Distribution network distributed photovoltaic collaborative optimization investment decision-making method and system

Abstract

The invention discloses a distributed photovoltaic collaborative optimization investment decision-making method and system for a power distribution network, and the method comprises the steps: predicting power utilization modes and power utilization demands in a target investment region at a plurality of times, and generating a power utilization demand analysis result of the target investment region; calculating the installation cost of each photovoltaic planning layout configuration scheme, and generating layout cost evaluation data of each photovoltaic planning layout configuration scheme; predicting the power generation capacity of each photovoltaic planning layout configuration scheme, evaluating the influence of photovoltaic power generation on a surrounding ecological system, and generating environmental influence evaluation information of each photovoltaic planning layout configuration scheme; and calculating the operation cost, evaluating the investment income and fund recovery cycle of each photovoltaic configuration scheme in combination with the electricity market price and the government subsidy information, and generating investment decision data of the target investment area. The method optimizes the operation and energy structure of a power grid, enables the planning of a photovoltaic system to meet the actual demands, guarantees the environmental sustainability of a project, provides all-around investment decision support for a decision maker, and enhances the economic and environmental benefits of the project.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart grids, and particularly relates to a method and system for collaborative optimization of investment decisions for distributed photovoltaic power generation in a distribution network. Background Art

[0002] Smart grids optimize the operation and management of power grids through information technology, communication technology, automation technology, and new energy management technology, enhancing the power grid's response ability to various energy demands. Through intelligent transformation of multiple links such as power generation, power transmission, power distribution, and power consumption, the automation and digitalization levels of the power grid are improved, the power grid investment decision-making technology for accessing multiple renewable energy sources such as wind energy and solar energy is optimized, the efficient utilization of energy and environmental sustainability are promoted, and the operation efficiency, reliability, and security of the power grid are enhanced.

[0003] Traditional power grid investment decision-making technologies lack pertinence and foresight in making investment decisions for distributed photovoltaic power generation projects, cannot accurately predict the power generation efficiency and cost-effectiveness at each location, and affect the economic feasibility assessment of projects; when considering environmental impacts, a general evaluation model is generally used, and the long-term impact of photovoltaic system construction on the ecosystem cannot be accurately analyzed, resulting in challenges from environmental protection regulations or social acceptance issues during project implementation; in terms of economic evaluation, the operation and maintenance costs and maintenance strategies cannot be comprehensively considered, and the cost-benefit analysis from project initiation to operation is lacking, restricting the power grid's ability to quickly adapt to and integrate emerging energy technologies and reducing the maximum benefit of energy utilization. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for collaborative optimization of investment decisions for distributed photovoltaic power generation in a distribution network in view of the above problems existing in the prior art.

[0005] To achieve the above objectives, the technical solutions of the present invention are as follows:

[0006] In the first aspect, the present invention proposes a method for collaborative optimization of investment decisions for distributed photovoltaic power generation in a distribution network, including:

[0007] S1. Collect the electricity consumption data set of the target investment area for time series analysis, and combine seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times within the target investment area, and generate the electricity consumption demand analysis result of the target investment area;

[0008] S2. Based on the electricity consumption demand analysis result of the target investment area, for each photovoltaic planning layout configuration plan of the target investment area, calculate the installation costs of the installation candidate positions of the photovoltaic devices for each photovoltaic planning layout configuration plan, and generate the layout cost evaluation data of each photovoltaic planning layout configuration plan;

[0009] S3. Based on the layout cost evaluation data of each photovoltaic planning layout configuration plan, predict the power generation capacity of each photovoltaic planning layout configuration plan, and based on the predicted power generation capacity, evaluate the impact of photovoltaic power generation on the surrounding ecosystem, and generate the environmental impact assessment information of each photovoltaic planning layout configuration plan;

[0010] S4. Based on the environmental impact assessment information of each photovoltaic planning layout configuration plan, calculate the operating cost of each photovoltaic planning layout configuration plan, and combined with the electricity market price and government subsidy information, evaluate the investment income and capital recovery period of each configuration plan, and generate the investment decision-making data of the target investment area.

[0011] The above S1 includes:

[0012] S11. Conduct time series analysis on the electricity consumption data set of the target investment area, and use the following formula to calculate the electricity consumption of the target investment area corresponding to the time period, and generate the electricity peak-valley period data:

[0013]

[0014] In the above formula, Y t is the electricity consumption at time t, C is the constant term, p is the order of the autoregressive term, φ i is the autoregressive coefficient, where i is the lag period of autoregression, Y t-i is the electricity consumption at time t-i, q is the order of the moving average term, θ j is the moving average coefficient, where j is the lag period of the moving average, ∈ t-i is the error term at time t-j, ∈ t is the error term at time t;

[0015] S12. Use the time series analysis technology of seasonal decomposition to process the electricity peak-valley period data of the target investment area, decompose the electricity peak-valley period data into seasonal, trend and random components through STL decomposition, and evaluate the trend and periodicity of the electricity consumption pattern in each season to generate seasonal demand change information data;

[0016] S13. Combining the seasonal demand change information data, predict the electricity demand of the target investment area through the following multivariate linear regression model, obtain the electricity demand prediction data, and generate the electricity demand analysis result of the target investment area. The electricity demand analysis result of the target investment area includes the electricity peak-valley period data of the target investment area, the seasonal demand change information data, and the electricity demand prediction data:

[0017] E = β0 + β a T + β b H + β c W + β d E′ + ∈;

[0018] In the above formula, E is the electricity demand in the target investment area, β0 is the intercept, β a , β b , β c , β d are all the regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is the binary variable of the working day, E′ is the binary variable of the special event, and ∈ is the error term.

[0019] The said S2 includes:

[0020] S21. Conduct a topographic feature analysis on the candidate positions for installing photovoltaic devices in each photovoltaic planning layout configuration plan, evaluate the slope and height of each candidate position for installing photovoltaic devices, and generate the topographic feature analysis data of each candidate position for installing photovoltaic devices;

[0021] S22. Based on the topographic feature analysis data of each candidate position for installing photovoltaic devices, collect the sunshine data of the corresponding terrain, and use the following formula to calculate the sunshine conditions of the candidate positions for installing photovoltaic devices, and generate the sunshine condition evaluation data:

[0022] S d =S a ×(sin(α)×cos(θ)+cos(α)×sin(θ)×cos(φ - φ s ));

[0023] In the above formula, S d is the sunshine condition, S a is the average sunshine intensity, α is the solar altitude angle of the candidate position for installing photovoltaic devices, θ is the slope of the candidate position for installing photovoltaic devices, φ is the azimuth angle of the candidate position for installing photovoltaic devices, and φ s is the azimuth angle of the sun;

[0024] S23. Based on the analysis results of the electricity demand in the target investment area, combined with the topographic features and sunshine conditions of the candidate positions for installing photovoltaic devices, use the following formula to evaluate the installation costs of photovoltaic devices at different candidate positions, and generate the layout cost evaluation data of each photovoltaic planning layout configuration plan. The layout cost evaluation data of each photovoltaic planning layout configuration plan includes the topographic feature analysis data, sunshine condition evaluation data, and installation cost data of the candidate positions for installing photovoltaic devices:

[0025] C = C land + C dev + C tech + λ(A + I + F);

[0026] In the above formula, C is the installation cost of photovoltaic devices at each candidate position, C landis the land acquisition cost, and the land area for installing sufficient photovoltaic panels is determined based on the predicted electricity demand data, C dev is the development cost, which is determined based on the terrain feature analysis data of the candidate locations for installing photovoltaic equipment, C tech is the technical implementation cost, including the installation and commissioning costs of photovoltaic panels and the construction cost of the system. λ is the weight coefficient used to adjust the impact of additional factors on the total cost. A is the accessibility score, I is the infrastructure support score, and F is the environmental sensitivity score.

[0027] The said S3 includes:

[0028] S31. Use the following formula to evaluate the expected power generation of each photovoltaic planning layout configuration plan under various weather conditions and generate a power generation prediction model:

[0029]

[0030]

[0031] In the above formula, P is the expected power generation of the photovoltaic planning layout configuration plan, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, is the incident angle between the photovoltaic panel and the sun, is the proportionality coefficient, which reflects the conversion relationship between the sunshine intensity and the radiation intensity per unit area under different regions and conditions, S d is the sunshine condition;

[0032] S32. Based on the power generation prediction model and the layout cost evaluation data of each photovoltaic planning layout configuration plan, evaluate the power generation efficiency of each photovoltaic planning layout configuration plan, and evaluate the economic benefits and feasibility of each photovoltaic planning layout configuration plan by comparing the installation cost and power generation efficiency of the photovoltaic equipment at each candidate location, and generate the power generation capacity prediction data of each photovoltaic planning layout configuration plan;

[0033] S33. Based on the power generation capacity prediction data of each photovoltaic planning layout configuration plan, combined with the ecological baseline data of biodiversity and water resources at each installation candidate location, use geographic information system to manage and analyze the ecological baseline data to form a comprehensive baseline environmental dataset, and use ecological simulation software to simulate the potential impact of photovoltaic power generation activities on the ecosystem of the target investment area according to the operating parameters of the photovoltaic equipment and the baseline data of the surrounding ecosystem, analyze the changes in biodiversity indicators and water resources, and generate the ecological impact prediction results of each photovoltaic planning layout configuration plan;

[0034] S34. Based on the ecological impact prediction results, combined with the standards of biodiversity conservation and water resource management, use an integrated environmental assessment model to evaluate the overall impact of each photovoltaic planning layout configuration plan on the surrounding ecosystem, generate the environmental impact assessment information of each photovoltaic planning layout configuration plan, and the environmental impact assessment information of each photovoltaic planning layout configuration plan includes the power generation prediction results and power generation capacity prediction data, as well as the ecological impact prediction results.

[0035] S4 includes:

[0036] S41. For each photovoltaic planning layout configuration plan, collect the equipment specifications and performance data of the required photovoltaic equipment, and based on the historical operation and maintenance records of each photovoltaic equipment and the fault database in the industry, analyze the correlation between the fault modes of each equipment and the equipment specifications through data mining technology, and generate a list of equipment performance and failure rates.

