A method and device for dynamically determining power limiting probability of a new energy station

Abstract

The application provides a new energy station power cut probability dynamic determination method and device, belonging to the new energy technical field, wherein the method constructs four-dimensional indexes through collecting four kinds of multi-source real-time data of station operation, power grid constraints, meteorological fluctuations and space-time coupling constraints, and obtains standardized index values through abnormal value truncation and adaptive dimensionless; then, based on multi-expert decision and time sequence deviation degree dynamic smoothing update subjective weight, combined with time sequence fluctuation and nonlinear correlation calculation objective weight, adaptive matching according to operation scene and game equilibrium to obtain combined weight; finally, through nonlinear weighted aggregation, the power cut probability is obtained, and the index contribution degree is dynamically graded and quantified according to the historical quantile. Through the above method, multi-dimensional, real-time and fine dynamic evaluation is realized, effectively solving the technical problem that the existing technology cannot accurately and efficiently determine the power cut probability, and achieving the technical effect of accurately and efficiently determining the power cut probability.

Description

Technical Field

[0001] This application belongs to the field of new energy technology, and in particular relates to a method and device for dynamically determining the probability of power curtailment at new energy power plants. Background Technology

[0002] With the rapid growth of installed capacity of new energy sources such as wind power and photovoltaics, the penetration rate of new energy power plants in the power system is constantly increasing. However, the intermittent, volatile, and anti-peak-shaving characteristics of new energy output can affect the safe and stable operation of the power system. In order to ensure grid stability, dispatching agencies often need to implement power curtailment measures for new energy power plants, which directly affects the power generation revenue of the projects. Therefore, accurately assessing the probability of power curtailment faced by new energy power plants is of great significance for project operation optimization and risk management.

[0003] However, no effective solution has yet been proposed for predicting the probability of power outages. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for dynamically determining the probability of power curtailment at new energy power plants, which can accurately and efficiently determine the probability of power curtailment.

[0005] This application provides a method and device for dynamically determining the probability of power curtailment at renewable energy power plants, which is implemented as follows: A method for dynamically determining the probability of power curtailment at renewable energy power plants, the method comprising: Collect real-time data from four sources—operation status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints—for the target renewable energy power plants to construct a four-dimensional power curtailment risk assessment index. Outlier truncation and adaptive segmentation dimensionless processing were performed on the four-dimensional power curtailment risk assessment index data to obtain standardized index values. Based on multi-expert decision-making and time-series state deviation, the standardized index values ​​are dynamically calculated and the subjective weights are smoothly updated. Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, the objective weights of the standardized indicator values ​​are dynamically calculated. The fusion ratio of subjective and objective weights is adaptively determined based on the current operating scenario, and the final combined weights are obtained by solving the game equilibrium based on the fusion ratio, subjective weights, and objective weights. The probability of power curtailment at the current moment is calculated by nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators. The probability of power curtailment at the current moment is used to dynamically classify risk levels according to historical risk quantiles and quantify the contribution of each indicator to the probability of power curtailment.

[0006] In one implementation, real-time data from four sources—operating status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints—are collected from the target renewable energy power plant to construct a four-dimensional power curtailment risk assessment index, including: Real-time operation data, power grid constraint data, meteorological forecast data, and spatiotemporal correlation data are collected from the station monitoring system, power grid dispatching system, meteorological platform, and regional cluster management system, respectively. The collected data is cleaned, verified, and completed. Based on four dimensions—station operation, power grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints—quantitative features strongly correlated with power curtailment are extracted to form secondary indicators. Each indicator is labeled as either a positive risk indicator or a negative risk indicator, thus completing the construction of a four-dimensional indicator system.

[0007] In one implementation, based on multi-expert decision-making and time-series state deviation, the standardized index values ​​are dynamically calculated and subjective weights are smoothly updated, including: Based on the optimal and worst indicators determined by multi-expert decision-making, the static subjective weights are obtained. Calculate the time-series sensitivity factor based on the degree of deviation between the real-time value and the historical average of the indicator; Calculate the time-series smoothing transmission coefficient based on the magnitude of changes in indicators at adjacent time points; The static subjective weight, time-sensitive factor, and smoothing transmission coefficient are fused together, and the dynamic subjective weight is obtained by dynamically calculating and smoothly updating.

[0008] In one implementation, static subjective weights are obtained based on the optimal and worst-case indices determined by multi-expert decision-making, including: Obtain the importance vector of the best indicator relative to other indicators for the current expert, and the importance vector of other indicators relative to the worst indicator. Establish an expert consensus optimization model by constructing optimization objectives and constraints to ensure maximum consistency and minimum bias among all experts:

[0009] in, This is the total deviation value. For the number of experts, For the number of indicators, The optimal index selected for the m-th expert. The worst-case indicator selected for the m-th expert. Let represent the importance of the optimal indicator relative to indicator i. The importance of the worst-case indicator relative to indicator i. The static subjective weight of index i, The static subjective weight of the optimal indicator selected for the m-th expert. The static subjective weight of the worst-case indicator selected by the m-th expert. Solving the aforementioned expert consensus model yields a static subjective weight vector:

[0010] in, This is a static subjective weight vector. The static subjective weight of indicator 1, The static subjective weight of indicator 2, Let n be the static subjective weight of the indicator n.

