A photovoltaic power station optimization method and device fusing component layout and electricity price response

Abstract

The application provides a photovoltaic power station optimization method and device fusing component layout and electricity price response. The method comprises the following steps: applying a cooperative optimization model, combining real-time electricity price data and power grid dispatching instructions, adjusting a current spatial layout parameter of a photovoltaic power station, so as to adjust the current spatial layout parameter to a target spatial layout parameter satisfying a maximum first net present value; determining a spatial hotspot and a time hotspot of power abandonment of the photovoltaic power station according to the target spatial layout parameter, and calculating an index value for a full life cycle economic evaluation of the photovoltaic power station; in response to the index value not satisfying a preset standard, adjusting a spatial layout parameter and / or a power dispatching strategy of the photovoltaic power station in combination with the spatial hotspot and the time hotspot. The economic benefit of the photovoltaic power station can be improved through the application.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power generation system optimization technology, and in particular to a method and apparatus for optimizing photovoltaic power plants that integrates component layout and electricity price response. Background Technology

[0002] The current energy sector has experienced rapid development in the photovoltaic (PV) industry, with the national installed capacity now exceeding 1 billion kilowatts, accounting for 30% of the country's total power generation capacity. In terms of installed capacity alone, PV has become the second largest power source. However, behind this vigorous development lie numerous problems, such as the mismatch between the volatility of PV output and the grid's absorption capacity, leading to significant curtailment (e.g., a curtailment rate exceeding 10% in Northwest China); and the high land costs making it difficult to reduce PV costs. Furthermore, in terms of system design: traditional designs separate and optimize spatial parameters such as module tilt angle and spacing from electricity pricing policies and energy storage configurations, neglecting the dynamic coupling effects of multiple factors; and the revenue calculated under static electricity price assumptions cannot reflect the actual revenue potential of time-of-use pricing and market bidding strategies.

[0003] Therefore, this application provides a photovoltaic power plant optimization method and apparatus that integrates component layout and electricity price response to solve one of the above-mentioned technical problems. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this application provides a photovoltaic power plant optimization method and apparatus that integrates component layout and electricity price response.

[0005] According to a first aspect of the embodiments of this application, a method for optimizing a photovoltaic power plant that integrates component layout and electricity price response is provided, the method comprising:

[0006] A collaborative optimization model is applied, combined with real-time electricity price data and grid dispatch instructions, to adjust the current spatial layout parameters of the photovoltaic power station to a target spatial layout parameter that maximizes the first net present value (NPV). The first NPV represents the capacity efficiency of the photovoltaic power station. The collaborative optimization model is defined as the mathematical relationship between the first NPV, the real-time electricity price data, the maximum dispatchable resources of the grid, and the spatial layout parameters. The maximum dispatchable resources of the grid are obtained based on the grid dispatch instructions. Based on the target spatial layout parameters, spatial and temporal hotspots for the photovoltaic power station to generate curtailed electricity are determined, and indicator values ​​for a full life-cycle economic evaluation of the photovoltaic power station are calculated. In response to the indicator values ​​not meeting preset standards, the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station are adjusted, taking into account the spatial and temporal hotspots.

[0007] In one embodiment, in the mathematical relationship, the factor terms of the spatial layout parameters are positively correlated with the first net present value, the factor terms of the real-time electricity price data are positively correlated with the first net present value, and the factor terms of the maximum dispatchable resources of the power grid are positively correlated with the first net present value.

[0008] In one embodiment, the index values ​​include curtailment rate, levelized cost of electricity (LCOE), and second net present value (NPV), whereby the second NPV characterizes the project benefits of the photovoltaic power station.

[0009] In one embodiment, the levelized cost of electricity (LCOE) is obtained by summing the initial investment cost and the operation and maintenance cost, and then quotienting the sum of the power generation; the second net present value (NPV) is obtained by quotienting the difference between revenue and cost and the discount rate, and then summing the values ​​over time.

[0010] In one embodiment, the spatial hotspot is used to provide a regional reference for component adjustment, and the temporal hotspot is used to provide a time-period reference for component adjustment. In response to the indicator value not meeting a preset standard, the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station are adjusted in conjunction with the spatial and temporal hotspots. This includes: in response to the levelized cost of electricity (LCOE) exceeding a cost threshold, increasing the component tilt angle, extending the component cleaning cycle, and / or appropriately compressing the component row spacing in low-shading areas; and / or in response to the curtailment rate exceeding a curtailment rate threshold, increasing the component row spacing in high-curtailment-risk areas, decreasing the component row spacing in low-curtailment-risk areas, and / or configuring buffer energy storage. The buffer energy storage is used for storing electricity when the grid's capacity is insufficient, and for supplying electricity to the grid when the photovoltaic power station's capacity is insufficient; and / or in response to the fluctuation range of the second net present value exceeding an amplitude threshold, prioritizing electricity sales during high-price periods, converting capacity for self-use or energy storage during low-price periods, and / or obtaining revenue subsidies in response to grid frequency regulation needs.

[0011] In one embodiment, determining the spatial and temporal hotspots for power curtailment generated by the photovoltaic power station based on the target spatial layout parameters includes: constructing a three-dimensional matrix containing component coordinates, time, and curtailment rate based on the historical irradiance curve data, component layout topology information, and grid curtailment command timestamps of the photovoltaic power station; calculating the curtailment amount and planned maintenance curtailment amount respectively; inputting the target spatial layout parameters, the three-dimensional matrix, the curtailment amount, and the planned maintenance curtailment amount into a machine learning algorithm, and performing curtailment feature analysis based on the machine learning algorithm to output the spatial and temporal hotspots for power curtailment generated by the photovoltaic power station; wherein, the curtailment amount is obtained by differentiating the grid curtailment target power and the actual inverter output power based on the non-grid curtailment period; the planned maintenance curtailment amount is obtained by differentiating the theoretical power generation power and the actual inverter output power based on the non-grid curtailment period.

[0012] In one embodiment, the current spatial layout parameters of the photovoltaic power station are obtained as follows: acquiring and preprocessing the solar resource data of the photovoltaic power station to obtain preprocessed solar resource data; performing three-dimensional shadow modeling on the photovoltaic power station based on the preprocessed solar resource data to obtain a three-dimensional shadow model of the photovoltaic power station; performing shadow occlusion analysis on the photovoltaic power station using the three-dimensional shadow model, and optimizing the initial spatial layout parameters of the photovoltaic power station based on the shadow occlusion analysis results to obtain the current spatial layout parameters of the photovoltaic power station.

