Design method and system of new energy and energy storage demonstration platform meeting multi-scenario requirements

Abstract

The application discloses a new energy and energy storage demonstration platform design method and system meeting multi-scene requirements, and belongs to the technical field of power system planning and intelligent optimization. The method comprises the following steps: obtaining typical scene characteristics to construct a multi-scene classification model; establishing an upper multi-objective optimization model to generate a configuration scheme candidate set; establishing a lower deviation calculation and constraint verification model to perform constraint verification, deviation quantification and risk mapping on the candidate scheme, and feeding back the results to the upper layer; using NSGAII and Gurobi solver double-layer iteration to solve the optimal configuration capacity; and through a scene scaling mechanism, the optimization result is reduced to the resource constraint range of the demonstration platform, and equipment configuration details and verification reports are output. The application realizes multi-scene adaptation, deviation risk quantification and double-layer collaborative optimization, can flexibly adapt to the demonstration requirements of scenes such as Shaguo desert, offshore wind power, source-grid-load-storage integration and the like, guarantees the rationality of equipment configuration, and reduces the engineering landing risk.

Description

Technical Field

[0001] This invention relates to the field of power system planning and intelligent optimization technology, and in particular to a design method and system for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios. Background Technology

[0002] In recent years, new power systems have shown characteristics such as high proportion of renewable energy access, uneven spatial and temporal distribution of resources, diversified loads, and increased multi-energy coupling. Research and engineering verification of new energy systems increasingly rely on reproducible and scalable empirical platforms.

[0003] Traditional planning methods, based on the assumption of continuous variables, construct linear models that struggle to accurately characterize the discrete, modular, and highly nonlinear resource characteristics of equipment such as photovoltaics, wind power, energy storage, electrolyzers, and fuel cells. Furthermore, the number of typical operating scenarios is gradually increasing, including "solar-dominated scenarios," "wind-dominated scenarios," "weak light but high load scenarios," "external transmission-constrained scenarios," and "electricity-hydrogen coupling scenarios." The availability, capacity range, and proportional constraints of equipment vary significantly across these scenarios, making traditional single-scenario planning or weighted average methods unable to cover complex engineering needs. This can easily lead to scenarios mismatch or wasted investment. Moreover, most existing capacity configuration methods lack evaluation methods for multi-scenario coverage; the constructed experimental conditions are often merely operational rather than covering more typical operating conditions, limiting their application to single-scenario verification and hindering cross-algorithm, cross-model, and cross-system verification needs.

[0004] In summary, existing capacity optimization and configuration technologies still have many shortcomings and are difficult to meet the actual needs of multi-scenario adaptation of new energy and energy storage demonstration platforms. There is an urgent need for a systematic method that can be used in the construction phase of experimental platforms. Through scenario and equipment pool construction, deviation analysis and two-layer optimization, a scientific, reasonable and reproducible capacity configuration scheme for experimental platforms can be obtained to meet the needs of various types of experimental research. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios. This method enables platform construction to move beyond experience-based design and instead generate equipment capacity combinations based on a systematic scenario framework and optimized theories. This maximizes the scenario reproducibility of the experimental platform, achieves comprehensive coverage of core operating modes within a limited budget, forms a reproducible, transferable, and benchmarkable experimental platform system, supports research on the multi-energy coupling mechanism of wind, solar, and hydrogen storage, and supports cross-scenario experimental verification.

[0006] On the one hand, a design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios is provided, the method including: To obtain the characteristics of typical application scenarios of new power systems, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and to construct a scenario classification model covering multiple scenarios such as large-scale power transmission bases in desert areas, offshore wind power bases, and source-grid-load-storage collaborative scenarios; A multi-objective optimization upper-level model and a lower-level model for deviation risk calculation and constraint verification are established. The device number limit and capacity demand vector of the corresponding scenario in the scenario classification model are obtained as constraints. The upper-level model is used to solve the configuration scheme candidate set of the new energy and energy storage demonstration platform. The lower-level model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper-level model, realizes scheme feasibility assessment and quantitative analysis of reproducibility, and feeds the results back to the upper-level optimization. The optimal configuration capacity is obtained through a two-level iterative solution. Through scene scaling and reproduction mechanisms, the optimal configuration capacity obtained through optimization is reduced to the actual resource constraints of the empirical platform by a unified scaling factor, and the final equipment configuration details, scene matching verification results and constraint satisfaction report are output.

[0007] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the upper-level model is solved using NSGA-II and the lower-level model is solved using Gurobi.

[0008] According to the design method of the new energy and energy storage empirical platform that meets the needs of multiple scenarios provided by the present invention, the upper-level model includes an objective function and constraints; the objective function includes minimizing the total cost of the empirical platform and minimizing the weighted deviation risk; the constraints include constraints on the number of devices, non-negative capacity constraints, lower capacity constraints, scenario adaptation constraints, integer constraints, and renewable energy proportion constraints.