[0037] S42. According to the power generation prediction results and power generation capacity prediction data in the environmental impact assessment information, evaluate the impact of the geographical and climatic conditions of each photovoltaic planning layout configuration plan on the equipment performance, and combined with the list of equipment performance and failure rates, use the fault mode and effect analysis and system reliability model to predict the potential fault points and maintenance frequencies of the key components of the photovoltaic equipment. By simulating the operation of the photovoltaic equipment under various environmental conditions, obtain the maintenance activities and time intervals under each planning layout configuration plan, and generate the maintenance demand prediction data.

[0038] S43. Based on the maintenance demand prediction data, combined with the material cost, labor cost and expected maintenance frequency, conduct a composite operating cost analysis, and use the following formula to calculate the operating cost of each photovoltaic planning layout configuration plan, and generate the operating cost prediction data:

[0039]

[0040] In the above formula, C y is the operating cost of the photovoltaic planning layout configuration plan, k is the number of types of photovoltaic equipment, n g is the quantity of the gth type of equipment, c mg is the material cost of the gth type of equipment, c lg is the labor cost of the gth type of equipment, f g is the maintenance frequency of the gth type of equipment;

[0041] S44. Obtain the real-time selling price of the electricity market and the subsidy policy information of the government, combined with the environmental impact assessment information and the operating cost prediction data of each photovoltaic planning layout configuration plan, and use the revenue assessment module in the financial analysis software to conduct revenue prediction on different photovoltaic layout configuration plans, and generate the power generation revenue and subsidy data of each photovoltaic planning layout configuration plan.

[0042] S45. Based on the power generation revenue and subsidy data of each photovoltaic planning layout configuration plan, use the following formula to calculate the investment return of each photovoltaic planning layout configuration plan, and generate the investment return analysis data of each photovoltaic planning layout configuration plan;

[0043]

[0044] In the above formula, R is the investment return of the photovoltaic planning layout configuration plan, and P t is the expected power generation of the photovoltaic planning layout configuration plan at time t, and G t is the electricity price at time t, and S t is the government subsidy ratio at time t, and C t is the total cost at time t, and r is the discount rate;

[0045] S46. Based on the investment return analysis data of each photovoltaic planning layout configuration plan, use the following formula to calculate the payback period of multiple layout planning configuration plans, compare the investment recovery time and investment return of each photovoltaic planning layout configuration plan, and combine the ecological impact prediction results in the environmental impact assessment information to generate the investment decision data of the target investment area:

[0046]

[0047] In the above formula, Y is the payback period of the photovoltaic planning layout configuration plan, and C init is the initial investment cost, x is the layout scale coefficient, and C setup is the installation and commissioning cost of photovoltaic equipment per unit scale, R is the investment return of the photovoltaic planning layout configuration plan, and C y is the operating cost of the photovoltaic planning layout configuration plan, M is the annual maintenance cost per unit scale, and T is the annual tax per unit scale.

[0048] In the second aspect, the present invention proposes a distribution network distributed photovoltaic collaborative optimization investment decision system, including an electricity demand analysis result generation module, a layout cost evaluation data generation module, an environmental impact assessment information generation module, and an investment decision data generation module;

[0049] The electricity demand analysis result generation module is used to collect the electricity consumption data set of the target investment area for time series analysis, and combine the seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times in the target investment area, and generate the electricity demand analysis result of the target investment area;

[0050] The layout cost evaluation data generation module is used to calculate the installation costs of the candidate installation locations of photovoltaic devices for each photovoltaic planning layout configuration plan in the target investment area based on the electricity demand analysis results of the target investment area, and generate the layout cost evaluation data for each photovoltaic planning layout configuration plan;

[0051] The environmental impact assessment information generation module is used to predict the power generation capacity of each photovoltaic planning layout configuration plan according to the layout cost evaluation data of each photovoltaic planning layout configuration plan, and evaluate the impact of photovoltaic power generation on the surrounding ecosystem based on the predicted power generation capacity, and generate the environmental impact assessment information for each photovoltaic planning layout configuration plan;

[0052] The investment decision data generation module is used to calculate the operating costs of each photovoltaic planning layout configuration plan based on the environmental impact assessment information of each photovoltaic planning layout configuration plan, and combine the electricity market price and government subsidy information to evaluate the investment returns and capital recovery periods of each configuration plan, and generate the investment decision data for the target investment area.

[0053] The electricity demand analysis result generation module includes an electricity peak-valley period data generation unit, a seasonal demand change information data generation unit, and an electricity demand analysis result generation unit;

[0054] The electricity peak-valley period data generation unit is used to perform time series analysis on the electricity consumption dataset of the target investment area, and calculate the electricity consumption of the target investment area corresponding to the period by using the following formula to generate the electricity peak-valley period data:

[0055]

[0056] In the above formula, Y t is the electricity consumption at time t, c is the constant term, p is the order of the autoregressive term, φ i is the autoregressive coefficient, where i is the lag period of autoregression, Y t-i is the electricity consumption at time t-i, q is the order of the moving average term, θ j is the moving average coefficient, where j is the lag period of the moving average, ∈ t-j is the error term at time t-j, ∈ t is the error term at time t;

[0057] The seasonal demand change information data generation unit is used to process the electricity peak-valley period data of the target investment area by using the seasonal decomposition time series analysis technology, decompose the electricity peak-valley period data into seasonal, trend and random components through STL, evaluate the trends and periodicities of the electricity consumption patterns in each season, and generate the seasonal demand change information data;

[0058] The electricity demand analysis result generation unit is used to combine the seasonal demand change information data, predict the electricity demand of the target investment area through the following multivariate linear regression model, obtain the electricity demand prediction data, and generate the electricity demand analysis result of the target investment area. The electricity demand analysis result of the target investment area includes the electricity peak-valley period data, seasonal demand change information data, and electricity demand prediction data of the target investment area:

[0059] E = β0 + β a T + β b H + β c W + β d E′ + ∈;

[0060] In the above formula, E is the electricity demand of the target investment area, β0 is the intercept, β a , β b , β c , β d are all regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is the binary variable of weekdays, E′ is the binary variable of special events, and ∈ is the error term.

[0061] The layout cost evaluation data generation module includes a terrain feature analysis data generation unit, a sunshine condition evaluation data generation unit, and a layout cost evaluation data generation unit;

[0062] The terrain feature analysis data generation unit is used to perform terrain feature analysis on the candidate positions for installing photovoltaic devices in each photovoltaic planning layout configuration scheme, evaluate the slope and height of each candidate position for installing photovoltaic devices, and generate terrain feature analysis data for each candidate position for installing photovoltaic devices;

[0063] The sunshine condition evaluation data generation unit is used to collect the sunshine data of the corresponding terrain based on the terrain feature analysis data of each candidate position for installing photovoltaic devices, calculate the sunshine condition of the candidate position for installing photovoltaic devices using the following formula, and generate sunshine condition evaluation data:

[0064] S d = S a ×((sin(α) × cos(θ) + cos(α) × sin(θ) × cos(φ - φ s ));

[0065] In the above formula, S d is the sunshine condition, S a is the average sunshine intensity, α is the solar altitude angle of the candidate position for installing photovoltaic devices, θ is the slope of the candidate position for installing photovoltaic devices, φ is the azimuth angle of the candidate position for installing photovoltaic devices, and φ s is the azimuth angle of the sun;

[0066] The layout cost evaluation data generation unit is used to evaluate the installation costs of photovoltaic devices at different candidate locations based on the analysis results of electricity demand in the target investment area, combined with the terrain features and sunlight conditions of the candidate locations for installing photovoltaic devices, and generate layout cost evaluation data for each photovoltaic planning layout configuration plan. The layout cost evaluation data for each photovoltaic planning layout configuration plan includes terrain feature analysis data, sunlight condition evaluation data, and installation cost data of the candidate locations for installing photovoltaic devices:

[0067] C = C land + C dev + C tech + λ(A + I + F);

[0068] In the above formula, C is the installation cost of the photovoltaic device at each candidate location, C land is the land acquisition cost, and the land area for installing sufficient photovoltaic panels is determined according to the electricity demand prediction data. C dev is the development cost, which is determined according to the terrain feature analysis data of the candidate locations for installing photovoltaic devices. C tech is the technical implementation cost, including the installation and commissioning costs of photovoltaic panels and the construction cost of the system. λ is the weight coefficient used to adjust the impact of additional factors on the total cost. A is the accessibility score, I is the infrastructure support score, and F is the environmental sensitivity score.

[0069] The environmental impact assessment information generation module includes a power generation prediction model generation unit, a power generation capacity prediction data generation unit, an ecological impact prediction result generation unit, and an environmental impact assessment information generation unit;

[0070] The power generation prediction result generation unit is used to evaluate the expected power generation of each photovoltaic planning layout configuration plan under various weather conditions by using the following formula and generate a power generation prediction model:

[0071]

[0072]

[0073] In the above formula, P is the expected power generation of the photovoltaic planning layout configuration plan, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, is the incident angle between the photovoltaic panel and the sun, is the proportionality coefficient, which reflects the conversion relationship between the sunlight intensity and the radiation intensity per unit area under different regions and conditions. S d is the sunlight condition;

[0074] The power generation capacity prediction data generation unit is used to evaluate the power generation efficiency of each photovoltaic planning layout configuration plan based on the power generation prediction model and the layout cost evaluation data of each photovoltaic planning layout configuration plan, and evaluate the economic benefits and feasibility of each photovoltaic planning layout configuration plan by comparing the installation costs and power generation efficiencies of photovoltaic devices at each candidate location, so as to generate the power generation capacity prediction data of each photovoltaic planning layout configuration plan;

[0075] The ecological impact prediction result generation unit is used to, based on the power generation capacity prediction data of each photovoltaic planning layout configuration plan, combine the ecological baseline data of biodiversity and water resources at each installation candidate location, manage and analyze the ecological baseline data using a geographic information system to form a comprehensive baseline environmental data set, and simulate the potential impact of photovoltaic power generation activities on the ecosystem of the target investment area according to the operating parameters of the photovoltaic devices and the baseline data of the surrounding ecosystem using ecological simulation software, analyze the changes in biodiversity indicators and water resources, and generate the ecological impact prediction results of each photovoltaic planning layout configuration plan;

[0076] The environmental impact assessment information generation unit is used to, based on the ecological impact prediction results, combine the standards for biodiversity protection and water resource management, and use a comprehensive environmental assessment model to evaluate the overall impact of each photovoltaic planning layout configuration plan on the surrounding ecosystem, generate the environmental impact assessment information of each photovoltaic planning layout configuration plan, and the environmental impact assessment information of each photovoltaic planning layout configuration plan includes the power generation prediction results and power generation capacity prediction data, as well as the ecological impact prediction results.