[0011] In one implementation, a time-series sensitivity factor is calculated based on the degree of deviation between the real-time value of the indicator and its historical mean, including: Calculate the time-series sensitivity factor using the following formula:

[0012] in, Let i be the time-series sensitivity factor of index i at time t. Let be the real-time value of index i at time t. Let i be the historical mean of the index. The historical standard deviation of index i; The temporal smoothing propagation coefficient is calculated based on the magnitude of changes in indicators at adjacent time points, including: Calculate the time-series smoothing propagation coefficient using the following formula:

[0013] in, For time-series smoothing conduction coefficient, For smoothing coefficients, Let be the real-time value of index i at time t. The real-time value of index i at time t is the value of index i at the time preceding time t. The static subjective weights, time-series sensitive factors, and smoothing transmission coefficients are fused together to dynamically calculate and smoothly update the dynamic subjective weights, including: The dynamic subjective weight is calculated using the following formula:

[0014] in, Let i be the dynamic subjective weight of index i at time t. Let be the static subjective weight of index i at time t.

[0015] In one implementation, based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, the objective weights of the standardized indicator values ​​are dynamically calculated, including: Calculate the time drift entropy using the following formula:

[0016] in, For temporal drift entropy, The time window length, Let represent the time series proportion of index i at time t. To prevent zero smoothing factor; Calculate the conflict coefficient using the following formula:

[0017] in, The conflict coefficient is used to characterize the degree of independence between indicators. The user quantifies the nonlinear relationship between the mutual information of indicator i and indicator j. Based on the time-series drift value and the conflict coefficient, the objective weight is dynamically calculated according to the following formula:

[0018] in, The objective weight of index i is calculated dynamically.

[0019] In one implementation, the fusion ratio of subjective and objective weights is adaptively determined based on the current operating scenario. Then, based on the fusion ratio, subjective weights, and objective weights, the final combined weights are obtained through game equilibrium solving, including: The combined weights are calculated using the following formula:

[0020] in, For the final combined weights, For the blending ratio, Subjective weighting, For objective weighting; The current operating scenario includes at least one of the following: normal scenario, extreme weather scenario, power grid maintenance scenario, and peak load scenario.

[0021] In one implementation, a nonlinear weighted aggregation is performed based on the final combined weights and the coupling relationship between indicators to calculate the probability of power curtailment at the current moment, including: The probability of power outages is calculated using the following formula:

[0022] in, Let be the probability of power outage at time t. To characterize the fuzzy measure of the interaction and coupling between indicators, For the final combined weights, Let i be the standardized value of index i.

[0023] A device for dynamically determining the probability of power curtailment at a renewable energy power station, comprising: The data acquisition module is used to collect real-time data from four sources: the operating status of the target new energy power station, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and to construct four-dimensional power curtailment risk assessment index data. The processing module is used to perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values. The subjective determination module is used to dynamically calculate the standardized index values ​​and smoothly update the subjective weights based on multi-expert decision-making and time-series state deviation. An objective determination module is used to dynamically calculate the objective weight of the standardized indicator value based on the time-series fluctuation characteristics of the indicator and the degree of nonlinear correlation between the indicators; The weight determination module is used to adaptively determine the fusion ratio of subjective weights and objective weights according to the current operating scenario, and then obtain the final combined weights by solving the game equilibrium based on the fusion ratio, subjective weights and objective weights. The calculation module is used to perform nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators to calculate the power curtailment probability at the current moment. The power curtailment probability at the current moment is used to dynamically classify risk levels according to historical risk quantiles and quantify the contribution of each indicator to the power curtailment probability.

[0024] An electronic device includes a processor and a memory for storing processor-executable instructions, wherein the processor, when executing the instructions, implements the steps of the method described above.

