A power curtailment rate prediction method for wind power and photovoltaic project investment

Abstract

The application discloses a power curtailment rate prediction method for wind power and photovoltaic project investment, relates to the technical field of new energy investment risk assessment and power system planning, and comprises the following steps: obtaining provincial historical and planning data, regional project historical data and project data; determining provincial power curtailment rate prediction results in different periods according to the provincial historical and planning data; determining regional power curtailment rate prediction results in different periods according to the regional project historical data and the provincial power curtailment rate prediction results; and correcting the regional power curtailment rate prediction results according to the project data to obtain project power curtailment rate prediction results. The application can realize accurate prediction of wind power and photovoltaic project full-life-cycle phased power curtailment rate, effectively solve the problems of insufficient provincial and regional consumption level linkage analysis, incomplete time dimension coverage and neglect of project characteristic differences, and the problem of insufficient power curtailment rate prediction accuracy.

Description

Technical Field

[0001] This invention relates to the fields of new energy investment risk assessment and power system planning technology, and in particular to a method for predicting curtailment rates for wind power and photovoltaic project investments. Background Technology

[0002] In wind power and photovoltaic project investment, the curtailment rate is a core indicator affecting the project's economic viability and feasibility, and its prediction accuracy is mainly constrained by the capacity to absorb new energy sources. With the continuous expansion of new energy installed capacity, how to establish accurate curtailment rate prediction methods to scientifically assess project investment risks has become a critical technical issue that urgently needs to be addressed in the field of new energy planning.

[0003] To address the issue of curtailment rate prediction, existing technologies primarily employ regression methods based on single historical data or simple power balance models. These methods attempt to describe the quantitative relationship between power supply and demand by analyzing historical power supply and demand data or establishing power system balance equations, thereby deriving the trend of curtailment rate changes and providing fundamental data support for investment decisions in wind power and photovoltaic projects.

[0004] However, existing forecasting methods have significant shortcomings. Existing methods have strong limitations: traditional forecasts often rely on regression analysis of single historical data or simple power balance models, failing to integrate the linkage analysis of provincial and regional power absorption levels, resulting in insufficient macro-level accuracy or poor micro-level adaptability in the forecast results. Incomplete dimensional coverage: existing technologies neglect factors such as regulation capacity (e.g., adjustable load ratio), grid architecture evolution, and energy storage configuration, failing to accurately reflect the dynamic impact of electricity demand, supply (including external transmission and purchase of electricity), and regulation capacity. Coarse-grained handling of time spans: short-term, medium-term, and long-term forecasts are often treated separately, failing to establish a unified framework based on energy planning trends, increasing investment uncertainty. Ignoring differentiated factors: differences in the output characteristics of wind power and photovoltaics (e.g., volatility) and energy storage configuration are not included in the model, severely affecting forecast accuracy.

[0005] In summary, existing technologies for predicting power curtailment rates suffer from technical defects, such as insufficient analysis of the linkage between provincial and regional power consumption levels, incomplete coverage of the time dimension, and neglect of differences in project characteristics, which lead to insufficient accuracy in predicting power curtailment rates. Summary of the Invention

[0006] The technical problem this invention aims to solve is to address the shortcomings of existing technologies, specifically the insufficient analysis of the linkage between provincial and regional power absorption levels, incomplete time dimension coverage, and neglect of project characteristic differences, leading to insufficient accuracy in curtailment rate prediction. Specifically, this invention provides a curtailment rate prediction method for wind power and photovoltaic project investment, as detailed below: 1) In a first aspect, the present invention provides a method for predicting the curtailment rate for wind power and photovoltaic project investments, the specific technical solution of which is as follows: S1, obtain provincial historical and planning data, regional project historical data, and project data; S2, Based on the aforementioned provincial historical and planning data, determine the predicted provincial power curtailment rate for different periods; S3. Based on the historical data of the regional projects and the provincial power curtailment rate prediction results, determine the regional power curtailment rate prediction results for different periods. S4. Based on the project data, the predicted power curtailment rate for the region is corrected to obtain the predicted power curtailment rate for the project.

[0007] The beneficial effects of the curtailment rate prediction method for wind power and photovoltaic project investment provided by this invention are as follows: By integrating provincial historical and planning data with regional project historical data, the predicted curtailment rates for the province and region are determined step by step, enabling a linked analysis of the province's and region's power absorption levels and avoiding the disconnect between macro-level forecasts and micro-level project forecasts. By determining the curtailment rate prediction results in different periods, the time dimension of the entire project lifecycle is covered, meeting the investment decision-making needs at different stages. At the same time, the regional curtailment rate prediction results are corrected based on project data, fully considering differences in project types and energy storage configuration factors, significantly enhancing the adaptability and prediction accuracy for different project scenarios.