[0077] The investment decision data generation module includes a device performance and failure rate list generation unit, a maintenance requirement prediction data generation unit, an operating cost prediction data generation unit, a power generation revenue and subsidy data generation unit, an investment revenue analysis data generation unit, and an investment decision data generation unit;

[0078] The device performance and failure rate list generation unit is used to, for each photovoltaic planning layout configuration plan, collect the device specifications and performance data of the required photovoltaic devices, analyze the correlation between the failure modes of each device and the device specifications based on the historical operation and maintenance records of each photovoltaic device and the failure database in the industry, and generate a device performance and failure rate list;

[0079] The maintenance requirement prediction data generation unit is used to evaluate the impact of the geographical and climatic conditions of each photovoltaic planning layout configuration scheme on the equipment performance according to the power generation prediction result and the power generation capacity prediction data in the environmental impact assessment information, and combine the equipment performance with the failure rate list. By using the failure mode and effect analysis and the system reliability model, the potential failure points and maintenance frequencies of the key components of the photovoltaic equipment are predicted. By simulating the operation of the photovoltaic equipment under various environmental conditions, the maintenance activities and time intervals under each planning layout configuration scheme are obtained, and the maintenance requirement prediction data is generated;

[0080] The operation cost prediction data generation unit is used to conduct a composite operation cost analysis based on the maintenance requirement prediction data, combined with the material cost, labor cost and expected maintenance frequency. The following formula is used to calculate the operation cost of each photovoltaic planning layout configuration scheme, and the operation cost prediction data is generated:

[0081]

[0082] In the above formula, C y is the operation cost of the photovoltaic planning layout configuration scheme, k is the number of types of photovoltaic equipment, and n g is the quantity of the g-th type of equipment, c mg is the material cost of the g-th type of equipment, c lg is the labor cost of the g-th type of equipment, and f g is the maintenance frequency of the g-th type of equipment;

[0083] The power generation revenue and subsidy data generation unit is used to obtain the real-time selling price of the power market and the subsidy policy information of the government, combine the environmental impact assessment information and the operation cost prediction data of each photovoltaic planning layout configuration scheme, and use the revenue assessment module in the financial analysis software to conduct revenue prediction on different photovoltaic layout configuration schemes, and generate the power generation revenue and subsidy data of each photovoltaic planning layout configuration scheme;

[0084] The investment return analysis data generation unit is used to calculate the investment return of each photovoltaic planning layout configuration scheme based on the power generation revenue and subsidy data of each photovoltaic planning layout configuration scheme by using the following formula, and generate the investment return analysis data of each photovoltaic planning layout configuration scheme;

[0085]

[0086] In the above formula, R is the investment return of the photovoltaic planning layout configuration scheme, and P t is the expected power generation of the photovoltaic planning layout configuration scheme at time t, G t is the power selling price at time t, S t is the government subsidy ratio at time t, C t is the total cost at time t, and r is the discount rate;

[0087] The investment decision data generation unit is used to calculate the payback period of multiple layout planning configuration schemes by using the following formula based on the investment income analysis data of each photovoltaic planning layout configuration scheme, compare the investment recovery time and investment income of each photovoltaic planning layout configuration scheme, and generate the investment decision data of the target investment area in combination with the ecological impact prediction results in the environmental impact assessment information:

[0088]

[0089] In the above formula, Y is the payback period of the photovoltaic planning layout configuration scheme, C init is the initial investment cost, x is the layout scale coefficient, C setup is the installation and commissioning cost of photovoltaic equipment per unit scale, R is the investment income of the photovoltaic planning layout configuration scheme, C y is the operation cost of the photovoltaic planning layout configuration scheme, M is the annual maintenance cost per unit scale, and T is the annual tax per unit scale.

[0090] Compared with the prior art, the beneficial effects of the present invention are:

[0091] The present invention provides a collaborative optimization investment decision-making method and system for distributed photovoltaic power in a distribution network. The method first collects the electricity consumption data set of the target investment area for time series analysis, and combines seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity demand at multiple times in the target investment area, generating the electricity demand analysis result of the target investment area. Then, based on the electricity demand analysis result of the target investment area, for each photovoltaic planning layout configuration plan of the target investment area, calculate the installation cost of the installation candidate positions of the photovoltaic equipment for each photovoltaic planning layout configuration plan, generating the layout cost evaluation data of each photovoltaic planning layout configuration plan. And according to the layout cost evaluation data of each photovoltaic planning layout configuration plan, predict the power generation capacity of each photovoltaic planning layout configuration plan, and based on the predicted power generation capacity, evaluate the impact of photovoltaic power generation on the surrounding ecosystem, generating the environmental impact evaluation information of each photovoltaic planning layout configuration plan. Finally, based on the environmental impact evaluation information of each photovoltaic planning layout configuration plan, calculate the operation cost of each photovoltaic planning layout configuration plan, and combine the electricity market price and government subsidy information to evaluate the investment return and capital recovery period of each configuration plan, generating the investment decision data of the target investment area. On the one hand, according to the electricity demand analysis result integrating seasonal changes and cyclic changes, the method provides accurate electricity demand prediction, making the planning of the photovoltaic system meet the actual demand, optimizing energy consumption and cost-effectiveness. On the other hand, the method conducts layout cost evaluation data for each photovoltaic planning layout configuration plan, considers the impact of photovoltaic power generation on the surrounding ecosystem, predicts the investment return and recovery period of each photovoltaic planning layout configuration plan in the target investment area, ensures the environmental sustainability of the project, optimizes the operation and energy structure of the power grid, reduces investment risks, improves the capital utilization efficiency, provides comprehensive investment decision support for decision-makers, and enhances the economic and environmental double benefits of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 It is the overall flowchart of the method described in the present invention.

[0093] Figure 2 It is the structure diagram of the system described in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0094] The present invention will be further described in detail below in conjunction with the detailed description of the embodiments and the drawings.

[0095] The present invention provides a method and system for collaborative optimization of investment decisions for distributed photovoltaics in a distribution network, which is used for the investment optimization of distributed photovoltaic power generation systems in a distribution network. The aim is to optimize the layout and operation of the photovoltaic system through data analysis and mathematical modeling, improve the investment efficiency and the economy of the power grid operation, assist decision-makers in making scientific investment decisions, ensure the economy and sustainability of photovoltaic power generation projects, optimize the energy structure of the power grid and improve the energy utilization efficiency, achieve the improvement of the distribution network and the effective access of renewable energy, and support the dual goals of environmental protection and energy economy.

[0096] Embodiment 1:

[0097] As Figure 1 shown, a method for collaborative optimization of investment decisions for distributed photovoltaics in a distribution network is carried out in the following steps in sequence:

[0098] 1. Collect the electricity consumption data set of the target investment area for time series analysis, and combine seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times in the target investment area, and generate the electricity consumption demand analysis result of the target investment area;

[0099] The electricity consumption demand analysis result of the target investment area includes the peak-valley period data of electricity consumption in the target investment area, the seasonal demand change information data, and the electricity consumption demand prediction data;

[0100] Based on the electricity consumption data set of the target investment area, perform time series analysis on the electricity consumption data set of the target investment area based on the autoregressive moving average model, and use the following formula to calculate the electricity consumption at the corresponding time period of the target investment area to generate the peak-valley period data of electricity consumption:

[0101]

[0102] In the above formula, Y t is the electricity consumption at time t, c is the constant term, p is the order of the autoregressive term, φ i is the autoregressive coefficient, where i is the lag period of autoregression, Y t-i is the electricity consumption at time t-i, q is the order of the moving average term, θ j is the moving average coefficient, where j is the lag period of the moving average, ∈ t-j is the error term at time t-j, ∈ t is the error term at time t; the calculation process is used to analyze the daily peak-valley of the power grid and generate the peak-valley period data of electricity consumption as the input for seasonal demand analysis;

[0103] Use time series analysis techniques with seasonal decomposition to process the data of peak and valley periods of electricity consumption in the target investment area. Decompose the time series into seasonal, trend, and random components through STL decomposition, and identify the changes in electricity demand of users in the four seasons of spring, summer, autumn, and winter. Specifically, by observing the periodic fluctuations of electricity demand in each season, identify the peaks and valleys of seasonal demand. For example, in summer, due to the increase in air conditioner usage, the electricity demand may rise significantly, while in winter, due to heating needs, the electricity demand may show different change patterns;

[0104] Consider external factors such as the average temperature, holiday effect, and weekday pattern in each season, including the impact of temperature changes on air conditioner or heating demand, higher electricity demand during holidays, and the differences in electricity consumption between weekdays and weekends. Conduct trend and periodic evaluations on the electricity consumption patterns in each season. By reconstructing the seasonal and trend components of the STL decomposition results, obtain the electricity consumption prediction for each season, including smoothing the seasonal components to remove short-term fluctuations and noise, retaining the long-term patterns of seasonal changes, and then correcting the trend components so that they can more accurately reflect the long-term change trends, such as the increasing or decreasing electricity demand year by year. Through the reconstructed seasonal and trend components, the electricity consumption demand prediction for each season can be obtained, improving the accuracy and practicality of the prediction. The reconstructed components will be used to generate information data on seasonal demand changes, helping to make more reasonable investment decisions and power resource allocations, ensuring the accuracy and practicality of the prediction, and generating information data on seasonal demand changes;

[0105] Combine the information data on seasonal demand changes and predict the electricity consumption demand in the target investment area through the following multiple linear regression model to obtain the electricity consumption demand prediction data and generate the electricity demand analysis results for the target investment area:

[0106] E = β0 + β a T + β b H + β c W + β d E′ + ∈;

[0107] In the above formula, E is the electricity consumption demand in the target investment area, β0 is the intercept, β a , β b , β c , β d are all regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is a binary variable for weekdays, W = 1 represents a weekday, E′ is a binary variable for special events, E′ = 1 represents a special event, and ∈ is the error term;

[0108] The electricity demand in the target investment area helps grid operators and policymakers understand electricity consumption patterns, predict electricity demand, provide scientific data support for grid operators and policymakers, optimize the allocation of power resources and enhance the load management efficiency of the grid. The generated electricity demand analysis results reflect the electricity demand and pattern changes in the target area.