[0009] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the lower-level model includes an objective function and constraints; the objective function is the minimum risk deviation; the constraints include equipment quantity limit, integer constraint, system deviation constraint, special constraint, and capacity-power conversion constraint.

[0010] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the deviation quantification includes the calculation of multi-dimensional deviation indicators such as type deviation, proportion deviation and specific deviation.

[0011] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the risk mapping uses the Logistic function to map the original deviation value to the risk value in the [0,1] interval, and the slope coefficient and inflection point parameter of the Logistic function are dynamically adjusted according to the scenario deviation risk sensitivity.

[0012] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the specific process of the two-layer iterative solution includes: generating an initial population after initializing parameters and module pool; entering the upper-layer NSGA. II. Optimize the loop, calling the lower-level Gurobi solver for each individual to verify constraints and calculate deviation indices. Obtain the deviation risk value through the Logistic function mapping. If feasible, output the deviation index; otherwise, trigger the penalty mechanism. After evaluating individual fitness, generate offspring populations through fast non-dominated sorting, crowding calculation, and genetic operations. Merge parents and offspring and select a new generation population. Repeat the loop until the maximum number of generations, outputting the Pareto optimal solution. Extract the best cost solution, the best deviation risk solution, and the compromise solution from it, and provide equipment configuration details and a verification report.

[0013] According to the design method of the new energy and energy storage demonstration platform that meets the needs of multiple scenarios provided by the present invention, the scenario scaling and reproduction mechanism adopts a unified scaling factor to linearly scale the optimal configuration capacity obtained by optimization, keeping the capacity ratio between each device unchanged, so that the scaled scheme adapts to the resource constraints of the demonstration platform and still meets the reproduction requirements of each scenario.

[0014] On the other hand, a design system for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios is provided. The system includes: The scenario classification model construction module obtains the characteristics of typical application scenarios of the new power system, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and constructs scenario classification models covering multiple scenarios such as large-scale power transmission bases in desert areas, offshore wind power bases, and source-grid-load-storage collaborative scenarios. The two-layer optimization solution module establishes an upper-layer model for multi-objective optimization and a lower-layer model for deviation risk calculation and constraint verification. It obtains the device number limit and capacity demand vector of the corresponding scenario in the scenario classification model as constraints. The upper-layer model is used to solve the candidate set of configuration schemes for the new energy and energy storage demonstration platform. The lower-layer model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper layer, realizes the feasibility assessment and reproducibility analysis of the scheme, and feeds the results back to the upper-layer optimization. The optimal configuration capacity is obtained through a two-level iterative solution. The scene scaling output module is used to reduce the optimized configuration capacity obtained by scene scaling and reproduction mechanism to the actual resource constraints of the empirical platform by a uniform scaling factor, and output the final equipment configuration details, scene matching verification results and constraint satisfaction report.

[0015] Furthermore, an electronic device is also provided, including: Memory, used for non-transitory storage of computer-readable instructions; and Processor, for executing the computer-readable instructions, When the computer-readable instructions are executed by the processor, they perform the method described in the first aspect above.

[0016] The above technical solution has the following advantages or beneficial effects: This invention proposes an integrated architecture that combines a multi-scenario adaptation system, a two-layer optimization model, a multi-dimensional deviation risk quantification mechanism, and scenario scaling and reproduction. This architecture transforms the construction goal of the empirical platform from traditional experience-based setting to scientific decision-making based on quantitative optimization. It effectively solves the problems of single scenario coverage, experience-dependent configuration, and difficulty in balancing reliability and economy in traditional platform design. The final empirical platform can accurately reproduce the core operating characteristics of various typical engineering scenarios, and significantly improve the confidence and engineering reference value of the empirical results while controlling construction and operation and maintenance costs. It provides a reliable and efficient quantitative decision-making basis for the verification, iteration, and implementation of new energy and energy storage technologies under the new power system. Attached Figure Description

[0017] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0018] Figure 1 Example 1: Framework diagram of design elements for a new energy and energy storage demonstration platform; Figure 2 This is a schematic diagram of the new energy and energy storage demonstration platform structure in Example 1; Figure 3 A detailed implementation flowchart for the design of a new energy and energy storage demonstration platform that meets the needs of multiple scenarios, as shown in Example 1; Figure 4 This is the Pareto solution set graph for the Logistic risk mapping in Example 1. Figure 5 This is the Pareto solution set diagram of the original deviation in Example 1; Figure 6 This is a bar chart comparing the overall capacity of Example 1. Detailed Implementation

[0019] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0020] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0021] All data acquisition in this embodiment is carried out in accordance with laws and regulations and with user consent, and the data is used legally.