[0008] Based on the above solution, the present invention can be further improved as follows.

[0009] Furthermore, the different periods include the first phase, the second phase, and the third phase. The first phase, the second phase, and the third phase are sequential and non-overlapping in time, together covering the entire life cycle of the project. The step of determining the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data includes: determining the predicted first provincial power curtailment rate for the first stage period based on the power supply and demand data in the provincial historical and planning data.

[0010] Furthermore, the step of determining the predicted provincial power curtailment rate for different periods based on the aforementioned provincial historical and planning data also includes: Based on the first provincial power curtailment rate prediction result and the power curtailment rate data in the provincial historical and planning data, the second provincial power curtailment rate prediction result corresponding to the second stage period is determined; And based on the aforementioned provincial historical and planning data, determine the predicted third provincial power curtailment rate for the third phase period.

[0011] Furthermore, determining the regional power curtailment rate forecast results for different periods based on the historical data of the regional projects and the provincial power curtailment rate forecast results includes: The regional difference coefficient is determined based on the historical data of the projects in the region. The regional power curtailment rate prediction results for different periods are determined based on the regional difference coefficient and the provincial power curtailment rate prediction results.

[0012] 2) In a second aspect, the present invention also provides a curtailment rate prediction system for wind power and photovoltaic project investment, the specific technical solution of which is as follows: a data acquisition module, a provincial calculation module, a regional calculation module, and a project correction module; The data acquisition module is used to acquire provincial historical and planning data, regional project historical data, and project data; The provincial measurement module is used to determine the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data. The regional calculation module is used to determine the regional power curtailment rate prediction results for different periods based on the historical data of the regional projects and the provincial power curtailment rate prediction results. The project correction module is used to correct the predicted power curtailment rate of the region based on the project data, and obtain the predicted power curtailment rate of the project.

[0013] Based on the above solution, the present invention can be further improved as follows.

[0014] Furthermore, the different periods include the first phase, the second phase, and the third phase. The first phase, the second phase, and the third phase are sequential and non-overlapping in time, together covering the entire life cycle of the project. The step of determining the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data includes: determining the predicted first provincial power curtailment rate for the first stage period based on the power supply and demand data in the provincial historical and planning data.

[0015] Furthermore, the step of determining the predicted provincial power curtailment rate for different periods based on the aforementioned provincial historical and planning data also includes: Based on the first provincial power curtailment rate prediction result and the power curtailment rate data in the provincial historical and planning data, the second provincial power curtailment rate prediction result corresponding to the second stage period is determined; And based on the aforementioned provincial historical and planning data, determine the predicted third provincial power curtailment rate for the third phase period.

[0016] Furthermore, determining the regional power curtailment rate forecast results for different periods based on the historical data of the regional projects and the provincial power curtailment rate forecast results includes: The regional difference coefficient is determined based on the historical data of the projects in the region. The regional power curtailment rate prediction results for different periods are determined based on the regional difference coefficient and the provincial power curtailment rate prediction results.

[0017] 3) In a third aspect, the present invention also provides a computer device, the computer device including a processor coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to enable the computer device to implement any of the above methods.

[0018] 4) In a fourth aspect, the present invention also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0019] It should be noted that the beneficial effects of the technical solutions of the second to fourth aspects of the present invention and their corresponding possible implementations can be found in the above description of the technical effects of the first aspect and its corresponding possible implementations, and will not be repeated here. Attached Figure Description

[0020] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating the steps of a method for predicting the curtailment rate for wind power and photovoltaic project investment, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0022] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for predicting the curtailment rate for wind power and photovoltaic project investment, comprising the following steps: S1, obtain provincial historical and planning data, regional project historical data, and project data; S2, based on provincial historical and planning data, determines the predicted provincial power curtailment rate for different periods; S3, based on historical data of regional projects and the forecast results of provincial power curtailment rates, determines the forecast results of regional power curtailment rates for different periods; S4. Based on the project data, the predicted regional power curtailment rate is corrected to obtain the predicted project power curtailment rate.

[0023] The beneficial effects of a curtailment rate prediction method for wind power and photovoltaic project investments provided by the present invention are as follows: By integrating provincial historical and planning data and regional project historical data, the curtailment rate prediction results at the provincial and regional levels are determined step by step, realizing the linkage analysis of the provincial and regional consumption levels and avoiding the disconnection between macro prediction and micro project prediction. By determining the curtailment rate prediction results in different periods, it covers the time dimension of the entire project life cycle and meets the investment decision-making needs at different stages. At the same time, the regional curtailment rate prediction results are corrected according to project data, fully considering project type differences and energy storage configuration factors, significantly enhancing the adaptability and prediction accuracy for different project scenarios.

