Green electricity direct connection system configuration method, device, equipment, medium and product

Abstract

The application discloses a green electricity direct connection system configuration method, device, equipment, medium and product, relates to the electric power technical field, and the method comprises the following steps: acquiring time sequence data and boundary parameters, wherein the time sequence data is used for representing data changing with time in the green electricity direct connection system, and the boundary parameters are used for representing constraint parameters in the green electricity direct connection system; candidate capacity sets of a transformer are determined according to the time sequence data and the boundary parameters; a plurality of candidate capacities in the candidate capacity sets are used to determine a plurality of groups of target energy storage parameters corresponding to the plurality of candidate capacities by using a preset algorithm, wherein the plurality of candidate capacities and the plurality of groups of target energy storage parameters are one-to-one corresponding; target configuration parameters are determined according to the plurality of candidate capacities and the plurality of groups of target energy storage parameters; and the green electricity direct connection system is configured according to the target configuration parameters. The application solves the technical problem that, in the prior art, the energy storage system and the transformer capacity are independently planned when the green electricity direct connection system is configured, and it is difficult to balance the economy and stability.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method, apparatus, equipment, medium and product for configuring a green electricity direct connection system. Background Technology

[0002] The large-scale development and application of new energy sources such as wind and solar power have become a core path for promoting energy structure transformation, giving rise to the green electricity direct connection model. According to the definition of the green electricity direct connection model in relevant policy documents, this model specifically refers to a power supply mode where new energy power generation projects are not directly connected to the public power grid, but instead supply green electricity to a single power user through a dedicated direct connection line, enabling clear physical traceability of the supplied electricity. Because it can effectively reduce grid transfer losses and ensure the authenticity of green electricity consumption, this model has gradually become the mainstream choice for large single power users in industries and commerce to achieve green energy use, and has broad application prospects.

[0003] The preliminary work for wind power projects encompasses several key stages, including project approval and filing, application, planning, proposal preparation, and feasibility studies, generally facing the challenges of tight deadlines and heavy workloads. Among these, wind power output and generation calculations are the core of the preliminary work. They directly relate to the assessment of the wind energy resource conditions at the project site and are crucial for wind farm site selection, rate-of-return calculations, and corporate investment decisions. They also serve as key input boundaries for grid connection configuration schemes and power dispatch during operation. However, despite the significant advantages of direct green power connections, in application scenarios where direct lines connect to the low-voltage side of the user's step-down substation, the planning of energy storage systems and transformer capacities in existing configuration technologies is independent, making it difficult to achieve a balance between the overall economic efficiency and stability of the system, even after determining the key input boundaries. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, equipment, medium and product for configuring a green electricity direct connection system, which can solve the technical problem in the prior art where the energy storage system and transformer capacity are planned independently, making it difficult to balance economy and stability.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for configuring a green electricity direct connection system, including: Acquire time-series data and boundary parameters, where time-series data is used to characterize the data that changes over time in the green electricity direct connection system, and boundary parameters are used to characterize the constraint parameters in the green electricity direct connection system; Based on time series data and boundary parameters, determine the candidate capacity set for the transformer; Using a preset algorithm, multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set are determined, wherein multiple candidate capacities and multiple sets of target energy storage parameters correspond one-to-one; The target configuration parameters are determined based on multiple candidate capacities and multiple sets of target energy storage parameters; Configure the green electricity direct connection system according to the target configuration parameters.

[0006] Optionally, a candidate capacity set for the transformer is determined based on time-series data and boundary parameters, specifically including: determining the apparent power sequence of the load based on the user load curve, wherein the user load curve is included in the time-series data; determining the capacity reference value based on the apparent power sequence of the load; and determining the candidate capacity set based on the capacity reference value and the transformer capacity reduction step size, wherein the transformer capacity reduction step size is included in the boundary parameters.

[0007] Optionally, a preset algorithm is used to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set. Specifically, this includes: for each candidate capacity in the candidate capacity set, using the preset algorithm, generating multiple sets of energy storage parameters to be screened for each candidate capacity; simulating the multiple sets of energy storage parameters to be screened according to a preset simulation strategy to obtain the performance indicators corresponding to the multiple sets of energy storage parameters to be screened; determining the fitness score of the multiple sets of energy storage parameters to be screened based on the performance indicators and a pre-constructed fitness function; and determining the target energy storage parameters corresponding to each candidate capacity from the multiple sets of energy storage parameters to be screened for each candidate capacity based on the fitness score to obtain multiple sets of target energy storage parameters.

[0008] Optionally, the construction of the fitness function includes: constructing system constraints, wherein the system constraints include transformer capacity constraints, energy storage operation constraints, and power balance constraints; and constructing the fitness function based on the system constraints, energy cost, and curtailment rate.

[0009] Optionally, the target configuration parameters are determined based on multiple candidate capacities and multiple sets of target energy storage parameters. Specifically, this includes: using a preset economic calculation strategy to determine multiple economic scores corresponding to multiple configuration schemes, wherein each configuration scheme includes a candidate capacity and its corresponding set of target energy storage parameters; and determining the target configuration parameters based on the multiple economic scores.

[0010] Optionally, a preset economic calculation strategy is used to determine multiple economic scores corresponding to multiple configuration schemes. Specifically, this includes: determining the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes according to the preset economic calculation strategy; performing sensitivity analysis on multiple configuration schemes to obtain multiple sensitivity coefficients; and determining multiple economic scores based on the multiple sensitivity coefficients, the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes.

[0011] Secondly, this application provides a green electricity direct connection system configuration device, comprising: The system comprises the following modules: an acquisition module for acquiring time-series data and boundary parameters, wherein the time-series data characterizes the data changing over time in the green power direct connection system, and the boundary parameters characterize the constraint parameters in the green power direct connection system; a first determination module for determining a candidate capacity set for transformers based on the time-series data and boundary parameters; a second determination module for determining multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set using a preset algorithm, wherein the multiple candidate capacities and multiple sets of target energy storage parameters correspond one-to-one; a third determination module for determining target configuration parameters based on the multiple candidate capacities and multiple sets of target energy storage parameters; and a configuration module for configuring the green power direct connection system based on the target configuration parameters.

[0012] Optionally, the first determining module is further configured to: determine the apparent power sequence of the load based on the user load curve, wherein the user load curve is included in the time series data; determine the capacity reference value based on the apparent power sequence of the load; and determine the candidate capacity set based on the capacity reference value and the transformer capacity reduction step size, wherein the transformer capacity reduction step size is included in the boundary parameters.

[0013] Optionally, the second determining module is further configured to: for each candidate capacity in the candidate capacity set, generate multiple sets of energy storage parameters to be screened corresponding to each candidate capacity using a preset algorithm; simulate the multiple sets of energy storage parameters to be screened according to a preset simulation strategy to obtain the performance indicators corresponding to the multiple sets of energy storage parameters to be screened respectively; determine the fitness score of the multiple sets of energy storage parameters to be screened based on the performance indicators and the pre-constructed fitness function; and determine the target energy storage parameters corresponding to each candidate capacity from the multiple sets of energy storage parameters to be screened corresponding to each candidate capacity based on the fitness score to obtain multiple sets of target energy storage parameters.

[0014] Optionally, the second determining module is further configured to: construct system constraints, wherein the system constraints include transformer capacity constraints, energy storage operation constraints, and power balance constraints; and construct a fitness function based on the system constraints, energy costs, and curtailment rate.

[0015] Optionally, the third determining module is further configured to: determine multiple economic scores corresponding to multiple configuration schemes using a preset economic calculation strategy, wherein each configuration scheme includes a candidate capacity and a corresponding set of target energy storage parameters; and determine target configuration parameters based on multiple economic scores.

[0016] Optionally, the third determining module is also used to: determine the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes according to a preset economic calculation strategy; perform sensitivity analysis on multiple configuration schemes to obtain multiple sensitivity coefficients; and determine multiple economic scores based on the multiple sensitivity coefficients, the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes.

[0017] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the green electricity direct connection system configuration method described in any one of the above.

[0018] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the green electricity direct connection system configuration method described above.

[0019] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the green electricity direct connection system configuration method described above.

