Revenue prediction method and device of photovoltaic power station, production planning method and device, electronic equipment and medium

Abstract

The invention discloses an income prediction method and device of a photovoltaic power station, a production planning method and device, electronic equipment and a medium. The method comprises the steps of obtaining basic data, power transaction disclosure data, historical power settlement data and power policy data of the photovoltaic power station; creating an electricity price prediction model and a generating capacity prediction model based on the basic data, the electricity transaction disclosure data and the historical electricity settlement data; on the basis of an electricity price prediction model, predicting the electricity price of the target duration to obtain a predicted electricity price; based on a generating capacity prediction model, predicting the generating capacity of the target duration to obtain predicted generating capacity; predicting the operation cost of the target duration based on the power transaction disclosure data, the power policy data and the predicted power generation amount; and according to the predicted electricity price, the predicted generating capacity and the predicted operation cost, determining the income of the target time length. And the accuracy of photovoltaic power station income prediction is improved.

Description

Technical Field

[0001] The present invention belongs to the field of power generation technology, and specifically relates to a revenue prediction method, a production planning method, a device, an electronic device and a medium for a photovoltaic power station. Background Art

[0002] As an important form of clean energy generation, the revenue of photovoltaic power plants is influenced by a variety of factors. Forecasting power generation revenue not only helps decision-makers make more informed decisions and avoid investment risks caused by insufficient information, but also guides power plant operators in optimizing management strategies and improving operational efficiency.

[0003] However, traditional revenue estimation often relies on single on-grid electricity price data and economic evaluation models, which are difficult to adapt to the complexity and dynamics of the electricity market, resulting in inaccurate revenue forecast results. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to address the above-mentioned deficiencies in the prior art and provide a photovoltaic power station profit prediction method, production planning method, device, electronic equipment and medium. The method can be used to accurately predict the profit of a photovoltaic power station.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting revenue of a photovoltaic power station, the method comprising:

[0006] Obtaining basic data, power transaction disclosure data, historical power settlement data, and power policy data of the photovoltaic power station, wherein the basic data includes parameters associated with the photovoltaic power station infrastructure;

[0007] Based on an electricity price prediction model, predicting the electricity price for the target duration to obtain a predicted electricity price, wherein the electricity price prediction model is created based on the electricity transaction disclosure data and historical electricity settlement data;

[0008] Based on the power generation prediction model, predicting the power generation of the target duration to obtain predicted power generation, wherein the power generation prediction model is created based on the basic data;

[0009] Predicting operating expenses for a target duration based on the power transaction disclosure data, the power policy data, and the predicted power generation;

[0010] The profit of the target duration is determined according to the predicted electricity price, the predicted power generation and the predicted operating expenses.

[0011] Preferably, the method further comprises:

[0012] Performing data analysis on the disclosed power transaction data and the historical power settlement data to extract key power price data;

[0013] Creating the electricity price prediction model based on the key electricity price data;

[0014] Performing simulation modeling on the photovoltaic power station based on the basic data to obtain a simulation model of the photovoltaic power station;

[0015] generating a power generation curve of the photovoltaic power station using the simulation model;

[0016] A power generation prediction model of the photovoltaic power station is obtained according to the power generation curve.

[0017] Preferably, the data analysis of the power transaction disclosure data and the historical power settlement data to extract key electricity price data specifically includes:

[0018] Determining electricity price period division rules based on the disclosed electricity transaction data;

[0019] Determine the transaction volume and settlement fee corresponding to each electricity price period based on the electricity price period division rules and the historical electricity settlement data;

[0020] The average electricity price corresponding to each electricity price period is determined based on the transaction volume and settlement fees corresponding to each electricity price period. The key electricity price data includes the electricity price period division rules and the average electricity price corresponding to each electricity price period.

[0021] Preferably, the basic data includes at least: the center coordinates of the power station location, project capacity, component power, component type, inverter type, bracket type, arrangement form, front-to-back spacing, installation inclination, first-year and year-on-year attenuation rates.

[0022] Preferably, the operating expenses include market operation sharing expenses and double rules assessment expenses.

[0023] The operation cost of the target duration is predicted based on the power transaction disclosure data, the power policy data and the predicted power generation, specifically including:

[0024] Determine the average value of market operation sharing costs based on the disclosed power transaction data;

[0025] Based on the electricity policy data, determine the average value of the double-rule assessment fees;

[0026] The operating expenses for the target duration are determined based on the average value of the market operation sharing expenses, the average value of the double-rule assessment expenses and the predicted power generation.

[0027] Preferably, determining the benefit of the target duration based on the predicted electricity price, the predicted power generation and the predicted operating expenses specifically includes:

[0028] The target duration benefit is calculated using the following formulas (1) to (6):

[0029] Peak power generation revenue = P 尖峰 ×(Q 尖峰1 +Q 尖峰(时段2) +…+

[0030] Q 尖峰(时段i) (1)

[0031] Peak power generation revenue = P 峰 ×(Q 峰*时段1) +Q 峰(时段2) +…+

[0032] Q 峰(时段j) )(2)

[0033] Flat-term power generation income = P 平 ×(Q 平(时段1) +Q 平(时段2) +…+

[0034] Q 平(时段k) )(3)

[0035] Valley power generation income = P 谷 ×(Q 谷(时段1) +Q 谷(时段2) +…+

[0036] Q 谷(时段l) )(4)

[0037] Total electricity cost during target duration = Peak power generation income + Peak power generation income + Flat power generation income + Valley power generation income (5)

[0038] Target duration income = target duration total electricity cost - predicted operating cost (6)

[0039] Among them, the peak period, peak period, flat period and valley period are determined according to the electricity price period division rules in the electricity transaction disclosure data, P is the predicted electricity price, Q is the predicted power generation, i is the number of peak periods in the target time length, j is the number of peak periods in the target time length, k is the number of flat periods in the target time length, and l is the number of valley periods in the target time length.

[0040] In a second aspect, an embodiment of the present invention further provides a revenue prediction device for a photovoltaic power station, the device comprising:

[0041] an acquisition module, configured to acquire basic data of the photovoltaic power station, power transaction disclosure data, historical power settlement data, and power policy data, wherein the basic data includes parameters associated with the infrastructure of the photovoltaic power station;

[0042] a first prediction module, connected to the acquisition module, for predicting the electricity price for the target duration based on an electricity price prediction model to obtain a predicted electricity price, wherein the electricity price prediction model is created based on the electricity transaction disclosure data and historical electricity settlement data;

[0043] a second prediction module, connected to the acquisition module, for predicting the power generation of the target duration based on the power generation prediction model to obtain the predicted power generation, wherein the power generation prediction model is created based on the basic data;

[0044] a third prediction model, connected to the acquisition module, for predicting the operating expenses of the target duration based on the power transaction disclosure data, the power policy data and the predicted power generation;

[0045] A determination module is connected to the first prediction module, the second prediction module and the third prediction module respectively, and is used to determine the income of the target duration according to the predicted electricity price, the predicted power generation and the predicted operating expenses.