[0013] According to a second aspect of the embodiments of this application, a photovoltaic power plant optimization device integrating component layout and electricity price response is provided, comprising:

[0014] The collaborative optimization module is used to apply a collaborative optimization model, combined with real-time electricity price data and grid dispatch instructions, to adjust the current spatial layout parameters of the photovoltaic power station to a target spatial layout parameter that maximizes the first net present value (NPV). The first NPV represents the capacity efficiency of the photovoltaic power station, and the collaborative optimization model is defined as the mathematical relationship between the first NPV, the real-time electricity price data, the maximum dispatchable resources of the grid, and the spatial layout parameters. The maximum dispatchable resources of the grid are obtained based on the grid dispatch instructions. The hotspot identification and evaluation module is used to determine the spatial and temporal hotspots where the photovoltaic power station generates curtailment based on the target spatial layout parameters, and to calculate index values ​​for a full life-cycle economic evaluation of the photovoltaic power station. The parameter adjustment module is used to adjust the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station in response to the index values ​​not meeting preset standards, in conjunction with the spatial and temporal hotspots.

[0015] According to a third aspect of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any of the first aspects.

[0016] According to a fourth aspect of this application, a computer-readable storage medium is provided that stores a computer program / instructions thereon, which, when executed by a processor, implements the method described in any one of the first aspects.

[0017] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0018] In this embodiment, a collaborative optimization model is used to dynamically adjust the spatial layout parameters of a photovoltaic power station by combining real-time electricity price data and grid dispatch instructions. This effectively balances the contradiction between power generation efficiency and grid absorption capacity. By using mathematical relationships to link net present value, electricity price fluctuations, grid dispatch constraints, and layout parameters, the power station layout not only adapts to sunlight conditions but also responds to peak and off-peak electricity prices and grid curtailment demands, thereby maximizing capacity benefits while meeting grid dispatch requirements. This dynamic adjustment mechanism significantly reduces curtailment losses and improves the overall economic return of the power station.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this application, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] Figure 1 A flowchart is shown for a photovoltaic power plant optimization method that integrates component layout and electricity price response;

[0022] Figure 2 A flowchart illustrating a method for determining the spatial and temporal hotspots of curtailed electricity generated by photovoltaic power plants is shown.

[0023] Figure 3 A flowchart illustrating a method for obtaining the current spatial layout parameters of a photovoltaic power plant is shown.

[0024] Figure 4 A schematic diagram of a process for optimizing a photovoltaic power plant is shown;

[0025] Figure 5 A schematic diagram of the processing logic of a dual-core engine is shown;

[0026] Figure 6 A unit block diagram of a photovoltaic power plant optimization device with integrated component layout and electricity price response according to an embodiment of this application is shown;

[0027] Figure 7 This is a block diagram of an electronic device for optimizing a photovoltaic power plant by integrating component layout and electricity price response, according to an exemplary embodiment. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0029] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0030] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0031] The embodiments of this application will now be described in detail.

[0032] like Figure 1 As shown, Figure 1 This application presents a flowchart illustrating a photovoltaic power plant optimization method integrating component layout and electricity price response according to an exemplary embodiment, comprising the following steps:

[0033] In step 101, the collaborative optimization model is applied, and the current spatial layout parameters of the photovoltaic power station are adjusted in combination with real-time electricity price data and grid dispatch instructions, so as to adjust the current spatial layout parameters to the target spatial layout parameters that satisfy the goal of maximizing the first net present value.

[0034] Among them, the first net present value represents the production capacity efficiency of the photovoltaic power station. The collaborative optimization model is defined as the mathematical relationship between the first net present value, real-time electricity price data, the maximum dispatchable resources of the power grid and spatial layout parameters. The maximum dispatchable resources of the power grid are obtained based on the power grid dispatch instructions.

[0035] In step 102, based on the target spatial layout parameters, the spatial hotspots and temporal hotspots for generating curtailed electricity from the photovoltaic power station are determined, and the index values ​​used for the full life-cycle economic evaluation of the photovoltaic power station are calculated.

[0036] In step 103, in response to the index value not meeting the preset standard, the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station are adjusted in combination with spatial hotspots and temporal hotspots.

[0037] The method provided in this application dynamically adjusts the spatial layout parameters of photovoltaic power plants by combining a collaborative optimization model with real-time electricity price data and grid dispatch instructions, effectively balancing the contradiction between power generation efficiency and grid absorption capacity. By using mathematical relationships to link the first net present value, electricity price fluctuations, grid dispatch constraints, and layout parameters, the power plant layout not only adapts to sunlight conditions but also responds to peak and off-peak electricity prices and grid curtailment demands. This maximizes production efficiency while meeting grid dispatch requirements. This dynamic adjustment mechanism significantly reduces curtailment losses and improves the overall economic return of the power plant.

[0038] In some embodiments, spatial hotspots include identifying areas where power generation efficiency is significantly reduced due to severe local shading or component aging. Temporal hotspots include predicting peak periods of insufficient grid absorption capacity (such as midday when sunlight is strongest), with the prediction results labeled with different risk levels (high, medium, low) to guide targeted intervention measures.

[0039] In some specific embodiments, spatial hotspots are used to provide regional references for component adjustment, and temporal hotspots are used to provide time-period references for component adjustment.

[0040] In some embodiments, this application provides a photovoltaic power plant optimization method that integrates component layout and electricity price response. The core of this method lies in dynamically adjusting the spatial layout parameters of the photovoltaic power plant through a collaborative optimization model to maximize capacity efficiency. This method first acquires real-time electricity price data and grid dispatch instructions, and then constructs a collaborative optimization model based on the current spatial layout parameters of the photovoltaic power plant (such as component tilt angle α and row spacing D). This model defines the mathematical relationship between the first net present value (NPV), electricity price, the maximum dispatchable resources of the grid, and the spatial layout parameters, transforming the optimization objective into a mathematical problem to be solved. The first NPV represents the capacity efficiency of the photovoltaic power plant, and its calculation requires comprehensive consideration of power generation revenue, curtailment losses, initial investment costs, and grid dispatch constraints.

[0041] In some embodiments, in the mathematical relationships represented by the collaborative optimization model, the factor terms of spatial layout parameters are positively correlated with the first net present value, the factor terms of real-time electricity price data are positively correlated with the first net present value, and the factor terms of the maximum dispatchable resources of the power grid are positively correlated with the first net present value.