[0025] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0026] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0027] The method for dynamically determining the probability of power curtailment at renewable energy power plants provided in this application constructs four-dimensional power curtailment risk assessment index data by collecting real-time data from four sources: the operating status of the target renewable energy power plant, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints. The index data undergoes outlier truncation and adaptive segmentation to obtain standardized index values. Subjective weights are dynamically calculated and smoothly updated based on multi-expert decision-making and temporal state deviation. Objective weights are dynamically calculated based on the temporal fluctuation characteristics of the indicators and the degree of nonlinear correlation between indicators. The ratio of subjective to objective weight fusion is adaptively determined according to the current operating scenario, and the final combined weight is obtained through game equilibrium solution. Then, nonlinear weighted aggregation is performed by combining the final combined weight with the coupling relationship between indicators to obtain the power curtailment probability at the current moment. Simultaneously, risk levels are dynamically classified based on historical risk quantiles, and the contribution of each indicator to the power curtailment probability is quantified. By employing the aforementioned synergistic technical means, key factors of power curtailment risk can be covered, abnormal data interference can be eliminated, and the impact of dimensional differences can be removed. This allows subjective weights to align with the inertia of power grid operation and reflect risk changes in real time, while objective weights can uncover data time-series patterns and nonlinear correlations. Combining weights with expert experience and data characteristics makes the calculation of power curtailment probability more closely aligned with the actual risk transmission mechanism. Ultimately, this achieves real-time, dynamic, and accurate assessment of power curtailment probability, effectively solving the technical problem of existing schemes being unable to accurately and efficiently determine power curtailment probability, and achieving the technical effect of accurate and efficient power curtailment probability prediction. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart of one embodiment of the method for dynamically determining the probability of power curtailment at new energy power plants provided in this application; Figure 2 This is a flowchart illustrating one embodiment of the method for implementing the power curtailment probability assessment index system for new energy power plants provided in this application. Figure 3 This is a hardware structure block diagram of an electronic device for a method of dynamically determining the probability of power curtailment at a new energy power station, as provided in this application. Figure 4 This is a schematic diagram of the module structure of one embodiment of the device for dynamically determining the probability of power curtailment at a new energy power station provided in this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0031] In renewable energy power plants, the probability of power curtailment refers to the likelihood that, at the current moment / within a short future period, a renewable energy power plant will be subject to forced power generation restrictions by the dispatching agency and will be unable to fully connect to the grid due to the combined effects of multiple factors such as power plant output, grid constraints, and weather fluctuations. The value ranges from [0, 1]. The closer the probability of power curtailment is to 1, the higher the risk of power curtailment; the closer the probability of power curtailment is to 0, the lower the risk of power curtailment. In other words, the probability of power curtailment is a quantitative probability value of a renewable energy power plant experiencing a forced power curtailment event, calculated through dynamic weighting and multi-indicator fusion, taking into account the power plant's operating status, grid transmission and absorption capacity, and weather forecasts and fluctuations, at a given time t. The probability of power curtailment is a pre-emptive, dynamic, and predictive risk value, while the curtailment rate is a post-event, static, and statistical ratio. In this example, the post-event statistics are transformed into a pre-event dynamic predictive probability.

[0032] Based on this, this example constructs a four-dimensional index by collecting real-time data from four sources: station operation, power grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints. Standardized index values ​​are obtained through outlier truncation and adaptive dimensionless transformation. Subjective weights are then dynamically and smoothly updated based on multi-expert decision-making and time-series deviation, while objective weights are calculated by combining time-series fluctuations and nonlinear correlations. These weights are adaptively allocated according to the operating scenario and obtained through game theory equilibrium. Finally, the probability of power curtailment is obtained through nonlinear weighted aggregation, and the index contribution is dynamically graded and quantified based on historical quantiles. In other words, this approach enables multi-dimensional, real-time, and refined dynamic evaluation, effectively solving the problems of static lag, fixed weights, and insufficient accuracy in existing technologies, and significantly improving the accuracy and practicality of the evaluation.

[0033] Figure 1This is a flowchart of one embodiment of the method for dynamically determining the probability of power curtailment at renewable energy power plants provided in this application. Although this application provides method operation steps or device structures as shown in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or device based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure described in the embodiments and figures of this application. When the method or module structure is applied in actual devices or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0034] Specifically, such as Figure 1 As shown, the method for dynamically determining the probability of power curtailment at renewable energy power plants can include the following steps: Step 101: Collect real-time data from four sources for the target renewable energy power plant: operating status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and construct four-dimensional power curtailment risk assessment index data; During implementation, four types of real-time data from multiple sources are collected for the target renewable energy power plants: operational status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints. This data is used to construct a four-dimensional power curtailment risk assessment index. This can include: collecting real-time operational data, grid constraint data, meteorological forecast data, and spatiotemporal correlation data from the power plant monitoring system, grid dispatch system, meteorological platform, and regional cluster management system, respectively; cleaning, verifying, and completing the collected data; extracting quantitative features strongly correlated with power curtailment according to the four dimensions of power plant operation, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints to form secondary indicators; and labeling each indicator as a positive or negative risk indicator to complete the construction of the four-dimensional indicator system.