[0046] In a third aspect, an embodiment of the present application provides a production planning method for a photovoltaic power station, the method comprising:

[0047] According to the profit prediction method of the photovoltaic power station according to the first aspect, the profit of the photovoltaic power station for the target duration is predicted;

[0048] Based on the revenue of the target duration, a production plan of the photovoltaic power station within the target duration is planned.

[0049] In a fourth aspect, an embodiment of the present invention further provides a production planning device for a photovoltaic power station, the device comprising:

[0050] The profit prediction device of the photovoltaic power station according to the second aspect is used to predict the profit of the photovoltaic power station for the target duration;

[0051] A planning module is used to plan a production plan of the photovoltaic power station within the target time period based on the revenue of the target time period.

[0052] In a fifth aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0053] When the processor executes the computer program instructions, the above-mentioned photovoltaic power station profit prediction method is implemented.

[0054] In a sixth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the above-mentioned photovoltaic power station revenue prediction method is implemented.

[0055] The photovoltaic power station revenue forecasting method proposed in this application creates a more accurate electricity price and power generation forecasting model by acquiring and comprehensively utilizing basic data, electricity trading disclosure data, historical electricity settlement data, and electricity policy data. This model comprehensively considers multiple factors, including policy changes, electricity market complexity, resource conditions, and power station operating efficiency. This method overcomes the shortcomings of traditional methods that rely solely on single on-grid electricity price data and simple economic models, and avoids the problem of unreliable forecast results caused by ignoring key influencing factors. This improves the accuracy of photovoltaic power station revenue forecasts. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 : A flow chart of a method for predicting revenue of a photovoltaic power station provided in an embodiment of the present application;

[0057] Figure 2 : A schematic diagram of the steps for establishing a database for each province provided in an embodiment of the present application;

[0058] Figure 3 : A schematic diagram of a power station settlement form provided in an embodiment of the present application;

[0059] Figure 4 : This is a schematic diagram of a time-of-use electricity price average data provided in an embodiment of the present application;

[0060] Figure 5 A regional electricity price representation provided in an embodiment of this application is intended to show:

[0061] Figure 6 An example diagram of the market operation cost allocation table provided in the embodiment of the present application;

[0062] Figure 7 An example diagram of the wind and solar dual-rule assessment fee table provided for the embodiment of this application;

[0063] Figure 8 A schematic diagram of a station software modeling provided in an embodiment of the present application;

[0064] Figure 9 A schematic diagram of an hourly power generation database for a proposed power station provided in an embodiment of the present application;

[0065] Figure 10 A schematic diagram of the total power generation data of a power station for 25 years provided in an embodiment of the present application;

[0066] Figure 11 A schematic diagram of a photovoltaic power generation curve provided in an embodiment of the present application;

[0067] Figure 12 : A structural diagram of a revenue prediction device for a photovoltaic power station provided in an embodiment of the present application;

[0068] Figure 13 : A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0070] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0071] Example 1:

[0072] Based on the above research, in order to solve the existing technical problems, such as Figure 1 As shown, this embodiment provides a method for predicting revenue of a photovoltaic power station, which specifically includes the following steps S11 to S15.

[0073] S11, obtain basic data of photovoltaic power plants, power transaction disclosure data, historical power settlement data and power policy data.

[0074] Basic data includes parameters related to the infrastructure of photovoltaic power plants, which can be divided into the following categories:

[0075] Equipment parameters: including the type, specifications, power, conversion efficiency, and attenuation rate of the photovoltaic modules. Geographic information: the location of the power station, including altitude, latitude, longitude, tilt angle, and azimuth. Environmental conditions: local meteorological data, such as sunshine intensity, temperature, humidity, rainfall, and wind speed. Power station scale: installed capacity, land area, grid voltage level, etc., which are not limited in this application.

[0076] Power transaction disclosure data is a collection of data covering power transaction information that is publicly released by power market operators (such as power trading centers) to market participants and the public in accordance with relevant laws, regulations and policies.

[0077] The following types of information can be included:

[0078] Market transaction information: transaction prices and volumes in the electricity spot market and medium- and long-term markets. Bidding results: data on the results of power bidding and grid access bidding. Market supply and demand: overall power supply and demand balance, peak and valley load characteristics, etc. (not limited in this application).

[0079] Historical electricity settlement data may include: settlement electricity price: the on-grid electricity price actually settled by the power station, including fixed electricity price and market-based electricity price; power generation record: historical power generation data, including monthly, quarterly and annual data; cost details: historical operating expenses, maintenance expenses, taxes, subsidies, etc.

[0080] Power policy data can include: Policies and regulations: National and local laws, regulations, and policy documents related to photovoltaic power generation; Subsidy policies: Policy details such as feed-in tariff subsidies, per-kilowatt-hour subsidies, and tax incentives; Market regulation: Policy updates on the progress of power market reform, renewable energy quota systems, and green certificate trading. And so on.

[0081] The above-mentioned electricity transaction disclosure data, historical electricity settlement data and electricity policy data may be different for different regions or provinces. The profit forecasting method proposed in this application can predict the power generation revenue separately for different provinces or regions.

[0082] S12, based on the electricity price prediction model, predicting the electricity price of the target duration to obtain a predicted electricity price.

[0083] Among them, the electricity price forecast model is created based on electricity transaction disclosure data and historical electricity settlement data.

[0084] For the electricity price prediction model, we can use the collected historical electricity price data, electricity transaction data, etc., and select a suitable prediction model according to the characteristics of the data, such as time series models (ARIMA, SARIMA), machine learning models (support vector machine, random forest), deep learning models (LSTM, GRU), etc., and use historical data to train the model to obtain the electricity price prediction model; we can also analyze the data to extract data features and build a mathematical model to predict electricity prices.

[0085] Specifically, first, determine the forecast time range (i.e., the target duration, such as the next one, five, or twenty years), input factors that may affect electricity prices in the future into the model, such as the expected economic growth rate, policy adjustment expectations, energy structure changes, etc., and use the trained electricity price forecast model to generate electricity price forecast values for each future time period.