[0109] 2. Based on the electricity demand analysis results of the target investment area, for each photovoltaic planning layout configuration plan in the target investment area, calculate the installation costs of the candidate installation locations of photovoltaic equipment for each photovoltaic planning layout configuration plan, and generate layout cost evaluation data for each photovoltaic planning layout configuration plan;

[0110] The layout cost evaluation data for each photovoltaic planning layout configuration plan includes terrain feature analysis data, sunshine condition evaluation data, and cost data of the candidate installation locations of photovoltaic equipment;

[0111] According to the electricity demand analysis results of the target investment area, extract the detailed information of each photovoltaic planning layout configuration plan, including the layout planning, installation cost, installed capacity, and expected power generation of multiple plans;

[0112] Conduct terrain feature analysis on the candidate installation locations of photovoltaic equipment in each layout planning configuration, collect digital elevation model data of the terrain, use geographic information system technology to evaluate the slope and height of each candidate installation location of photovoltaic equipment, and generate terrain feature analysis data of the candidate installation locations of photovoltaic equipment. Among them, the slope feature is evaluated by the slope of the terrain, that is, the maximum height change of each grid is divided by the corresponding horizontal distance, and the height feature is evaluated by analyzing the absolute height difference between the ground and the sea level; the generated terrain feature analysis data indicates the potential challenges and risks of installing photovoltaic equipment, describes the terrain conditions of each location, and identifies the areas that require additional engineering support, that is, the candidate installation locations of photovoltaic equipment that require terrain leveling and additional support structures, providing the necessary basic data for subsequent sunshine condition evaluation and cost calculation;

[0113] Based on the terrain feature analysis data of the candidate installation locations of photovoltaic equipment, collect the sunshine data of the corresponding terrain, and use the following formula to calculate the sunshine conditions of the candidate installation locations of photovoltaic equipment to generate sunshine condition evaluation data:

[0114] S d =S a ×(sin(α)×cos(θ)+cos(α)×sin(θ)×cos(φ - φ s ));

[0115] In the above formula, S d is the sunshine condition, S ais the average sunshine intensity, α is the solar altitude angle of the candidate location for installing photovoltaic equipment, θ is the slope of the candidate location for installing photovoltaic equipment, φ is the azimuth angle of the candidate location for installing photovoltaic equipment, and φ s is the azimuth angle of the sun;

[0116] Sunshine conditions are used to determine the suitability of the candidate locations for installing photovoltaic equipment, provide key data to support the decision-making of photovoltaic equipment installation, help evaluate the specific impact of sunshine conditions on photovoltaic efficiency, and optimize the photovoltaic layout;

[0117] Based on the analysis results of the electricity demand in the target investment area, combined with the topographic features and sunshine conditions of the candidate locations for installing photovoltaic equipment, the following formula is used to evaluate the installation costs of photovoltaic equipment at different candidate locations, and generate the layout cost evaluation data for each photovoltaic planning layout configuration plan:

[0118] C = C land + C dev + C tech + λ(A + I + F);

[0119] In the above formula, C is the installation cost of photovoltaic equipment at each candidate location, and C land is the land acquisition cost. The land area for installing sufficient photovoltaic panels is determined according to the electricity demand prediction data. C dev is the development cost, which is determined according to the topographic feature analysis data of the candidate location for installing photovoltaic equipment. The development cost involves the cost of transforming the land parcel into a suitable one for installing photovoltaic equipment, including the leveling of the terrain. For example, areas with larger slopes may require more engineering adjustments, increasing the development cost, as well as the construction of infrastructure, etc. C tech is the technology implementation cost, including the installation and commissioning costs of photovoltaic panels and the construction cost of the system, which depends on factors such as the geographical conditions of the installation location, the required equipment, the installation difficulty, labor costs, infrastructure, etc. The sunshine conditions at the installation location will affect the type and configuration of the required photovoltaic panels, and affect the difficulty and implementation cost of installation and commissioning. λ is the weight coefficient used to adjust the impact of additional factors on the total cost. A is the accessibility score, I is the infrastructure support score, and F is the environmental sensitivity score;

[0120] The installation costs of photovoltaic equipment at each candidate location provide a clear financial basis for each photovoltaic planning layout configuration plan, support the decision-making process and the feasibility of the project. The generated layout cost evaluation data provides a comprehensive cost analysis of each configuration plan, which is crucial for formulating the investment and construction strategies of photovoltaic projects, and ensures the economic benefits and sustainable development of project investment.

[0121] 3. Based on the layout cost assessment data of each photovoltaic planning layout configuration plan, predict the power generation capacity of each photovoltaic planning layout configuration plan, and evaluate the impact of photovoltaic power generation on the surrounding ecosystem according to the predicted power generation capacity, and generate the environmental impact assessment information of each photovoltaic planning layout configuration plan;

[0122] The environmental impact assessment information of the photovoltaic planning layout configuration plan includes the power generation prediction model, the power generation capacity prediction data, and the ecological impact prediction result;

[0123] Collect the weather information of the candidate locations for photovoltaic equipment installation from local meteorological stations and international climate databases, including climate variables such as temperature, rainfall, and wind speed, to ensure the accuracy and update of the data, and record the performance index parameters of various brands and models of photovoltaic panels, including the maximum power output, conversion efficiency, durability, etc. of the photovoltaic panels, to ensure that the performance analysis of each installation plan is based on the latest environmental and technical data, and optimize the overall design and performance of the photovoltaic system;

[0124] According to the terrain feature analysis data and sunshine condition assessment data in the layout cost assessment data of each photovoltaic planning layout configuration plan, combined with the weather information and the performance index parameters of various brands and models of photovoltaic panels, use the following formula to evaluate the expected power generation of each photovoltaic planning layout configuration plan under various weather conditions, and generate the power generation prediction model:

[0125]

[0126]

[0127] In the above formula, P is the expected power generation of the photovoltaic planning layout configuration plan, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, is the incident angle between the photovoltaic panel and the sun, is the proportionality coefficient, which reflects the conversion relationship between the sunshine intensity and the radiation intensity per unit area under different regions and conditions, S d is the sunshine condition; this prediction helps to evaluate the power generation capacity of each photovoltaic planning layout configuration plan under various weather conditions, determine the most suitable installation location, and maximize the source collection and power generation efficiency;

[0128] Based on the power generation prediction model and layout cost evaluation data, the source simulation software is used to simulate the power generation response under various weather conditions, and evaluate the power generation efficiency of each photovoltaic planning layout configuration scheme. Software such as PVsyst or SAM can very accurately evaluate the power generation efficiency of photovoltaic devices under different installation schemes. These software simulate the impact of various weather conditions, such as sunny, cloudy, rainy days, etc. on the power generation efficiency by inputting the technical specifications of the photovoltaic panels, such as area, efficiency, installation angle, and climate data of the installation location. Such simulations help us analyze the power generation potential and possible problems in different environmental conditions at each installation location, such as insufficient sunlight or maintenance difficulties. By comparing the installation costs and power generation efficiencies of photovoltaic devices at each candidate location, the economic benefits and feasibility of each photovoltaic planning layout configuration scheme are analyzed, providing quantitative power generation efficiency data for the installation design of photovoltaic devices, generating power generation capacity prediction data for each photovoltaic planning layout configuration scheme, providing a scientific basis for systematic configuration and investment decisions, and ensuring the optimization of the photovoltaic system design;

[0129] Collect ecological baseline data on biodiversity and water resources at multiple installation candidate locations, including vegetation types, animal populations, water body status, and quality indicators at the target location. Based on the power generation capacity prediction data and layout cost evaluation data of each photovoltaic planning layout configuration scheme, combined with the ecological baseline data on biodiversity and water resources of each photovoltaic planning layout configuration scheme, use the Geographic Information System (GIS) to manage and analyze the ecological baseline data. Through GIS technology, detailed spatial analysis of ecological baseline data such as surrounding biodiversity and water resources is carried out to identify key ecologically sensitive areas, forming a comprehensive baseline environmental dataset. The baseline environmental dataset records the ecological characteristics and historical change data of each location and is the basis for evaluating the potential environmental impact of photovoltaic projects, ensuring that the planning of any photovoltaic power generation project is based on an in-depth understanding and respect for the ecological environment. Using the comprehensive baseline environmental dataset, through ecological simulation software such as InVEST or ARIES, according to the operating parameters of photovoltaic devices and the baseline data of the surrounding ecosystem, simulate the potential impact of photovoltaic power generation activities on the ecosystem, such as ground cover, surface water flow, and biological habitats, analyze changes in biodiversity indicators and water resources, such as the reduction of vegetation-covered areas and the increase in water body evaporation rates, generate ecological impact prediction results for each photovoltaic planning layout configuration scheme, provide decision-making support for environmental protection measures, and ensure that the sustainable development of photovoltaic projects does not damage the local natural balance;

[0130] Based on the ecological impact prediction results, combined with the standards of biodiversity conservation and water resource management, considering the power generation efficiency and potential ecological risks under each configuration plan, such as the impacts on sensitive areas like water source areas and protected areas, a comprehensive environmental assessment model is used to evaluate the overall impact of each photovoltaic planning layout configuration plan on the ecosystem of the target investment area, such as ecological footprint analysis or ecological service value assessment, providing a quantitative method to analyze the environmental impacts of each installation location, ensuring that all proposed photovoltaic planning layout configuration plans meet the standards of biodiversity conservation and water resource management, forming a detailed environmental impact assessment report that details the changes in various environmental indicators and the overall impact on the surrounding ecosystem, generating environmental impact assessment information for each photovoltaic planning layout configuration plan, ensuring the environmental friendliness of the photovoltaic project layout decision-making, providing a scientific basis for decision-makers, optimizing the project layout, and reducing the negative impact on the ecosystem.