[0035] In other words, by collecting data from multiple system data sources, cleaning and verifying data, and splitting dimensions and labeling positive / negative indicators, reliable access to multi-source data and standardized construction of a four-dimensional indicator system can be achieved, thereby improving the comprehensiveness and accuracy of the evaluation basis and ensuring the stability and reliability of subsequent calculations.

[0036] For example, collecting four types of multi-source real-time data can include: 1) Station operation data: The station's operational data can be obtained from the station's SCADA system, power prediction system, and power generation management system. This operational data can include: real-time output, planned output, historical curtailment rate, power prediction deviation, unit availability status, and shutdown information.

[0037] 2) Power grid constraint data: Power grid constraint data can be obtained from the power grid dispatching system, EMS energy management system, and transmission section monitoring device. The power grid constraint data may include: power flow / capacity of the sending section, the penetration rate of new energy sources at nodes, measured load values, peak shaving margin, operating capacity of thermal power units, and maintenance plans.

[0038] 3) Meteorological fluctuation data: Meteorological fluctuation data can be obtained from weather radar, numerical weather prediction (NWP), wind towers / irradiance meters, and meteorological early warning platforms. This meteorological fluctuation data can include: wind speed / light intensity forecasts, meteorological warning levels, temperature / air pressure / humidity, and forecast error sequences.

[0039] 4) Spatiotemporal coupling constraint data: Spatiotemporal coupling constraint data can be obtained from regional new energy cluster monitoring systems, cross-regional dispatching and interaction systems, and geographic information GIS. Among them, spatiotemporal coupling constraint data can include: output correlation of surrounding stations, cross-regional cross-sectional transmission margin, difference in meteorological spatial distribution, and delay in dispatching instructions.

[0040] Furthermore, the collected multi-source real-time data is classified and cleaned to remove abnormal, missing, and timed-out data. Then, it is categorized according to four dimensions and key features are extracted to form primary indicators. Under each primary indicator, it is further divided into secondary indicators based on historical power curtailment causes, real-time status, and predicted trends. Positive / negative attribute labels are applied to the indicators to determine their correlation with power curtailment risk, thereby forming a standardized, quantifiable, and dynamically updatable four-dimensional power curtailment risk assessment indicator system.

[0041] The four-dimensional indicator system may include: 1) Power plant operation indicators, such as: historical curtailment rate, power prediction output coefficient, output prediction deviation rate, unit availability, and power plant generation efficiency; 2) Power grid constraints, such as: transmission section utilization rate, node renewable energy output penetration rate, node load demand, system peak-shaving resource sufficiency rate, thermal power unit operating rate, and transmission equipment maintenance status. 3) Meteorological fluctuation indicators, such as: weather warning level, wind and solar resource forecast intensity, weather forecast deviation rate, and short-term weather fluctuation rate; 4) Spatiotemporal coupling constraint indicators, such as: power output correlation coefficient of power station cluster, transmission margin of cross-regional power transmission section, geographical and meteorological spatial zoning deviation, dispatch instruction delay coefficient, and spatial transmission coefficient of new energy consumption.

[0042] Step 102: Perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values; Specifically, in the established evaluation index system, the larger the positive index value, the higher the risk of power rationing; the larger the negative index value, the lower the risk of power rationing. Through dimensionless processing, indicators with different dimensions and properties can be normalized to the [0, 1] interval, facilitating comprehensive comparison and calculation.

[0043] Specifically, adaptive piecewise dimensionless transformation and outlier truncation are performed on the indicator, and the indicator is normalized to [0,1] using the following formula: Positive indicators:

[0044] Contrarian Indicators:

[0045] in, This is the outlier cutoff coefficient. The standard deviation of the indicator. Let be the original value of the i-th indicator at time j. The value is the dimensionless value. This is the historical minimum value of the indicator. This represents the historical maximum value of the indicator.

[0046] Step 103: Based on multi-expert decision-making and time-series state deviation, dynamically calculate the standardized index values ​​and smoothly update the subjective weights; Step 104: Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, dynamically calculate the objective weights of the standardized indicator values; Step 105: Adaptively determine the fusion ratio of subjective weights and objective weights based on the current operating scenario, and obtain the final combined weights through game equilibrium solution; Step 106: Perform nonlinear weighted aggregation based on the coupling relationship between indicators to calculate the power curtailment probability at the current time. The power curtailment probability at the current time is used to dynamically classify risk levels according to historical risk quantiles and quantify the contribution of each indicator to the power curtailment probability.

[0047] In practical implementation, step 103 above, based on multi-expert decision-making and time-series state deviation, dynamically calculates the standardized index value and smoothly updates the subjective weights, which may include: S1: Based on the optimal and worst indicators determined by multi-expert decision-making, the static subjective weights are obtained by solving. Specifically, we can obtain the importance vector of the optimal indicator relative to other indicators, and the importance vector of other indicators relative to the worst indicator, for the current experts; we can then establish an expert consensus optimization model, by constructing optimization objectives and constraints, to ensure that all experts' judgments are most consistent and that the bias is minimized.