[0024] It should be noted that for the convenience of understanding, the technical terms appearing in this solution are explained one by one below and will not be elaborated further later: Provincial historical and planning data: Refers to the basic data set that covers the entire provincial administrative region and reflects the operating status and development plan of the power system. It is divided into historical data and planning data, specifically including operating data such as power demand, power supply (including power transmitted out and power purchased externally), adjustable load ratio, and provincial historical curtailment rate data (such as the average curtailment rate of the whole province in the recent 1 year, the average growth rate of the curtailment rate in the recent 3 years, etc.) in historical periods, as well as planning data such as grid architecture parameters and energy planning documents that describe the construction goals and layout of the future power system. Historical data is usually collected for the recent 3 years, and planning data usually covers the development plan for the next 5 years.

[0025] Regional project historical data: Refers to the actual operation record data of the newly commissioned new energy projects in a specific geographical area, used to characterize the new energy consumption characteristics at the regional level. Specifically includes the installed capacity of the operating projects, regional location information, the statistical data of the annual curtailment rate in the recent 3 years, and the detailed monthly curtailment rate data in the recent 1 year.

[0026] Project data: Refers to the parameter set that characterizes the technical and economic characteristics of the project to be predicted. In this solution, it specifically includes project type parameters and energy storage configuration parameters. Project type parameters are used to distinguish the technical differences between wind power projects and photovoltaic projects, and energy storage configuration parameters are used to describe the technical specifications and capacity configuration levels of the project's supporting energy storage system.

[0027] Project type parameters: Refers to the classification identifiers and corresponding correction factors used to distinguish the technical characteristics of wind power generation projects and photovoltaic power generation projects. Due to the differences in output characteristics (such as volatility, simultaneity rate) between wind power and photovoltaic power, the curtailment risks of the two are different under the same consumption conditions. In this solution, curtailment rate correction factors are set separately for different project types, and the correction factor for wind power projects is better than that for photovoltaic projects.

[0028] Energy storage configuration parameters: These refer to the set of parameters describing the technical specifications of the project's supporting electrochemical energy storage or other forms of energy storage systems, specifically including the energy storage capacity configuration ratio. In this scheme, by calculating the ratio of the theoretical charge / discharge capacity of energy storage to the theoretical power generation of the project, an energy storage-curtailment rate elasticity coefficient is established to quantify the contribution of energy storage configuration to reducing the curtailment rate.

[0029] Provincial curtailment rate forecast results: These refer to the predicted curtailment rate of new energy sources covering the entire provincial administrative region, obtained based on historical and planning data, through supply and demand balance analysis and trend extrapolation. This scheme divides the forecast period into different stages, generating corresponding first, second, and third provincial curtailment rate forecast results, which respectively characterize the overall absorption level of the province in different time periods.

[0030] The first provincial-level power curtailment rate prediction result refers to the provincial-level power curtailment rate value predicted for the first phase period (usually the period from the initial stage of project commissioning to the 5th year). The determination process mainly relies on the power supply and demand data in the provincial historical and planning data. It is obtained by analyzing the changing trend of the difference between power supply and power demand and fitting it with historical power curtailment rate data.

[0031] The second provincial curtailment rate forecast result refers to the provincial-level curtailment rate value predicted for the second phase period (usually the 5th to 10th year cycle). It is determined based on the first provincial curtailment rate forecast result, and is obtained by analyzing the curtailment rate data in the provincial historical and planning data through time series continuity analysis, combined with the constraints such as the newly added regulation capacity during the planning period. It reflects the change in the power system's absorption level after the implementation of the medium-term plan.

[0032] The third provincial curtailment rate prediction result refers to the provincial-level curtailment rate value predicted for the third phase period (usually the 10th year to the end of the project operation). It is determined mainly based on grid architecture parameters and energy planning documents, and is obtained by fitting the long-term decay trend of curtailment rate with the degree of grid perfection, which represents the absorption level after the power system becomes mature and stable.

[0033] Regional curtailment rate prediction results: These refer to the predicted curtailment rate values ​​for a specific region, obtained by adjusting for regional differences based on the provincial curtailment rate prediction results. In this scheme, a regional difference coefficient is introduced to correct the provincial prediction results, resulting in curtailment rate prediction values ​​applicable to the specific geographical area where the project is located. This includes the regional curtailment rate prediction results for the first, second, and third phases.

[0034] Regional disparity coefficient: This refers to a correction parameter quantified using a regression model by analyzing historical curtailment rate data from the same or adjacent regions, regional economic development plans, and grid architecture adaptability indicators. This coefficient characterizes the degree of deviation of a specific region from the provincial average power absorption rate, and is used to adjust provincial-level macro-forecast results to a regional-level micro-adaptability. The historical curtailment rate data from the same or adjacent regions, regional economic development plans, and grid architecture adaptability indicators are derived from historical data of regional projects.