[0022] Example 1 like Figure 3 As shown, this embodiment provides a design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios, specifically including: S1: Obtain the characteristics of typical application scenarios of new power systems, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and construct a scenario classification model covering multiple scenarios such as large-scale power transmission bases in the desert, offshore wind power bases, and source-grid-load-storage collaborative scenarios. S2: Establish an upper-level model for multi-objective optimization and a lower-level model for deviation calculation and constraint verification. Obtain the device number limit and capacity demand vector of the corresponding scenario in the scenario classification model as constraints. The upper-level model is used to solve the candidate set of configuration schemes for the new energy and energy storage demonstration platform. The lower-level model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper-level model to realize the feasibility assessment and reproducibility quantitative analysis of the scheme, and feeds the results back to the upper-level optimization. S3: The optimal configuration capacity is obtained through a two-level iterative solution; S4: Through scene scaling and reproduction mechanisms, the optimized configuration capacity is reduced to the actual resource constraints of the empirical platform by a unified scaling factor, and the final equipment configuration details, scene matching verification results and constraint satisfaction report are output.

[0023] For new power systems, in order to carry out specific design work on new energy and energy storage demonstration platforms, it is necessary to first clarify the construction goals and application boundaries of the new energy and energy storage demonstration platforms, such as... Figure 1 The design elements of the verification platform are clearly defined, including the types of scenarios that the platform needs to cover, such as desert and wasteland scenarios, offshore wind power scenarios, and integrated generation, grid, load and storage scenarios, etc. The core application requirements of each scenario are clearly defined, such as the types of equipment required, capacity ratios, and whether special equipment is required. The core optimization target boundaries of the platform are defined, considering the minimization of the two core objectives of total cost and deviation risk, that is, taking into account both economy and reliability. The priority adaptation rules of the two types of objectives are clearly defined, and the weights can be adjusted according to actual engineering needs.

[0024] The equipment selection range for the design platform, such as Figure 2 The system covers core equipment types including photovoltaic units, wind turbines, electrochemical energy storage, hydrogen energy storage, thermal power units, and load modules. It determines the technical parameters and cost data of the selected equipment types, constructs an equipment module pool based on actual engineering needs, and requires the module pool to differentiate between power-type equipment and establish a unique identifier and attribute mapping relationship for each module. It also sets configuration rules for each device under different scenarios and performance requirements such as the platform's overall new energy installation capacity limit and new energy type.

[0025] Multi-scenario classification and rule definition are carried out. For different typical scenarios, sub-scenarios are further subdivided to clarify the core characteristics of each sub-scenarios: for example, some sub-scenarios prohibit gas turbines, hydrogen energy-related equipment, some sub-scenarios focus on verifying the output characteristics of photovoltaic / wind power, and some sub-scenarios focus on the coordinated operation of electricity and hydrogen. Equipment configuration rules are formulated for each type of sub-scenarios, that is, the maximum number of single-type equipment in the scenario. The rules need to match the empirical needs of the scenario, and scenario capacity requirement rules are formulated to clarify the target capacity range of core equipment in each scenario, such as the lower limit of the total installed capacity of photovoltaic and wind power, and the capacity threshold of energy storage equipment.

[0026] Specifically, the scenario classification model defines the configuration rules and capacity requirements for different typical scenarios, expressed mathematically as follows: (1) In the formula, For scene collection, For the number of scenes, For the first i One scenario, As a scene type, For the first i Device limit for each scenario For the first i Capacity demand vector for each scenario.

[0027] The upper-level model of the multi-objective optimization model includes an objective function and constraints. The objective function includes minimizing the total cost of the empirical platform and minimizing the weighted deviation risk. The constraints include constraints on the number of devices, non-negative capacity constraints, lower capacity constraints, scenario adaptation constraints, integer constraints, and renewable energy proportion constraints.

[0028] Specifically, the upper-level objective function: 1) Total cost of the empirical platform: (2) (3) In the formula, It is the cost of equipment procurement and construction. It is to constrain the cost of punishment for violations. This is the baseline cost for operation and maintenance; n This refers to the total number of equipment types involved in the empirical platform, such as photovoltaic cells and electrolytic cells. It is the first i Number of devices configured It is the first i The unit purchase cost of this type of equipment It is the first i Unit installation cost of this type of equipment; It is the unit penalty coefficient for resource shortage. m This refers to the total number of resource types involved in the empirical platform. It is the first j Total demand for such resources It is the first j The actual supply of such resources The unit penalty coefficient for total deviation in hydrogen energy. It is the total matching deviation of the hydrogen energy system; It is the first i The unit annual operation and maintenance cost of this type of equipment It is the maintenance time of the empirical platform.

[0029] 2) Weighted bias risk: (4) (5) In the formula, This refers to the deviation risk obtained through the Logistic function mapping in the lower-level model for deviation calculation and constraint verification. The weighting of different deviation values ​​(type deviation, proportion deviation, hydrogen power matching deviation, and hydrogen capacity matching deviation) in each scenario can be adjusted appropriately according to the needs of different scenarios, so that the deviation risk and scenario can be accurately matched. After obtaining the original deviation value, it is processed according to the aforementioned normalization method and then mapped to the [0,1] interval through the Logistic function.

