacity constraint value and the green electricity rate constraint value of each new energy power generation branch; the population generation module 520 includes: a main population generation unit, used to assign values ​​to individual genes in the main population according to the regional power grid power constraint conditions.

[0157] The main population generation unit is specifically used for: randomly assigning values ​​to the genes of the first type of individuals in the main population within a first capacity range, where the first capacity range is from 0 to the working capacity constraint value of the new energy power generation branch; randomly assigning values ​​to the genes of the second type of individuals in the main population within a second capacity range, where the second capacity range is the product of the load power of the new energy power generation branch and the green electricity rate constraint value of the branch to the working capacity constraint value of the new energy power generation branch; and randomly assigning values ​​to the genes of the third type of individuals in the main population within a third capacity range, where the third capacity range is from the working capacity constraint value of the new energy power generation branch to G times the working capacity constraint value of the new energy power generation branch, where G>1.

[0158] Based on the above embodiments, optionally, the new energy system capacity configuration device further includes: an acquisition module, used to acquire environmental constraints, regional power grid topology, predicted load trajectories of each load branch within a preset time period, predicted non-new energy power generation trajectories of each load branch within a preset time period, and regional climate and weather data; wherein, the regional climate and weather data is used to calculate the predicted new energy power generation trajectory of each new energy power generation branch in each entity within the preset time period during the optimization calculation process; the predicted load trajectory, predicted non-new energy power generation trajectory, and predicted new energy power generation trajectory are used to calculate the predicted power trajectory of each load branch.

[0159] Based on the above embodiments, optionally, the scheme selection module 540 includes a classification unit and a selection unit. The classification unit is used to classify multiple target individuals; wherein the classification criteria include at least one of the following: the location of new energy power generation branches with non-zero capacity within the individuals, the energy type of the new energy power generation branches, and the configuration capacity range of the new energy power generation branches. The selection unit is used to select the new energy configuration capacity result of one target individual in a category of target individuals as the new energy system capacity configuration scheme in the regional power grid, based on search conditions.

[0160] This invention also provides a regional power grid system, including: multiple regional power grids, each regional power grid being connected to multiple load branches, and at least some of the load branches being equipped with new energy systems. The capacity of each new energy system is configured according to the configuration method provided in any embodiment of this invention, and has corresponding beneficial effects.

[0161] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for configuring the capacity of a new energy system, characterized in that, include: Individual gene sequences are established based on the regional power grid topology; wherein, the individual gene sequence is the sequence of each load branch connected to the main grid line of each region in the region, the load branch includes the new energy power generation branch, and the new energy configuration capacity of the new energy power generation branch is used as the individual gene; Multiple populations are generated; wherein each population comprises multiple individuals, and the gene sequence of an individual after gene assignment is completed is considered as an individual; Based on environmental constraints and the predicted power trajectories of each load branch of each individual within a preset time period, optimization calculations are performed on multiple populations to obtain multiple target individuals. Once the gene order in an individual's gene sequence is determined, it remains unchanged. The optimization process targets the configuration capacity values ​​of each gene in the individual's gene sequence. During the optimization process, the optimization direction for the capacity configuration of all new energy power generation branches within the region is: to maximize the installed capacity of new energy sources while satisfying the constraints, thereby maximizing the overall green electricity rate of the region. The renewable energy configuration capacity results of each renewable energy power generation branch in a target individual are selected as the renewable energy system capacity configuration scheme in the regional power grid.

2. The new energy system capacity configuration method according to claim 1, characterized in that, The population is the main population, and the individual genes of the main population are assigned values ​​according to the regional power grid power constraints. The optimization calculation of multiple populations to obtain multiple target individuals includes: Based on the aforementioned environmental constraints, gene cross-linking and screening of individuals within the main population are performed to obtain the main populations after each treatment. Based on the aforementioned environmental constraints, gene crossover and screening of individuals in each of the treated main populations are performed, and the resulting individuals are grouped to form multiple new main populations. Based on the aforementioned environmental constraints, gene cross-linking and screening processes are performed on individuals within and between each of the newly formed main populations to obtain multiple target individuals.

3. The new energy system capacity configuration method according to claim 2, characterized in that, Gene crossover and screening were performed on individuals within the main population to obtain various treated main populations, including: Gene crossover is performed on individuals within the main population a predetermined number of times to obtain crossover individuals within the population. These crossover individuals and the individuals before the crossover process constitute a fused main population. The behavioral trajectory of an individual is updated based on the genes of the individuals in the fusion main population; wherein, the behavioral trajectory of an individual includes the predicted new energy power generation trajectory of each of the new energy power generation branches; The recessive genes of each individual are assigned values ​​based on the regional power grid power hard constraint condition; wherein, the recessive genes include the energy storage capacity of each load branch in the individual; Based on the predicted power trajectory of each load branch within the preset time period, individuals in the fusion main population that do not meet the environmental constraints are eliminated; wherein, the predicted power trajectory is calculated based on the predicted load trajectory of the load branch within the preset time period, the predicted non-new energy power generation trajectory, the energy storage capacity, and the updated predicted new energy power generation trajectory. The merged main population after elimination is subjected to iterative processing of individual gene crossover and screening within the population until the number of iterations reaches the first threshold, thus obtaining the processed main population.