[0048] in, This is the total deviation value. For the number of experts, For the number of indicators, The optimal index selected for the m-th expert. The worst-case indicator selected for the m-th expert. Let represent the importance of the optimal indicator relative to indicator i. The importance of the worst-case indicator relative to indicator i. The static subjective weight of index i, The static subjective weight of the optimal indicator selected for the m-th expert. The static subjective weight of the worst-case indicator selected by the m-th expert. Solving the aforementioned expert consensus model yields a static subjective weight vector:

[0049] in, This is a static subjective weight vector. The static subjective weight of indicator 1, The static subjective weight of indicator 2, Let n be the static subjective weight of the indicator n.

[0050] S2: Calculate the time-series sensitivity factor based on the degree of deviation between the real-time value and the historical average of the indicator; For example, the timing sensitivity factor can be calculated using the following formula:

[0051] in, Let i be the time-series sensitivity factor of index i at time t. Let be the real-time value of index i at time t. Let i be the historical mean of the index. The historical standard deviation of index i; S3: Calculate the time-series smoothing transmission coefficient based on the magnitude of changes in indicators at adjacent time points; For example, the time-series smoothing propagation coefficient can be calculated using the following formula:

[0052] in, For time-series smoothing conduction coefficient, For smoothing coefficients, Let be the real-time value of index i at time t. The real-time value of index i at time t is the value of index i at the time preceding time t. S4: The static subjective weight, time-series sensitive factor, and smoothing transmission coefficient are fused together, and the dynamic subjective weight is dynamically calculated and smoothly updated.

[0053] For example, dynamic subjective weights can be calculated using the following formula:

[0054] in, Let i be the dynamic subjective weight of index i at time t. Let be the static subjective weight of index i at time t.

[0055] In other words, by solving the multi-expert importance vector and consistency optimization model, the scientific integration of the experience of multiple experts is achieved, reducing single subjective biases and improving the rationality and consistency of static weights. By amplifying the impact of abnormal states through time-series sensitive factors and ensuring continuous weight transition through time-series smoothing transmission coefficients, the dynamic subjective weights are made more consistent with the actual operation of the power grid, significantly enhancing the model's adaptability to various scenarios. Through the fusion calculation of static subjective weights, time-series sensitive factors, and time-series smoothing transmission coefficients, subjective weights are dynamically adjusted according to the operating state and maintain a smooth transition, avoiding abrupt weight changes, thereby improving the stability and timeliness of the evaluation results.

[0056] In practical implementation, based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, the objective weights of the standardized indicator values ​​are dynamically calculated, which may include: S1: Calculate the time drift entropy using the following formula:

[0057] in, For temporal drift entropy, The time window length, Let represent the time series proportion of index i at time t. To prevent zero smoothing factor; S2: Calculate the conflict coefficient using the following formula:

[0058] in, The conflict coefficient is used to characterize the degree of independence between indicators. The user quantifies the nonlinear relationship between the mutual information of indicator i and indicator j. S3: Based on the time-series drift value and conflict coefficient, the objective weight is dynamically calculated according to the following formula:

[0059] in, The objective weight of index i is calculated dynamically.

[0060] When adaptively determining the fusion ratio of subjective and objective weights based on the current operating scenario, and obtaining the final combined weights through game equilibrium solutions, the combined weights can be calculated using the following formula:

[0061] in, For the final combined weights, For the blending ratio, Subjective weighting, For objective weighting; The aforementioned current operating scenarios include at least one of the following: routine scenarios, extreme weather scenarios, power grid maintenance scenarios, and peak load scenarios.

[0062] In practical implementation, the probability of power curtailment at the current moment is calculated by nonlinear weighted aggregation based on the coupling relationship between indicators. The probability of power curtailment can be calculated using the following formula:

[0063] in, Let be the probability of power outage at time t. To characterize the fuzzy measure of the interaction and coupling between indicators, For the final combined weights, Let i be the standardized value of index i.

[0064] That is, by introducing fuzzy measures to achieve nonlinear weighted aggregation, the coupling and interaction between indicators are fully considered, making the calculation of power rationing probability more in line with the actual risk transmission mechanism, which can significantly improve the accuracy and reliability of the assessment.

[0065] Given that most existing power curtailment probability calculations rely on historical data averages or fixed scenarios, they fail to adequately consider the real-time changes and temporal correlations of power curtailment influencing factors, resulting in assessments that cannot reflect short-term risk fluctuations. Secondly, the assessment dimensions are too singular, with indicators focusing primarily on single dimensions such as the power plant's own output characteristics or grid capacity, lacking a systematic and comprehensive consideration of multiple constraints including weather forecast accuracy, system peak-shaving resources, and load demand. Furthermore, the fixed indicator weights, typically given statically by expert experience or calculated once based on historical data, cannot adapt to the dynamic changes in the importance of various factors under different operating scenarios.