[0042] As a feasible implementation, the mathematical relationship of the collaborative optimization model can be specifically expressed as follows:

[0043] ;

[0044] in, The maximum value of the first net present value; η(α,D) is the power generation efficiency determined by the tilt angle and spacing. Its physical meaning lies in quantifying the impact of the module tilt angle α (unit: degrees) and row spacing D (unit: meters) on the power generation efficiency. Specifically, it is calculated through geometric optics models in solar engineering (such as the Perez model or the Liu-Jordan model), or determined based on empirical fitting formulas. t is the time period identifier, T is the number of samples in the time period; G The effective irradiance on the component surface at time t (unit: kWh / m²) is derived from meteorological monitoring data or the output of numerical meteorological models (such as WRF models), and needs to be corrected for topographic shading effects by combining topographic mapping data (such as DEM elevation maps); P The real-time electricity price for time period t (unit: yuan / kWh) is taken from electricity market transaction data; This is the curtailment loss function, which covers the economic losses caused by curtailment due to grid dispatch instructions and the performance losses caused by layout parameters (such as the decrease in power generation due to shading). This represents the initial investment cost (unit: yuan), corresponding to the construction cost of the photovoltaic power station; The maximum amount of resources that the power grid can dispatch in time period t (unit: kW) is obtained based on power grid dispatch instructions or prediction models (such as load forecasting algorithms); For Lagrange multipliers (unit: , adjustment is needed to ensure...) (Unit: yuan), used to balance the objective function and power grid constraints during the optimization process.

[0045] As a specific implementation, the above model aims to maximize the first net present value (NPV) over the entire lifecycle T (where T is the number of time-period samples) by adjusting the component tilt angle α and row spacing D. The optimization process needs to comprehensively consider multiple factors: First, historical and predicted irradiance data are generated using numerical meteorological models, and topographic mapping techniques are combined to analyze the terrain undulations and shadow distribution in the component layout area, thereby accurately calculating η(α,D); second, the power generation revenue term η(α,D)⋅G(t)⋅P(t) is dynamically adjusted using real-time electricity price data (such as time-of-use pricing or spot market quotations) to address the impact of electricity price fluctuations on revenue; third, the curtailment loss function... (α,D) needs to be modeled based on grid dispatch instructions and historical power curtailment data to ensure that the optimization strategy takes into account the grid's absorption capacity; finally, the grid dispatch constraints (such as R) are applied using the Lagrange multiplier λ. grid Incorporate it into the objective function to avoid the risk of grid overload caused by excessive pursuit of power generation.

[0046] For example, in low-latitude regions, the module tilt angle α is typically set to 1-3 times the local latitude, while the row spacing D needs to be determined through shading analysis (such as a 3D shading model based on topographic mapping) to reduce mutual shading between adjacent modules. When the real-time electricity price P(t) is high (such as during midday peak electricity consumption), the model will prioritize increasing the weight of η(α,D)⋅G(t)⋅P(t), prompting the module layout to adjust towards higher power generation efficiency; while during low-electricity-price periods (such as at night or on rainy days), the initial investment cost may be reduced by compressing the row spacing D or adjusting the tilt angle α. Furthermore, when the power grid dispatch command displays... As the value of λ approaches the upper limit, it will increase significantly, forcing the optimization results to favor layout schemes that reduce power curtailment losses (such as increasing the row spacing D to reduce the probability of shadow occlusion).

[0047] Through the above implementation methods, this application can achieve economic optimization of photovoltaic power plants under dynamic electricity prices and grid dispatch constraints. Specifically, by using meteorological service technologies (such as high-resolution irradiance prediction) and topographic mapping technologies (such as shading analysis) to provide accurate inputs to the model, and combining the Lagrange multiplier method to handle multi-constraint optimization problems, the final output of the module tilt angle α and row spacing D can maximize power generation revenue while avoiding the risk of curtailment, thereby significantly improving the first net present value of the photovoltaic power plant throughout its entire life cycle.

[0048] In this embodiment, the mathematical formula introduces a power generation efficiency factor η(α,D) and a Lagrange multiplier λ to quantitatively correlate component tilt angle, row spacing, electricity price fluctuations, and grid dispatch constraints, providing clear mathematical support for the optimization process. The power generation efficiency factor comprehensively considers factors such as shading and ground reflection, while the introduction of electricity price and grid dispatch constraints ensures that the optimization results conform to actual market conditions. This formulaic expression not only improves the computability of the model but also enables rapid generation of the optimal layout scheme through iterative optimization, thereby maximizing net present value under complex operating conditions.

[0049] In this embodiment of the application, the index values ​​include curtailment rate, levelized cost of electricity (LCOE), and second net present value (NPV), where the second NPV characterizes the project benefits of the photovoltaic power station.

[0050] In some embodiments, this application constructs a full life-cycle economic evaluation system for photovoltaic power plants by integrating the levelized cost of electricity (LCOE) and the second net present value (NPV). This system uses initial investment cost, operation and maintenance cost, power generation, revenue, and cost as core parameters, combined with real-time electricity price data (P(t)) and grid dispatch instructions, to achieve a dynamic assessment of the power plant's economic viability. Specifically, the LCOE quantifies the long-term cost efficiency per unit of power generation by discounting initial investment and operation and maintenance costs and allocating them to the total life-cycle power generation; the NPV comprehensively reflects the overall profitability of the project by discounting the difference between revenue and cost at different time periods. This dual-indicator collaborative analysis mechanism can balance cost control and revenue growth targets, providing a scientific basis for optimizing power plant layout.

[0051] In some embodiments, the levelized cost of electricity (LCOE) is obtained by summing the initial investment cost and the operation and maintenance cost, and then quotienting the sum of the power generation.

[0052] As a feasible implementation, the formula for calculating the levelized cost of electricity (LCOE) is specifically expressed as follows:

[0053] ;

[0054] in, To levelize the cost of electricity, C cap For the initial investment cost, C O&M For operating and maintenance costs, Egen represents power generation, t represents the time period identifier, and T represents the number of samples in the time period.

[0055] in, The initial investment cost (unit: yuan) covers the construction costs of components, inverters, support systems, etc. Operating and maintenance costs (unit: yuan) include cleaning, inspection and equipment repair expenses; The actual power generation in time period t (unit: kWh) needs to be calculated using numerical meteorological models from meteorological service technologies to predict irradiance, and topographic mapping techniques should be used to correct for shading effects. The present value of power generation in the denominator needs to consider the impact of component degradation rates, inverter efficiency, and grid curtailment orders on theoretical power generation, thus more accurately reflecting the actual available power. This formula balances the time value of money through a discount factor (1+r)-(t-1), making the comparison of costs and benefits more financially reasonable, where r is the discount rate, which is dimensionless.