[0020] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, equipment, medium, and product for configuring a green electricity direct connection system. The method acquires time-series data and boundary parameters of the green electricity direct connection system to provide data support for collaborative optimization. Secondly, by determining a set of candidate transformer capacities, it avoids the blindness of traditional experience-based capacity selection and provides a multi-faceted selection basis for the collaborative matching of energy storage parameters and transformer capacity. Thirdly, it uses a preset algorithm to synchronously optimize the corresponding target energy storage parameters for each candidate transformer capacity, achieving a one-to-one correspondence and collaborative adaptation between transformer capacity and energy storage parameters, improving the situation of independent planning for both, and ensuring that the energy storage parameter configuration fits the capacity constraints of the corresponding transformer. Finally, by selecting and determining the target configuration parameters from multiple candidate configurations and using them for system configuration, it can achieve a dynamic balance between green electricity output, user load, transformer capacity, and energy storage parameters in the green electricity direct connection system. This avoids the overload risk caused by insufficient transformer capacity, ensures system operational stability, reduces investment waste caused by transformer capacity redundancy and unreasonable energy storage configuration, and improves the economic efficiency of system operation. Thus, it solves the technical problem in the prior art where energy storage system and transformer capacity are planned independently, making it difficult to balance economy and stability when configuring green electricity direct connection systems. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is an application environment diagram of a green electricity direct connection system configuration method according to an embodiment of this application; Figure 2 A flowchart illustrating a green electricity direct connection system configuration method provided in an embodiment of this application; Figure 3 A schematic diagram of the architecture of a green electricity direct connection system provided in an embodiment of this application; Figure 4 A flowchart illustrating a green electricity direct connection system configuration method provided in an embodiment of this application; Figure 5 A schematic diagram of a green electricity direct connection system configuration device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] The green electricity direct connection system configuration method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send time-series data and boundary parameters to server 104. After receiving the time-series data and boundary parameters, server 104 uses a preset algorithm to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set, wherein the multiple candidate capacities and multiple sets of target energy storage parameters correspond one-to-one; based on the multiple candidate capacities and multiple sets of target energy storage parameters, target configuration parameters are determined; based on the target configuration parameters, the green electricity direct connection system is configured. Server 104 can feed back the obtained target configuration parameters to terminal 102. Furthermore, in some embodiments, the green electricity direct connection system configuration method can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly process the time-series data and boundary parameters, or server 104 can obtain the time-series data and boundary parameters from the data storage system and process them.

[0026] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, and IoT devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0027] In one exemplary embodiment, such as Figure 2 As shown, a method for configuring a green electricity direct connection system is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 205. Wherein: Step S201: Obtain time-series data and boundary parameters, wherein the time-series data is used to characterize the data that changes over time in the green electricity direct connection system, and the boundary parameters are used to characterize the constraint parameters in the green electricity direct connection system.

[0028] In this embodiment of the invention, step S201 is the basic prerequisite for the entire green electricity direct connection system configuration method. The task is to collect and organize the data required for system operation, so as to provide a data foundation for subsequent steps.

[0029] Among them, time-series data is used to characterize the data changing over time in the green electricity direct connection system. It records the dynamic operating status of the system at a fixed time resolution (which can be on an hourly basis) and includes three types of data, which work together to support subsequent steps: Green electricity output curve: A continuous hourly output curve of renewable energy power generation equipment (such as wind power and photovoltaics) in the green electricity direct connection system, recording the output over 8760 hours throughout the year, visually reflecting the intermittent and fluctuating characteristics of green electricity output; User load curve (including active load P at time t). L (t), reactive load Q at time t L (t)), in hours, records the continuous curve of a single user's electricity demand for 8760 hours throughout the year in the green electricity direct connection system; time-series electricity price data, in hours, records the continuous data of electricity price standards for different time periods in the system, which is consistent with the time resolution of the green electricity output curve and the user load curve, including peak, valley and normal differentiated electricity prices.

[0030] Boundary parameters characterize the constraints in a green electricity direct-connection system and are the hard conditions that limit the system's safe, compliant, and economical operation. They include six categories of parameters: New energy installed capacity: The total installed capacity of green electricity supply equipment, serving as the upper limit constraint for green electricity output; Power factor: The ratio of active power to apparent power, reflecting energy utilization efficiency and constraining the actual carrying capacity of transformers; Transformer rated capacity: The maximum apparent power that a transformer can carry for long-term safe operation, which is the core safety constraint for transformer operation; Transformer capacity reduction step size: A fixed reduction interval when screening candidate transformer capacities, standardizing the candidate set screening logic; Discount rate: A ratio that measures the time value of money, used for full life cycle economic accounting; Energy storage charging and discharging efficiency: The energy conversion efficiency of the energy storage system, reflecting the degree of energy loss and constraining energy storage operation strategies.

[0031] It should be noted that in the time series data, the green electricity output curve is calculated based on the new energy resource endowment of the project location, the user load curve is obtained based on historical data or user annual electricity consumption combined with load characteristics, and the electricity price data is obtained based on the electricity price policy of the province where the project is located and the transaction electricity price information disclosed by the power trading center.

[0032] Optionally, in some embodiments of the present invention, it is necessary to perform completeness and rationality checks on the acquired data. For completeness checks, if the data missing rate is ≤5%, interpolation fitting is used to supplement the data; if the data missing rate is >5%, the user is prompted to supplement the data; if the continuous data missing duration is >24 hours, the user is prompted to manually input or replace the missing data segment. For rationality checks, this includes load non-negativity checks, power factor within a preset range (default 0.85~1.0) checks, and load change rate ≤30% between adjacent time points (excluding impact loads); for detected outliers, adjacent mean replacement is used for correction; missing values ​​are filled using linear interpolation.

[0033] Step S201 above, by comprehensively acquiring the two types of data, provides unified and complete support for the subsequent coordinated optimization of transformers and energy storage, ensuring that the optimization results are consistent with the actual operating conditions of the system.

[0034] Step S202: Determine the candidate capacity set of the transformer based on the time series data and boundary parameters.

[0035] In this embodiment of the invention, step S202 is to select a series of reasonable and feasible transformer capacity candidate values ​​based on the time series data and boundary parameters obtained in S201, forming a candidate capacity set, which provides a basis for multiple selections for subsequent coordinated matching with energy storage parameters.

[0036] For example, based on the green electricity output curve and user load curve in the time series data, the maximum power demand after their superposition is calculated, that is, the extreme operating condition power of the superposition of the peak green electricity output and the peak user load, and the minimum carrying capacity requirement that the transformer capacity must meet is determined; combined with the transformer rated capacity (limiting the upper limit of capacity), new energy installed capacity (assisting in calculating the extreme operating condition power), and power factor (converting apparent power into active power to accurately determine carrying capacity) in the boundary parameters, two types of unreasonable capacity are eliminated: one is transformers with too small a capacity (unable to carry extreme operating condition power, which is prone to overload risk), and the other is transformers with too high capacity redundancy (far exceeding the actual power demand, resulting in wasted equipment investment); according to the decreasing step size of the transformer capacity in the boundary parameters, from the maximum reasonable capacity to the minimum reasonable capacity, multiple sets of transformer capacities that meet the requirements of safe operation and economic feasibility are screened out, and finally a set of candidate transformer capacities is formed.

[0037] Step 202 above, through the coordinated application of time series data and boundary parameters, not only ensures that each candidate capacity can meet the requirements for safe system operation, but also avoids the overload risk or investment waste caused by blind selection, and provides a structured and comparable alternative basis for subsequent collaborative optimization.

[0038] Step S203: Using a preset algorithm, determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set, wherein the multiple candidate capacities and the multiple sets of target energy storage parameters correspond one-to-one.

[0039] In this embodiment of the invention, step S203 is the core link in solving the independent planning of energy storage and transformers. The task is to use a preset optimization algorithm to match a set of optimal energy storage parameters for each transformer capacity in the candidate capacity set, so as to achieve one-to-one correspondence and coordinated adaptation between the two.