[0035] Project curtailment rate prediction results: These refer to the final curtailment rate prediction values ​​obtained by further correcting the regional curtailment rate prediction results based on the project's own characteristic data. By introducing corrections for differences in project type and the impact of energy storage configuration, the general prediction at the regional level is transformed into personalized prediction results for specific projects, directly serving project investment decisions.

[0036] Phase 1, Phase 2, and Phase 3: These refer to the three consecutive, non-overlapping time intervals into which the project's entire lifecycle is divided in this plan. Phase 1 typically covers the period from the initial stage of project commissioning to year 5; Phase 2 typically covers the period from year 5 to year 10; and Phase 3 typically covers the period from year 10 to the end of project operation. These three phases are sequentially linked, with the end date of one phase serving as the start date of the next, together forming a complete project operation cycle.

[0037] Electricity supply and demand data refers to fundamental data characterizing the quantitative relationship between the power system's supply capacity and consumer demand. This includes electricity demand (total electricity load of the entire society) and electricity supply (total power generation from various sources), while also encompassing electricity transmitted to other provinces (electricity transmitted outside the province, recorded as a negative value) and electricity purchased from other provinces (electricity purchased from other provinces, recorded as a positive value). By analyzing the differences and growth rates of these data, the balance between power supply and demand and the trend of power curtailment risks can be determined.

[0038] Power curtailment rate data: refers to the statistical value of the actual power curtailment rate that occurred in a historical period, including the annual average power curtailment rate and detailed records of the monthly power curtailment rate.

[0039] In another embodiment of this solution, S1 is specifically implemented as follows: Obtain provincial historical and planning data covering the provincial administrative divisions for the past 3 years and the next 5 years, specifically including electricity demand, electricity supply (including electricity transmitted to other provinces and electricity purchased from other provinces), adjustable load ratio, historical power curtailment rate data for the whole province, power grid architecture parameters, and energy planning documents; Obtain historical data of regional projects generated during the historical operation of new energy projects that have been put into operation, including installed capacity, regional location, annual curtailment rate for the past 3 years and monthly curtailment rate for the past 1 year; The technical characteristic parameters of the project to be predicted are obtained as project data, including project type parameters to distinguish between wind power and photovoltaic power generation, and energy storage configuration parameters to describe the technical specifications of the supporting energy storage system.

[0040] In another embodiment of this solution, S2 is specifically implemented as follows: The entire project lifecycle is divided into three consecutive and non-overlapping time intervals: the first phase, the second phase, and the third phase.

[0041] S201, Determine the predicted results of the first provincial power curtailment rate for the first phase period: For the first phase period (corresponding to the period from the initial stage of project commissioning to the 5th year), based on the electricity demand, electricity supply (including external transmission and external purchase) and adjustable load ratio in the provincial historical and planning data, the power balance method is applied to simulate the changes in the supply and demand relationship, calculate the difference between the electricity supply and the electricity demand, and calculate the supply and demand growth rate based on the annual change of the difference. A positive supply and demand growth rate indicates an increased risk of power curtailment, while a negative supply and demand growth rate indicates a decreased risk of power curtailment.

[0042] Meanwhile, by combining historical data analysis to fit the trend of power curtailment rate, based on the power curtailment rate data in the provincial historical and planning data, the average power curtailment rate of the province in the past year is used as the base value, multiplied by (1 + the average growth rate of power curtailment rate in the past 3 years) to obtain the first preliminary power curtailment rate prediction value. The first preliminary power curtailment rate prediction value is then corrected for seasonal fluctuations using detailed power curtailment rate data for the past 12 months after data cleaning.

[0043] Based on the combined results of the power balance method and historical data analysis, the predicted first provincial power curtailment rate for the first phase period is determined.

[0044] Among them, the power balance method refers to the technical method of assessing the risk of power curtailment by analyzing the difference between the supply and demand quantities of the power system in real-time operation or planning state and its dynamic changes. It is an existing technology.

[0045] Historical data analysis refers to the technical method of predicting future power curtailment rates based on historical operational statistics through trend extrapolation and fluctuation correction, and it is an existing technology.

[0046] Data cleaning refers to the process of identifying and processing outliers in the raw power curtailment rate monitoring data for the past 12 months. This includes removing abnormally high or low values ​​caused by extreme weather conditions, equipment failures, or statistical errors, and retaining only the actual power curtailment level data under normal absorption conditions to ensure the reliability and representativeness of the monthly data benchmark used for correction.

[0047] Seasonal fluctuation correction refers to comparing and verifying the initial curtailment rate forecast calculated based on the annual average and growth rate with the detailed curtailment rate data for the past 12 months after data cleaning on a monthly basis. By analyzing the monthly fluctuation characteristics and seasonal patterns, the annual forecast value is adjusted for volatility to eliminate the monthly differences masked by the annual average, making the forecast results closer to the seasonal absorption characteristics of the actual power system operation.