[0056] In some embodiments, the second net present value is obtained by quoting the difference between revenue and cost with the discount rate and then summing the values ​​over time.

[0057] As a specific embodiment, the formula for calculating the second net present value is as follows:

[0058] ;

[0059] Wherein, Benefit(t) represents the revenue in period t, mainly derived from electricity sales revenue, calculated as the annual sum of η(α,D)⋅G(t)⋅P(t)-Closs(α,D), where η(α,D) is the layout efficiency factor, quantifying the impact of module tilt angle α and row spacing D on power generation efficiency based on a solar engineering model; G(t) is the effective irradiance on the module surface in period t (unit: kWh / m²), which needs to be corrected for shading effects based on meteorological monitoring data and topographic mapping results; P(t) is the real-time electricity price in period t (unit: yuan / kWh), taken from electricity market transaction data; C loss (α,D) is the curtailment loss function (unit: yuan), encompassing the economic losses from curtailment caused by grid dispatch instructions and the performance losses due to layout parameters. Cost(t) is the operating cost for time period t (unit: yuan), mainly consisting of C. O&M This formula uses a discount factor. Cash flows from each period are discounted to a base time point to comprehensively assess the project's absolute profitability and cash flow value.

[0060] For example, in scenarios with high curtailment rates or volatile electricity prices, dynamic weighting mechanisms can significantly improve the adaptability of economic evaluations. When the curtailment rate index RE... t (defined as RE) t = (Gross curtailment + Planned maintenance curtailment) / Eth(t), where Eth(t) is the weight W of the levelized cost of electricity (LCOE) when the theoretical power generation during the forecast period exceeds a preset threshold. lcoe The price will be dynamically adjusted upwards to prioritize optimizing unit power generation costs; conversely, when the electricity price volatility index PV... t When it increases significantly, the weight W of the second net present value npv The model will prioritize upward adjustments to maximize electricity sales revenue. For example, in low-latitude regions, if historical data shows significant fluctuations in midday electricity prices, the model will adjust the module tilt angle α and row spacing D to prioritize increasing generation efficiency η(α,D) during high-price periods, thereby increasing Benefit(t) and ultimately improving NPV. In areas with high curtailment risk, the model will increase row spacing D to reduce shading losses and configure buffer energy storage systems to reduce the curtailment rate RE. t This optimizes LCOE. This dynamic weighting mechanism makes the economic evaluation results more closely reflect the actual operating environment, driving the optimization model to generate layout schemes that balance costs and benefits.

[0061] Through the above implementation methods, this solution can optimize the economics of photovoltaic power plants under complex meteorological conditions and grid dispatch constraints. Specifically, by utilizing meteorological service technology and topographic mapping technology to provide accurate input for indicator calculation, and combining a dynamic weighting mechanism to adapt to different operating scenarios, the final output of the module tilt angle α and row spacing D can both reduce the unit power generation cost and improve the overall project revenue, thereby significantly enhancing the economic return rate of the photovoltaic power plant throughout its entire life cycle.

[0062] In this embodiment, the formula for calculating the levelized cost of electricity (LCOE) discounts the initial investment and operation and maintenance costs and allocates them to the total power generation, thus directly reflecting the long-term cost efficiency of the power plant. The calculation of the second net present value (NPV) comprehensively considers the time value of revenue and costs, dynamically assessing the project's profitability. This dual-indicator system not only covers the two core objectives of cost control and revenue growth but also adapts to different operating environments through dynamic weight adjustments, thereby enhancing the flexibility and applicability of the optimization strategy.

[0063] In some embodiments, spatial hotspots include identifying areas where power generation efficiency is significantly reduced due to severe local shading or component aging. Temporal hotspots include predicting peak periods of insufficient grid absorption capacity (such as midday when sunlight is strongest), with the prediction results labeled with different risk levels (high, medium, low) to guide targeted intervention measures.

[0064] In some specific embodiments, spatial hotspots are used to provide regional references for component adjustment, and temporal hotspots are used to provide time-period references for component adjustment.

[0065] Based on this, and taking into account spatial and temporal hotspots, the spatial layout parameters and / or power dispatch strategies of photovoltaic power plants are adjusted in the following ways.

[0066] Method 1: In response to the levelized cost of electricity exceeding the cost threshold, increase the module tilt angle, extend the module cleaning cycle, and / or appropriately compress the module row spacing in low shading areas;

[0067] Method 2: In response to the curtailment rate exceeding the curtailment rate threshold, increase the module row spacing in high-risk curtailment areas, decrease the module row spacing in low-risk curtailment areas, and / or configure buffer energy storage.

[0068] Among them, buffer energy storage is used to store electricity when the grid's capacity is insufficient, and to supply electricity to the grid when the photovoltaic power plant's capacity is insufficient;

[0069] Method 3: In response to fluctuations in the second net present value exceeding the threshold, prioritize selling electricity during periods of high electricity prices, convert capacity for self-use or energy storage during periods of low electricity prices, and / or obtain revenue subsidies in response to grid frequency regulation needs.

[0070] Correspondingly, when each indicator value meets the preset requirements, the final layout drawing and parameter table can be generated, clarifying technical details such as component coordinates, tilt angle, and row spacing. At the same time, a full-cycle economic analysis report is output, including cost breakdown, revenue forecast, and risk warning.

[0071] In this application embodiment, targeted adjustment measures are taken for abnormal situations of different economic indicators, which can significantly improve the economic efficiency and stability of power plant operation. For example, increasing the tilt angle of modules and compressing the row spacing can reduce the unit land cost and improve power generation efficiency, thereby reducing the levelized cost of electricity (LCOE); increasing the row spacing in high-risk areas of curtailment can reduce power generation losses caused by shading, while configuring buffer energy storage can store electricity when the grid's capacity is insufficient and release it when capacity is insufficient, thus achieving power balance; prioritizing electricity sales or energy storage during periods of drastic electricity price fluctuations can maximize electricity sales revenue and avoid revenue losses during periods of low electricity prices. These measures directly address specific problems and improve the resource utilization rate and revenue stability of the power plant.