[0030] It should be noted that the slope coefficient in the Logistic function... inflection point of the function It needs to be set and adjusted according to the needs of different scenarios. For highly sensitive scenarios, such as offshore wind power, The value should be set higher, inflection point Moving the values ​​forward slightly indicates that even slight deviations could trigger a higher risk of deviation, requiring close monitoring.

[0031] Upper-level constraints: 1) Equipment quantity constraint: (6) In the formula, For the first i The maximum number of such devices that can be configured in the corresponding scenario should be limited to avoid excessive land use.

[0032] 2) Capacity non-negativity constraint: (7) In the formula, It is the first jThe actual total capacity of this type of equipment; No. j Number of devices of this type configured; It is the first j The rated capacity of a single unit (set) of equipment, i.e. the standard design capacity parameters of the equipment, is determined by the manufacturer or specifications.

[0033] 3) Capacity lower limit constraint (violation triggers penalty): (8) In the formula, It is the first j The minimum capacity to be configured for this type of device. If the configured capacity is lower than this value, a penalty set by the system will be triggered.

[0034] 4) Scene adaptation constraints Device disabling / restriction rules are set for different scenarios to ensure that the solution matches the characteristics of the scenario: (9) In the formula, It is the set of devices that are disabled in the current target scenario, determined by the environment and functional characteristics of the scenario.

[0035] The configuration of scenario devices needs to meet the actual engineering requirements. For example, in offshore wind power scenarios, it is necessary to disable equipment such as photovoltaic units and gas turbine units. This needs to be done manually in the device pool to avoid the platform design from deviating from reality and the heuristic algorithm evolution mutation direction from too much.

[0036] 5) Integer constraints (10) In the formula, For the set of natural numbers, ensure It should be 0 or a positive integer, consistent with the actual project where equipment is purchased in units / sets.

[0037] 6) Constraints on the proportion of renewable energy: (11) In the formula, It is the total capacity of all the photovoltaic devices configured. It is the total capacity of all the wind power equipment configured. It refers to the total capacity of all configured power generation equipment, including photovoltaic, wind power, and gas turbines. This is the required percentage of new energy installed capacity as specified by the system. The required percentage of new energy installed capacity must not be lower than this value, and it can be adjusted according to different project requirements.

[0038] The lower-level model for deviation calculation and constraint verification includes an objective function and constraints. The objective function is the minimum weighted deviation risk. The constraints include equipment quantity limits, integer constraints, system deviation constraints, special constraints, and capacity-power conversion constraints.

[0039] Specifically, the lower-level objective function: (12) The lower layer aims to minimize the risk deviation so that it can be fed back to the upper layer to solve the multi-objective problem.

[0040] Lower-level constraints: 1) Equipment quantity limit (13) In the formula, It is the lower level i The actual number of devices configured and used in this type of equipment; It is the first generated by the upper layer. i The number of these devices that can be selected by the lower level is [number].

[0041] 2) Integer constraints (14) In the formula, For the set of natural numbers, ensure It should be 0 or a positive integer, consistent with the actual project where equipment is purchased in units / sets.

[0042] 3) System deviation constraints (15) In the formula, This refers to type bias, which is the average relative deviation between the actual capacity of each device and the target capacity of the scenario. It is the maximum allowable threshold for type deviation, determined by the accuracy requirements of scenario empirical studies; It is the proportional deviation, that is, the Euclidean distance between the capacity ratio of each device and the target ratio of the scene. It is the maximum allowable threshold for proportional deviation, set according to the requirements of scene structure rationality.

[0043] 4) Specific constraints Different typical scenarios require different equipment, and the actual usage also varies. Therefore, it is necessary to impose specific constraints on specific typical scenarios. The following example illustrates the specific constraints for the electro-hydrogen coupling scenario.

[0044] Power matching constraints: Based on the actual engineering projects surveyed, it can be seen that there is a certain ratio between the electrolyzer, hydrogen storage tank, and fuel cell. The design of the empirical platform needs to be as close as possible to the actual engineering projects.

[0045] (16) In the formula, It is the lower limit of the power ratio between the fuel cell and the electrolyzer, which is determined by the minimum adaptability requirement of the hydrogen storage tank; It is the upper limit of the power ratio of fuel cells to electrolyzers, which is determined by the maximum adaptability requirement of hydrogen storage tanks; It is the total power of the electrolyzer, which is the core parameter that determines the hydrogen production capacity, and it is matched with the hydrogen inlet capacity of the hydrogen storage tank; It is the total power of the fuel cell, a core parameter that determines the amount of hydrogen used, and is matched with the hydrogen output of the hydrogen storage tank.