[0048] S202, Determine the second provincial power curtailment rate prediction result corresponding to the second phase period: For the second phase period (corresponding to the 5th to 10th year cycle), based on the first provincial power curtailment rate prediction result corresponding to the first phase period and the historical power curtailment rate data of the past 3 years in the provincial historical and planning data, a trend continuation model is established using time series analysis method, and extrapolation is used to obtain the second preliminary power curtailment rate prediction value corresponding to the second phase period.

[0049] By combining the weight of renewable energy consumption within the province and the planning of new regulation capacity in the provincial historical and planning data, the second preliminary curtailment rate forecast value is constrained and corrected to determine the second provincial curtailment rate forecast result corresponding to the second stage period.

[0050] Time series analysis refers to the technical means of predicting future development trends by establishing mathematical models based on the sequence characteristics of historical data over time through statistical analysis methods. It is an existing technology.

[0051] Trend continuation model: This refers to a predictive model constructed using time series analysis based on the assumption that historical development trends have a continuous inertial characteristic. In this scheme, it specifically refers to establishing a trend extrapolation equation based on the changing trends (such as upward, downward, or stable trends) of the power curtailment rate data over the past three years and the first phase, extending the mathematical expression of the above trends to the future time axis, and obtaining the second preliminary power curtailment rate prediction value corresponding to the second phase.

[0052] The weight of renewable energy consumption within the province comes from the allocation ratio of renewable energy consumption targets recorded in the energy planning documents in the provincial historical and planning data. Specifically, it refers to the proportion target or consumption responsibility weight of new energy sources such as wind power and photovoltaics in the power supply structure as specified in the planning documents. This weight directly determines the priority order of consumption of different types of renewable energy in the power system dispatch.

[0053] The new regulation capacity plan is derived from the regulation capacity construction targets recorded in the provincial historical and planning data and energy planning documents. Specifically, it includes the planned capacity scale of flexible regulation power sources such as pumped storage, gas peak shaving, and electrochemical energy storage during the planning period, as well as the target for increasing the proportion of adjustable load.

[0054] Constraint correction refers to the process of adjusting and correcting the second preliminary curtailment rate forecast value obtained from trend extrapolation by introducing planning-level constraints and factors affecting changes in regulation capacity. In this scheme, it specifically refers to adjusting the boundary constraints of the second preliminary curtailment rate forecast value output by the trend continuation model. When the newly added regulation capacity significantly increases during the planning period, constraint correction manifests as a decrease in the predicted curtailment rate value; when the weight of renewable energy consumption is mismatched with the system's regulation capacity, constraint correction manifests as an increase or maintenance of the predicted curtailment rate value, ensuring that the forecast results conform to the physical constraints and policy orientation of the power system development plan.

[0055] S203, Determine the predicted results of the third provincial power curtailment rate for the third phase period: For the third phase period (corresponding to the period from the 10th year to the end of project operation), based on the power grid architecture parameters in the provincial historical and planning data and energy planning documents, a long-term decay curve is constructed using the historical data fitting method to determine the predicted results of the third provincial power curtailment rate for the third phase period.

[0056] Among them, the historical data fitting method refers to the technical method of constructing a model describing the trend of power curtailment rate over time by using mathematical fitting techniques based on the long-term evolution law of historical statistical data, which is an existing technology.

[0057] The long-term decay curve is a mathematical curve model constructed by fitting historical data, which characterizes the decreasing trend of the curtailment rate as the grid architecture improves and eventually tends to a stable state. It reflects the long-term evolution law of the curtailment rate decreasing from a high value range to a low value range and converging to a steady state as the grid architecture construction continues to advance, the regulation capacity continues to increase, and the conditions for the absorption of new energy gradually improve.

[0058] In another embodiment of this solution, S3 is specifically implemented as follows: S301. For the first phase, a historical data regression model is constructed based on the power curtailment rate data of the same or adjacent regions over the past 12 months, regional economic development plans, and project power grid architecture adaptability indicators. The influence coefficient of regional factors on the power curtailment rate is quantified and used as the regional difference coefficient. The prediction result of the first provincial power curtailment rate corresponding to the first phase is multiplied by the regional difference coefficient to obtain the prediction result of the first regional power curtailment rate corresponding to the first phase.

[0059] The power curtailment rate data for the same or adjacent areas over the past 12 months is derived from the detailed monthly power curtailment rate data for the past year in the historical data of regional projects.

[0060] Regional economic development plans are development planning documents at the regional level. They can be obtained by associating regional location information with the corresponding regional economic development plans based on historical data of regional projects.