[0072] Figure 2 A flowchart illustrating a method for determining the spatial and temporal hotspots of curtailed electricity from photovoltaic power plants is shown, such as... Figure 2 As shown, it includes the following steps.

[0073] In step 201, based on the historical irradiance curve data of the photovoltaic power plant, the module layout topology information and the grid curtailment command timestamp, a three-dimensional matrix containing module coordinates, time and curtailment rate is constructed, and the curtailment amount and planned maintenance curtailment amount are calculated respectively.

[0074] In step 202, the target spatial layout parameters, three-dimensional matrix, curtailment amount and planned maintenance curtailment amount are input into the machine learning algorithm, and curtailment feature analysis is performed based on the machine learning algorithm to output the spatial hotspots and temporal hotspots of curtailment generated by the photovoltaic power station.

[0075] In this embodiment, a three-dimensional matrix containing component coordinates, time, and curtailment rate is constructed, and a dual-path model is used to calculate the curtailment amount and planned maintenance curtailment amount, thereby achieving precise location of spatiotemporal hotspots for photovoltaic power plant curtailment. This method first constructs a three-dimensional matrix based on historical irradiance curve data, component layout topology information (component coordinates, source: topographic mapping data and power plant design drawings), and grid curtailment command timestamps. Each element in the matrix corresponds to the curtailment rate of a specific component at a specific time point. The difference between theoretical power generation (P_th) and actual power generation (P_c) is used to quantify the curtailment loss caused by grid dispatch or equipment failure. This process requires the use of meteorological service technologies (such as high-resolution irradiance prediction) to correct for topographic shading effects, and the acquisition of three-dimensional coordinate information of component layout through topographic mapping technology to ensure the spatiotemporal accuracy of the matrix data.

[0076] In some embodiments, the amount of power curtailment is obtained by taking the derivative of the difference between the grid curtailment target power and the actual output power of the inverter, based on the non-grid curtailment period.

[0077] In some specific embodiments, the amount of curtailed solar power is calculated using the following formula:

[0078] Curtailment of solar power = ;

[0079] Where [t0, t1] represents the non-grid power curtailment period; AGC is the grid power curtailment target power (unit: kW), which is derived from the dispatch command system; The actual output power of the inverter (unit: kW) is taken from real-time data of the Supervisory Control and Data Acquisition (SCADA) system. This formula calculates the power loss due to curtailment caused by power restriction during the grid command period through integration. The economic loss needs to be quantified in conjunction with the market electricity price (P_loss(t), unit: yuan / kWh) of the corresponding period and included in the total curtailment loss function Closs(α,D). For example, during the midday peak period of the typical photovoltaic output curve (11:00-16:00) in the Qinghai power grid, if the grid dispatch command AGC is lower than the theoretical power generation P_th, the amount of curtailed photovoltaic power will increase significantly. It is necessary to optimize the layout by adjusting the module tilt angle α and row spacing D (based on the shading analysis of terrain mapping) to reduce the curtailment rate.

[0080] In some embodiments, the planned curtailment of solar power is obtained by differentiating the theoretical power generation from the actual output power of the inverter, and then differentiating based on the off-grid curtailment period.

[0081] In some specific embodiments, the planned maintenance curtailment volume is calculated using the following formula:

[0082] Planned maintenance waste of light = ;

[0083] in, The lossless ideal power generation (unit: kW) is calculated based on the nominal power of the components and correction factors (temperature, irradiance deviation, etc.). [t0, t1] represents the actual output power of the inverter (unit: kW), taken from SCADA data; [t0, t1] represents the off-grid curtailment period (such as equipment maintenance or downtime due to faults). This formula quantifies the power loss due to equipment issues, and the economic loss needs to be calculated in conjunction with the market electricity price (P(t), unit: yuan / kWh) for the corresponding period. For example, on a cloudy winter day with low irradiance, if the photovoltaic modules suffer power loss due to an excessively long cleaning cycle... Below If this happens, the amount of light wasted during planned maintenance will increase significantly, and losses will need to be reduced by optimizing the cleaning cycle or adjusting the component layout (based on shadow distribution analysis from topographic mapping).

[0084] For example, by using machine learning algorithms to perform feature analysis on three-dimensional matrices, curtailment volume of solar power, and planned maintenance curtailment volume, spatial and temporal hotspots for power curtailment in power plants can be identified. For instance, in high-altitude areas of Northwest China, if topographic mapping data shows that insufficient row spacing of components in a certain area leads to severe shading, spatial hotspot identification will suggest increasing the row spacing. Similarly, if meteorological service forecasts indicate frequent changes in grid dispatch instructions during a certain period, temporal hotspot analysis will suggest configuring buffer energy storage systems to balance the risk of power curtailment. This data-driven analysis method not only improves the accuracy of hotspot identification but also predicts future curtailment risks using historical data, thereby enabling the development of optimization strategies in advance and reducing economic losses.

[0085] Through the above-described implementation methods, this application enables precise control of power curtailment losses under complex meteorological conditions and grid dispatch constraints. Specifically, it utilizes meteorological service technology to provide dynamic input, combines topographic mapping technology to optimize component layout, and then uses a dual-path model to distinguish between the sources of power curtailment caused by grid dispatch and equipment failures. Ultimately, it drives a collaborative optimization model to generate targeted adjustment schemes. This multi-dimensional analysis mechanism significantly improves the economic efficiency and stability of power plant operation.

[0086] In some embodiments, before performing layout optimization based on the collaborative optimization model, some preparatory steps are required to perform preliminary optimization of the initial spatial layout parameters of the photovoltaic power station to obtain the current spatial layout parameters used as input to the collaborative optimization model.

[0087] Figure 3 A flowchart illustrating a method for obtaining the current spatial layout parameters of a photovoltaic power plant is shown, such as... Figure 3 As shown, it includes the following steps.

[0088] In step 301, the solar resource data of the photovoltaic power station is acquired and preprocessed to obtain the preprocessed solar resource data;

[0089] In step 302, based on the preprocessed light resource data, a three-dimensional shadow model of the photovoltaic power station is performed to obtain the three-dimensional shadow model of the photovoltaic power station.

[0090] In step 303, the shading analysis of the photovoltaic power station is performed using a three-dimensional shading model, and the initial spatial layout parameters of the photovoltaic power station are optimized based on the shading analysis results to obtain the current spatial layout parameters of the photovoltaic power station.