[0046] Capacity matching constraints: (17) In the formula, and These are the upper and lower limits of the ratio of hydrogen storage tank capacity to the total power of the electrolyzer, determined by the hydrogen storage demand corresponding to the hydrogen production rate of the electrolyzer. It is the total power of the electrolyzer, a core parameter representing hydrogen production capacity. This is the total capacity of the hydrogen storage tank, representing a core parameter for storing hydrogen energy; and These are the upper and lower limits of the ratio between the hydrogen storage tank capacity and the total power of the fuel cell, determined by the hydrogen storage demand corresponding to the hydrogen consumption rate of the fuel cell. It is the total power of the fuel cell, a core parameter representing the hydrogen utilization capacity.

[0047] 5) Capacity-to-power conversion constraints (18) In the formula, It is the first i Number of devices configured It is the first i The rated power of a single unit of this type of equipment, that is, the standard power parameter of a single unit of equipment. It is the first i The total installed power of a class of equipment, that is, the sum of the power of all equipment of that class; It is the first i The rated capacity of a single unit of equipment, i.e., the standard capacity parameter of a single unit of equipment, such as the hydrogen storage capacity of a single hydrogen storage tank. It is the first i The total capacity of a class of devices, that is, the sum of the capacities of all devices of that class.

[0048] The process of using NSGA-II to solve the upper-level model and the Gurobi solver to solve the lower-level model, obtaining the optimal configuration capacity through a two-layer iterative solution, is as follows: S31: Initialize parameters and module pool, input constraints, and set algorithm parameters such as population size, crossover probability, mutation probability, and maximum number of generations.

[0049] S32: Generate an initial population that meets the upper and lower limits of the number of devices. The population size is POP_SIZE, and each individual corresponds to a set of device configuration schemes. (19) In the formula, It is a set of initial configuration schemes for the algorithm. It refers to population size. It is the first k A candidate configuration scheme in an individual population; It is the first k In the first scheme i The number of such devices, and Integer constraints.

[0050] S33: Enter the upper-level NSGA-II optimization loop and perform the following operations for each generation of the population; S331: Individual Decoding Convert the number of units into quantifiable metrics such as equipment capacity and cost: (20) In the formula, It is the first k Among the individuals, the first i The actual total capacity of this type of equipment It is the first i Rated capacity of a single unit of this type of equipment; It is the first k Total equipment purchase cost for each individual It is the first i The unit purchase cost of this type of equipment.

[0051] S332: Lower-level Gurobi scenario solution. For each individual's corresponding equipment configuration scheme, an integer programming model is established using Gurobi. The constraint satisfaction is verified and the deviation index is calculated. The calculated deviation index and feasibility indicator are returned to the upper layer for use.

[0052] 1) Define decision variables Define a device selection variable, an integer variable, representing the number of units configured for each module.

[0053] 2) Establish constraints These include constraints on the number of equipment units, capacity, and hydrogen energy systems.

[0054] 3) Construct auxiliary variables for deviation calculation Define a bias auxiliary variable and calculate the type bias and proportion bias. a. Type bias auxiliary variable: (twenty one) In the formula, It is the first i The number of models included in this type of equipment. It is the first i The first type of equipment j Number of units configured for each model It is the first i Class of equipment j The rated capacity of a single unit for each model, It is the first i Target capacity for similar devices in various scenarios It is a very small positive number used to avoid division by zero.

[0055] By weighted summing of the absolute capacity deviations of all devices, a comprehensive type deviation is obtained, reflecting the overall degree of deviation between the capacity of a single device and the target scenario.

[0056] (twenty two) In the formula, It is the first i The type deviation weight of the device is set by the importance of the device in the scene. This represents the total number of equipment types.

[0057] b. Auxiliary variable for proportional deviation: (twenty three) In the formula, and They are the first i Class and First j In the class of devices, the first k Number of units configured for each model It is the first i Class and First j In the class of devices, the first k The rated capacity of a single unit of a particular model, that is, the standard design capacity of that model of equipment. and They are the first i Class and First j The ratio of the preset capacity requirement of the device type in the target scenario to the expected capacity of the scenario is the first-order value of the device. i Class and the j The capacity ratio of different types of equipment.

[0058] By weighted summing of the capacity ratio deviations of each pair of devices, a comprehensive ratio deviation is obtained, which reflects the overall degree of deviation between the capacity structure of the devices and the target scenario.

[0059] (twenty four) In the formula, It is the first i Class and the j Weighting of the proportional deviation of equipment types; It is the total number of pairs of devices that are not duplicated.

[0060] (c) Special deviation verification: There are many typical scenarios in new power systems, and different special deviation verification modules need to be designed for different scenarios.

[0061] Below is an example of a new hydrogen energy storage-specific deviation model for the electro-hydrogen coupling scenario, designed to ensure capacity / power matching in the hydrogen energy process.