[0066] To address the shortcomings of existing assessment methods that fail to dynamically and multidimensionally integrate multi-source information such as power plant operation, real-time grid status, and meteorological fluctuations, resulting in static, lagging, and inaccurate curtailment probability assessments and increased operational risks for renewable energy power plants, this paper presents a real-time curtailment probability assessment method that reflects the temporal coupling and dynamic evolution of multiple factors. This provides a scientific basis for the intelligent operation of renewable energy projects. Specifically, to resolve the technical problems of existing renewable energy power plant curtailment probability assessment methods, such as static nature, single dimension, fixed weights, and poor model adaptability, this paper provides a method that can comprehensively assess curtailment probability in real-time, dynamically, and from multiple dimensions. This improves the accuracy, timeliness, and practicality of the assessment, providing more reliable risk warnings and decision support for renewable energy project operation.

[0067] Considering quantitative analysis, this example proposes a new energy power plant power curtailment probability assessment index system from another perspective, such as... Figure 2 As shown in Table 1, the probability assessment index system for renewable energy curtailment is based on the following: First-level indicators include power station operation, grid constraints, and meteorological fluctuations. Second-level indicators are further subdivided into more secondary indicators, taking into account historical performance, real-time status, and forecast information. Table 1

[0068] The aforementioned power station operation indicators reflect the station's technical performance, power output reliability, and forecast accuracy. The historical curtailment rate directly reflects the degree of curtailment, while the power forecast output coefficient and forecast deviation rate reflect the predictability and volatility risk of future power output.

[0069] The aforementioned grid constraint indicators reflect the power system's ability to absorb new energy sources. The utilization rate of transmission sections and the renewable energy output coefficient at nodes characterize the congestion risk of grid transmission channels and local nodes. Node load demand and peak-shaving resource sufficiency rate measure the absorption capacity from the perspective of system balance. Thermal power generation rate reflects the willingness and ability of conventional power sources to regulate.

[0070] The aforementioned meteorological fluctuation indicators reflect the uncertainty of the most fundamental natural factors affecting new energy output. Meteorological warning levels and resource forecast intensity are directly related to future output expectations; the historical meteorological forecast deviation rate measures the reliability of meteorological forecasts, and the greater the deviation, the higher the risk of actual output deviating from the forecast.

[0071] The above indicators cover multiple dimensions such as power stations, power grids, and meteorology, and can comprehensively capture the key driving factors that lead to power rationing. They have advantages such as being systematic, objective, and practical.

[0072] Therefore, in this example, the indicators are dimensionless. According to the above evaluation indicator system, the larger the positive indicator value, the higher the risk of power rationing; the larger the negative indicator value, the lower the risk of power rationing. By dimensionless processing, indicators with different dimensions and properties are normalized to the [0, 1] interval to facilitate comprehensive comparison and calculation.

[0073] Specifically, the dimensionless processing of positive indicators can be performed according to the following formula:

[0074] The dimensionless processing of contrarian indicators can be performed according to the following formula:

[0075] in, The value is the dimensionless value of the indicator. The original value of the indicator. This represents the highest value of the indicator for each time period. This represents the lowest value of the indicator for each time period.

[0076] In this embodiment, based on the constructed indicator system, an improved subjective and objective combined weighting method is first used to dynamically calculate the weight of each indicator at the evaluation time point, and then a comprehensive evaluation value of the power curtailment probability is obtained through weighted synthesis. This method includes: Time-sensitive modified multi-expert optimal and worst-case method: Based on the Analytic Hierarchy Process (AHP), the optimal and worst-case indicators are first determined, and then their relative importance is compared with other indicators, making it easier and faster to calculate subjective weight values. However, new energy projects are generally operated by multiple staff members, and existing optimal-worst methods can only handle the judgment of a single decision-maker. The improved multi-expert optimal-worst method in this example can include: S1: For One expert, there Evaluation indicators ,in, , They represent experts respectively. The selected optimal and worst indicators.

[0077] S2: Compare the optimal indicator selected by each expert with other indicators. Compared to other indicators The relative importance can be represented using a scale of 1 to 9, resulting in an evaluation vector. Where 1 represents and Equally important, 9 indicates compared to Extremely important.

[0078] S3: The worst indicator selected by each expert Compared to other indicators The relative importance is represented by a scale of 1 to 9, resulting in an evaluation vector. Where 1 represents and Equally unimportant, 9 represents compared to Extremes are not important.

[0079] S4: Let the optimal subjective weight vector be... The objective function and constraints of the optimization problem are as follows:

[0080] in, For experts Consistency deviation, for The weight, for The weight, for Subjective weighting.