[0086] S13, predicting the power generation of the target duration based on the power generation prediction model to obtain the predicted power generation.

[0087] For the power generation prediction model, the historical power generation data, meteorological data, equipment operation data, etc. in the collected basic data can be used to predict power generation using physical modeling (such as photovoltaic power formula), statistical model or machine learning model.

[0088] Specifically, it can be to obtain or predict meteorological condition data for future periods, including sunshine, temperature, etc., input future meteorological data, equipment performance parameters, etc. into the power generation prediction model, and calculate the expected power generation in each future period through the model.

[0089] S14, based on electricity trading disclosure data, electricity policy data and predicted power generation, predicts the operating expenses for the target duration.

[0090] Among them, operating expenses can be estimated by using electricity trading disclosure data to estimate the relevant costs of participating in electricity market transactions, such as transaction service fees and settlement fees; referring to electricity policy data, considering the impact of policy changes on costs, such as new tax policies and additional costs caused by environmental protection requirements; and then combining the predicted power generation to determine some costs related to power generation, such as equipment wear and tear, consumables usage, etc.

[0091] S15, determining the profit of the target duration based on the predicted electricity price, the predicted power generation and the predicted operating expenses.

[0092] Finally, the expected revenue for the period is calculated by combining the obtained predicted electricity price, predicted power generation and predicted operating expenses.

[0093] For example: Revenue = (forecasted electricity price × forecasted power generation) - forecasted operating expenses.

[0094] This example, by acquiring and comprehensively utilizing basic data, electricity trading disclosure data, historical electricity settlement data, and electricity policy data, creates a more accurate electricity price and power generation forecast model. This model comprehensively considers multiple factors, including policy changes, electricity market complexity, resource conditions, and power plant operating efficiency. This model overcomes the shortcomings of traditional methods that rely solely on single on-grid electricity price data and simple economic models, and avoids the unreliable forecast results caused by ignoring key influencing factors. This improves the accuracy of photovoltaic power plant revenue forecasts.

[0095] Optionally, the above-mentioned photovoltaic power station revenue prediction method may further include the following steps:

[0096] Conduct data analysis on power transaction disclosure data and historical power settlement data to extract key electricity price data;

[0097] Create electricity price prediction models based on key electricity price data;

[0098] Conduct simulation modeling of the photovoltaic power station based on basic data to obtain a simulation model of the photovoltaic power station;

[0099] Use the simulation model to generate the power generation curve of the photovoltaic power station;

[0100] According to the power generation curve, the power generation prediction model of the photovoltaic power station is obtained.

[0101] Specifically, for the electricity price prediction model:

[0102] The first step is to collect publicly disclosed electricity price data from the power trading market and the power plant's own historical settlement data. By conducting detailed statistical analysis and data mining on this data, key factors influencing electricity prices can be extracted. For example, these factors may involve market supply and demand, seasonal fluctuations, policy adjustments, and differences in peak and valley electricity prices. Common methods include time series analysis, regression analysis, and correlation analysis to identify patterns and trends in electricity price fluctuations. The second step is to construct an electricity price forecasting model using methods such as time series models (such as ARIMA and SARIMA models, which capture the time dependence and seasonality of electricity prices), machine learning algorithms (such as support vector machines (SVM), artificial neural networks (ANN), and random forests, which use historical data to train models to predict future electricity prices), and regression analysis (which establishes a mathematical relationship between electricity prices and influencing factors and creates an electricity price forecasting model based on key electricity price data).

[0103] For the power generation prediction model, in the first step, the basic data may include the geographical location of the photovoltaic power station, installation parameters (such as inclination and azimuth), equipment parameters (such as component type, inverter efficiency), meteorological data (such as solar radiation and temperature), etc. Use these basic data to establish a physical simulation model of the power station. Commonly used simulation software includes PVsyst, HOMER, etc., which can simulate the performance and output of the power station under different conditions. The second step is to run the simulation model, input different meteorological conditions and operating parameters, and generate the power generation curve of the power station within a specific time range. The power generation curve can reflect the output power of the power station over time, and reflect the power fluctuations under the influence of daytime, seasonality and weather; the third step is to use the obtained power generation curve to integrate and perform statistical analysis to establish a power generation prediction model.

[0104] In this example, by integrating market electricity price information, historical transaction data, and the power plant's own basic parameters, accurate electricity price and power generation forecasting models were established. This fully considers market dynamics, equipment performance, and environmental impacts, making revenue forecasts more accurate and reliable.

[0105] Optionally, the above data analysis is performed on the power transaction disclosure data and historical power settlement data to extract key electricity price data, including:

[0106] Determine the electricity price period division rules based on the disclosed data of electricity transactions;

[0107] Determine the transaction volume and settlement fees corresponding to each electricity price period based on the electricity price period division rules and historical electricity settlement data;

[0108] Based on the transaction volume and settlement fees corresponding to each electricity price period, the average electricity price corresponding to each electricity price period is determined. The key electricity price data include the electricity price period division rules and the average electricity price corresponding to each electricity price period.

[0109] Specifically, the system first collects and analyzes electricity price information disclosed by the power trading market, determines the rules for dividing electricity prices into different time periods, and then divides the day into several time periods based on the patterns of electricity price fluctuations, such as peak, flat, and off-peak periods. Longer-term divisions may also be made based on seasonal variations. After determining the time period division rules, the system utilizes the power plant's historical electricity settlement data to categorize the transaction volume and settlement fees in the historical settlement data according to the electricity price period. The system then determines the total transaction volume and corresponding settlement fees within each preset electricity price period. The system then calculates the average electricity price for each price period, and combines the average electricity price for each period with the time period division rules to form a complete key electricity price dataset. This key data provides the basic input for the electricity price forecasting model, enabling the model to accurately reflect the changing characteristics of electricity prices over different time periods.

[0110] In this embodiment, through systematic analysis of power transaction disclosure data and historical power settlement data, key data such as the electricity price period division rules and the average electricity price in each period can be accurately extracted. This provides high-quality input data for the electricity price prediction model, significantly improving the accuracy of electricity price prediction.

[0111] Optionally, the above basic data includes at least: the center coordinates of the power station location, project capacity, component power, component type, inverter type, bracket type, arrangement form, front-to-back spacing, installation inclination, first-year and year-on-year attenuation rate.

[0112] The center coordinates of the power station determine the local solar energy resources, including sunshine intensity, sunshine hours, and meteorological conditions. Accurate solar radiation data and meteorological data can be obtained through the center coordinates of the power station.