[0061] The project's power grid architecture adaptability index is an assessment data that characterizes the technical conditions of the regional power grid infrastructure. It can be obtained by associating the regional location information in the historical data of regional projects with the corresponding regional power grid architecture assessment data.

[0062] Historical data regression models are mathematical models constructed using statistical regression analysis based on historical data of regional projects. These models are used to identify the quantitative relationship between regional characteristics and power curtailment rates. In this scheme, the influence coefficient obtained from the historical data regression model is used as the regional difference coefficient.

[0063] S302, for the second phase period, based on the regional power curtailment rate difference data and the regional power grid architecture perfection index, combined with the regional difference coefficient, a long-term decay curve is fitted, and the second provincial power curtailment rate prediction result corresponding to the second phase period is multiplied by the regional difference coefficient to obtain the second regional power curtailment rate prediction result corresponding to the second phase period.

[0064] Among them, the regional power curtailment rate difference data is calculated based on the annual power curtailment rate statistics for the past three years and the detailed monthly power curtailment rate data for the past year from the historical data of regional projects. It is obtained by statistically analyzing the dispersion of power curtailment rate values ​​among operational projects in the same or adjacent regions.

[0065] The regional power grid architecture completeness index is obtained by correlating the regional location information in the historical data of regional projects with the completeness of the power grid infrastructure in the project area.

[0066] The long-term decay curve describes a mathematical model of how the curtailment rate gradually decreases and tends to a stable state over time and with the improvement of the power grid architecture. It reflects the long-term evolution of regional absorption conditions as infrastructure improves.

[0067] The process of fitting the long-term decay curve is as follows: taking the regional difference coefficient determined in the first stage as the starting point and the convergence of the regional difference coefficient to a value of 1 after the grid architecture is improved as the ending point, the decay rate is determined based on the regional grid architecture improvement index, and the quantitative relationship between the time variable and the regional difference coefficient is established using the exponential decay function. The prediction result of the second provincial power curtailment rate corresponding to the second stage is multiplied by the regional difference coefficient that changes with time to obtain the prediction result of the regional power curtailment rate corresponding to the second stage.

[0068] S303, for the third phase, based on the trend of convergence in the curtailment rates of various regions within the province after the improvement of the power grid architecture, the predicted provincial curtailment rate for the third phase is corrected for convergence. The process is as follows: Based on the technical state where the differences in absorption conditions between various regions within the province are basically eliminated after the power grid architecture is highly improved, the regional difference coefficient converges to a value of 1. At this time, the curtailment rate level of the project area tends to be consistent with the provincial average level. The predicted third provincial curtailment rate for the third phase is directly used as the predicted curtailment rate value of the project area, or a small fluctuation range correction is made based on the unified steady-state level of the province, so that the predicted third regional curtailment rate of the project area is similar to the steady-state curtailment rate level of the province, thereby completing the convergence correction and obtaining the predicted third regional curtailment rate for the third phase.

[0069] Among them, the convergence correction refers to the adjustment of the predicted third provincial power curtailment rate for the third stage period based on the trend of gradually narrowing differences in power curtailment rates among different regions within the province after the improvement of the power grid architecture, so that the predicted third regional power curtailment rate for the project area is closer to the steady-state level of the whole province.

[0070] In another embodiment of this solution, S4 is specifically implemented as follows: Based on the project type parameters in the project data, a first curtailment rate correction coefficient is set for wind power projects and a second curtailment rate correction coefficient is set for photovoltaic projects. Since photovoltaic power generation has a high simultaneous output characteristic, that is, photovoltaic output is concentrated during the sunshine period and has strong volatility, its curtailment risk is higher than that of wind power. Therefore, the first curtailment rate correction coefficient is better than the second curtailment rate correction coefficient. Specifically, the value of the first curtailment rate correction coefficient is smaller than the value of the second curtailment rate correction coefficient.

[0071] The application process of the first and second curtailment rate correction coefficients is as follows: The first curtailment rate correction coefficient is used to weight and correct the predicted regional curtailment rates for the first, second, and third phases of wind power projects, respectively; or the second curtailment rate correction coefficient is used to weight and correct the predicted regional curtailment rates for the first, second, and third phases of photovoltaic projects, respectively, thereby obtaining preliminary project curtailment rate prediction results for each period that reflect the actual curtailment levels of different project types.