[0081] The above is the BWM without considering time attributes, but the importance of factors affecting the risk of power curtailment from renewable energy sources changes dynamically over time. For example, during extreme weather warnings, the weight of meteorological indicators should be significantly increased; during grid maintenance, the weight of grid constraint indicators will increase. Based on this, a time-series coefficient is introduced in this example to correct the static weights.

[0082] S5: The time-series sensitivity factor of the indicator can be calculated using the following formula. Used to characterize indicators The greater the deviation of the indicator from historical norms at time t, the more abnormal the indicator is, and its contribution to the current risk of power rationing should be emphasized.

[0083] in, As an indicator The historical long-term standardized mean, As an indicator The standard deviation of historical data.

[0084] S6: The time lag propagation coefficient can be calculated using the following formula. This is used to characterize the degree of inheritance of the current weight from the previous weight, achieving horizontal 24-hour time-series coupling, thereby avoiding drastic changes in weights due to short-term data fluctuations, making the evaluation results more stable and consistent with the inertial characteristics of power system operation.

[0085] Where e is a constant, the smaller the change in the index between adjacent time points, the better. The closer a value is to 1, the smaller the change in weight, and the greater the change in the indicator between adjacent time points. The closer it gets to 0, the greater the change in weight.

[0086] S7: Calculate the final dynamic subjective weight value at time t using the following formula:

[0087] in, The subjective weight value of the indicator considering time-series sensitivity at time t.

[0088] Considering that using standard deviation to measure indicator variability is susceptible to extreme or overly concentrated values, leading to distorted indicator weights, this example uses time-series drift entropy instead of standard deviation to reflect the impact of time-series correlations. Specifically, this can include: S1: Data standardization. That is, standardize the indicator values ​​according to the above method.

[0089] S2: Calculate volatility and conflict coefficients: Existing methods use standard deviation to measure variability, but standard deviation cannot capture the distribution and evolution of data over time. In this example, time-series information entropy is used instead of standard deviation:

[0090] in, Indicator at time t The percentage of values, As an indicator Information entropy This represents the number of points to be evaluated.

[0091]

[0092] in, Let be the correlation coefficient between time t and time t-1. represents the conflict coefficient at each point in time.

[0093] S3: Calculate information content and objective weights:

[0094] in, To evaluate the information content of the indicators. To evaluate the objective weights of the indicators.

[0095] Furthermore, in order to balance expert experience with data patterns and to dynamically adjust the fusion ratio, the dynamic fusion coefficient is calculated using the following formula in this example:

[0096] in, Indicator at time t fusion coefficient; Then, a dynamic combination weight that comprehensively considers time-series sensitivity, expert judgment, and the inherent patterns of the data is calculated:

[0097] in, For intermediate process variables, Indicator at time t The final weight.

[0098] After obtaining the dynamic weights and standardized values ​​of each indicator at each time point, a comprehensive assessment model for the probability of power curtailment can be constructed through linear weighted aggregation:

[0099] in, Let be the probability of power curtailment at the renewable energy power station at time t. The closer this value is to 1, the higher the risk of power curtailment at the power station under the combined effect of multiple factors; the closer it is to 0, the lower the risk. Indicator at time t The standardized value.

[0100] Based on the probability of power outages, and combined with historical projects and work experience, different levels of power outage probability and corresponding response strategies can be set, as shown in Table 2 below: Table 2

[0101] In the example above, the dynamic updating of weights and assessment results is achieved through time-series sensitivity factors and lag transmission coefficients, enabling more accurate capture of short-term risk fluctuations and enhancing the timeliness of the assessment. A three-dimensional indicator system covering power plants, power grids, and meteorology is constructed, comprehensively reflecting the sources of power curtailment risks and making the assessment more systematic. The consideration of the time-series dimension is strengthened, and the ratio of subjective to objective weights is adaptively adjusted through dynamic fusion coefficients, making the weighting more scientific and reasonable, overcoming the limitations of single weighting methods. Most of the data required by the model can be obtained from existing energy management systems, dispatching systems, and meteorological platforms. The process is clear and can be embedded into various new energy management platforms, providing real-time and quantitative risk data for operation management.

[0102] To verify the effectiveness of the model provided in this example, calculations and analyses were performed using data from a photovoltaic power station. The station's index data is shown in Table 3 below, and the data after standard processing is shown in Table 4 below. Table 3

[0103] Table 4

[0104] Based on the model established in this example, the weights of the indicators at each time point are calculated. For ease of display, the time points 0:00, 12:00, and 23:00 are selected for detailed display. Table 5 shows the indicator weights at 0:00, Table 6 shows the indicator weights at 12:00, and Table 7 shows the indicator weights at 23:00.