[0131] 4. Based on the environmental impact assessment information of each photovoltaic planning layout configuration plan, calculate the operating cost of each photovoltaic planning layout configuration plan, and combined with the electricity market price and government subsidy information, evaluate the investment return and capital recovery period of each configuration, generating investment decision-making data for the target investment area;

[0132] For multiple photovoltaic planning layout configuration plans, collect the equipment specifications and performance data of the required photovoltaic equipment, including parameters such as the maximum power, efficiency, expected life, and environmental adaptability of the equipment. Based on the historical operation and maintenance records of each photovoltaic equipment and the fault database in the industry, through data mining techniques, such as association rule learning, by analyzing the relationship between various specifications of the equipment, such as power, efficiency, and material type, and the frequency of faults, it is possible to identify that certain power levels or equipment with material characteristics may be more prone to overheating or short circuits; clustering analysis classifies equipment with similar fault patterns and specifications into the same category by clustering the specifications of the equipment, such as installation location, usage environment, technical parameters, and fault history data, identifying common fault types that occur in similar usage environments, and providing preventive maintenance strategies for equipment in the same category; regression analysis obtains multiple factors affecting the occurrence of faults through a multiple regression model, predicts the fault probability of equipment under specific specification conditions, and analyzes the correlation between the fault mode of each equipment and the equipment specifications.

[0133] Through these analyses, identify which specification parameters may lead to higher failure rates or specific types of faults, generating a performance and failure rate list for each equipment that details the performance standards and predicted failure rates of each equipment, providing a basis for subsequent maintenance strategies and fault prevention.

[0134] Based on the power generation prediction results and power generation capacity prediction data in the environmental impact assessment information, evaluate the geographical and climatic conditions of each photovoltaic planning layout configuration scheme, such as the impact of climate changes like temperature, humidity, wind speed, etc. on the performance of the equipment. For example, high temperature or high humidity may accelerate the aging of certain components. Combine the equipment performance with the failure rate list, and use Failure Mode and Effects Analysis (FMEA) to list in detail the possible failure modes, such as short circuits in photovoltaic panels or inverter failures. Consider the impact of environmental factors on the failure modes, including determining the potential causes of failures, the probability of failure occurrence, and the possible consequences to identify the risk priority numbers of failure modes in photovoltaic equipment. Use system reliability models, such as system dynamics models to simulate the equipment behavior by constructing a dynamic interaction system that includes equipment components and environmental factors, or Monte Carlo simulation to evaluate the response of the equipment under various climate conditions through random sampling techniques. Simulate the operation of photovoltaic equipment under various environmental conditions to obtain the maintenance activities and time intervals for each planning layout configuration scheme. These models help predict the potential failure points and maintenance frequencies of key components of photovoltaic equipment under actual operating conditions. Integrate the above analysis results to generate maintenance requirement prediction data, which will be used to formulate optimized maintenance plans and preventive failure strategies, reduce downtime, and lower maintenance costs;

[0135] Based on the maintenance requirement prediction data, conduct a composite operating cost analysis by combining material costs, labor costs, and expected maintenance frequencies. Use the following formula to calculate the operating costs of each photovoltaic planning layout configuration scheme and generate operating cost prediction data:

[0136]

[0137] In the above formula, C y is the operating cost of the planning layout configuration scheme, including periodic costs such as daily maintenance, material replacement, and labor. k is the number of types of photovoltaic equipment, n g is the quantity of the g-th type of equipment, c mg is the material cost of the g-th type of equipment, C lg is the labor cost of the g-th type of equipment, f g is the maintenance frequency of the g-th type of equipment;

[0138] Obtain the real-time selling price of the electricity market and the government's subsidy policy information through the market regulatory agency or the electricity trading platform. Estimate the power generation revenue by combining the real-time electricity selling price and the predicted power generation volume, which is automatically updated through the dynamic data acquisition module. Combine the environmental impact assessment information of the photovoltaic planning layout configuration plan to understand the potential environmental compliance costs faced by the project planning layout configuration. Provide the estimated costs for photovoltaic equipment maintenance, renewal, and daily operations through the operation cost prediction data. Then, use the revenue evaluation module in the financial analysis software to predict the revenue of different photovoltaic layout configuration plans based on the input revenue and cost data, including the revenue based on power generation and various subsidies available, and generate the power generation revenue and subsidy data for each planning layout configuration plan;

[0139] Based on the power generation revenue and subsidy data of each planning layout configuration plan, use the following formula to calculate the investment return of each planning layout configuration plan and generate the investment return analysis data for each planning layout configuration plan;

[0140]

[0141] In the above formula, R is the investment return of the photovoltaic planning layout configuration plan, which is a key indicator to measure the overall economic efficiency of the project and is used to evaluate the net benefit after adjusting the input and future revenue for the time value. P t is the expected power generation volume of the photovoltaic planning layout configuration plan at time t, which refers to the total power output of the photovoltaic equipment during that period. G t is the electricity selling price at time t, which reflects the selling price per kilowatt-hour of electric energy. S t is the government subsidy ratio at time t, which reflects the degree of financial support from the government for renewable energy power generation. C t is the total cost at time t, including the operation, maintenance, labor expenses, etc. of the photovoltaic equipment. r is the discount rate, which is used to adjust the present value of future cash flows and reflects the time value of funds; the investment return of the photovoltaic planning layout configuration plan means the economic performance of the project under the subsidy policy, cost, and electricity selling price;

[0142] Combined with the investment return analysis data of each planning layout configuration plan, use the following formula to calculate the payback period of the photovoltaic planning layout configuration plan, compare the investment recovery time and investment return of each photovoltaic planning layout configuration plan, and combine the ecological impact prediction results in the environmental impact assessment information to generate the investment decision data for the target investment area:

[0143]

[0144] In the above formula, Y is the payback period of the photovoltaic planning layout configuration plan. C init$C_0$ is the initial investment cost, including one-time costs such as land acquisition, equipment procurement, and installation and commissioning. $x$ is the layout scale factor. setup $C_1$ is the installation and commissioning cost of photovoltaic equipment per unit scale. $R$ is the investment return of the photovoltaic planning layout configuration plan. y $C_2$ is the operating cost of the photovoltaic planning layout configuration plan. $M$ is the annual maintenance cost per unit scale, and $T$ is the annual tax per unit scale.

[0145] By comparing the economic and ecological impacts of multiple configuration plans, investment decision support data for the target investment area is formed, providing a decision-making basis for the project management team, helping investors make more comprehensive and scientific investment decisions, optimizing capital allocation and investment returns, and ensuring the financial success and sustainability of the project.

[0146] Example 2:

[0147] As Figure 2 shown, a distribution network distributed photovoltaic collaborative optimization investment decision-making system includes an electricity demand analysis result generation module, a layout cost evaluation data generation module, an environmental impact evaluation information generation module, and an investment decision data generation module.

[0148] The electricity demand analysis result generation module is used to collect the electricity consumption data set of the target investment area for time series analysis, and combine seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times in the target investment area, and generate the electricity demand analysis result of the target investment area.

[0149] The layout cost evaluation data generation module is used to calculate the installation cost of the installation candidate locations of the photovoltaic equipment for each photovoltaic planning layout configuration plan in the target investment area based on the electricity demand analysis result of the target investment area, and generate the layout cost evaluation data of each photovoltaic planning layout configuration plan.

[0150] The environmental impact evaluation information generation module is used to predict the power generation capacity of each photovoltaic planning layout configuration plan according to the layout cost evaluation data of each photovoltaic planning layout configuration plan, and evaluate the impact of photovoltaic power generation on the surrounding ecosystem according to the predicted power generation capacity, and generate the environmental impact evaluation information of each photovoltaic planning layout configuration plan.

[0151] The investment decision data generation module is used to calculate the operating cost of each photovoltaic planning layout configuration plan based on the environmental impact evaluation information of each photovoltaic planning layout configuration plan, and combine the electricity market price and government subsidy information to evaluate the investment return and capital recovery period of each configuration plan, and generate the investment decision data of the target investment area.

[0152] The electricity demand analysis result generation module includes an electricity peak-valley period data generation unit, a seasonal demand change information data generation unit, and an electricity demand analysis result generation unit;

[0153] The electricity peak-valley period data generation unit is used to perform time series analysis on the electricity consumption dataset of the target investment area, calculate the electricity consumption of the target investment area corresponding to the period using the following formula, and generate electricity peak-valley period data:

[0154]

[0155] In the above formula, Y t is the electricity consumption at time t, c is the constant term, p is the order of the autoregressive term, φ i is the autoregressive coefficient, where i is the lag period of autoregression, Y t-i is the electricity consumption at time t-i, q is the order of the moving average term, θ j is the moving average coefficient, where j is the lag period of the moving average, ∈ t-j is the error term at time t-j, ∈ t is the error term at time t;

[0156] The seasonal demand change information data generation unit is used to process the electricity peak-valley period data of the target investment area using the seasonal decomposition time series analysis technique, decompose the electricity peak-valley period data into seasonal, trend, and random components through STL decomposition, evaluate the trends and periodicities of the electricity consumption patterns in each season, and generate seasonal demand change information data;

[0157] The electricity demand analysis result generation unit is used to combine the seasonal demand change information data, predict the electricity demand of the target investment area through the following multivariate linear regression model to obtain the electricity demand prediction data, and generate the electricity demand analysis result of the target investment area. The electricity demand analysis result of the target investment area includes the electricity peak-valley period data of the target investment area, the seasonal demand change information data, and the electricity demand prediction data:

[0158] E = β0 + β a T + β b H + β c W + β d E′ + ∈;

[0159] In the above formula, E is the electricity demand of the target investment area, β0 is the intercept, β a , β b , β c , β d are all regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is the binary variable of weekdays, E′ is the binary variable of special events, and ∈ is the error term.