[0040] For example, the first step is to select a preset algorithm, such as an intelligent optimization algorithm (e.g., genetic algorithm, particle swarm optimization). The core objective of the algorithm is to ensure that the energy storage parameters are highly compatible with the corresponding transformer capacity, while also considering system operating efficiency and economy. Then, optimization is performed one by one, with each candidate transformer capacity in the candidate capacity set being optimized individually. Taking the transformer capacity as the core constraint, combined with the green electricity output curve and user load curve in the time series data, as well as the energy storage charging and discharging efficiency and power factor in the boundary parameters, the algorithm iteratively optimizes to find a set of optimal energy storage parameters (including the maximum charging and discharging power of energy storage and the rated capacity of energy storage). Finally, a one-to-one correspondence is formed between a candidate transformer capacity and a set of target energy storage parameters, i.e., multiple sets of transformer capacity-energy storage parameter pairing schemes. This ensures that in each scheme, the energy storage parameters strictly fit the capacity constraints of the corresponding transformer, while adapting to the fluctuation characteristics of green electricity output and user load, avoiding problems of improper adaptation.

[0041] Step S203 above breaks through the drawbacks of independent planning of energy storage and transformer in the existing technology, and realizes synchronous and coordinated optimization of the two. The energy storage parameters are no longer designed independently, but are constrained by the corresponding transformer capacity and combined with the operating characteristics reflected by time series data to achieve precise matching. This effectively avoids problems such as low system efficiency (e.g., energy storage charging and discharging power exceeds the transformer's carrying capacity) and waste of equipment investment (e.g., energy storage capacity is too large but the transformer cannot carry its output) caused by improper matching of the two, and lays the foundation for achieving a balance between economy and stability in the future.

[0042] Step S204: Determine the target configuration parameters based on multiple candidate capacities and multiple sets of target energy storage parameters.

[0043] In this embodiment of the invention, the task of step S204 is to select the set with the best overall performance from the multiple sets of transformer capacity-energy storage parameter matching schemes obtained in S203, and use it as the target configuration parameter for the green electricity direct connection system.

[0044] For example, a comprehensive evaluation system is first established, with evaluation dimensions covering three major categories of indicators, all of which need to be calculated using time-series data and boundary parameters: Operational stability indicators: By combining time-series data to simulate 8760 hours of operation throughout the year, the overload duration of the transformer and the number of times the energy storage SOC exceeds the limit are calculated to determine whether the scheme meets the safety constraints in the boundary parameters (such as the rated capacity of the transformer and the energy storage SOC range). Economic indicators: By combining time-series electricity price data and the discount rate in the boundary parameters, the total life cycle investment cost, operation and maintenance cost, green electricity consumption revenue, and surplus electricity grid connection revenue are calculated to accurately determine the economic feasibility of the plan; System efficiency indicators: By combining the green electricity output curve and user load curve in the time series data, the green electricity absorption rate and curtailment rate are calculated. Combined with the energy storage charging and discharging efficiency in the boundary parameters, the energy utilization efficiency of the scheme is judged.

[0045] Then, multiple schemes are compared and the best one is selected. For each set of transformer capacity-energy storage parameter matching schemes, the above three types of indicators are calculated one by one. The comprehensive performance of each scheme is compared and the best comprehensive scheme with no overload risk, high green electricity consumption rate, reasonable investment cost and convenient operation and maintenance is selected. The transformer capacity and energy storage parameters corresponding to this scheme are the target configuration parameters.

[0046] The above step S204 avoids the limitations of a single solution by comparing and selecting the best among multiple options. At the same time, relying on the accurate support of time series data and boundary parameters, it ensures that the final target configuration parameters can not only meet the safe and stable operation requirements of the green electricity direct connection system (such as avoiding transformer overload), but also minimize equipment investment and operating costs (such as reducing capacity redundancy waste), achieving a balance between stability and economy, and providing a clear and feasible basis for the actual configuration of the system.

[0047] Step S205: Configure the green electricity direct connection system according to the target configuration parameters.

[0048] In this embodiment of the invention, step S205 is the implementation phase of the solution. According to the target configuration parameters determined in step S204, the actual equipment selection and engineering configuration of the green electricity direct connection system are completed, i.e., selecting transformers of the corresponding capacity level and configuring energy storage systems with matching rated power and capacity. Based on this collaboratively optimized configuration scheme, the green electricity direct connection system can adapt to the dynamic fluctuations of green electricity output and user load during actual operation, achieving a dynamic balance between power supply and demand. This avoids overload problems caused by insufficient transformer capacity, ensuring system operational stability, and reduces investment waste caused by transformer capacity redundancy and unreasonable energy storage configuration, improving the overall operational economy of the system. Ultimately, it achieves dual optimization of the green electricity direct connection system's operational stability and economy, effectively solving the technical problem of balancing energy storage and transformer independent planning in existing technologies.

[0049] Through the above embodiments, the method provided by the present invention provides data support for collaborative optimization by acquiring time-series data and boundary parameters of the green electricity direct connection system. Secondly, by determining the candidate transformer capacity set, it avoids the blindness of traditional experience-based capacity selection and provides a multi-selection basis for the collaborative matching of energy storage parameters and transformer capacity. Thirdly, by using a preset algorithm to synchronously optimize the corresponding target energy storage parameters for each candidate transformer capacity, it achieves a one-to-one correspondence and collaborative adaptation between transformer capacity and energy storage parameters, improving the situation of independent planning of the two and making the energy storage parameter configuration fit the capacity constraints of the corresponding transformer. Finally, by selecting and determining the target configuration parameters from multiple candidate configurations and using them for system configuration, it can achieve a dynamic balance between green electricity output, user load, transformer capacity and energy storage parameters in the green electricity direct connection system. This avoids the overload risk caused by insufficient transformer capacity, ensures the stability of system operation, reduces investment waste caused by transformer capacity redundancy and unreasonable energy storage configuration, and improves the economic efficiency of system operation. Thus, it solves the technical problem in the prior art that when configuring a green electricity direct connection system, the energy storage system and transformer capacity are planned independently, making it difficult to balance economy and stability.

[0050] Optionally, in step S202, the candidate capacity set of the transformer is determined based on the time series data and boundary parameters, specifically including the following steps: Step S2021: Determine the apparent power sequence of the load based on the user load curve, wherein the user load curve is included in the time series data.

[0051] In this embodiment of the invention, step S2021 is the basic calculation step for screening candidate transformer capacities. The task is to calculate the apparent power sequence of the load for 8760 hours throughout the year based on the user load curve in the time series data and through the formula.

[0052] For example, according to the formula (t=1~8760), calculate the apparent power S(t) of the load at each moment. Apparent power is the vector sum of active power and reactive power. This formula can accurately quantify the user's actual total electricity demand (including active power consumption and reactive power loss) at each time period.

[0053] After completing 8760 hours of hourly calculations, a set of apparent power load sequences containing 8760 data points was obtained. This sequence intuitively reflects the fluctuations in the actual load demand of users at different times of the year and serves as the quantitative basis for determining the benchmark value of transformer capacity.

[0054] Step S2022: Determine the capacity baseline value based on the load apparent power sequence.

[0055] In this embodiment of the invention, step S2022 is to determine the transformer capacity benchmark value and clarify the starting range of candidate capacity by extracting quantile values ​​and correcting the apparent power sequence of the load obtained in step S2021 through quantile value extraction and safety factor correction.

[0056] For example, the apparent power quantile is extracted: First, statistical analysis is performed on the 8760-hour load apparent power sequence obtained in step S2021, and the 99th percentile value S of the sequence is extracted. 99 This means that the apparent power of the load exceeds this value only 1% of the time throughout the year, which also means that during 99% of the operating period, the apparent power of the user's electricity load is lower than or equal to S. 99 This value accurately reflects the normal peak demand of user load, avoiding the waste of capacity redundancy caused by calculating based on extreme peak values ​​(such as the 100th percentile).

[0057] Calculate the capacity baseline value: according to formula S 基准 =k×S 99 This function calculates the transformer capacity baseline value, where k is the safety factor, with a default value of 1.08. This value can be flexibly adjusted based on user load characteristics (such as load fluctuation amplitude and the proportion of impact loads). The core purpose of setting the safety factor k is to reserve a certain safety margin to cope with uncertainties such as sudden load fluctuations and equipment aging, preventing transformer overload due to instantaneous load exceeding the baseline value, and ensuring the safe and stable operation of the system.