[0062] Since the hydrogen production, storage, and discharge processes of a hydrogen energy system are decoupled from the electrolyzer, storage tank, and fuel cell, the platform design needs to consider the three types of equipment in a coordinated manner.

[0063] Hydrogen power matching deviation ( ): (25) In the formula, It is the target ratio of fuel cell power to electrolyzer power, representing the preset matching standard for the power generation-hydrogen production dimension of the hydrogen energy system.

[0064] Hydrogen capacity matching deviation ( ): (26) In the formula, It is the target ratio of the energy capacity of the hydrogen storage tank to the power of the electrolyzer, representing the preset matching standard in the dimension of hydrogen storage capacity - hydrogen production power; It is the target ratio of hydrogen storage tank energy capacity to fuel cell power, and it is a preset matching standard in the dimension of hydrogen storage capacity and hydrogen power generation capacity.

[0065] The above are just examples of electro-hydrogen coupling scenarios. Further detailed modeling and analysis can be carried out according to the specific needs of different scenarios.

[0066] 4) Calculate the original deviation value and map it to the [0,1] interval using the Logistic function to obtain the deviation risk value.

[0067] In engineering demonstrations, small deviations are generally acceptable and pose extremely low risk; however, when the deviation exceeds a certain threshold (e.g., >20%), the confidence level of the demonstration results will decrease exponentially and eventually tend to saturate. The S-curve characteristic of the Logistic function perfectly matches this engineering characteristic. Therefore, in the optimization design scheme of the new energy and energy storage demonstration platform, the Logistic mapping function is used to map the original deviation value to the [0,1] interval, realizing the standardization and nonlinear scaling of deviation risk, and adapting to the sensitivity requirements of deviation risk in engineering scenarios.

[0068] Basic Logistic mapping function: (27) In the formula, The slope coefficient determines the rate of function growth. The higher the value, the steeper the rate of change of the function near the inflection point, and the higher the sensitivity to the threshold. Given the inflection point of the function, it is set based on the control benchmark of the industry empirical platform and serves as the critical reference point for the original deviation value. It can also be adjusted according to different needs.

[0069] Preprocessing of raw deviation values. Since there is no strict upper limit to the range of raw deviation values, to avoid extreme values ​​causing saturation of the Logistic function (output approaching 1), the raw deviation values ​​can be preprocessed by normalization: (28) In the formula, The preset upper limit threshold for deviation risk is set based on historical data or engineering specifications to ensure... .

[0070] The adapted Logistic function is: (29) 5) Solution and Feasibility Assessment Call the Gurobi solver. If the solution status is optimal (GRB.OPTIMAL), time-limited (GRB.TIME_LIMIT), or suboptimal (GRB.SUBOPTIMAL), the solution is deemed feasible and the deviation index is output; otherwise, it is marked as infeasible and a penalty mechanism is triggered.

[0071] S333: Individual fitness assessment: The objective function is calculated for each individual in the population, and the results are stored in a cache.

[0072] Calculate the objective function and substitute it into the total cost. f 1. Weighted Bias Risk f Formula 2 yields the individual's target value: (30) In the formula, Let the total cost value be that of the k-th individual. This is the weighted bias risk value for the k-th individual.

[0073] Cache storage, establish key-value pairs When encountering the same individual again, the cached result will be called directly.

[0074] S334: Quick Non-Dominant Sort The population is divided into different frontier layers according to the dominance relationship. The first frontier layer is the non-dominated solution, that is, no other individual is better at both objectives.

[0075] Definition of dominance relationship: If individual A satisfies If A dominates B, and at least one inequality holds strictly, then A is said to dominate B.

[0076] Frontier layer generation: a. Traverse the population and count the number of times each individual is dominated. n p and the dominant set of individuals S p ; b. Order n p Individuals with a value of 0 are in the first frontier layer. F 1; c. To F Each individual in 1, the individual it controls. q of n q Subtract 1, if n q =0, then q Add a second frontier layer F 2; d. Repeat the above process until all individuals have been assigned to the frontal layer. F 1, F 2,..., F m .

[0077] S335: Congestion Calculation: Calculate the crowding density of individuals within each front layer to reflect the sparsity of individuals in the target space, thus ensuring population diversity: a. For the frontier layer F l Individuals in, according to f 1. Sort in ascending order to obtain the sequence.

[0078] b. Calculate the crowding degree for the sorted individuals. Ip : (31) In the formula, For the first in this frontier layer m The maximum and minimum values ​​of each target; c. Set the first and last individuals in the sequence. This is to ensure that the boundary solution is not eliminated.