4. The new energy system capacity configuration method according to claim 3, characterized in that, The regional power grid power constraints include: the lower limit of the green electricity rate of each of the aforementioned new energy power generation branches; After updating the individual's behavioral trajectory, the method further includes: performing evolutionary mutation processing on at least some of the individual's genes based on the lower limit of the branch green electricity rate.

5. The new energy system capacity configuration method according to claim 4, characterized in that, Evolutionary mutation treatment of the gene includes: The branch green electricity rate of the new energy power generation branch is calculated based on the predicted load trajectory of the new energy power generation branch corresponding to the gene and the updated predicted new energy power generation trajectory. If the green electricity rate of the branch is lower than the lower limit of the green electricity rate of the branch, the updated predicted new energy power generation trajectory is corrected based on the green electricity rate of the branch and the lower limit of the green electricity rate of the branch.

6. The new energy system capacity configuration method according to claim 2, characterized in that, The population also includes: a perturbed population, wherein the individual genes of the perturbed population are randomly assigned values; The perturbed population is used to perturb the main population during the cross-selection process of the main population.

7. The new energy system capacity configuration method according to claim 6, characterized in that, The perturbed population performs perturbation processing on the main population, including: In the process of gene crossover between individuals within at least some secondary dominant populations, and / or, in the process of gene crossover between individuals in at least some secondary dominant populations, gene crossover is performed between individuals in the perturbed population and individuals in the dominant population.

8. The new energy system capacity configuration method according to claim 2, characterized in that, The power constraints of the regional power grid include: the working capacity constraint value and the green electricity rate constraint value of each of the new energy power generation branches; The individual genes of the main population are assigned values ​​according to the regional power grid power constraints, including: For the genes of the first type of individuals in the main population, random values ​​are assigned within a first capacity range, where the first capacity range is from 0 to the working capacity constraint value of the new energy power generation branch. For the genes of the second type of individuals in the main population, random values ​​are assigned within a second capacity range, where the second capacity range is the product of the load power of the new energy power generation branch and the green electricity rate constraint value of the branch to the working capacity constraint value of the new energy power generation branch. For the genes of the third type of individuals in the main population, random values ​​are assigned within a third capacity range, where the third capacity range is from the working capacity constraint value of the new energy power generation branch to G times the working capacity constraint value of the new energy power generation branch, and G>1.

9. The new energy system capacity configuration method according to claim 1, characterized in that, Before establishing individual gene sequences based on the regional power grid topology, the following steps are also included: The environmental constraints, the regional power grid topology, the predicted load trajectory of each load branch in the preset time period, the predicted non-new energy power generation trajectory of each load branch in the preset time period, and regional climate and weather data are obtained. The regional climate and weather data are used to calculate the predicted new energy power generation trajectory of each of the new energy power generation branches in each individual within the preset time period during the optimization calculation process; the predicted load trajectory, the predicted non-new energy power generation trajectory, and the predicted new energy power generation trajectory are used to calculate the predicted power trajectory of each load branch.

10. The new energy system capacity configuration method according to claim 1, characterized in that, The environmental constraints include: regional power grid stability constraints and regional power grid green electricity rate limits.

11. The new energy system capacity configuration method according to claim 10, characterized in that, The regional power grid stability constraints include: regional power grid frequency stability constraints, regional power grid voltage stability constraints, and regional power grid fault occurrence transition stability constraints.

12. The new energy system capacity configuration method according to claim 1, characterized in that, Selecting the renewable energy configuration capacity results of each renewable energy power generation branch in a target individual as the renewable energy system capacity configuration scheme in the regional power grid includes: Multiple target individuals are classified; the classification criteria include at least one of the following: the location of the new energy power generation branch with a capacity not equal to 0 in the individual, the energy type of the new energy power generation branch, and the configuration capacity range of the new energy power generation branch. Based on the search criteria, the renewable energy configuration capacity result of one target individual in a category is selected as the renewable energy system capacity configuration scheme in the regional power grid.

13. A capacity configuration device for a new energy system, characterized in that, include: An individual gene sequence construction module is used to establish individual gene sequences based on the regional power grid topology; wherein, the individual gene sequence is the sequence of each load branch connected to the main network of each region in the region, the load branch includes new energy power generation branches, and the new energy configuration capacity of the new energy power generation branches is used as the individual's gene; A population generation module is used to generate multiple populations; wherein, each population includes multiple individuals, and the gene sequence of an individual after gene assignment is completed is considered as an individual; The individual screening module is used to perform optimization calculations on multiple populations based on environmental constraints and the predicted power trajectories of each load branch of each individual within a preset time period to obtain multiple target individuals. The order of genes in an individual's gene sequence remains unchanged once determined, and the optimization process targets the configuration capacity value of each gene in the individual's gene sequence. During the optimization process, the optimization direction for the capacity configuration of all new energy power generation branches within the region is: to maximize the installed capacity of new energy sources while satisfying the constraints, thereby maximizing the overall green electricity rate of the region. The scheme selection module is used to select the new energy configuration capacity results of each new energy power generation branch in a target individual as the new energy system capacity configuration scheme in the regional power grid.

14. A regional power grid system, characterized in that, include: Multiple regional power grids, each of which connects to multiple load branches, with at least some of the load branches equipped with new energy systems, and the capacity of each new energy system configured according to the configuration method described in any one of claims 1-12.

Images