[0091] In this embodiment, by preprocessing light resource data and establishing a three-dimensional shadow model, the shadow shading effect of different seasons and time periods can be accurately simulated, providing a reliable basis for optimizing the initial spatial layout parameters. The shadow shading analysis results can guide the adjustment of component tilt angle and row spacing, reducing power generation efficiency loss caused by shadows. This optimization method based on real light resource data ensures the scientific and practical nature of the layout parameters, thereby reducing potential power generation losses and improving overall operating efficiency during the power plant design phase.

[0092] Figure 4 A schematic diagram of a process for optimizing a photovoltaic power plant is shown.

[0093] like Figure 4 As shown, this application achieves dynamic adjustment of power plant spatial layout parameters and full life-cycle economic verification by combining meteorological service technology, topographic mapping data, and a collaborative optimization model. The method first collects solar irradiance, temperature, humidity, and other light resource data of the target area using high-precision sensors, and then performs standardization processing based on time series data to form a reliable data foundation. Subsequently, by combining topographic mapping data from a geographic information system with component layout topology information, a three-dimensional shadow model of the photovoltaic power plant is constructed to simulate the shadow shading effect in different seasons and time periods, providing a basis for subsequent spatial parameter optimization.

[0094] As a feasible implementation, the 3D shadow modeling process specifically includes: based on preprocessed light resource data and component coordinate information, using a numerical meteorological model to predict the solar altitude angle and azimuth angle, and dynamically calculating the shadow occlusion loss between components. For example, in high-altitude areas of Northwest China, if topographic mapping data shows that a certain area is occluded by mountains, the model will quantify the duration of shadows on components in that area on a winter morning and suggest increasing row spacing or adjusting component tilt angle accordingly. The shadow occlusion analysis results identify high-risk areas through machine learning algorithms, generating component-level occlusion loss maps to provide input for subsequent optimization.

[0095] As a specific implementation, spatial layout parameter optimization includes the joint adjustment of component tilt angle and row spacing. Tilt angle optimization determines the optimal value by iteratively calculating the amount of direct radiation received by the component surface under different α values ​​and combining it with a temperature correction factor. Row spacing optimization balances land utilization and shading loss based on a shading loss function. For example, in low-latitude regions, if meteorological service technology forecasts that the peak midday irradiance in summer reaches 1200 W / m², while topographic mapping data shows that insufficient row spacing leads to significant afternoon shading loss, the system will suggest adjusting the row spacing from 3.5 meters to 4.2 meters to reduce shading loss to below 5%.

[0096] In some embodiments, the collaborative optimization model integrates real-time electricity price data (such as peak-valley price differences), grid dispatch instructions, and spatial layout parameters, and drives parameter adjustments by defining a mathematical relationship of the first net present value.

[0097] For example, when the grid dispatch command shows that the maximum dispatchable power during a certain period (such as 12:00-14:00) is lower than the power plant's theoretical generating capacity, the system increases the row spacing D to reduce shading losses (e.g., from 3.8 meters to 4.5 meters), thereby increasing the actual power generation during that period. If meteorological service forecasts indicate that the irradiance intensity in a certain area fluctuates significantly during the winter and spring seasons over the next five years (standard deviation exceeding 0.15 kWh / m²), the system will further optimize the module tilt angle α to maintain high power generation efficiency even during periods of low irradiance.

[0098] In some embodiments, curtailment hotspot prediction is based on collaborative optimization results, using machine learning algorithms to analyze curtailment characteristics in historical data. Spatial hotspot identification combines topographic mapping data to locate densely populated areas of solar panels or areas obstructed by mountains, marking them as high-risk areas; temporal hotspots are predicted using grid dispatch command timestamps and electricity price volatility indices to indicate periods of insufficient grid absorption capacity. For example, in the eastern coastal region, if meteorological service technology indicates a sharp drop in irradiance at photovoltaic power plants due to cloud cover during typhoon season, and grid dispatch commands indicate limited absorption capacity during this period, the system will suggest configuring an energy storage system to store surplus electricity and release it during peak electricity price periods to improve net present value.

[0099] With both indicators met, the system generates final layout drawings and parameter tables, clearly defining technical details such as component coordinates, tilt angles, and row spacing. Simultaneously, it outputs a full-cycle economic analysis report, including cost breakdown, revenue forecasting, and sensitivity analysis. After each parameter adjustment, the system updates the electricity pricing strategy library and the evaluation weights of the dual-core economic engine, feeding back to the collaborative optimization model to initiate the next iteration, forming an "execution-evaluation-correction" closed loop. The three core deliverables are a physical layout plan, an operation strategy manual, and an economic analysis report, ensuring the long-term economic viability and feasibility of the plan under complex meteorological conditions and grid constraints.

[0100] Figure 5 A schematic diagram of the processing logic of a dual-core engine is shown.

[0101] like Figure 5As shown, this application provides an energy economics analysis method based on a dual-core engine of Levelized Cost of Electricity (LCOE) and Dynamic Second Net Present Value (NPV). By integrating long-term cost-benefit and dynamic return on investment assessment, it provides a scientific basis for the whole life cycle decision-making of photovoltaic power plants. The core of this method lies in combining meteorological service technology and topographic mapping data to quantify the economic performance of projects in complex environments. Specifically, LCOE calculates the long-term average cost per unit of electricity generated by discounting the initial investment cost, operation and maintenance cost, and component degradation loss and allocating them to the total life cycle power generation; while dynamic NPV comprehensively reflects the absolute profitability and cash flow value of the project by discounting the difference between revenue and cost in each period. This dual-indicator synergy mechanism can take into account both cost control and revenue growth targets, and is particularly suitable for areas with significant grid dispatch constraints or drastic electricity price fluctuations.

[0102] As a feasible implementation, LCOE calculation incorporates cost sensitivity analysis, covering key factors such as land cost, module degradation, row spacing economics, and cleanliness optimization. Land cost is assessed using topographic mapping data and land policy evaluation; module degradation rate is based on irradiance prediction using solar engineering models combined with meteorological services, quantifying the decline in module performance over time; row spacing economics balances shading loss with land utilization; and cleanliness optimization relies on pollution deposition prediction using meteorological services to determine the optimal cleanliness cycle to improve power generation efficiency. For example, in high-altitude areas of Northwest China, if topographic mapping data shows that insufficient row spacing in a certain area leads to shading loss of up to 12% in winter, the system will suggest increasing the row spacing to 4.5 meters to reduce shading loss to 5%, thereby optimizing LCOE.