[0079] S336: Genetic Operations Offspring populations are generated through selection-crossover-mutation: a. Tournament selection, randomly chosen. k =3 individuals, select the individual with the highest non-dominant level and the greatest crowding as the parent. b. Uniform crossover: Perform uniform crossover on the two parent generations with a crossover probability CX_PROB=0.8 to generate offspring C: (32) In the formula, It is the first parent individual's first i One gene locus, The second parent individual's first i One gene locus, Generate a random number that is uniformly distributed in the range of 0 to 1.

[0080] c. Random mutation, adjusting the number of devices in an individual, with a mutation range of [missing value]. : (33) In the formula, It is the mutated first i The gene locus, corresponding to the _ ... i Number of units configured for this type of device It is the first i The lower limit constraint on the number of equipment units, that is, the minimum allowable number of equipment units in the project. It is the first i The upper limit constraint on the number of devices of a certain type, that is, the maximum allowable number of devices in the project. Before the mutation i The values ​​of each gene locus.

[0081] S337: Population Update By merging the parent and offspring populations and selecting from them, the next generation population can be obtained. a. According to the priority of the frontier layer ( F 1> F 2>...) Individuals are added to the next generation of the population in sequence; b. If the population size exceeds a given value after adding a certain front layer, select the individual with the highest crowding in that front layer until the population size is POP_SIZE.

[0082] S338: Iteration Termination Judgment Repeat the above loop until the population reaches the set upper limit for the number of generations, then terminate the iteration and output the first frontier layer. F 1 is the Pareto optimal solution.

[0083] S339: Output Pareto front solution Extract the optimal cost solution, the optimal deviation risk solution, and the compromise solution from the Pareto solution set, and provide detailed equipment configuration details, scenario matching verification results, and constraint satisfaction reports.

[0084] The optimal cost solution, selected from the Pareto solution set, is the total cost. f The minimum solution: (34) The optimal deviation risk solution is selected from the Pareto solution set by weighted deviation risk. f 2. Minimal solution: (35) The compromise solution uses a standardized weighted sum method, which normalizes costs and deviation risks, sums them by weight, and selects the solution with the minimum weighted sum. a. Standardization Objectives (36) b. Weighted sum calculation (37) In the formula, It is the weighting coefficient of the multi-objective comprehensive evaluation, which indicates the importance of allocating the two normalized objective functions.

[0085] The weight coefficients of the two objective functions can be set according to the specific engineering requirements. In this study, they are set to 0.3 and 0.7, taking deviation risk as the main factor to be considered in the design of the empirical platform, while also taking into account economic efficiency to a certain extent.

[0086] c. Compromise (38) The actual engineering projects of each typical scenario in a new power system are often on a relatively large scale in terms of new energy installed capacity and equipment capacity, while the demonstration platform base is relatively limited in terms of both resource endowment and engineering funding, making it difficult to reproduce the typical scenarios one-to-one. This invention, through adjustment of the normalized scaling function, can ensure that different equipment ratios match the specific circumstances of actual projects, while also taking into account requirements such as economy to a certain extent.

[0087] Figure 4 This shows the Pareto solution set after the Logistic risk mapping. Figure 5 This is the Pareto solution set under the original bias. As can be seen from the comparison, after mapping with the Logistic function, the solution set is more sparsely distributed in the high-risk region, which helps in screening low-risk solutions. Figure 6 A bar chart comparing the total capacity of the optimal cost solution, the optimal deviation risk solution, and the compromise solution is presented, showing that the compromise solution achieves a good balance between total cost and deviation risk. These results verify the effectiveness of the method presented in this invention.

[0088] The physical formula for the scene scaling and reproduction mechanism is: (39) In the formula, It refers to the actual capacity or power of equipment in typical scenarios in actual engineering projects. This is the equipment scaling factor, which can be specified according to the actual engineering requirements. The empirical platform obtained through scaling calculations represents the equipment capacity or power required to recreate a typical scenario.

[0089] Example 2 The purpose of this embodiment is to provide a design system for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios; including: The scenario classification model construction module obtains the characteristics of typical application scenarios of the new power system, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and constructs scenario classification models covering multiple scenarios such as large-scale power transmission bases in desert areas, offshore wind power bases, and source-grid-load-storage collaborative scenarios. The two-layer optimization solution module establishes an upper-layer model for multi-objective optimization and a lower-layer model for deviation calculation and constraint verification. It obtains the device number limit and capacity demand vector of the corresponding scenario in the scenario classification model as constraints. The upper-layer model is used to solve the candidate set of configuration schemes for the new energy and energy storage demonstration platform. The lower-layer model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper layer, realizes the feasibility assessment and reproducibility quantitative analysis of the scheme, and feeds the results back to the upper-layer optimization. The optimal configuration capacity is obtained through a two-level iterative solution. The scene scaling output module is used to reduce the optimized configuration capacity obtained by scene scaling and reproduction mechanism to the actual resource constraints of the empirical platform by a uniform scaling factor, and output the final equipment configuration details, scene matching verification results and constraint satisfaction report.