[0160] The layout cost evaluation data generation module includes a terrain feature analysis data generation unit, a sunlight condition evaluation data generation unit, and a layout cost evaluation data generation unit;

[0161] The terrain feature analysis data generation unit is used to perform terrain feature analysis on the candidate positions for installing photovoltaic devices in each photovoltaic planning layout configuration scheme, evaluate the slope and height of each candidate position for installing photovoltaic devices, and generate terrain feature analysis data for each candidate position for installing photovoltaic devices;

[0162] The sunlight condition evaluation data generation unit is used to collect sunlight data of the corresponding terrain based on the terrain feature analysis data of each candidate position for installing photovoltaic devices, calculate the sunlight conditions of the candidate positions for installing photovoltaic devices using the following formula, and generate sunlight condition evaluation data:

[0163] S d =S a ×(sin(α)×cos(θ)+cos(α)×sin(θ)×cos(φ - φ s ));

[0164] In the above formula, S d is the sunlight condition, S a is the average sunlight intensity, α is the solar altitude angle of the candidate position for installing photovoltaic devices, θ is the slope of the candidate position for installing photovoltaic devices, φ is the azimuth angle of the candidate position for installing photovoltaic devices, and φ s is the azimuth angle of the sun;

[0165] The layout cost evaluation data generation unit is used to evaluate the installation costs of photovoltaic devices at different candidate positions based on the analysis result of the electricity demand in the target investment area, combined with the terrain features and sunlight conditions of the candidate positions for installing photovoltaic devices, using the following formula to generate layout cost evaluation data for each photovoltaic planning layout configuration scheme. The layout cost evaluation data for each photovoltaic planning layout configuration scheme includes terrain feature analysis data, sunlight condition evaluation data, and installation cost data of the candidate positions for installing photovoltaic devices:

[0166] C = C land + C dev + C tech + λ(A + I + F);

[0167] In the above formula, C is the installation cost of photovoltaic devices at each candidate position, C land is the land acquisition cost, and the land area for installing sufficient photovoltaic panels is determined according to the electricity demand prediction data. C dev is the development cost, which is determined according to the terrain feature analysis data of the candidate positions for installing photovoltaic devices. C techFor the technical implementation cost, including the installation and commissioning costs of photovoltaic panels and the construction cost of the system, λ is the weight coefficient used to adjust the impact of additional factors on the total cost, A is the accessibility score, I is the infrastructure support score, and F is the environmental sensitivity score.

[0168] The environmental impact assessment information generation module includes a power generation prediction model generation unit, a power generation capacity prediction data generation unit, an ecological impact prediction result generation unit, and an environmental impact assessment information generation unit;

[0169] The power generation prediction result generation unit is used to evaluate the expected power generation of each photovoltaic planning layout configuration scheme under various weather conditions by using the following formula and generate a power generation prediction model:

[0170]

[0171]

[0172] In the above formula, P is the expected power generation of the photovoltaic planning layout configuration scheme, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, is the incident angle between the photovoltaic panel and the sun, is the proportionality coefficient, which reflects the conversion relationship between the sunshine intensity and the radiation intensity per unit area under different regions and conditions, S d is the sunshine condition;

[0173] The power generation capacity prediction data generation unit is used to evaluate the power generation efficiency of each photovoltaic planning layout configuration scheme based on the power generation prediction model and the layout cost evaluation data of each photovoltaic planning layout configuration scheme, and evaluate the economic benefits and feasibility of each photovoltaic planning layout configuration scheme by comparing the installation cost and power generation efficiency of the photovoltaic equipment at each candidate location, and generate the power generation capacity prediction data of each photovoltaic planning layout configuration scheme;

[0174] The ecological impact prediction result generation unit is used to, based on the power generation capacity prediction data of each photovoltaic planning layout configuration scheme, combine the ecological baseline data of biodiversity and water resources at each installation candidate location, use a geographic information system to manage and analyze the ecological baseline data, form a comprehensive baseline environmental dataset, and simulate the potential impact of photovoltaic power generation activities on the ecosystem of the target investment area according to the operating parameters of the photovoltaic equipment and the baseline data of the surrounding ecosystem by using ecological simulation software, analyze the changes in biodiversity indicators and water resources, and generate the ecological impact prediction results of each photovoltaic planning layout configuration scheme;

[0175] The environmental impact assessment information generation unit is used to evaluate the overall impact of each photovoltaic planning layout configuration scheme on the surrounding ecosystem by using an integrated environmental assessment model based on the ecological impact prediction results, combined with the standards of biodiversity conservation and water resource management, and generate the environmental impact assessment information of each photovoltaic planning layout configuration scheme. The environmental impact assessment information of each photovoltaic planning layout configuration scheme includes the power generation prediction results, power generation capacity prediction data, and ecological impact prediction results.

[0176] The investment decision data generation module includes a device performance and failure rate list generation unit, a maintenance requirement prediction data generation unit, an operating cost prediction data generation unit, a power generation income and subsidy data generation unit, an investment income analysis data generation unit, and an investment decision data generation unit;

[0177] The device performance and failure rate list generation unit is used to collect the device specifications and performance data of the required photovoltaic devices for each photovoltaic planning layout configuration scheme, analyze the correlation between the failure modes of each device and the device specifications based on the historical operation and maintenance records of each photovoltaic device and the failure database in the industry, and generate a device performance and failure rate list;

[0178] The maintenance requirement prediction data generation unit is used to evaluate the impact of the geographical and climatic conditions of each photovoltaic planning layout configuration scheme on the device performance according to the power generation prediction results and power generation capacity prediction data in the environmental impact assessment information, and combine the device performance and failure rate list, and use failure mode and effect analysis and system reliability models to predict the potential failure points and maintenance frequencies of the key components of the photovoltaic devices, and obtain the maintenance activities and time intervals under each planning layout configuration scheme by simulating the operation of the photovoltaic devices under various environmental conditions, and generate maintenance requirement prediction data;

[0179] The operating cost prediction data generation unit is used to perform a composite operating cost analysis based on the maintenance requirement prediction data, combined with material costs, labor costs, and expected maintenance frequencies, and calculate the operating costs of each photovoltaic planning layout configuration scheme by using the following formula to generate operating cost prediction data:

[0180]

[0181] In the above formula, C y is the operating cost of the photovoltaic planning layout configuration scheme, k is the number of types of photovoltaic devices, n g is the quantity of the g-th type of device, c mg is the material cost of the g-th type of device, c lg is the labor cost of the g-th type of device, f g is the maintenance frequency of the g-th type of device;

[0182] The power generation revenue and subsidy data generation unit is used to obtain the real-time selling price in the power market and the subsidy policy information of the government, combine the environmental impact assessment information of each photovoltaic planning layout configuration plan and the operation cost prediction data, and use the revenue assessment module in the financial analysis software to predict the revenue of different photovoltaic layout configuration plans, and generate the power generation revenue and subsidy data of each photovoltaic planning layout configuration plan;

[0183] The investment income analysis data generation unit is used to calculate the investment income of each photovoltaic planning layout configuration plan based on the power generation income and subsidy data of each photovoltaic planning layout configuration plan, and generate the investment income analysis data of each photovoltaic planning layout configuration plan by using the following formula;

[0184]

[0185] In the above formula, R is the investment income of the photovoltaic planning layout configuration plan, and P t is the expected power generation of the photovoltaic planning layout configuration plan at time t, and G t is the power selling price at time t, and S t is the government subsidy ratio at time t, and C t is the total cost at time t, and r is the discount rate;

[0186] The investment decision data generation unit is used to calculate the capital recovery period of multiple layout planning configuration plans based on the investment income analysis data of each photovoltaic planning layout configuration plan, compare the investment recovery time and investment income of each photovoltaic planning layout configuration plan, and combine the ecological impact prediction results in the environmental impact assessment information to generate the investment decision data of the target investment area:

[0187]

[0188] In the above formula, Y is the investment recovery period of the photovoltaic planning layout configuration plan, and c init is the initial investment cost, x is the layout scale coefficient, and C setup is the installation and commissioning cost of photovoltaic equipment per unit scale, R is the investment income of the photovoltaic planning layout configuration plan, and C y is the operation cost of the photovoltaic planning layout configuration plan, M is the annual maintenance cost per unit scale, and T is the annual tax per unit scale.

Claims

1. A collaborative optimization investment decision-making method for distributed photovoltaic in a distribution network, characterized in that the method includes: S1. Collect the electricity consumption data set of the target investment area for time series analysis, and combine seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times in the target investment area, and generate the electricity demand analysis result of the target investment area; S2. Based on the electricity demand analysis result of the target investment area, for each photovoltaic planning layout configuration plan of the target investment area, calculate the installation cost of the installation candidate positions of the photovoltaic equipment for each photovoltaic planning layout configuration plan, and generate the layout cost evaluation data of each photovoltaic planning layout configuration plan; S3. According to the layout cost evaluation data of each photovoltaic planning layout configuration plan, predict the power generation capacity of each photovoltaic planning layout configuration plan, and evaluate the impact of photovoltaic power generation on the surrounding ecosystem according to the predicted power generation capacity, and generate the environmental impact evaluation information of each photovoltaic planning layout configuration plan; S4. Based on the environmental impact evaluation information of each photovoltaic planning layout configuration plan, calculate the operating cost of each photovoltaic planning layout configuration plan, and combine the electricity market price and government subsidy information to evaluate the investment income and capital recovery period of each configuration plan, and generate the investment decision data of the target investment area.

2. The collaborative optimization investment decision-making method for distributed photovoltaic in a distribution network according to claim 1, characterized in that the S1 includes: S11. Conduct time series analysis on the electricity consumption data set of the target investment area, and use the following formula to calculate the electricity consumption of the target investment area in the corresponding period, and generate the peak-valley electricity consumption period data: In the above formula, Y t is the electricity consumption at time t, c is the constant term, p is the order of the autoregressive term, φ i is the autoregressive coefficient, where i is the lag period of autoregression, Y t-i is the electricity consumption at time t - i, q is the order of the moving average term, θ j is the moving average coefficient, where j is the lag period of the moving average, ∈ t-i is the error term at time t - j, ∈ t is the error term at time t; S12. Use the seasonal decomposition time series analysis technique to process the peak-valley electricity consumption period data of the target investment area, decompose the peak-valley electricity consumption period data into seasonal, trend and random components through STL decomposition, and evaluate the trend and periodicity of the electricity consumption patterns in each season to generate seasonal demand change information data; S13. Combine the seasonal demand change information data, and predict the electricity consumption demand of the target investment area through the following multivariable linear regression model to obtain the electricity consumption demand prediction data, and generate the electricity demand analysis result of the target investment area. The electricity demand analysis result of the target investment area includes the peak-valley electricity consumption period data of the target investment area, the seasonal demand change information data, and the electricity consumption demand prediction data: E = β0 + β a T + β b H + β c W + β d E′ + ∈; In the above formula, E is the electricity demand in the target investment area, β0 is the intercept, β a , β b , β c , β d are all the regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is the binary variable of weekdays, E′ is the binary variable of special events, and ∈ is the error term.