[0058] Finally, the transformer capacity reference value S was obtained. 基准 This value serves as the starting benchmark for generating the candidate capacity set. It ensures that the transformer can meet the user's regular load demand for more than 99% of the time, while also reserving a reasonable margin through the safety factor, thus balancing safe operation with investment economy.

[0059] The above step S2022 scientifically determines the capacity baseline value through quantile statistics and safety factor correction, abandoning the traditional method of estimating the baseline capacity based on experience, so that the selection of candidate capacity has an accurate starting basis, and at the same time lays the foundation for the subsequent generation of candidate capacity.

[0060] Step S2023: Determine the candidate capacity set based on the capacity reference value and the transformer capacity reduction step size, wherein the transformer capacity reduction step size is included in the boundary parameters.

[0061] In this embodiment of the invention, step S2023 is the generation step of screening candidate transformer capacities. The task is to generate a set of reasonable and feasible candidate capacities based on the capacity benchmark value determined in step S2022 and combined with the transformer capacity decreasing step size in the boundary parameters, forming a set of candidate transformer capacities, and providing multiple alternative solutions for the subsequent step S203 energy storage parameter collaborative optimization.

[0062] In the process of determining the candidate capacity set, starting from the capacity benchmark value S 基准 Initially, candidate capacities are generated sequentially by decreasing the transformer capacity in a set step size until the set limit on the number of elements or the maximum decrease range is reached, at which point generation stops. For example, if the base capacity is 100 MVA, the transformer capacity decrease step size is 10 MVA, and the set limit on the number of elements is 4 groups, then the generated candidate capacities are 100 MVA, 90 MVA, 80 MVA, and 70 MVA, forming a candidate capacity sequence.

[0063] Optionally, in some embodiments of the invention, based on the generated candidate capacity sequence, unreasonable capacities are further eliminated by combining the boundary parameters (such as transformer rated capacity and new energy installed capacity) and time-series data (extreme operating power obtained by superimposing the green power output curve and the load curve) from step S201. That is, candidate capacities that are too small (unable to bear extreme operating power and easily cause overload risk) and those with excessive capacity redundancy (far exceeding actual needs and causing investment waste) are eliminated, ultimately forming a set of candidate transformer capacities.

[0064] The above step S2023 generates a structured and diversified set of candidate capacities, which not only ensures the rationality and security of the candidate capacities, but also avoids the blindness of traditional selection.

[0065] Optionally, in step S203, a preset algorithm is used to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set, specifically including the following steps: Step S2031: For each candidate capacity in the candidate capacity set, use a preset algorithm to generate multiple sets of energy storage parameters to be screened for each candidate capacity.

[0066] In this embodiment of the invention, step S2031 is to generate multiple sets of energy storage parameters to be screened for each candidate capacity in the candidate capacity set of transformers determined in step S2023, based on a preset algorithm, so as to provide a multi-option basis for subsequent simulation verification and optimal screening, and ensure that the energy storage parameters most suitable for the candidate capacity can be screened in the future.

[0067] In step S2031, energy storage parameters are generated for each candidate capacity (such as 100MVA, 90MVA, 80MVA, etc.) in the transformer candidate capacity set generated in step S2023, to ensure that each candidate capacity has multiple sets of corresponding energy storage parameters to be screened.

[0068] The preset algorithm can be an intelligent optimization algorithm (such as genetic algorithm, particle swarm algorithm, etc.). The core input of the algorithm is the time series data (green power output curve, user load curve, time series electricity price data) and boundary parameters (energy storage charging and discharging efficiency, energy storage SOC safe range, etc.) obtained in step S201. At the same time, the capacity of the candidate transformer that is currently adapted is used as the core constraint condition (that is, the energy storage parameters must be adapted to the carrying capacity range of the candidate capacity).

[0069] For example, the algorithm initialization settings include: initial energy storage state, with an initial SOC (state of charge) of 50%; algorithm parameters, with a population size of 100, number of iterations of 200, crossover probability of 0.8, and mutation probability of 0.1; and variable encoding, specifying the maximum charge / discharge power (PESS) of the energy storage system. max Energy storage rated capacity E ESS Perform encoding optimization.

[0070] Each set of energy storage parameters to be screened includes key energy storage indicators, mainly including rated energy storage capacity and maximum charging and discharging power.

[0071] For each candidate transformer capacity, multiple sets of energy storage parameters to be screened are generated iteratively through a preset algorithm, forming a correspondence between a candidate capacity and multiple sets of energy storage parameters to be screened. For example, for a 100MVA candidate capacity, 10 sets of energy storage parameters with different rated capacities and different charging and discharging powers are generated to provide sufficient alternatives for subsequent simulation screening.

[0072] The above step S2031 generates multiple sets of parameters to be screened through a preset algorithm, avoiding the limitations of the traditional single design of energy storage parameters. At the same time, the candidate transformer capacity is used as the core constraint to ensure that each set of energy storage parameters to be screened has the basic conditions to be adapted to the candidate capacity, thus providing a guarantee for subsequent accurate screening.

[0073] Step S2032: According to the preset simulation strategy, simulate multiple sets of energy storage parameters to be screened to obtain the performance indicators corresponding to the multiple sets of energy storage parameters to be screened.

[0074] In this embodiment of the invention, step S2032 is a simulation verification step for energy storage parameter optimization. The task is to simulate the actual working conditions of each set of energy storage parameters to be screened and the corresponding candidate transformer capacity through full-time simulation, quantify the operating performance of each set of parameters, and provide an objective and accurate quantitative basis for subsequent fitness scoring.

[0075] In step S2032, the preset simulation strategy adopts a full-time simulation mode of 8760 hours throughout the year. The simulation input data relies on the time-series data (green electricity output curve, user load curve, time-series electricity price data) and boundary parameters (energy storage charging and discharging efficiency, transformer rated capacity, power factor, etc.) obtained in step S201. The simulation scenario completely simulates the actual operating conditions of the green electricity direct connection system to ensure the authenticity and reliability of the simulation results.

[0076] Simulation process: For each set of energy storage parameters to be screened generated in step S2031, combined with the corresponding candidate transformer capacity, an independent 8760-hour full-time simulation is performed to simulate the hourly output of green electricity and the hourly load changes of users, simulate the charging and discharging behavior of the energy storage system (such as charging during off-peak hours and discharging during peak hours), and monitor the operating status of the transformer (such as whether it is overloaded) and record the entire operation data.

[0077] For example, the maximum amount of green electricity that can be absorbed and the amount of abandoned electricity P are calculated hourly. abandoned (t); Based on green electricity output P G (t) and load demand P L (t), determine the energy storage charging and discharging power P ESS (t), and according to the formula Update the energy storage SOC. Among these... For energy storage charging and discharging efficiency; the SOC operating range is limited to 5%~98%.

[0078] Performance index output: After the simulation is completed, performance indices are extracted for each set of energy storage parameters to be screened. The indices cover three main categories: Operational stability indicators: transformer overload duration percentage, number of times energy storage SOC exceeds limits, and power balance satisfaction rate, are used to evaluate the safety and stability of system operation; System efficiency indicators: green electricity consumption rate, curtailment rate, and energy storage utilization rate, used to evaluate energy utilization efficiency; Economic indicators: hourly electricity purchase and sale cost and energy storage operation loss cost, which are used for economic accounting in subsequent fitness scoring.

[0079] The above step S2032 transforms abstract energy storage parameters into quantifiable operational performance indicators through full-time simulation, avoiding the limitations of judging parameter suitability solely based on theoretical calculations, and ensuring that the subsequently selected energy storage parameters can fit the actual operating conditions of the system.

[0080] Step S2033: Determine the fitness scores of multiple sets of energy storage parameters to be screened based on performance indicators and pre-constructed fitness functions.

[0081] In this embodiment of the invention, step S2033 is the scoring step for energy storage parameter optimization. The task is to transform the multiple sets of performance indicators obtained in step S2032 into a unified fitness score through a pre-constructed fitness function, so as to achieve a comprehensive quantitative evaluation of each set of energy storage parameters to be screened, and provide a clear basis for subsequent selection of target energy storage parameters.