[0113] Project capacity refers to the total installed capacity of a photovoltaic power station, usually measured in kilowatts (kW) or megawatts (MW). It determines the scale and potential power generation capacity of the power station and is the basic parameter for calculating total power generation and revenue.

[0114] Module power, the rated output power of a single photovoltaic module, usually expressed in watts (W) or peak watts (Wp);

[0115] The technology type of PV modules, such as monocrystalline silicon, polycrystalline silicon, and thin film, has different conversion efficiencies, temperature coefficients, and attenuation characteristics, which affect power generation and long-term performance.

[0116] Inverters convert the direct current (DC) generated by photovoltaic panels into alternating current (AC). Types include centralized, string, and microinverters. Different inverter types vary in efficiency, lifespan, and maximum power point tracking (MPPT) capabilities, impacting overall system efficiency and reliability.

[0117] Bracket type, arrangement, front-to-back spacing, and installation inclination: Bracket types include fixed brackets, adjustable brackets, or tracking brackets. Different types affect power generation efficiency and cost. The arrangement affects land utilization, shading between components, and ventilation conditions. Too small a spacing may cause components to block each other, reducing power generation efficiency. Too large a spacing will increase land costs. The installation inclination affects the efficiency of photovoltaic modules in receiving solar radiation.

[0118] First-year degradation rate: The percentage of performance degradation of a component in the first year. The performance of a new component decreases during the initial operation phase and needs to be taken into account in the power generation forecast.

[0119] Year-on-year degradation rate: The percentage of component performance degradation in subsequent years affects the long-term power generation capacity and profit expectations of the power station and needs to be evaluated throughout the entire life cycle.

[0120] In this example, a refined simulation model was constructed by comprehensively collecting and analyzing basic data of the photovoltaic power station, including geographical location, equipment parameters, and performance degradation. This detailed basic data ensures that the model's input parameters are accurate and reliable, making the prediction of the power station's power generation performance and revenue more accurate.

[0121] Optionally, the above operating expenses include market operation sharing expenses and double rules assessment expenses,

[0122] Based on electricity trading disclosure data, electricity policy data, and predicted power generation, the operating expenses for the target duration are predicted, including:

[0123] Determine the average value of market operation sharing costs based on electricity trading disclosure data;

[0124] Based on electricity policy data, determine the average cost of double-rule assessment;

[0125] The operating expenses for the target duration are determined based on the average market operating cost sharing, the average double-rule assessment cost and the predicted power generation.

[0126] Market operating expenses refer to the various costs incurred during electricity market operations, which are shared among market participants according to specific rules. These expenses may include market management fees, system operation fees, and dispatch fees. The publicly released power trading data by power trading centers or regulatory agencies typically includes the market operating expenses previously borne by each market participant.

[0127] Specifically, the specific amounts of market operating expenses allocated over a historical period can be extracted from disclosed data. Historical data can then be statistically analyzed to calculate the average value of these expenses. This calculation should take into account the time span, seasonal variations, and possible outliers of these expenses. Based on known market trends or regulatory policy changes, the average value can be adjusted to more accurately reflect future expense levels.

[0128] Dual-rule assessment fees typically refer to the detailed rules governing and assessing the grid-connected operations and ancillary services of power generation companies within the power system. These fees cover aspects such as power deviation, power quality, and frequency and peak regulation. Collect the latest power policy data, including the specific assessment standards, billing methods, and penalty measures for the dual-rule assessments. These policies are issued by government departments or power grid companies.

[0129] Specifically, the content of the "double detailed rules" should be interpreted to clarify the composition and calculation method of the assessment fee. If historical assessment fee data is available, past fees should be compiled (this can be obtained from settlement data) and the average calculated. Based on the operating characteristics and predicted power generation of the power plant, the potential future assessment fees should be simulated. For example, the deviation assessment fee should be calculated using the predicted power generation and the possible deviation rate. The average value of the "double detailed rules" assessment fee should be determined by combining historical data and simulation results.

[0130] Finally, the average value of the market operation sharing costs and the average value of the double rules assessment costs are added together to obtain the total average operating cost corresponding to the unit power generation.

[0131] In this example, through in-depth analysis of electricity trading disclosures and electricity policy data, we accurately extracted the average values of market operating expenses and dual-rule assessment fees. Combining this key cost data with projected power generation, we accurately predicted operating expenses for the target period. This approach makes operating expense estimates more reliable and precise.

[0132] Optionally, the above S16 specifically includes:

[0133] The target duration benefit is calculated using the following formulas (1) to (6):

[0134] Peak power generation revenue = P 尖峰 ×(Q 尖峰1 +Q 尖峰(时段2) +…+

[0135] Q 尖峰(时段i) (1)

[0136] Peak power generation revenue = P 峰 ×(Q 峰(时段1) +Q 峰(时段2) +…+

[0137] Q 峰(时段j) )(2)

[0138] Flat-term power generation income = P 平 ×(Q 平(时段1) +Q 平(时段2) +…+

[0139] Q 平(时段k) )(3)

[0140] Valley power generation income = P 谷 ×(Q 谷(时段1) +Q 谷(时段2) +…+

[0141] Q 谷(时段l) )(4)

[0142] Total electricity cost during target duration = Peak power generation income + Peak power generation income + Flat power generation income + Valley power generation income (5)

[0143] Target duration income = target duration total electricity cost - predicted operating cost (6)

[0144] Among them, the peak section, peak section, flat section and valley section are determined according to the electricity price period division rules in the electricity trading disclosure data. P is the predicted electricity price, Q is the predicted power generation, i is the number of peak sections in the target time, j is the number of peak sections in the target time, k is the number of flat sections in the target time, and l is the number of valley sections in the target time.

[0145] In this embodiment, the above formula comprehensively utilizes the predicted electricity price, predicted power generation, and predicted operating expenses to accurately calculate the revenue of the photovoltaic power station within the target duration. This comprehensive consideration of time-varying electricity price differences, the time-varying distribution of power generation, and operating costs ensures the accuracy and reliability of the revenue forecast.

[0146] In an example, assuming the target duration is one month in the future (30 days), the electricity price period division rules are as follows (based on the disclosed data of electricity trading):

[0147] Peak hours: 10:00-12:00 every day, a total of 2 hours; Peak hours: 8:00-10:00 and 14:00-16:00 every day, a total of 4 hours; Normal hours: 6:00-8:00 and 16:00-18:00 every day, a total of 4 hours; Off-peak hours: 0:00-6:00 and 18:00-24:00 every day, a total of 12 hours.