[0103] As a specific implementation, the dynamic net present value (NPV) calculation incorporates an electricity price response strategy, using the peak-valley price difference of the power grid and the green certificate premium to formulate energy storage discharge and power exchange schemes. When the peak-valley price difference is large, the system prioritizes releasing stored energy during peak electricity price periods to maximize electricity sales revenue; the green certificate premium converts surplus power generation into green certificate trading revenue through a power exchange mechanism. For example, in the eastern coastal areas, if meteorological service technology forecasts that the peak irradiance intensity reaches 1200W / m² during a certain period, and the power grid dispatch instructions indicate that the absorption capacity is limited during this period, the system will suggest configuring an energy storage system to store surplus electricity and releasing it during peak electricity price periods, while simultaneously obtaining additional revenue through green certificate trading, thereby improving the dynamic NPV. For example, in the western mountainous areas with complex terrain and variable meteorological conditions, this method accurately assesses land costs and row spacing economics through topographic mapping data, combined with meteorological service technology to predict component degradation rates and clean energy requirements. Suppose a photovoltaic project is located on a mountainous area with a slope of 15°. Topographical survey data shows that the land acquisition cost is 800 yuan / square meter, while meteorological service technology predicts an average annual irradiance of 1600 kWh / m², an average annual module degradation rate of 2%, and a cleaning cycle that needs to be shortened to once a month. In this case, the system will prioritize optimizing row spacing to reduce shading losses, and simultaneously calculate the energy storage configuration scheme through a dynamic net present value model to ensure that revenue can be maximized through energy storage discharge and green certificate trading even during periods of grid dispatch constraints. This multi-dimensional analysis mechanism reduces LCOE by 12% and increases the second net present value by 18%, significantly enhancing the project's economic viability.

[0104] Through the above-described implementation methods, this application achieves accurate economic assessment of energy projects under complex meteorological conditions and terrain constraints. Specifically, it utilizes meteorological service technology to correct component performance parameters, combines topographic mapping technology to optimize spatial layout, and then dynamically adjusts the operation strategy through an LCOE / NPV dual-core engine. The final output of component tilt angle, row spacing, and power dispatch schemes can both reduce unit power generation costs and maximize revenue, providing strong support for the scientific decision-making and sustainable operation of photovoltaic power plants.

[0105] This application also provides apparatus embodiments that follow the above embodiments, for implementing the method steps of the above embodiments. The interpretation of the same names is the same as that of the above embodiments, and they have the same technical effects as those of the above embodiments, so they will not be repeated here.

[0106] like Figure 6 As shown, this application provides a photovoltaic power plant optimization device 600 that integrates component layout and electricity price response, comprising:

[0107] The collaborative optimization module 601 is used to apply a collaborative optimization model, combined with real-time electricity price data and grid dispatch instructions, to adjust the current spatial layout parameters of the photovoltaic power station, so as to adjust the current spatial layout parameters to the target spatial layout parameters that maximize the first net present value; wherein, the first net present value represents the production efficiency of the photovoltaic power station, and the collaborative optimization model is defined as the mathematical relationship between the first net present value, real-time electricity price data, the maximum dispatchable resources of the grid, and the spatial layout parameters, and the maximum dispatchable resources of the grid are obtained based on grid dispatch instructions;

[0108] The hotspot identification and evaluation module 602 is used to determine the spatial and temporal hotspots that generate curtailment of photovoltaic power plants based on the target spatial layout parameters, and to calculate the index values ​​used for the full life cycle economic evaluation of photovoltaic power plants.

[0109] The parameter adjustment module 603 is used to adjust the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station in response to the indicator value not meeting the preset standard, combined with spatial hotspots and temporal hotspots.

[0110] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0111] Figure 7 This is a block diagram of an electronic device 700 for optimizing a photovoltaic power plant by integrating component layout and electricity price response, according to an exemplary embodiment.

[0112] like Figure 7 As shown, one embodiment of this application provides an electronic device 700. The electronic device 700 includes a memory 701, a processor 702, and an input / output (I / O) interface 703. The memory 701 stores instructions. The processor 702 is used to execute the photovoltaic power plant optimization method for integrated component layout and electricity price response according to embodiments of this application by calling the instructions stored in the memory 701. The processor 702 is connected to both the memory 701 and the I / O interface 703, for example, via a bus system and / or other forms of connection mechanisms (not shown). The memory 701 can be used to store programs and data, including the program for the photovoltaic power plant optimization method for integrated component layout and electricity price response involved in embodiments of this application. The processor 702 executes various functional applications and data processing of the electronic device 700 by running the program stored in the memory 701.

[0113] In this embodiment, the processor 702 can be implemented using at least one of the following hardware forms: digital signal processor (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 702 can be one or a combination of several of the following: central processing unit (CPU) or other processing units with data processing capability and / or instruction execution capability.

[0114] The memory 701 in this embodiment may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0115] In this embodiment, the I / O interface 703 can be used to receive input instructions (such as numeric or character information, and to generate key signal inputs related to user settings and function control of the electronic device 700), and can also output various information (such as images or sounds) to the outside. In this embodiment, the I / O interface 703 may include one or more of the following: a physical keyboard, function keys (such as volume control keys, power buttons, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, and a touch panel.

[0116] In some embodiments, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, perform any of the methods described above.

[0117] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0118] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0119] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0120] Those skilled in the art will readily conceive of other embodiments of this application upon reading this specification and implementing it. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not claimed in this application. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0121] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0122] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A photovoltaic power plant optimization method integrating component layout and electricity price response, characterized in that, include: By applying a collaborative optimization model and combining real-time electricity price data and grid dispatch instructions, the current spatial layout parameters of the photovoltaic power station are adjusted to meet the target spatial layout parameters that maximize the first net present value. Wherein, the first net present value represents the production capacity efficiency of the photovoltaic power station, and the collaborative optimization model is defined as the mathematical relationship between the first net present value, the real-time electricity price data, the maximum dispatchable resources of the power grid, and the spatial layout parameters, wherein the maximum dispatchable resources of the power grid are obtained based on the power grid dispatch instructions; Based on the target spatial layout parameters, determine the spatial hotspots and temporal hotspots for the generation of curtailed electricity by the photovoltaic power station, and calculate the index values ​​used for the full life-cycle economic evaluation of the photovoltaic power station. In response to the indicator value not meeting the preset standard, the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station are adjusted in combination with the spatial hotspots and temporal hotspots; the spatial layout parameters include the component tilt angle α and the row spacing D; The mathematical relationship of the collaborative optimization model is expressed as follows: ； in, The maximum value of the first net present value; η(α,D) is the power generation efficiency determined by the tilt angle and spacing, its physical meaning lies in quantifying the impact of the module tilt angle α and row spacing D on the power generation efficiency, specifically calculated through the geometric optics model in solar engineering, or determined based on an empirical fitting formula; t is the time period identifier, T is the number of samples in the time period; G The effective irradiance on the component surface during time period t is derived from meteorological monitoring data or the output of numerical meteorological models, and needs to be corrected for topographic shading effects by combining topographic mapping data; P The real-time electricity price for time period t is taken from electricity market transaction data; This is the power curtailment loss function, which covers the economic losses caused by power curtailment due to grid dispatch instructions and the performance losses caused by layout parameters; This represents the initial investment cost, corresponding to the construction cost of the photovoltaic power station; The maximum amount of resources that the power grid can schedule in time period t is obtained based on power grid scheduling instructions or prediction models. These are Lagrange multipliers used to balance the objective function with grid constraints during the optimization process.