[0082] In step S2033, the pre-constructed fitness function is the core mathematical model used to comprehensively evaluate the adaptability of energy storage parameters. Its construction core is to combine the three types of performance indicators (stability, efficiency, and economy) obtained in step S2032, and incorporate the boundary parameter constraints in step S201. The core objective of the function is to maximize the comprehensive performance of the system (high absorption, high stability, and low cost).

[0083] The core components of the fitness function can include three parts: first, the stability index score (e.g., high scores are obtained for no transformer overload and no energy storage exceeding limits); second, the efficiency index score (e.g., higher scores are obtained for higher green electricity consumption rate and lower curtailment rate); and third, the economic index score (e.g., higher scores are obtained for lower electricity purchase and sale costs and lower energy storage losses). At the same time, penalty items are incorporated (e.g., corresponding points are deducted for violating boundary constraints) to ensure the rationality of the scoring.

[0084] During the scoring calculation process, the performance indicators corresponding to each set of energy storage parameters to be screened are substituted into the pre-constructed fitness function one by one, and the fitness score corresponding to each set of parameters is obtained through function calculation (the higher the score, the better the compatibility between the set of energy storage parameters and the corresponding candidate transformer capacity, and the better the overall performance).

[0085] Finally, the fitness score corresponding to each set of energy storage parameters to be screened is obtained, forming a correspondence between "energy storage parameters to be screened - fitness score". For example, for the 10 sets of energy storage parameters to be screened corresponding to a candidate capacity of 100MVA, different scores such as 85, 92 and 78 are calculated respectively, providing a quantitative standard for subsequent selection.

[0086] The above step S2033 transforms multi-dimensional performance indicators into a unified score through a fitness function, solving the problem of difficulty in comprehensively comparing multiple indicators, and realizing an objective and comprehensive evaluation of each group of energy storage parameters to be screened, providing a clear quantitative basis for subsequent accurate screening of target energy storage parameters.

[0087] Step S2034: Based on the fitness score, determine the target energy storage parameters corresponding to each candidate capacity from multiple sets of energy storage parameters to be screened for each candidate capacity to obtain multiple sets of target energy storage parameters.

[0088] In this embodiment of the invention, step S2034 is to select the optimal energy storage parameters (i.e. target energy storage parameters) for each candidate transformer capacity based on the fitness score obtained in step S2033, and finally form multiple sets of configuration schemes with one-to-one correspondence between candidate capacity and target energy storage parameters.

[0089] In step S2034, for each candidate transformer capacity, the fitness scores of the corresponding multiple sets of energy storage parameters to be screened are compared, and the set of energy storage parameters with the highest fitness score is selected and determined as the target energy storage parameters corresponding to that candidate capacity. The highest score means that the set of energy storage parameters has the best fit with the corresponding candidate transformer capacity, and can achieve the best balance between system stability, efficiency and economy.

[0090] Optionally, if multiple sets of energy storage parameters to be screened have the same score (or very small difference), a second verification is performed in conjunction with the performance indicators obtained in step S2032. The set of parameters with higher green electricity consumption rate, lower transformer overload risk, and lower overall cost is selected as the target energy storage parameters to ensure the accuracy of the screening results.

[0091] After completing the selection of all candidate capacities, multiple sets of target energy storage parameters are obtained, and these multiple sets of target energy storage parameters correspond one-to-one with multiple candidate capacities in the candidate capacity set. For example, a 100MVA candidate capacity corresponds to one set of target energy storage parameters (such as a rated capacity of 50MWh and a charging and discharging power of 10MW), and a 90MVA candidate capacity corresponds to another set of suitable target energy storage parameters, forming a pairing scheme of multiple sets of transformer candidate capacity-target energy storage parameters.

[0092] The above step S2034 selects the best by using fitness scoring to ensure that each candidate transformer capacity can be matched with the optimal energy storage parameters, thereby achieving coordinated adaptation between transformer capacity and energy storage parameters. This solves the core problem of independent planning and poor adaptability of the two in the prior art. At the same time, it provides multiple high-quality alternative schemes for the subsequent step S204 to select target configuration parameters, supporting the realization of the overall optimization goal of the system.

[0093] Optionally, the construction of the fitness function includes: Step S203a: Construct system constraints, which include transformer capacity constraints, energy storage operation constraints, and power balance constraints.

[0094] In this embodiment of the invention, step S203a is to sort out the core hard constraints of the green electricity direct connection system operation and transform them into mathematical constraints that can be identified by the fitness function, so as to ensure that the fitness function constructed subsequently can meet the requirements of safe and compliant operation of the system.

[0095] Transformer capacity constraint: The core is to limit the compatibility between the energy storage parameters to be screened and the corresponding candidate transformer capacity. In essence, it is an extension of the transformer rated capacity constraint in the boundary parameters. The mathematical constraint expression can be simplified to: ,in For the current candidate transformer capacity, It is the power factor. Its purpose is to prevent the superposition of energy storage charging and discharging power and green electricity output from exceeding the safe carrying capacity of the transformer, thus preventing transformer overload.

[0096] Energy storage operation constraints: The core is to limit the safe operating range of the energy storage system, which mainly includes two aspects: one is the energy storage state of charge (SOC) constraint, i.e. SOC min ≤ SOC(t) ≤ SOC max (where SOC) min SOC max The first is the safety range set in the boundary parameters (which can be 5% to 98%), to avoid overcharging and over-discharging of energy storage devices and damage; the second is the constraint on the charging and discharging power of energy storage, i.e. Ensure that energy storage operations comply with equipment performance limits.

[0097] Power balance constraint: The core is to ensure the hourly power supply and demand balance of the green electricity direct-connection system. The mathematical constraint expression can be simplified to: P Grid (t) represents the grid interaction power at time t. Its core purpose is to ensure that during system operation, the output of green electricity and the charging and discharging behavior of energy storage can accurately match the user load demand, so as to avoid power imbalance leading to system instability.

[0098] The three constraints mentioned above are transformed into standardized mathematical inequalities or equations and incorporated into the subsequent construction of the fitness function as the constraint premise for fitness scoring. If the operating state corresponding to the energy storage parameter to be screened violates any system constraint, a penalty term will be triggered in the fitness scoring, reducing its fitness score and ensuring that the screened energy storage parameter meets the system's safe operation requirements.

[0099] Step S203a above clarifies the constraint boundary of the fitness function, avoids the constructed function from deviating from the actual operating requirements of the system, and ensures that the subsequent fitness score can not only reflect the comprehensive performance of the energy storage parameters, but also take into account the safe and compliant operation of the system, thus laying the foundation for the scientific construction of the fitness function.

[0100] Step S203b: Construct a fitness function based on system constraints, energy costs, and curtailment rate.

[0101] In this embodiment of the invention, step S203b is to integrate the system constraints constructed in step S203a and the core performance indicators (energy cost and curtailment rate) in step S2032 to construct a mathematical model that can comprehensively evaluate the adaptability of energy storage parameters.

[0102] In step S203b, system constraints refer to the transformer capacity constraints, energy storage operation constraints, and power balance constraints constructed in step S203a, which serve as constraints on the function and are incorporated into the function calculation through penalty terms. Energy cost comes from the economic indicators output by the simulation in step S2032, the core of which includes hourly electricity purchase and sale costs and energy storage operation loss costs, and is the core indicator for evaluating the economic efficiency of energy storage parameters. The curtailment rate comes from the system efficiency indicator output by the simulation in step S2032, which is the ratio of the total amount of green electricity curtailed to the total output of green electricity, and is the core indicator for evaluating the ability of energy storage parameters to absorb green electricity (the lower the curtailment rate, the better the green electricity absorption effect and the stronger the adaptability of energy storage parameters).

[0103] The core objective of the fitness function is to maximize overall performance. Therefore, it adopts a construction logic of maximizing positive indicators, minimizing negative indicators, and imposing constraints. At the same time, it normalizes each indicator (converting indicators of different dimensions into values ​​in the range of 0 to 1) to avoid affecting the fairness of the scoring due to differences in indicator dimensions.