[0090] The proposed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and the division of modules described above is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0091] Example 3 This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory to cause the electronic device to perform the method described in Embodiment 1.

[0092] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0093] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0094] In the implementation process, each step of the above method can be completed by the integrated logic circuits in the processor hardware or by software instructions.

[0095] The method in Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0096] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0097] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios, characterized in that, include: To obtain the characteristics of typical application scenarios of new power systems, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and to construct a scenario classification model covering multiple scenarios such as large-scale power transmission bases in desert areas, offshore wind power bases, and source-grid-load-storage collaborative scenarios; A multi-objective optimization upper-level model and a deviation calculation and constraint verification lower-level model are established. The device number limit and capacity demand vector of the corresponding scenario in the scenario classification model are obtained as constraints. The upper-level model is used to solve the configuration scheme candidate set of the new energy and energy storage demonstration platform. The lower-level model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper-level model, realizes the feasibility assessment and reproducibility quantitative analysis of the scheme, and feeds the results back to the upper-level optimization. The optimal configuration capacity is obtained through a two-level iterative solution. Through scene scaling and reproduction mechanisms, the optimal configuration capacity obtained through optimization is reduced to the actual resource constraints of the empirical platform by a unified scaling factor, and the final equipment configuration details, scene matching verification results and constraint satisfaction report are output.

2. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The upper-level model is solved using NSGA-II, and the lower-level model is solved using Gurobi.

3. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The upper-level model includes an objective function and constraints; the objective function includes minimizing the total cost of the empirical platform and minimizing the weighted bias risk; the constraints include constraints on the number of devices, non-negative capacity constraints, lower capacity constraints, scenario adaptation constraints, integer constraints, and renewable energy proportion constraints.

4. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The lower-level model includes an objective function and constraints; the objective function is to minimize risk deviation; the constraints include equipment quantity limits, integer constraints, system deviation constraints, special constraints, and capacity-power conversion constraints.

5. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The deviation quantification includes the calculation of multi-dimensional deviation indicators such as type deviation, proportion deviation, and specific deviation.

6. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The risk mapping uses the Logistic function to map the original deviation value to a risk value in the [0,1] interval, and the slope coefficient and inflection point parameter of the Logistic function are dynamically adjusted according to the scenario deviation risk sensitivity.

7. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The specific process of the two-layer iterative solution includes: initializing parameters and module pools to generate an initial population; entering the upper-layer NSGA. II. Optimize the loop, calling the lower-level Gurobi solver for each individual to verify constraints and calculate deviation indices. Obtain the deviation risk value through the Logistic function mapping. If feasible, output the deviation index; otherwise, trigger the penalty mechanism. After evaluating individual fitness, generate offspring populations through fast non-dominated sorting, crowding calculation, and genetic operations. Merge parents and offspring and select a new generation population. Repeat the loop until the maximum number of generations, outputting the Pareto optimal solution. Extract the best cost solution, the best deviation risk solution, and the compromise solution from it, and provide equipment configuration details and a verification report.

8. The design method for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios as described in claim 1, characterized in that, The scenario scaling and reproduction mechanism uses a uniform scaling factor to linearly scale the optimal configuration capacity obtained through optimization, keeping the capacity ratio between devices unchanged, so that the scaled solution adapts to the resource constraints of the empirical platform and still meets the reproduction requirements of each scenario.

9. A design system for a new energy and energy storage demonstration platform that meets the needs of multiple scenarios, characterized in that: The method described by any one of claims 1-8 comprises: The scenario classification model construction module obtains the characteristics of typical application scenarios of the new power system, including equipment type information, equipment configuration rules, and capacity requirements for each scenario, and constructs scenario classification models covering multiple scenarios such as large-scale power transmission bases in desert areas, offshore wind power bases, and source-grid-load-storage collaborative scenarios. The two-layer optimization solution module establishes an upper-layer model for multi-objective optimization and a lower-layer model for deviation calculation and constraint verification. It obtains the device number limit and capacity demand vector of the corresponding scenario in the scenario classification model as constraints. The upper-layer model is used to solve the candidate set of configuration schemes for the new energy and energy storage demonstration platform. The lower-layer model performs constraint verification, deviation quantification and risk mapping on each device configuration candidate scheme generated by the upper layer, realizes the feasibility assessment and reproducibility quantitative analysis of the scheme, and feeds the results back to the upper-layer optimization. The optimal configuration capacity is obtained through a two-level iterative solution. The scene scaling output module is used to reduce the optimized configuration capacity obtained by scene scaling and reproduction mechanism to the actual resource constraints of the empirical platform by a uniform scaling factor, and output the final equipment configuration details, scene matching verification results and constraint satisfaction report.

10. An electronic device, characterized in that, include: Memory, one or more processors; The electronic device also includes one or more computer programs, wherein the processor and the memory are connected via a bus, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-8.

Images