2. The method according to claim 1, characterized in that, In the mathematical relationship, the factors of the spatial layout parameters are positively correlated with the first net present value, the factors of the real-time electricity price data are positively correlated with the first net present value, and the factors of the maximum dispatchable resources of the power grid are positively correlated with the first net present value.

3. The method according to claim 1, characterized in that, The indicators include curtailment rate, levelized cost of electricity (LCOE), and net present value (NPV), with the NPV representing the project benefits of the photovoltaic power station.

4. The method according to claim 3, characterized in that, The levelized cost per kilowatt-hour is obtained by summing the initial investment cost and the operation and maintenance cost, and then quotienting the sum of the power generation. The second net present value is obtained by quotienting the difference between revenue and cost and the discount rate, and then summing the values ​​over time.

5. The method according to claim 4, characterized in that, The spatial hotspots are used to provide regional references for component adjustment, and the temporal hotspots are used to provide time-period references for component adjustment; In response to the indicator value not meeting the preset standard, the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station are adjusted in conjunction with the spatial hotspots and temporal hotspots, including: In response to the levelized cost of electricity (LCOE) exceeding a cost threshold, the module tilt angle is increased, the module cleaning cycle is extended, and / or the module row spacing is appropriately compressed in low-shading areas; and / or in response to the curtailment rate exceeding a curtailment rate threshold, the module row spacing in high-curtailment-risk areas is increased, the module row spacing in low-curtailment-risk areas is decreased, and / or buffer energy storage is configured; wherein the buffer energy storage is used for storing electricity when the grid's capacity is insufficient, and for transmitting electricity to the grid when the photovoltaic power plant's capacity is insufficient; and / or in response to the fluctuation range of the second net present value exceeding an amplitude threshold, priority is given to selling electricity during periods of high electricity prices, and during periods of low electricity prices, the capacity is converted to self-use or energy storage, and / or revenue subsidies are obtained in response to grid frequency regulation requirements.

6. The method according to claim 1, characterized in that, The step of determining the spatial and temporal hotspots for the generation of curtailed electricity by the photovoltaic power station based on the target spatial layout parameters includes: Based on the historical irradiance curve data, component layout topology information, and grid curtailment command timestamps of the photovoltaic power station, a three-dimensional matrix containing component coordinates, time, and curtailment rate is constructed, and the curtailment amount and planned maintenance curtailment amount are calculated respectively. The target spatial layout parameters, the three-dimensional matrix, the amount of curtailed solar power, and the amount of planned maintenance curtailment are input into a machine learning algorithm, and curtailment feature analysis is performed based on the machine learning algorithm to output the spatial hotspots and temporal hotspots of curtailment generated by the photovoltaic power station. The amount of power curtailment is obtained by taking the derivative of the difference between the grid curtailment target power and the actual output power of the inverter, based on the non-grid curtailment period. The planned curtailment of solar power is obtained by differentiating the theoretical power generation and the actual output power of the inverter, and then taking the derivative based on the off-grid curtailment period. The amount of curtailed solar power is calculated in the following way: Curtailment of solar power = ; Where [t0, t1] represents the non-grid power curtailment period; AGC is the grid power curtailment target power; This represents the actual output power of the inverter. The planned curtailment of solar power during maintenance is calculated using the following method: Planned maintenance waste of light = ; in, Ideal power generation with no loss; [t0, t1] represents the actual output power of the inverter; [t0, t1] represents the off-grid power curtailment period.

7. The method according to claim 1, characterized in that, The current spatial layout parameters of the photovoltaic power station are obtained in the following way: Acquire solar resource data from photovoltaic power plants and preprocess it to obtain preprocessed solar resource data; Based on the preprocessed light resource data, a three-dimensional shadow model of the photovoltaic power station is performed to obtain the three-dimensional shadow model of the photovoltaic power station. The photovoltaic power station is subjected to shadow occlusion analysis using the three-dimensional shadow model. Based on the results of the shadow occlusion analysis, the initial spatial layout parameters of the photovoltaic power station are optimized to obtain the current spatial layout parameters of the photovoltaic power station.

8. A photovoltaic power plant optimization device integrating component layout and electricity price response, characterized in that, The photovoltaic power plant optimization method for integrated module layout and electricity price response according to any one of claims 1-7, wherein the photovoltaic power plant optimization device for integrated module layout and electricity price response comprises: The collaborative optimization module is used to apply a collaborative optimization model, combined with real-time electricity price data and grid dispatch instructions, to adjust the current spatial layout parameters of the photovoltaic power station, so as to adjust the current spatial layout parameters to the target spatial layout parameters that maximize the first net present value; wherein, the first net present value represents the production efficiency of the photovoltaic power station, and the collaborative optimization model is defined as the mathematical relationship between the first net present value, the real-time electricity price data, the maximum dispatchable resources of the grid, and the spatial layout parameters, and the maximum dispatchable resources of the grid are obtained based on the grid dispatch instructions; The hotspot identification and evaluation module is used to determine the spatial and temporal hotspots that generate curtailed electricity from the photovoltaic power station based on the target spatial layout parameters, and to calculate the index values ​​used for the full life-cycle economic evaluation of the photovoltaic power station. The parameter adjustment module is used to adjust the spatial layout parameters and / or power dispatch strategy of the photovoltaic power station in response to the indicator value not meeting the preset standard, in combination with the spatial hotspot and temporal hotspot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the method described in any one of claims 1-7.

Images