[0072] Based on the energy storage configuration parameters in the project data, the ratio of theoretical energy storage charge / discharge capacity to the project's theoretical power generation is calculated to establish an energy storage-curtailment rate elasticity coefficient model to determine the extent of curtailment rate reduction. The energy storage-curtailment rate elasticity coefficient model is a mathematical model that quantitatively assesses the contribution of energy storage to reducing curtailment rates based on energy storage system configuration parameters. Input parameters include energy storage configuration parameters. The calculation logic of the energy storage-curtailment rate elasticity coefficient model is as follows: The ratio of theoretical charge / discharge capacity to theoretical power generation is calculated, representing the configuration intensity of energy storage capacity relative to the project's power generation scale; based on this ratio, an elastic mapping relationship is established between energy storage configuration and the extent of curtailment rate reduction. This elastic mapping relationship reflects the mechanism by which energy storage reduces wind and solar power curtailment by smoothing power output fluctuations and providing peak-shaving capabilities. The output of the energy storage-curtailment rate elasticity coefficient model is the energy storage-curtailment rate elasticity coefficient, which quantifies the specific impact of energy storage configuration on reducing curtailment rates. It is used to downward correct the regional curtailment rate prediction results, and the correction magnitude is positively correlated with the ratio of the theoretical charge / discharge capacity to the theoretical power generation.

[0073] By using the energy storage-curtailment rate elasticity coefficient, the preliminary project curtailment rate prediction results for each period are weighted and corrected to obtain the project curtailment rate prediction results for the corresponding period. The results are then aggregated to generate project curtailment rate prediction results covering the entire project lifecycle.

[0074] It should be noted that in step S4, the process of correcting the regional curtailment rate prediction results (including regional curtailment rate prediction results at different times) by the first curtailment rate correction coefficient, the second curtailment rate correction coefficient, and the energy storage-curtailment rate elasticity coefficient is not sequential and can be selected in any order according to actual needs.

[0075] Furthermore, the different periods include the first phase, the second phase, and the third phase. The first phase, the second phase, and the third phase are sequential in time and do not overlap, together covering the entire life cycle of the project. Based on provincial historical and planning data, the predicted results of provincial power curtailment rates for different periods are determined, including: based on the power supply and demand data in the provincial historical and planning data, the predicted results of the first provincial power curtailment rate for the first phase period are determined.

[0076] Furthermore, based on provincial historical and planning data, the predicted provincial power curtailment rates for different periods are determined, including: Based on the first provincial power curtailment rate forecast results and the power curtailment rate data in the provincial historical and planning data, the second provincial power curtailment rate forecast results corresponding to the second phase period are determined. And based on provincial historical and planning data, the predicted results of the third provincial power curtailment rate for the third phase period were determined.

[0077] Furthermore, based on historical data of regional projects and provincial power curtailment rate forecasts, the regional power curtailment rate forecasts for different periods are determined, including: Determine the regional difference coefficient based on historical data of regional projects; The predicted regional power curtailment rates for different periods are determined based on the regional difference coefficient and the predicted provincial power curtailment rates.

[0078] The beneficial effects are as follows: By integrating provincial and regional power absorption levels, the model avoids a disconnect between macro and micro perspectives, significantly reducing forecast errors. It processes near-, medium-, and long-term forecasts in stages to adapt to investment cycle needs and improve decision-making reliability. By integrating existing planning and historical data, no new hardware is required, reducing forecasting costs. Through energy storage configuration and wind-solar differential correction, the model's adaptability to different project scenarios is enhanced. It outputs project curtailment rate forecasts to help investors avoid projects with high curtailment risks.

[0079] In the above embodiments, although the steps are numbered S1, S2, etc., they are only specific embodiments given by the present invention. Those skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, and these situations are also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0080] Furthermore, the acquisition process of the data involved in this application follows the principles of legality, legitimacy, and necessity. Based on obtaining the explicit authorization and consent of the user, only the minimum necessary information required to achieve the purpose is collected, and data security protection obligations are fulfilled in accordance with the law.

[0081] The present invention also provides a curtailment rate prediction system for wind power and photovoltaic project investment, the specific technical solution of which is as follows: a data acquisition module, a provincial calculation module, a regional calculation module, and a project correction module; The data acquisition module is used to acquire provincial historical and planning data, regional project historical data, and project data; The provincial calculation module is used to determine the predicted provincial power curtailment rate for different periods based on provincial historical and planning data. The regional calculation module is used to determine the regional power curtailment rate forecast results for different periods based on historical data of regional projects and provincial power curtailment rate forecast results. The project correction module is used to correct the regional power curtailment rate prediction results based on project data, and obtain the project power curtailment rate prediction results.

[0082] It should be noted that the beneficial effects of the curtailment rate prediction system for wind power and photovoltaic project investment provided in the above embodiments are the same as those of the curtailment rate prediction method for wind power and photovoltaic project investment described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0083] like Figure 2 As shown, an embodiment of the present invention provides a computer device 300, which includes a processor 320 coupled to a memory 310. The memory 310 stores at least one computer program 330, which is loaded and executed by the processor 320 to enable the computer device 300 to implement any of the above-described methods. Specifically: The computer device 300 can vary considerably due to differences in configuration or performance. It may include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310. The memories 310 store at least one computer program 330, which is loaded and executed by the processors 320 to enable the computer device 300 to implement the curtailment rate prediction method for wind power and photovoltaic project investment provided in the above embodiments. Of course, the computer device 300 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input / output. The computer device 300 may also include other components for implementing device functions, which will not be elaborated upon here.