[0104] For example, the function formula is: ,in, , Weighting coefficients (can be adjusted as needed); This is the normalized value of the overall energy cost; This is the normalized value of the curtailment rate; To constrain penalties, infeasible individuals (those who violate constraints) are penalized with an additional 1.0 penalty value, while feasible individuals are penalized proportionally when their indicators exceed the threshold.

[0105] The above step S203b integrates the three core requirements of system constraints, economy, and green energy consumption efficiency into a unified mathematical model, which solves the problem of the difficulty in comprehensively evaluating multi-dimensional indicators. It provides a calculable and quantifiable core basis for the fitness score in step S2033, ensuring that the target energy storage parameters selected in the subsequent process can achieve the comprehensive goals of safety and compliance, economic efficiency, and high green energy consumption.

[0106] Optionally, in step S204, the target configuration parameters are determined based on multiple candidate capacities and multiple sets of target energy storage parameters, specifically including the following steps: Step S2041: Using a preset economic calculation strategy, determine multiple economic scores corresponding to multiple configuration schemes. Each configuration scheme includes a candidate capacity and a corresponding set of target energy storage parameters.

[0107] In this embodiment of the invention, step S2041 is the economic quantification step for screening target configuration parameters. The task is to perform full life cycle economic accounting on each set of candidate capacity-target energy storage parameter configuration schemes output in step S2034 through a preset economic calculation strategy, and convert it into a unified economic score, so as to provide an objective and accurate quantitative basis for subsequent selection.

[0108] In step S2041, the core of the preset economic calculation strategy is full life cycle cost accounting. The accounting period can be the design service life of the green electricity direct connection system. The calculation strategy relies on the time series data (time series electricity price data) and boundary parameters (discount rate, energy storage charging and discharging efficiency, transformer rated capacity, etc.) obtained in step S201 to ensure the scientificity and accuracy of the accounting results.

[0109] After completing the economic calculation of all configuration schemes, an economic score is obtained for each configuration scheme, forming a one-to-one correspondence between configuration schemes and economic scores, providing a clear quantitative standard for the subsequent selection in step S2042.

[0110] The above step S2041 transforms the abstract configuration scheme into a quantifiable economic score through full life cycle economic accounting, solving the problem that it is difficult to compare multiple configuration schemes from an economic perspective. At the same time, relying on the time series data and boundary parameters mentioned above, it ensures that the accounting results are consistent with the actual project and provides a reliable economic basis for the selection of target configuration parameters.

[0111] Step S2042: Determine the target configuration parameters based on multiple economic scores.

[0112] In this embodiment of the invention, step S2042 is the selection step for screening target configuration parameters. The task is to select the set with the best overall performance from multiple candidate capacity-target energy storage parameter configuration schemes based on the multiple economic scores obtained in step S2041 and the system operation stability requirements, as the target configuration parameters of the green electricity direct connection system.

[0113] The core principle of selection is to prioritize both economic efficiency and stability compliance. This means prioritizing the configuration with the highest economic score while ensuring that the configuration meets the requirements for safe and stable system operation, avoiding the pursuit of economy at the expense of operational safety.

[0114] First, a preliminary screening is conducted. All configuration schemes obtained in step S2041 are sorted from high to low according to their economic efficiency scores, and the configuration scheme with the highest score is selected as the candidate target configuration parameter.

[0115] It should be noted that screening can be conducted solely based on economic performance scores.

[0116] Then, stability verification is performed. For the high-scoring schemes initially selected, a second verification is conducted by combining the operational stability indicators (transformer overload duration percentage, number of times energy storage SOC exceeds the limit) output by the simulation in step S2032 and the system constraints in step S203a. This verifies that the candidate transformer capacity and target energy storage parameters corresponding to the scheme can meet the transformer capacity constraints, energy storage operation constraints and power balance constraints, and that the transformer has no obvious overload risk and the energy storage operation is stable (e.g., overload duration percentage ≤ 0.1%, no SOC exceeding the limit).

[0117] If the solution with the highest economic score fails the stability test (e.g., frequent overload), the solution will be removed, and the solution with the second highest score will be selected for stability test until a solution with both high economic score and stability compliance is selected. If the economic scores of multiple schemes are very close (e.g., the difference is ≤3 points), then their stability indicators and green electricity consumption rates should be compared further, and the scheme with better stability and higher green electricity consumption rate should be selected as the target configuration parameter.

[0118] After screening and verification, the target configuration parameters are determined. These parameters are a set of optimal transformer capacity-target energy storage parameter matching schemes. For example, the final selection is a candidate capacity of 90MVA + energy storage parameters of 45MWh / 9MW as the target configuration parameters.

[0119] The above step S2042 uses a dual screening process of economic scoring and stability verification to ensure that the final target configuration parameters can minimize the system's total lifecycle cost and achieve optimal economic efficiency, while also meeting the requirements for safe and stable system operation and avoiding operational risks caused by simply pursuing economic efficiency.

[0120] Optionally, in step S2041, a preset economic calculation strategy is used to determine multiple economic scores corresponding to multiple configuration schemes, specifically including the following steps: Step S2041a: Based on the preset economic calculation strategy, determine the total life cycle cost, energy cost and investment payback period corresponding to multiple configuration schemes.

[0121] In this embodiment of the invention, step S2041a is to rely on a preset full life cycle economic calculation strategy to accurately calculate three core economic indicators (full life cycle cost, energy cost, and investment payback period) for each configuration scheme.

[0122] Lifecycle cost: The scope of the calculation is the sum of the present values ​​of all costs throughout the system's entire lifecycle. The core costs include initial investment cost, operation and maintenance cost, and total lifecycle electricity cost. Initial investment cost corresponds to the purchase and installation costs of the candidate transformer and energy storage system. Operation and maintenance cost is calculated as a fixed percentage of equipment capacity (considering losses and maintenance in conjunction with energy storage charging and discharging efficiency). Electricity cost is calculated based on time-series electricity pricing and 8760 hours of simulated operating conditions. Finally, all future costs are discounted to their present value using a discount rate to obtain the total lifecycle cost (unit: RMB 10,000) for each scheme. The lower the cost, the more economical the scheme.

[0123] For example, the total life cycle cost is calculated using the formula Calculate, where r disc C is the discount rate. 运维，n For the maintenance cost in year n, C ESS更换 Cost of replacing battery cells for energy storage systems.

[0124] Energy Costs: The calculation logic relies on the time-series electricity price data from step S201, combined with the simulation logic from step S2032, to simulate the operating conditions of each configuration scheme for 8760 hours throughout the year, and calculate the electricity purchase and sale costs hourly (grid purchase costs when green electricity is insufficient, grid connection revenue when green electricity is surplus, and revenue offsetting costs). At the same time, the energy loss costs caused by the energy storage charging and discharging efficiency are added to calculate the total energy cost of each scheme throughout its entire life cycle. The lower the energy cost, the better the real-time operating economy of the scheme.

[0125] Payback period: This refers to the time required to recover the initial investment cost of the system. It is a core indicator for measuring the feasibility of a project. The calculation logic is to combine the initial investment cost of each project with the average annual net income over the entire life cycle (average annual green electricity consumption income + grid connection income - average annual operation and maintenance costs - average annual energy costs). The payback period is calculated using the formula: Payback period = Initial investment cost ÷ Average annual net income. The shorter the payback period, the higher the return on investment and the better the economic performance of the project.

[0126] After completing the calculation of all configuration schemes, we obtain three sets of core data for each scheme: total life cycle cost, energy cost, and investment payback period, forming a one-to-one correspondence between the configuration scheme and the three major economic indicators.

[0127] Step S2041a calculates three major economic indicators, avoiding the limitations of a single cost indicator, while ensuring that the calculation logic is consistent with the previous steps, providing a more comprehensive and accurate quantitative basis for subsequent comprehensive scoring, and making the economic evaluation more targeted.

[0128] Step S2041b: Perform sensitivity analysis on multiple configuration schemes to obtain multiple sensitivity coefficients.