3. The collaborative optimization investment decision-making method for distributed photovoltaic in a distribution network according to claim 1, characterized in that in the S2, for each photovoltaic planning layout configuration plan of the target investment area, the specific steps of calculating the installation cost of the installation candidate positions of the photovoltaic equipment for each photovoltaic planning layout configuration plan and generating the layout cost evaluation data of each photovoltaic planning layout configuration plan include: S21. Conduct terrain feature analysis on the installation candidate positions of the photovoltaic equipment in each photovoltaic planning layout configuration plan, evaluate the slope and height of each installation candidate position of the photovoltaic equipment, and generate the terrain feature analysis data of each installation candidate position of the photovoltaic equipment; S22. Based on the terrain feature analysis data of each candidate location for installing photovoltaic equipment, collect the sunshine data of the corresponding terrain, and use the following formula to calculate the sunshine conditions of the candidate locations for installing photovoltaic equipment, and generate sunshine condition evaluation data: S d = S a ×(sin(α)×cos(θ)+cos(α)×sin(θ)×cis(φ - φ s )); In the above formula, S d is the sunshine condition, S a is the average sunshine intensity, α is the solar altitude angle of the candidate location for installing the photovoltaic device, θ is the slope of the candidate location for installing the photovoltaic device, φ is the azimuth angle of the candidate location for installing the photovoltaic device, φ s is the azimuth angle of the sun; S23. Based on the analysis results of the electricity demand in the target investment area, combined with the terrain features and sunshine conditions of the candidate locations for installing photovoltaic equipment, use the following formula to evaluate the installation costs of photovoltaic equipment at different candidate locations, and generate layout cost evaluation data for each photovoltaic planning layout configuration plan. The layout cost evaluation data for each photovoltaic planning layout configuration plan includes terrain feature analysis data, sunshine condition evaluation data, and installation cost data of the candidate locations for installing photovoltaic equipment: C=C land +C dev +C tech +λ(A + I + F); In the above formula, C is the installation cost of the photovoltaic equipment at each candidate location, C land is the land acquisition cost, and the land area for installing sufficient photovoltaic panels is determined according to the electricity demand prediction data, C dev is the development cost, which is determined according to the terrain feature analysis data of the candidate locations for installing photovoltaic equipment, C tech is the technology implementation cost, including the installation and commissioning costs of photovoltaic panels and the construction cost of the system. λ is the weight coefficient used to adjust the impact of additional factors on the total cost, a is the accessibility score, i is the infrastructure support score, and F is the environmental sensitivity score.

4. The method for collaborative optimization investment decision of distributed photovoltaic in a distribution network according to claim 1, wherein in S3, according to the layout cost evaluation data of each photovoltaic planning layout configuration plan, predict the power generation capacity of each photovoltaic planning layout configuration plan, and according to the predicted power generation capacity, evaluate the impact of photovoltaic power generation on the surrounding ecosystem, and generate the specific steps of the environmental impact evaluation information of each photovoltaic planning layout configuration plan include: S31. Use the following formula to evaluate the expected power generation of each photovoltaic planning layout configuration plan under various weather conditions, and generate a power generation prediction model: P = B·D·η·COS(ζ); In the above formula, p is the expected power generation of the photovoltaic planning layout configuration scheme, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, ζ is the incident angle between the photovoltaic panel and the sun, is a proportionality coefficient that reflects the conversion relationship between the sunshine intensity and the radiation intensity per unit area under different regions and conditions, S d is the sunshine condition; S32. Based on the power generation prediction model and the layout cost evaluation data of each photovoltaic planning layout configuration plan, evaluate the power generation efficiency of each photovoltaic planning layout configuration plan, and by comparing the installation costs and power generation efficiencies of photovoltaic equipment at each candidate location, evaluate the economic benefits and feasibility of each photovoltaic planning layout configuration plan, and generate the power generation capacity prediction data of each photovoltaic planning layout configuration plan; S33. Based on the power generation capacity prediction data of each photovoltaic planning layout configuration plan, combined with the ecological baseline data of biodiversity and water resources at each installation candidate location, use a geographic information system to manage and analyze the ecological baseline data to form a comprehensive baseline environmental dataset, and use ecological simulation software according to the operating parameters of photovoltaic equipment and the baseline data of the surrounding ecosystem to simulate the potential impact of photovoltaic power generation activities on the ecosystem of the target investment area, analyze the changes in biodiversity indicators and water resources, and generate the ecological impact prediction results of each photovoltaic planning layout configuration plan; S34. Based on the ecological impact prediction results, combined with the standards of biodiversity protection and water resource management, use a comprehensive environmental assessment model to evaluate the overall impact of each photovoltaic planning layout configuration plan on the surrounding ecosystem, and generate the environmental impact evaluation information of each photovoltaic planning layout configuration plan. The environmental impact evaluation information of each photovoltaic planning layout configuration plan includes the power generation prediction results, the power generation capacity prediction data, and the ecological impact prediction results.

5. The method for collaborative optimization investment decision of distributed photovoltaic in a distribution network according to claim 1, wherein In S4, based on the environmental impact assessment information of each photovoltaic planning layout configuration plan, calculate the operating cost of each photovoltaic planning layout configuration plan, and combine the electricity market price and government subsidy information to evaluate the investment return and capital recovery period of each configuration plan. The specific steps are as follows: S41. For each photovoltaic planning layout configuration plan, collect the equipment specifications and performance data of the required photovoltaic equipment. Based on the historical operation and maintenance records of each photovoltaic equipment and the fault database in the industry, analyze the correlation between the fault modes of each equipment and the equipment specifications through data mining technology, and generate a list of equipment performance and failure rates; S42. According to the power generation prediction results and power generation capacity prediction data in the environmental impact assessment information, evaluate the impact of the geographical and climatic conditions of each photovoltaic planning layout configuration plan on the equipment performance. Combine the equipment performance and failure rate list, and use the fault mode and effect analysis and system reliability model to predict the potential fault points and maintenance frequencies of the key components of the photovoltaic equipment. By simulating the operation of the photovoltaic equipment under various environmental conditions, obtain the maintenance activities and time intervals under each planning layout configuration plan, and generate maintenance demand prediction data; S43. Based on the maintenance demand prediction data, combine the material cost, labor cost and expected maintenance frequency for composite operating cost analysis, and use the following formula to calculate the operating cost of each photovoltaic planning layout configuration plan, and generate operating cost prediction data: In the above formula, C y is the operating cost of the photovoltaic planning layout configuration scheme, k is the number of types of photovoltaic equipment, and n g is the quantity of the g-th type of equipment, c mg is the material cost of the g-th type of equipment, c lg is the labor cost of the g-th type of equipment, and f g is the maintenance frequency of the g-th type of equipment; S44. Obtain the real-time selling price of the electricity market and the government subsidy policy information. Combine the environmental impact assessment information and the operating cost prediction data of each photovoltaic planning layout configuration plan, and use the revenue assessment module in the financial analysis software to predict the revenue of different photovoltaic layout configuration plans, and generate the power generation revenue and subsidy data of each photovoltaic planning layout configuration plan; S45. Based on the power generation revenue and subsidy data of each photovoltaic planning layout configuration plan, use the following formula to calculate the investment return of each photovoltaic planning layout configuration plan, and generate the investment return analysis data of each photovoltaic planning layout configuration plan; In the above formula, R is the investment return of the photovoltaic planning layout configuration plan, and P t is the expected power generation of the photovoltaic planning layout configuration plan at time t, and G t is the electricity price at time t, and S t is the government subsidy ratio at time t, and C t is the total cost at time t, and r is the discount rate; S46. Based on the investment return analysis data of each photovoltaic planning layout configuration plan, use the following formula to calculate the capital recovery period of multiple layout planning configuration plans, compare the investment recovery time and investment return of each photovoltaic planning layout configuration plan, and combine the ecological impact prediction results in the environmental impact assessment information to generate the investment decision data of the target investment area: In the above formula, Y is the investment recovery period of the photovoltaic planning layout configuration scheme, C init is the initial investment cost, x is the layout scale coefficient, C setup is the installation and commissioning cost of photovoltaic equipment per unit scale, R is the investment income of the photovoltaic planning layout configuration scheme, C y is the operating cost of the photovoltaic planning layout configuration scheme, M is the annual maintenance cost per unit scale, and T is the annual tax per unit scale.

6. A distributed photovoltaic collaborative optimization investment decision system for a distribution network, characterized in that the system includes an electricity demand analysis result generation module, a layout cost assessment data generation module, an environmental impact assessment information generation module, and an investment decision data generation module; the electricity demand analysis result generation module is used to collect the electricity consumption data set of the target investment area for time series analysis, and combine the seasonal changes and cyclic changes to predict the electricity consumption patterns and electricity consumption demands at multiple times in the target investment area, and generate the electricity demand analysis result of the target investment area; The layout cost evaluation data generation module is used to calculate the installation costs of the candidate installation locations of photovoltaic devices for each photovoltaic planning layout configuration plan in the target investment area based on the electricity demand analysis results of the target investment area, and generate the layout cost evaluation data for each photovoltaic planning layout configuration plan; The environmental impact assessment information generation module is used to predict the power generation capacity of each photovoltaic planning layout configuration plan according to the layout cost evaluation data of each photovoltaic planning layout configuration plan, and evaluate the impact of photovoltaic power generation on the surrounding ecosystem according to the predicted power generation capacity, and generate the environmental impact assessment information for each photovoltaic planning layout configuration plan; The investment decision data generation module is used to calculate the operating costs of each photovoltaic planning layout configuration plan based on the environmental impact assessment information of each photovoltaic planning layout configuration plan, and evaluate the investment returns and capital recovery periods of each configuration plan in combination with the electricity market price and government subsidy information, and generate the investment decision data of the target investment area.