[0148] The predicted electricity price is: P 尖峰 =1.2 yuan / kWh; P 峰 =1.0 yuan / kWh; P 平 =0.8 yuan / kWh; P 谷 =0.5 yuan / kWh.

[0149] Forecasted power generation (based on the power generation prediction model): Average power generation at each time period of the day (since the photovoltaic power station does not generate electricity at night, the power generation during the off-peak period is 0):

[0150] Peak period (2 hours): 200 kWh / day; Peak period (4 hours): 300 kWh / day; Normal period (4 hours): 150 kWh / day; Valley period (12 hours): 0 kWh / day.

[0151] Estimated operating expenses for target duration: 2,400 yuan.

[0152] Based on the above assumptions, by substituting the parameters into the above formulas (1) to (6), it can be calculated that the target duration benefit is 17,400 yuan.

[0153] To facilitate understanding of the revenue prediction method for a photovoltaic power station provided in this embodiment, a practical application description of the revenue prediction method for a photovoltaic power station is provided herein.

[0154] The specific steps for verifying PV revenue under multi-provincial electricity spot trading are as follows:

[0155] S1: Create a basic data table for each province (see Figure 2 ).

[0156] S101. Data collection: First, obtain information through official channels (such as provincial and municipal development and reform commissions, State Grid / Southern Grid, and power trading centers), including: collecting original documents and information on time-of-use electricity price policies, power trading rules, power trading disclosure data, irradiation data, photovoltaic power station operation data, etc. from multiple provincial government websites, power trading centers, optical resource platforms, and photovoltaic power station operation platforms.

[0157] Specifically, it includes the following categories of data:

[0158] A. Basic data of power station:

[0159] Data such as the center coordinates of the proposed site location, project capacity / MW, module power / Wp, module type, inverter, bracket type, arrangement form, bracket front and rear spacing / m, installation inclination / °, first-year attenuation and year-on-year attenuation (%), etc.

[0160] B. Transaction data:

[0161] Electricity trading disclosure data.

[0162] C. Power station operation data.

[0163] D. Policy documents: Detailed implementation details of electricity pricing policies and power trading in various provinces. Examples include the "Notice of the Hebei Provincial Development and Reform Commission on Further Clarifying the Scope of Implementation of the Time-of-Use Electricity Pricing Mechanism in Our Province" and the "Implementation Plan for Medium- and Long-Term Power Trading in the Xinjiang Uyghur Autonomous Region in 2024."

[0164] S102. Separation of key data.

[0165] 1. Data collation of the collected transaction data and policy documents from various provinces to obtain information on time period division, price mechanism, direct electricity trading in the new energy market, transaction settlement, ancillary service market settlement, and settlement of the "two detailed rules"

[0166] The collected policy documents were interpreted in detail, and the key factors affecting the benefits of photovoltaic power generation projects were extracted from the grid overview, power generation and consumption load, power supply and demand balance forecast, direct power trading in the new energy market, and transaction settlement, such as time-of-use electricity price period division, peak-valley electricity price differences, ancillary services and two detailed rules.

[0167] 2. Extract the key factors that affect the revenue of photovoltaic power generation projects: including the time-sharing electricity price period division; the monthly time-sharing electricity price in the most recent full year: including the average peak transaction price (yuan / MWh), the average peak transaction price (yuan / MWh), the average flat transaction price (yuan / MWh), and the average valley transaction price (yuan / MWh); the market operation settlement price or proportion and the double-term settlement price or proportion, etc.

[0168] For example, the time-of-use electricity price in northern Hebei is divided into peak and valley periods: Summer (June, July, and August each year): Valley: 00-07:00, 23-24:00; Flat: 7:00-10:00, 12-16:00, 22-23:00; Peak: 10:00-12:00, 16-17:00, 20-22:00; Peak: 17-20:00. Winter (November, December, and January each year): Valley: 01-07:00, 12-14:00; Flat: 00-01:00, 7:00-8:00, 10-12:00, 14-16:00, 22-24:00; Peak: 8:00-10:00, 16-17:00, 19-22:00; Peak: 17-19:00. In other seasons (February, March, April, May, September and October every year), low hours: 1-7 am, 12-14 pm; flat hours: 0-1 am, 7-8 am, 10-12 pm, 2-16 pm, 10-22 pm; peak hours: 8-10 am, 4-16 pm.

[0169] For example, monthly time-of-use electricity prices: According to the "January 2024 Hebei North Power Market Monthly Information Disclosure Report (Summary)": The average settlement price in January was 419.36 yuan / MWh. The average settlement price during peak hours was 861.82 yuan / MWh; the average settlement price during peak hours was 712.17 yuan / MWh; the average settlement price during normal hours was 418.37 yuan / MWh; and the average settlement price during off-peak hours was 112.00 yuan / MWh. This provides a complete annual monthly time-of-use electricity price data table. For example, from July 2022 to June 2024, the average market operating cost per kilowatt-hour for new energy in the Shanxi market was approximately 2.3 cents. Since 2022, the average double-detailed assessment fee has been 2.3 yuan / MWh.

[0170] (3) Obtaining power station settlement data

[0171] Data access: Establish a data interface with photovoltaic power stations participating in electricity trading and regularly obtain their monthly settlement statements.

[0172] Data analysis: Statistical analysis is conducted on key indicators such as power generation, electricity sales, and electricity revenue in the settlement statement to identify the main factors affecting price changes, such as weather conditions, equipment efficiency, and market supply and demand conditions.

[0173] Feature extraction:

[0174] Based on the analysis results, characteristic items that have a significant impact on the revenue of photovoltaic power generation are extracted, including electricity trading, market operating expenses, ancillary service transaction fees, and two detailed fees. The positive and negative values affecting the revenue are evaluated to provide a basis for subsequent model optimization.

[0175] For example: Figure 3 As shown in the figure, the settlement statement of a power station in a certain province actually trades electricity, allocates market operation expenses and allocates double detailed expenses in the statement, which is used for subsequent verification with the forecast results. This data can also be used to measure the power stations that have been built around the power station.

[0176] S2: Establish key databases for each province

[0177] S201. The key electricity price database includes: the most recent complete month-by-month data on peak electricity volume (100 million kWh), peak average transaction price (RMB / MWh), peak-period electricity volume (100 million kWh), peak average transaction price (RMB / MWh), flat-period electricity volume (100 million kWh), flat average transaction price (RMB / MWh), valley-period electricity volume (100 million kWh), valley average transaction price (RMB / MWh). Construct an electricity price database that includes on-grid electricity prices, time-of-use period divisions, monthly time-of-use electricity prices, and historical price trends. Simultaneously, use statistical analysis methods to analyze electricity price fluctuation patterns across different time dimensions. Organize the analyzed policy information into structured data, and establish a policy database for each province to facilitate subsequent query, call, and comparative analysis.