[0129] In this embodiment of the invention, step S2041b involves identifying key factors affecting the economic efficiency of each configuration scheme through sensitivity analysis, calculating sensitivity coefficients, and quantifying the degree of impact of fluctuations in key factors on the economic efficiency of the scheme.

[0130] During the operation of the green electricity direct connection system, some key parameters (such as time-series electricity price, energy storage charging and discharging efficiency, and discount rate) may fluctuate, which may affect the economics of the scheme. Sensitivity analysis can clarify the impact of these parameter fluctuations on the economics of each scheme, avoid scoring deviations due to parameter fluctuations, and make the economics score more reliable.

[0131] Three to four key factors that have the greatest impact on the economics of the scheme are selected, all of which are variable parameters in the system operation as sensitive factors. Specifically, these include: ① Time-series electricity price fluctuations (derived from time-series data, such as peak-valley electricity price adjustments); ② Energy storage charging and discharging efficiency fluctuations (derived from boundary parameters, such as efficiency decline due to aging of energy storage equipment); ③ Discount rate fluctuations (derived from boundary parameters, such as changes in capital costs); ④ Green electricity output fluctuations (derived from time-series data, such as unstable photovoltaic / wind power output).

[0132] The sensitivity coefficient calculation includes: Set fluctuation range: For each sensitive factor, set a reasonable fluctuation range (such as ±10%, ±15%, which is close to the actual fluctuation range of the project). For example, the energy storage charging and discharging efficiency can be fluctuated from 0.9 to 0.81 (-10%) and 0.99 (+10%).

[0133] Factor-by-factor fluctuation accounting: For each configuration scheme, keep other parameters unchanged and only change the value of a certain sensitive factor (fluctuating by a set range), recalculate the full life cycle cost of the scheme, and record the amount of cost change as the factor fluctuates.

[0134] Calculate the sensitivity coefficient: The sensitivity coefficient is used to quantify the impact of fluctuations in sensitive factors on total life cycle cost. The formula can be simplified to: Sensitivity coefficient = (rate of change in total life cycle cost ÷ volatility of sensitive factor). The larger the absolute value of the coefficient, the greater the impact of the factor on the economics of the project (e.g., a sensitivity coefficient of -2.5 means that if the sensitive factor increases by 10%, the total life cycle cost will decrease by 25%).

[0135] For each configuration scheme, calculate the sensitivity coefficients corresponding to all selected sensitive factors to obtain multiple sensitivity coefficients for each scheme (e.g., 4 sensitive factors correspond to 4 sensitivity coefficients), forming a correspondence between configuration schemes and sensitivity coefficients.

[0136] Step S2041b supplements the risk considerations of economic scoring, avoids the limitations of single-calculation of basic economic indicators, and quantifies the impact of parameter fluctuations through sensitivity coefficients, making subsequent economic scoring more in line with the uncertainties in engineering practice, and improving the scientificity and reliability of the scoring.

[0137] Step S2041c: Based on multiple sensitivity coefficients and the full life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes, determine multiple economic scores.

[0138] In the embodiment of the invention, step S2041c is to integrate the three core economic indicators of step S2041a with the sensitivity coefficient of step S2041b, and transform the multi-dimensional data into a unified economic score through a comprehensive scoring model.

[0139] For example, the scoring model is first constructed by building a comprehensive scoring model that combines basic index scores with sensitivity coefficient correction. The scoring range is still 0 to 100 points. The higher the score, the better the economic efficiency of the solution.

[0140] Calculation of total score for basic indicators: The three core economic indicators (life cycle cost, energy cost, and investment payback period) obtained in step S2041a are normalized (converted into a range of 0 to 80 points), and then converted into the total score for basic indicators according to the set weights.

[0141] Sensitivity coefficient correction (maximum score 20 points): Based on the sensitivity coefficient obtained in step S2041b, the score of the basic indicator is corrected. The core logic is that the stronger the resistance to volatility, the higher the correction score, as detailed below: Sensitivity coefficient comprehensive evaluation: A comprehensive analysis of all sensitivity coefficients for each group of schemes is conducted, and the average value of the absolute values ​​of the sensitivity coefficients is calculated. The smaller the average value, the stronger the scheme's resistance to parameter fluctuations and the more stable its economic performance.

[0142] Correction score calculation: Based on the comprehensive evaluation results of the sensitivity coefficient, a correction score is assigned (e.g., if the average sensitivity coefficient is ≤0.5, 20 points are awarded; if 0.5 < average value ≤1.0, 15 points are awarded; if the average value >1.0, 10 points or less are awarded). The stronger the resistance to fluctuations, the higher the correction score, and vice versa.

[0143] Finally, the economic efficiency score is calculated: the final economic efficiency score for each group of schemes = basic indicator score + sensitivity coefficient correction score, with a score range of 0 to 100 points, ensuring that the score reflects both the basic economic efficiency of the scheme and the economic stability of the scheme.

[0144] After completing the scoring calculation for all configuration schemes, the final economic score for each configuration scheme is obtained, forming a one-to-one correspondence between configuration schemes and economic scores.

[0145] The above step S2041c integrates basic economic indicators and sensitivity coefficients, improves the calculation logic of economic performance scoring, avoids the limitations of scoring based on a single indicator or ignoring parameter fluctuations, and makes economic performance scoring more comprehensive, accurate, and in line with engineering practice.

[0146] Reference Figure 3 The diagram illustrates two access methods for a green electricity direct connection system. The side containing the main transformer is the grid side, which includes 220 / 110kV high-voltage transmission lines, the main transformer (which reduces the voltage to 35 / 10kV), and the distribution-side load facing users. The primary side containing the energy storage system is the new energy generation side, consisting of new energy units such as photovoltaic and wind power equipped with energy storage systems, which are connected to the grid through two different paths.

[0147] Method 1 is a direct connection on the high-voltage side, where renewable energy is connected to the 220 / 110kV high-voltage bus via a step-up substation, and then stepped down by the main transformer before being supplied to users. Method 2 is a direct connection on the low-voltage side, where renewable energy is connected directly to the 35 / 10kV distribution bus via a switching station and a direct connection line, which is closer to the user load and can reduce energy loss in the main transformer stage. This is the core research scenario for green electricity direct connection systems. The safety responsibility boundary in the diagram is the dividing point of rights and responsibilities between the power grid and renewable energy owners.

[0148] It should be noted that the configuration method provided by this invention is applied to the configuration of method two.

[0149] Reference Figure 4 The method provided by this invention is implemented as follows: wind power is used as a new energy power generation station, and a direct connection line is connected to the low-voltage side of the user's step-down substation. The core basic parameters of the project are as follows: New energy installed capacity: 120MW; User load: Annual electricity consumption of 400 million kWh, annual load utilization hours of 8,000 hours, maximum load of 50 MW. Power factor: 0.9 Transformer rated capacity: 60MVA Transformer capacity reduction step size: 5MVA Discount rate 8% Energy storage charging and discharging efficiency 0.95 Step 1: Data Preprocessing (a) Data import Import 8760 hours of time-series data and boundary parameters for the entire year of the project: Green electricity output curve: wind power hourly output data, with annual effective output hours calculated based on 2200 hours; User load curve: based on an annual electricity consumption of 400 million kWh and an annual utilization of 8,000 hours; Time-series electricity price data: the daily clearing price of the electricity market in the province where the project is located over the past year.

[0150] (ii) Data verification and correction After integrity and rationality checks, linear interpolation is used to supplement missing data, correct outliers, and generate preprocessed load curves and time-series electricity price curves.

[0151] Step 2: Optimize the capacity of the upper-level transformer (a) Calculation of apparent power Calculate apparent power using the formula ( t =1~8760) Calculate the apparent power sequence of the load.

[0152] (ii) Determination of capacity benchmark value Extract the 99th percentile value S of the apparent power sequence 99% =55MVA, safety factor k Taking 1.08, the result is calculated according to the formula benchmark: From an engineering perspective, 60MVA is selected.

[0153] (III) Generation of candidate capacity optimization set Based on the project's predetermined transformer capacity of 60MVA, additional candidate capacities were added, resulting in the final optimized candidate capacity set of {60MVA, 55MVA, 50MVA, 45MVA}.