7. The distributed photovoltaic collaborative optimization investment decision-making method for a distribution network according to claim 6, characterized in that The electricity demand analysis result generation module includes an electricity peak-valley period data generation unit, a seasonal demand change information data generation unit, and an electricity demand analysis result generation unit; The electricity peak-valley period data generation unit is used to perform time series analysis on the electricity consumption data set of the target investment area, and calculate the electricity consumption of the target investment area in the corresponding period by using the following formula to generate the electricity peak-valley period data: In the above formula, Y t is the power consumption at time t, c is the constant term, p is the order of the autoregressive term, φ is the autoregressive coefficient, where i is the lag period of autoregression, and Y t-i is the power consumption at time t - i, q is the order of the moving average term, and θ j is the moving average coefficient, where j is the lag period of the moving average, and ∈ t-j is the error term at time t - j, and ∈ t is the error term at time t; The seasonal demand change information data generation unit is used to process the electricity peak-valley period data of the target investment area by using the seasonal decomposition time series analysis technology, decompose the electricity peak-valley period data into seasonal, trend and random components through STL, and evaluate the trends and periodicities of the electricity consumption patterns in each season to generate the seasonal demand change information data; The electricity demand analysis result generation unit is used to combine the seasonal demand change information data, and predict the electricity demand of the target investment area through the following multivariable linear regression model to obtain the predicted electricity demand data, and generate the electricity demand analysis result of the target investment area. The electricity demand analysis result of the target investment area includes the electricity peak-valley period data of the target investment area, the seasonal demand change information data, and the predicted electricity demand data: E = β0 + β a T + β b H + β c W + β d E′ + ∈; In the above formula, E is the electricity demand in the target investment area, β b is the intercept, β a , β b , β c , β d are all the regression coefficients of the corresponding independent variables, T is the temperature, H is the humidity, W is the binary variable of weekdays, E′ is the binary variable of special events, and ∈ is the error term.

8. The distributed photovoltaic collaborative optimization investment decision-making system for a distribution network according to claim 6, characterized in that The layout cost evaluation data generation module includes a terrain feature analysis data generation unit, a sunshine condition evaluation data generation unit, and a layout cost evaluation data generation unit; The terrain feature analysis data generation unit is used to perform terrain feature analysis on the candidate installation locations of photovoltaic devices in each photovoltaic planning layout configuration plan, evaluate the slopes and heights of each candidate installation location of photovoltaic devices, and generate the terrain feature analysis data of each candidate installation location of photovoltaic devices; The sunshine condition evaluation data generation unit is used to collect the sunshine data of the corresponding terrain based on the terrain feature analysis data of each candidate location for installing photovoltaic equipment, and calculate the sunshine conditions of the candidate locations for installing photovoltaic equipment by using the following formula to generate sunshine condition evaluation data: S d = S a ×(sin(α)×cos(θ)+cos(α)×sin(θ)×cos(φ - φ s )); In the above formula, S d is the sunshine condition, S a is the average sunshine intensity, α is the solar altitude angle of the candidate location for installing the photovoltaic device, θ is the slope of the candidate location for installing the photovoltaic device, φ is the azimuth angle of the candidate location for installing the photovoltaic device, φ s is the azimuth angle of the sun; The layout cost evaluation data generation unit is used to evaluate the installation costs of photovoltaic equipment at different candidate locations by using the following formula based on the electricity demand analysis results of the target investment area, combined with the terrain features and sunshine conditions of the candidate locations for installing photovoltaic equipment, and generate layout cost evaluation data for each photovoltaic planning layout configuration plan. The layout cost evaluation data for each photovoltaic planning layout configuration plan includes terrain feature analysis data, sunshine condition evaluation data, and installation cost data of the candidate locations for installing photovoltaic equipment: C=C land +C dev +C tech +λ(A + I + F); In the above formula, C is the installation cost of the photovoltaic equipment at each candidate location, C land is the land acquisition cost. The land area for installing sufficient photovoltaic panels is determined according to the electricity demand prediction data, C dev is the development cost, which is determined according to the terrain feature analysis data of the candidate locations for installing the photovoltaic equipment, C tech is the technology implementation cost, including the installation and commissioning costs of the photovoltaic panels and the construction cost of the system. λ is the weight coefficient used to adjust the impact of additional factors on the total cost. A is the accessibility score, I is the infrastructure support score, and F is the environmental sensitivity score.

9. The distributed photovoltaic collaborative optimization investment decision-making system for a distribution network according to claim 6, wherein The environmental impact assessment information generation module includes a power generation prediction model generation unit, a power generation capacity prediction data generation unit, an ecological impact prediction result generation unit, and an environmental impact assessment information generation unit; The power generation prediction result generation unit is used to evaluate the expected power generation of each photovoltaic planning layout configuration plan under various weather conditions by using the following formula to generate a power generation prediction model: P = B·D·η·cos(ζ); In the above formula, P is the expected power generation of the photovoltaic planning layout configuration scheme, B is the area of the photovoltaic panel, D is the solar radiation per unit area, η is the conversion efficiency of the photovoltaic panel, ζ is the incident angle between the photovoltaic panel and the sun, is a proportionality coefficient that reflects the conversion relationship between the sunshine intensity and the radiation intensity per unit area under different regions and conditions, S d is the sunshine condition; The power generation capacity prediction data generation unit is used to evaluate the power generation efficiency of each photovoltaic planning layout configuration plan based on the power generation prediction model and the layout cost evaluation data of each photovoltaic planning layout configuration plan, and evaluate the economic benefits and feasibility of each photovoltaic planning layout configuration plan by comparing the installation costs and power generation efficiencies of the photovoltaic equipment at each candidate location, and generate power generation capacity prediction data for each photovoltaic planning layout configuration plan; The ecological impact prediction result generation unit is used to manage and analyze the ecological baseline data by using a geographic information system based on the power generation capacity prediction data of each photovoltaic planning layout configuration plan, combined with the ecological baseline data of biodiversity and water resources at each installation candidate location, form a comprehensive baseline environmental data set, and simulate the potential impact of photovoltaic power generation activities on the ecological system of the target investment area according to the operating parameters of the photovoltaic equipment and the baseline data of the surrounding ecological system by using ecological simulation software, analyze the changes in biodiversity indicators and water resources, and generate ecological impact prediction results for each photovoltaic planning layout configuration plan; The environmental impact assessment information generation unit is used to evaluate the overall impact of each photovoltaic planning layout configuration plan on the surrounding ecological system by using a comprehensive environmental assessment model based on the ecological impact prediction results, combined with the standards for biodiversity protection and water resource management, and generate environmental impact assessment information for each photovoltaic planning layout configuration plan. The environmental impact assessment information for each photovoltaic planning layout configuration plan includes power generation prediction results, power generation capacity prediction data, and ecological impact prediction results.

10. The distributed photovoltaic collaborative optimization investment decision-making system for a distribution network according to claim 6, wherein The investment decision data generation module includes a device performance and failure rate list generation unit, a maintenance requirement prediction data generation unit, an operating cost prediction data generation unit, a power generation revenue and subsidy data generation unit, an investment return analysis data generation unit, and an investment decision data generation unit; The device performance and failure rate list generation unit is used to collect the device specifications and performance data of the required photovoltaic devices for each photovoltaic planning layout configuration scheme, analyze the correlation between the failure modes of each device and the device specifications based on the historical operation and maintenance records of each photovoltaic device and the failure database in the industry, and generate a device performance and failure rate list; The maintenance requirement prediction data generation unit is used to evaluate the impact of the geographical and climatic conditions of each photovoltaic planning layout configuration scheme on the device performance according to the power generation prediction result and power generation capacity prediction data in the environmental impact assessment information, and combine the device performance and failure rate list, and use failure mode and effect analysis and system reliability models to predict the potential failure points and maintenance frequencies of the key components of the photovoltaic devices. By simulating the operation of the photovoltaic devices under various environmental conditions, the maintenance activities and time intervals under each planning layout configuration scheme are obtained, and maintenance requirement prediction data is generated; The operating cost prediction data generation unit is used to conduct a composite operating cost analysis based on the maintenance requirement prediction data, combine the material cost, labor cost, and expected maintenance frequency, and calculate the operating costs of each photovoltaic planning layout configuration scheme using the following formula to generate operating cost prediction data: In the above formula, C y is the operating cost of the photovoltaic planning and layout configuration scheme, k is the number of types of photovoltaic equipment, and n g is the quantity of the g-th type of equipment, c mg is the material cost of the g-th type of equipment, c lg is the labor cost of the g-th type of equipment, and f g is the maintenance frequency of the g-th type of equipment; The power generation revenue and subsidy data generation unit is used to obtain the real-time selling price of the power market and the subsidy policy information of the government, combine the environmental impact assessment information of each photovoltaic planning layout configuration scheme and the operating cost prediction data, and use the revenue evaluation module in the financial analysis software to predict the revenue of different photovoltaic layout configuration schemes to generate the power generation revenue and subsidy data of each photovoltaic planning layout configuration scheme; The investment return analysis data generation unit is used to calculate the investment returns of each photovoltaic planning layout configuration scheme using the following formula based on the power generation revenue and subsidy data of each photovoltaic planning layout configuration scheme, and generate the investment return analysis data of each photovoltaic planning layout configuration scheme; In the above formula, R is the investment return of the photovoltaic planning layout configuration plan, and P t is the expected power generation of the photovoltaic planning layout configuration plan in period t, and G t is the electricity selling price in period t, and S t is the government subsidy ratio in period t, and C t is the total cost in period t, and r is the discount rate; The investment decision data generation unit is used to calculate the payback period of multiple layout planning configuration schemes using the following formula based on the investment return analysis data of each photovoltaic planning layout configuration scheme, compare the investment recovery time and investment returns of each photovoltaic planning layout configuration scheme, and combine the ecological impact prediction result in the environmental impact assessment information to generate the investment decision data of the target investment area: In the above formula, Y is the investment recovery period of the photovoltaic planning layout configuration scheme, C init is the initial investment cost, x is the layout scale coefficient, C setup is the installation and commissioning cost of photovoltaic equipment per unit scale, R is the investment income of the photovoltaic planning layout configuration scheme, C y is the operating cost of the photovoltaic planning layout configuration scheme, M is the annual maintenance cost per unit scale, and T is the annual tax per unit scale.

Images