[0178] Specifically, it can include the following provincial databases:

[0179] A. Database of time periods for each province:

[0180] For example: the Hebei North time-of-use electricity price average price data table, Xinjiang time-of-use electricity price average price data table, etc., form a database for time division of each province, see for details. Figure 4 .

[0181] B. Monthly time-of-use electricity price database for each province:

[0182] For example: Hebei North Time-of-Use Electricity Price Data Table, Xinjiang Time-of-Use Electricity Price Data Table, etc., form the transaction electricity price database of each province. Figure 5 .

[0183] C. Database of market operation cost sharing and double detailed cost sharing prices in each province:

[0184] For example: Shanxi market operating cost per kWh allocation table, wind and solar dual detailed rules assessment cost table, please refer to Figure 6 and Figure 7 .

[0185] S3: Establish a photovoltaic power generation power curve library.

[0186] S301. Obtain the basic data for the power station collected in step S101 above, including the site location. The data monitoring points are selected at the latitude and longitude points with low, medium, and high irradiance values to ensure comprehensive and representative data coverage. Data such as the site center coordinates, project capacity (MW), module power (Wp), module type, inverter, bracket type, arrangement, bracket spacing (m), inclination (°), irradiance (kWh / ㎡), first-year and annual attenuation (%), and capacity-to-load ratio are collected for use in PV site power generation modeling.

[0187] S302, site power generation modeling: Use photovoltaic power generation system simulation software to calculate photovoltaic power generation in each time period. The frequency of exporting power generation data from the software or system is 1 hour, starting from 00:00 to 24:00:00 on typical days of each month from January to December, to form a power generation data table for each time period. Then, combine the surrounding historical power generation data to optimize the selection of data sources. Site software modeling is as follows Figure 8 shown.

[0188] The details are as follows:

[0189] 1. Create an hourly power generation database for photovoltaic stations.

[0190] Based on the basic data of the power station, including the center coordinates of the planned site, project capacity / MW, component power / Wp, component type, inverter, bracket type, arrangement form, front and rear spacing of the bracket / m, and installation inclination / °, professional software is used to model the power stations planned to be built in multiple provinces and export monthly time-sharing power generation data.

[0191] For example, the software exports the first year's monthly time-of-day power generation data table of a power station in Xinjiang, which contains 12 (months) * 24 (hours) matrix power generation data. According to this method, an hourly power generation database of power stations to be built in each province is established. For details, see Figure 9 .

[0192] 2. Create a database of power generation year by year and hour by hour.

[0193] Based on the power station attenuation data in the basic data of the power station, a table of hourly power generation data for the first year to the 25th year of the life cycle of the photovoltaic power station is established. For example, the total power generation data of a power station for 25 years is shown in the table below. Figure 10 .

[0194] S303: Build a power curve library.

[0195] The power generation data of each target area in each period is sorted into a photovoltaic power generation curve (such as Figure 11 ), and build a photovoltaic power curve library for each region to provide basic data for power generation forecasting and revenue calculation.

[0196] S4: Create a revenue forecasting model.

[0197] Establish a year-by-year calculation model for the life cycle of a photovoltaic power station (for example, the first to the 25th year), make monthly, daily, and hourly revenue forecasts for each year, and use different colors to distinguish between daily peak, peak, flat, and valley periods.

[0198] S401. Calculate income.

[0199] A year-by-year calculation model for the first to 25 years of a photovoltaic power station's life cycle is modeled. The year-by-year calculation model includes revenue calculation data blocks from 0:00 to 24:00 on typical days of each month from January to December, with different color blocks representing daily peak, valley and normal periods. Combined with the electricity price database and the photovoltaic power generation power curve library, the yearly and month-by-month time-based revenue is calculated.

[0200] 1. Calculate the total monthly cost of electricity trading income

[0201] The calculation formulas for electric energy trading income are as follows: Formula (1) to Formula (4):

[0202] Peak power generation revenue = P 尖峰 ×(Q 尖峰(时段1) +Q 尖峰(时段2) +…+Q 尖峰(时段i) (1)

[0203] Peak power generation revenue = P 峰 ×(Q 峰(时段1) +Q 峰(时段2) +…+Q 峰(时段j) ) (2)

[0204] Flat-term power generation income = P 平 ×(Q 平(时段1) +Q 平)时段2) +…+Q 平(时段k) ) (3)

[0205] Valley power generation income = P 谷 ×(Q 谷(时段1) +Q 谷(时段2) +…+Q 谷(时段l) ) (4)

[0206] Each time period is based on the policy document, and the total number of time periods i, j, k, and l is 24 hours. 尖峰、 Q 峰、 Q 平 , Q 谷 The predicted power generation (MWh) of the photovoltaic power station during peak, peak, flat and valley periods, P 尖峰 、P 峰 、P 平 、P 谷 The monthly average transaction price during peak, peak, flat and valley periods (yuan / MWh)

[0207] The formula for calculating the total monthly cost of electricity energy trading income is as follows (5):

[0208] The total monthly cost of electricity trading income = peak period power generation income + peak period power generation income + flat period power generation income + valley period power generation income (5).

[0209] 2. Calculate the market operation sharing expenses and the double rules sharing expenses.

[0210] Market operation sharing fee = average market operation sharing fee of power plant transaction electricity (yuan / kWh)

[0211] Double rules apportionment fee = average value of double rules assessment fee for power station transaction electricity (yuan / kWh)

[0212] For example: The average value of market operation sharing costs in Shanxi is about 0.023 yuan / kWh, and the average value of double-rule assessment costs is about 0.0023 yuan / kWh.

[0213] 3. Calculate the total monthly income.

[0214] The monthly electricity bill calculation formula is as follows (6):

[0215] Monthly electricity bill = electricity energy cost - market operation sharing cost - double detailed sharing cost (6)

[0216] 4. Calculate the annual power station revenue based on the monthly total revenue.

[0217] 5. Calculate the 25-year total revenue of power plants in each province based on the annual revenue of the power plants.

[0218] The calculation results are shown in Table 1 below.

[0219]

[0220] Table 1

[0221] S5: Display of measurement results: Display the measurement results in the form of intuitive charts, curves, combination charts, etc.

[0222] S6: Measurement verification and decision support: Compare and verify the measurement results with actual operating data, evaluate the reliability of the measurement, and provide decision support such as investment advice and operation optimization strategies.