[0084] An embodiment of the present invention provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above-described methods.

[0085] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0086] In an exemplary embodiment, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the above-described methods for predicting curtailment rates for wind power and solar power project investments.

[0087] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0088] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0089] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0090] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for predicting curtailment rates in wind power and photovoltaic project investments, characterized in that, include: S1, obtain provincial historical and planning data, regional project historical data, and project data; S2, Based on the aforementioned provincial historical and planning data, determine the predicted provincial power curtailment rate for different periods; S3. Based on the historical data of the regional projects and the provincial power curtailment rate prediction results, determine the regional power curtailment rate prediction results for different periods. S4. Based on the project data, the predicted power curtailment rate for the region is corrected to obtain the predicted power curtailment rate for the project.

2. The method for predicting curtailment rates for wind power and photovoltaic project investment according to claim 1, characterized in that, The different periods include the first phase, the second phase, and the third phase. The first phase, the second phase, and the third phase are sequential in time and do not overlap, together covering the entire life cycle of the project. The step of determining the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data includes: determining the predicted first provincial power curtailment rate for the first stage period based on the power supply and demand data in the provincial historical and planning data.

3. The method for predicting curtailment rates for wind power and photovoltaic project investment according to claim 2, characterized in that, The step of determining the predicted provincial power curtailment rate for different periods based on the aforementioned provincial historical and planning data also includes: Based on the first provincial power curtailment rate prediction result and the power curtailment rate data in the provincial historical and planning data, the second provincial power curtailment rate prediction result corresponding to the second stage period is determined; And based on the aforementioned provincial historical and planning data, determine the predicted third provincial power curtailment rate for the third phase period.

4. The method for predicting curtailment rates for wind power and photovoltaic project investment according to claim 1, characterized in that, The step of determining the regional power curtailment rate forecast results for different periods based on the historical data of the regional projects and the provincial power curtailment rate forecast results includes: The regional difference coefficient is determined based on the historical data of the projects in the region. The regional power curtailment rate prediction results for different periods are determined based on the regional difference coefficient and the provincial power curtailment rate prediction results.

5. A curtailment rate prediction system for wind power and photovoltaic project investment, characterized in that, include: The system includes a data acquisition module, a provincial measurement module, a regional measurement module, and a project correction module. The data acquisition module is used to acquire provincial historical and planning data, regional project historical data, and project data; The provincial measurement module is used to determine the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data. The regional calculation module is used to determine the regional power curtailment rate prediction results for different periods based on the historical data of the regional projects and the provincial power curtailment rate prediction results. The project correction module is used to correct the predicted power curtailment rate of the region based on the project data, and obtain the predicted power curtailment rate of the project.

6. A curtailment rate prediction system for wind power and photovoltaic project investment according to claim 5, characterized in that, The different periods include the first phase, the second phase, and the third phase. The first phase, the second phase, and the third phase are sequential in time and do not overlap, together covering the entire life cycle of the project. The step of determining the predicted provincial power curtailment rate for different periods based on the provincial historical and planning data includes: determining the predicted first provincial power curtailment rate for the first stage period based on the power supply and demand data in the provincial historical and planning data.

7. A curtailment rate prediction system for wind power and photovoltaic project investment according to claim 6, characterized in that, The step of determining the predicted provincial power curtailment rate for different periods based on the aforementioned provincial historical and planning data also includes: Based on the first provincial power curtailment rate prediction result and the power curtailment rate data in the provincial historical and planning data, the second provincial power curtailment rate prediction result corresponding to the second stage period is determined; And based on the aforementioned provincial historical and planning data, determine the predicted third provincial power curtailment rate for the third phase period.

8. A curtailment rate prediction system for wind power and photovoltaic project investment according to claim 5, characterized in that, The step of determining the regional power curtailment rate forecast results for different periods based on the historical data of the regional projects and the provincial power curtailment rate forecast results includes: The regional difference coefficient is determined based on the historical data of the projects in the region. The regional power curtailment rate prediction results for different periods are determined based on the regional difference coefficient and the provincial power curtailment rate prediction results.

9. A computer device, characterized in that, The computer device includes a processor coupled to a memory storing at least one computer program, which is loaded and executed by the processor to enable the computer device to implement a curtailment rate prediction method for wind power and photovoltaic project investment as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to enable the computer to implement a curtailment rate prediction method for wind power and photovoltaic project investment as described in any one of claims 1 to 4.

Images