[0154] Step 3: Optimization of lower-level energy storage parameters For each transformer capacity in the candidate capacity optimization set, a genetic algorithm is used to drive optimization. The specific process is as follows: (I) Algorithm Setup and Initialization Initial SOC of energy storage: 50%; Algorithm parameters: population size 100, number of iterations 200, crossover probability 0.8, mutation probability 0.1; Variable encoding: Maximum charge / discharge power of energy storage P ESS_max Energy storage capacity E ESS Perform binary encoding; Weighting coefficients ω1=0.6, ω2=0.4; Penalty for exceeding limits: During the optimization process, exceeding the limits once will result in a fine of 20,000 yuan.

[0155] Step 4: Output Results Transformer capacity: 55MVA; Energy storage system parameters: Maximum charging and discharging power. P ESS_max = 50MW, energy storage capacity E ESS =200MWh.

[0156] Based on the same inventive concept, this application also provides a green electricity direct connection system configuration device for implementing the green electricity direct connection system configuration method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the green electricity direct connection system configuration device provided below can be found in the limitations of the green electricity direct connection system configuration method described above, and will not be repeated here.

[0157] In one exemplary embodiment, such as Figure 5 As shown, a green electricity direct connection system configuration device 50 is provided, comprising: an acquisition module 501, used to acquire time-series data and boundary parameters, wherein the time-series data is used to characterize the data changing over time in the green electricity direct connection system, and the boundary parameters are used to characterize the constraint parameters in the green electricity direct connection system; a first determination module 502, used to determine a candidate capacity set of transformers based on the time-series data and boundary parameters; a second determination module 503, used to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set using a preset algorithm, wherein the multiple candidate capacities and the multiple sets of target energy storage parameters correspond one-to-one; a third determination module 504, used to determine target configuration parameters based on the multiple candidate capacities and the multiple sets of target energy storage parameters; and a configuration module 505, used to configure the green electricity direct connection system according to the target configuration parameters.

[0158] Optionally, the first determining module 502 is further configured to: determine the apparent power sequence of the load based on the user load curve, wherein the user load curve is included in the time series data; determine the capacity reference value based on the apparent power sequence of the load; and determine the candidate capacity set based on the capacity reference value and the transformer capacity reduction step size, wherein the transformer capacity reduction step size is included in the boundary parameters.

[0159] Optionally, the second determining module 503 is further configured to: for each candidate capacity in the candidate capacity set, generate multiple sets of energy storage parameters to be screened corresponding to each candidate capacity using a preset algorithm; simulate the multiple sets of energy storage parameters to be screened according to a preset simulation strategy to obtain the performance indicators corresponding to the multiple sets of energy storage parameters to be screened respectively; determine the fitness score of the multiple sets of energy storage parameters to be screened based on the performance indicators and the pre-constructed fitness function; and determine the target energy storage parameters corresponding to each candidate capacity from the multiple sets of energy storage parameters to be screened corresponding to each candidate capacity based on the fitness score to obtain multiple sets of target energy storage parameters.

[0160] Optionally, the second determining module 503 is further configured to: construct system constraints, wherein the system constraints include transformer capacity constraints, energy storage operation constraints, and power balance constraints; and construct a fitness function based on the system constraints, energy costs, and curtailment rate.

[0161] Optionally, the third determining module 504 is further configured to: determine multiple economic scores corresponding to multiple configuration schemes using a preset economic calculation strategy, wherein each configuration scheme includes a candidate capacity and a corresponding set of target energy storage parameters; and determine target configuration parameters based on the multiple economic scores.

[0162] Optionally, the third determining module 504 is further configured to: determine the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes according to a preset economic calculation strategy; perform sensitivity analysis on multiple configuration schemes to obtain multiple sensitivity coefficients; and determine multiple economic scores based on the multiple sensitivity coefficients, the total life cycle cost, energy cost, and investment payback period corresponding to multiple configuration schemes.

[0163] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores timing data and boundary data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a green electricity direct connection system configuration method.

[0164] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0166] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0167] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0168] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0169] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0170] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0171] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0172] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for configuring a green electricity direct connection system, characterized in that, The configuration method for the green electricity direct connection system includes: Acquire time-series data and boundary parameters, wherein the time-series data is used to characterize the data changing over time in the green energy direct connection system, and the boundary parameters are used to characterize the constraint parameters in the green energy direct connection system; Based on the time series data and the boundary parameters, a candidate capacity set for the transformer is determined; Using a preset algorithm, multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set are determined, wherein the multiple candidate capacities and the multiple sets of target energy storage parameters correspond one-to-one; Based on the multiple candidate capacities and the multiple sets of target energy storage parameters, the target configuration parameters are determined; Configure the green electricity direct connection system according to the target configuration parameters.

2. The green electricity direct connection system configuration method according to claim 1, characterized in that, The step of determining the candidate capacity set of the transformer based on the time-series data and the boundary parameters specifically includes: Based on the user load curve, determine the apparent power sequence of the load, wherein the user load curve is included in the time series data; Determine the capacity baseline value based on the apparent power sequence of the load; The candidate capacity set is determined based on the capacity baseline value and the transformer capacity reduction step size, wherein the transformer capacity reduction step size is included in the boundary parameters.

3. The green electricity direct connection system configuration method according to claim 1, characterized in that, The step of using a preset algorithm to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set specifically includes: For each candidate capacity in the candidate capacity set, a preset algorithm is used to generate multiple sets of energy storage parameters to be screened for each candidate capacity; According to the preset simulation strategy, the multiple sets of energy storage parameters to be screened are simulated to obtain the performance indicators corresponding to the multiple sets of energy storage parameters to be screened. Based on the performance indicators and the pre-constructed fitness function, determine the fitness scores of the multiple sets of energy storage parameters to be screened; Based on the fitness score, the target energy storage parameters corresponding to each candidate capacity are determined from the multiple sets of energy storage parameters to be screened for each candidate capacity, so as to obtain the multiple sets of target energy storage parameters.

4. The green electricity direct connection system configuration method according to claim 3, characterized in that, The construction of the fitness function includes: Construct system constraints, which include transformer capacity constraints, energy storage operation constraints, and power balance constraints; The fitness function is constructed based on the system constraints, energy costs, and curtailment rate.

5. The green electricity direct connection system configuration method according to claim 1, characterized in that, The step of determining the target configuration parameters based on the multiple candidate capacities and the multiple sets of target energy storage parameters specifically includes: Using a pre-defined economic calculation strategy, multiple economic scores are determined for multiple configuration schemes. Each configuration scheme includes a candidate capacity and a corresponding set of target energy storage parameters. The target configuration parameters are determined based on the multiple economic scores.

6. The green electricity direct connection system configuration method according to claim 5, characterized in that, The process of determining multiple economic scores corresponding to multiple configuration schemes using a preset economic calculation strategy specifically includes: Based on a preset economic calculation strategy, the total life cycle cost, energy cost, and investment payback period corresponding to the multiple configuration schemes are determined. Sensitivity analysis was performed on the multiple configuration schemes to obtain multiple sensitivity coefficients; The multiple economic scores are determined based on the multiple sensitivity coefficients, the total life cycle cost, energy cost, and investment payback period corresponding to the multiple configuration schemes.

7. A green electricity direct connection system configuration device, characterized in that, The green electricity direct connection system configuration device includes: An acquisition module is used to acquire time-series data and boundary parameters, wherein the time-series data is used to characterize the data that changes over time in the green electricity direct connection system, and the boundary parameters are used to characterize the constraint parameters in the green electricity direct connection system; The first determining module is used to determine the candidate capacity set of the transformer based on the time series data and the boundary parameters; The second determining module is used to determine multiple sets of target energy storage parameters corresponding to multiple candidate capacities in the candidate capacity set using a preset algorithm, wherein the multiple candidate capacities and the multiple sets of target energy storage parameters correspond one-to-one. The third determining module is used to determine the target configuration parameters based on the multiple candidate capacities and the multiple sets of target energy storage parameters; The configuration module is used to configure the green electricity direct connection system according to the target configuration parameters.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the green electricity direct connection system configuration method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the green electricity direct connection system configuration method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the green electricity direct connection system configuration method according to any one of claims 1-6.

Images