[0223] The photovoltaic revenue prediction method under multi-provincial electricity spot trading provided in this embodiment has the following features: (1) Comprehensive consideration of multiple factors: The model comprehensively considers multiple factors such as policies of different provinces, trading rules of the electricity market, electricity price fluctuations, resource conditions, and photovoltaic power station operation data, thereby improving the comprehensiveness of verification. (2) Real-time update and adjustment: The database called by the model has monthly and hourly dynamic update and adjustment requirements to adapt to market changes and maintain high prediction precision. (3) Decision support: The model provides intuitive prediction results and decision support tools. Based on the establishment of the database, it evaluates the annual and time-based revenue of photovoltaic power generation projects, providing a basis and suggestions for investors and operators to optimize the operation and investment decisions of photovoltaic power stations.

[0224] Example 2:

[0225] like Figure 12As shown, this embodiment provides a photovoltaic power station revenue prediction device 1200 to implement the steps of the photovoltaic power station revenue prediction method provided in any of the above embodiments.

[0226] The photovoltaic power station revenue prediction device 1200 specifically includes:

[0227] Acquisition module 1201, for acquiring basic data of photovoltaic power plants, power transaction disclosure data, historical power settlement data and power policy data, where the basic data includes parameters associated with the photovoltaic power plant infrastructure;

[0228] The first prediction module 1202 is connected to the acquisition module and is used to predict the electricity price of the target duration based on the electricity price prediction model to obtain the predicted electricity price;

[0229] The second prediction module 1203 is connected to the acquisition module and is used to predict the power generation of the target duration based on the power generation prediction model to obtain the predicted power generation;

[0230] The third prediction model 1204 is connected to the acquisition module and is used to predict the operating expenses of the target time period based on the power transaction disclosure data, power policy data and predicted power generation;

[0231] The determination module 1205 is connected to the first prediction module, the second prediction module and the third prediction module respectively, and is used to determine the profit of the target duration according to the predicted electricity price, the predicted power generation and the predicted operating expenses.

[0232] Optionally, the creation module 1202 includes:

[0233] An extraction unit is used to analyze power transaction disclosure data and historical power settlement data to extract key electricity price data;

[0234] A first creation unit, connected to the extraction unit, is used to create an electricity price prediction model based on the key electricity price data;

[0235] The second creation unit is used to simulate and model the photovoltaic power station based on the basic data to obtain a simulation model of the photovoltaic power station;

[0236] a third creation unit, connected to the second creation unit, for generating a power generation curve of the photovoltaic power station using the simulation model;

[0237] The fourth creation unit is used to obtain a power generation prediction model of the photovoltaic power station according to the power generation curve.

[0238] Optionally, the extraction unit includes:

[0239] A first determining subunit is used to determine the electricity price period division rules based on the electricity transaction disclosure data;

[0240] The second determination subunit is used to determine the transaction volume and settlement fee corresponding to each electricity price period according to the electricity price period division rules and historical electricity settlement data;

[0241] The third determination subunit is used to determine the average electricity price corresponding to each electricity price period based on the transaction volume and settlement fees corresponding to each electricity price period. The key electricity price data includes the electricity price period division rules and the average electricity price corresponding to each electricity price period.

[0242] Example 3:

[0243] This embodiment provides a production planning method for a photovoltaic power station, including:

[0244] The profit prediction method of the photovoltaic power station provided by any one of the above embodiments is used to predict the profit of the photovoltaic power station for the target duration;

[0245] Based on the revenue of the target duration, the production plan of the photovoltaic power station within the target duration is planned.

[0246] Specifically, in PV power plant production planning, revenue forecasting methods are first used to assess the economic benefits of the PV plant over a specific target timeframe. By analyzing historical data and market trends, the aforementioned PV power plant revenue forecasting methods are used to obtain a revenue forecast for the target timeframe. Based on this revenue data, a production plan for the PV plant is then formulated. Production planning must consider the goal of maximizing revenue, rationally arranging power generation times and output. For example, during peak periods when revenue is higher, the PV plant can increase power generation, while during off-peak periods when revenue is lower, it can appropriately reduce power generation or perform maintenance. Dynamic adjustments can also be made based on factors such as market fluctuations, weather conditions, and electricity demand. Through real-time monitoring and data analysis, PV power plants can promptly adjust production plans to respond to changes in the external environment and ensure continuous optimization of revenue.

[0247] In this example, by combining revenue forecasting with production planning, the economic benefits of a photovoltaic power plant are comprehensively improved. Accurate revenue forecasting allows the photovoltaic power plant to optimize its power generation strategy within the target timeframe and flexibly adjust its production plan, thereby maximizing revenue and improving resource utilization efficiency.

[0248] Example 4:

[0249] This embodiment provides a production planning device for a photovoltaic power station, including:

[0250] The profit prediction device for a photovoltaic power station provided by any one of the above embodiments is used to predict the profit of the photovoltaic power station for a target duration;

[0251] The planning module is used to plan the production plan of the photovoltaic power station within the target time based on the profit of the target time.

[0252] Example 5:

[0253] Figure 13 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0254] The electronic device may include a processor 1301 and a memory 1302 storing computer program instructions.

[0255] Specifically, the processor 1301 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0256] Memory 1302 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 1302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1302 may include removable or non-removable (or fixed) media. Where appropriate, memory 1302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, memory 1302 is a non-volatile solid-state memory.

[0257] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure (the above-mentioned photovoltaic power plant revenue prediction method).

[0258] The processor 1301 implements any one of the scheduling methods in the above embodiments by reading and executing computer program instructions stored in the memory 1302 .

[0259] In one example, the electronic device may further include a communication interface 1303 and a bus 4013. Figure 13As shown, the processor 1301 , the memory 1302 , and the communication interface 1303 are connected via a bus 1310 and communicate with each other.

[0260] The communication interface 1303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0261] Bus 1310 includes hardware, software or both, and the components of online data flow metering equipment are coupled to each other. For example, and not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 1310 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0262] In addition, in conjunction with the scheduling method in the above embodiments, the present application embodiment may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the scheduling methods in the above embodiments is implemented.

[0263] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0264] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0265] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0266] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable scheduling device to produce a machine so that these instructions executed by the processor of the computer or other programmable scheduling device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0267] The above is only a specific implementation method of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with this technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application.

Claims

1. A method for predicting the revenue of a photovoltaic power station, characterized in that: The method comprises: Obtaining basic data, power transaction disclosure data, historical power settlement data, and power policy data of the photovoltaic power station, wherein the basic data includes parameters associated with the photovoltaic power station infrastructure; Based on an electricity price prediction model, predicting the electricity price for the target duration to obtain a predicted electricity price, wherein the electricity price prediction model is created based on the electricity transaction disclosure data and historical electricity settlement data; Based on the power generation prediction model, predicting the power generation of the target duration to obtain predicted power generation, wherein the power generation prediction model is created based on the basic data; Predicting operating expenses for a target duration based on the power transaction disclosure data, the power policy data, and the predicted power generation; The profit of the target duration is determined according to the predicted electricity price, the predicted power generation and the predicted operating expenses.

2. The method according to claim 1, characterized in that The method further comprises: Performing data analysis on the disclosed power transaction data and the historical power settlement data to extract key power price data; Creating the electricity price prediction model based on the key electricity price data; Performing simulation modeling on the photovoltaic power station based on the basic data to obtain a simulation model of the photovoltaic power station; generating a power generation curve of the photovoltaic power station using the simulation model; A power generation prediction model of the photovoltaic power station is obtained according to the power generation curve.

3. The method according to claim 2, characterized in that The data analysis of the power transaction disclosure data and the historical power settlement data to extract key power price data specifically includes: Determining electricity price period division rules based on the disclosed electricity transaction data; Determine the transaction volume and settlement fee corresponding to each electricity price period based on the electricity price period division rules and the historical electricity settlement data; The average electricity price corresponding to each electricity price period is determined based on the transaction volume and settlement fees corresponding to each electricity price period. The key electricity price data includes the electricity price period division rules and the average electricity price corresponding to each electricity price period.

4. The method according to claim 2, characterized in that The basic data includes at least: the center coordinates of the power station location, project capacity, component power, component type, inverter type, bracket type, arrangement form, front-to-back spacing, installation inclination, first-year and year-on-year attenuation rate.

5. The method according to claim 1, wherein The operating expenses include market operation sharing expenses and double rules assessment expenses. The operation cost of the target duration is predicted based on the power transaction disclosure data, the power policy data and the predicted power generation, specifically including: Determine the average value of market operation sharing costs based on the disclosed power transaction data; Based on the electricity policy data, determine the average value of the double-rule assessment fees; The operating expenses for the target duration are determined based on the average value of the market operation sharing expenses, the average value of the double-rule assessment expenses and the predicted power generation.

6. The method according to any one of claims 1 to 5, characterized in that The determining of the benefit of the target duration based on the predicted electricity price, the predicted power generation, and the predicted operating expenses specifically includes: The target duration benefit is calculated using the following formulas (1) to (6): Peak power generation revenue = P 尖峰 ×(Q 尖峰1 +Q 尖峰(时段2) +…+ Q 尖峰(时段i) (1) Peak power generation revenue = P 峰 ×(Q 峰(时段1) +Q 峰(时段2) +…+ Q 峰(时段j) )(2) Flat-term power generation income = P 平 ×(Q 平(时段1) +Q 平(时段2) +…+Q 平(时段k) )(3) Valley power generation income = P 谷 ×(Q 谷(时段1) +Q 谷(时段2) +…+ Q 谷(时段l) )(4) Total electricity cost during target duration = peak period power generation revenue + peak period power generation revenue + flat period power generation revenue + valley period power generation revenue (5) Target duration income = target duration total electricity cost - predicted operating cost (6) Among them, the peak period, peak period, flat period and valley period are determined according to the electricity price period division rules in the electricity transaction disclosure data, P is the predicted electricity price, Q is the predicted power generation, i is the number of peak periods in the target time length, j is the number of peak periods in the target time length, k is the number of flat periods in the target time length, and l is the number of valley periods in the target time length.

7. A photovoltaic power station revenue prediction device, characterized in that: described an acquisition module, configured to acquire basic data of the photovoltaic power station, power transaction disclosure data, historical power settlement data, and power policy data, wherein the basic data includes parameters associated with the infrastructure of the photovoltaic power station; A creation module, connected to the acquisition module, for creating an electricity price prediction model and a power generation prediction model based on the basic data, power transaction disclosure data and historical power settlement data; A first prediction module, connected to the creation module, is used to predict the electricity price of the target duration based on the electricity price prediction model to obtain a predicted electricity price; A second prediction module, connected to the creation module, is used to predict the power generation of the target duration based on the power generation prediction model to obtain the predicted power generation; a third prediction model, connected to the creation module, for predicting the operating expenses of the target duration based on the power transaction disclosure data, the power policy data and the predicted power generation; A determination module is connected to the first prediction module, the second prediction module and the third prediction module respectively, and is used to determine the income of the target duration according to the predicted electricity price, the predicted power generation and the predicted operating expenses.

8. The device according to claim 7, characterized in that The creation module includes: An extraction unit, configured to perform data analysis on the power transaction disclosure data and the historical power settlement data to extract key power price data; a first creating unit, connected to the extracting unit, configured to create the electricity price prediction model based on the key electricity price data; a second creating unit, configured to perform simulation modeling on the photovoltaic power station based on the basic data to obtain a simulation model of the photovoltaic power station; a third creation unit, connected to the second creation unit, configured to generate a power generation curve of the photovoltaic power station using the simulation model; The fourth creation unit is used to obtain a power generation prediction model of the photovoltaic power station according to the power generation curve.

9. The device according to claim 8, characterized in that The extraction unit comprises: A first determining subunit, configured to determine a power price period division rule based on the power transaction disclosure data; A second determining subunit is configured to determine the transaction volume and settlement fee corresponding to each electricity price period according to the electricity price period division rule and the historical electricity settlement data; The third determination subunit is used to determine the average electricity price corresponding to each electricity price period based on the transaction volume and settlement fee corresponding to each electricity price period, and the key electricity price data includes the electricity price period division rules and the average electricity price corresponding to each electricity price period.

10. A production planning method for a photovoltaic power station, characterized in that: The method comprises: The method for predicting the revenue of a photovoltaic power station according to any one of claims 1 to 6, wherein the revenue of the photovoltaic power station for the target duration is predicted; Based on the revenue of the target duration, a production plan of the photovoltaic power station within the target duration is planned.

11. A production planning device for a photovoltaic power station, characterized in that: The device comprises: The profit prediction device for a photovoltaic power station according to any one of claims 7 to 9, configured to predict the profit of the photovoltaic power station for a target duration; A planning module is used to plan a production plan of the photovoltaic power station within the target time period based on the revenue of the target time period.

12. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method according to any one of claims 1 to 6 is implemented.

13. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 6.

Images