[0105] Table 5

[0106] Table 6

[0107] Table 7

[0108] As shown in Tables 5, 6, and 7 above, the weights of power transmission section utilization and meteorological warning levels increase significantly during the day, while automatically decreasing at night, perfectly aligning with time-sensitive correction. Furthermore, the weights transition smoothly between adjacent time periods, without abrupt changes or jumps, strictly adhering to the time-lag transmission coefficient, consistent with the grid's operational inertia. Based on this, the probability of power curtailment at each time period can be calculated as shown in Table 8 below: Table 8

[0109] As shown in Table 8 above, the overall risk level is low to medium at night; the risk level reaches medium to high between 11:00 and 12:00, which is completely consistent with the actual pattern of high power generation and curtailment during the day and low risk at night for photovoltaic power plants.

[0110] The methods and embodiments provided in the above-described embodiments of this application can be executed in a mobile terminal, computer terminal, or similar computing device. Taking operation on an electronic device as an example... Figure 3 This is a hardware structure block diagram of the electronic device used in the method for dynamically determining the probability of power curtailment at a new energy power station, as provided in this application. Figure 3 As shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (processors 02 may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 04 for storing data, and a transmission module 06 for communication functions. Those skilled in the art will understand that... Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, electronic device 10 may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0111] The memory 04 can be used to store software programs and modules for application software, such as the program instructions / modules corresponding to the dynamic determination method for power curtailment probability of new energy power plants in this embodiment of the application. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, thereby realizing the aforementioned application of the dynamic determination method for power curtailment probability of new energy power plants. The memory 04 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 04 may further include memory remotely located relative to the processor 02, and these remote memories can be connected to the electronic device 10 via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] The transmission module 06 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 10. In one example, the transmission module 06 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 06 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0113] At the software level, the aforementioned dynamic determination device for the probability of power curtailment at renewable energy power plants can be as follows: Figure 4 As shown, it includes: The data acquisition module 401 is used to collect real-time data from four sources: the operating status of the target new energy power station, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and to construct four-dimensional power curtailment risk assessment index data. Processing module 402 is used to perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values; The subjective determination module 403 is used to dynamically calculate the standardized index value and smoothly update the subjective weight based on multi-expert decision-making and time-series state deviation. The objective determination module 404 is used to dynamically calculate the objective weight of the standardized indicator value based on the time-series fluctuation characteristics of the indicator and the degree of nonlinear correlation between the indicators. The weight determination module 405 is used to adaptively determine the fusion ratio of subjective weight and objective weight according to the current running scenario, and then obtain the final combined weight by solving the game equilibrium based on the fusion ratio, subjective weight and objective weight. The calculation module 406 is used to perform nonlinear weighted aggregation based on the final combined weight and the coupling relationship between indicators to calculate the power curtailment probability at the current time. The power curtailment probability at the current time is used to dynamically classify the risk level according to the historical risk quantile and quantify the contribution of each indicator to the power curtailment probability.

[0114] In one implementation, the data acquisition module 401 can specifically acquire real-time operation data, power grid constraint data, meteorological forecast data, and spatiotemporal correlation data from the station monitoring system, power grid dispatching system, meteorological platform, and regional cluster management system, respectively; clean, verify, and complete the acquired data; extract quantitative features strongly correlated with power curtailment according to four dimensions: station operation, power grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, forming secondary indicators; label each indicator as a positive risk indicator or a negative risk indicator, and complete the construction of a four-dimensional indicator system.

[0115] In one implementation, the subjective determination module 403 can specifically obtain static subjective weights based on the optimal and worst indicators determined by multi-expert decision-making; calculate time-series sensitive factors based on the deviation between the real-time values ​​of the indicators and the historical averages; calculate time-series smoothing transmission coefficients based on the magnitude of changes in indicators at adjacent times; and fuse the static subjective weights, time-series sensitive factors, and smoothing transmission coefficients to dynamically calculate and smoothly update dynamic subjective weights.

[0116] In one implementation, the static subjective weights are obtained by solving for the optimal and worst indices determined by multi-expert decision-making, and may include: S1: Obtain the importance vector of the best indicator relative to other indicators and the importance vector of other indicators relative to the worst indicator for the current expert. S2: Establish an expert consensus model by constructing optimization objectives and constraints to ensure the most consistent judgments from all experts and minimize bias.

[0117] in, This is the total deviation value. For the number of experts, For the number of indicators, The optimal index selected for the m-th expert. The worst-case indicator selected for the m-th expert. Let represent the importance of the optimal indicator relative to indicator i. The importance of the worst-case indicator relative to indicator i. The static subjective weight of index i, The static subjective weight of the optimal indicator selected for the m-th expert. The static subjective weight of the worst-case indicator selected by the m-th expert. S3: Solve the expert consensus model to obtain the static subjective weight vector:

[0118] in, This is a static subjective weight vector. The static subjective weight of indicator 1, The static subjective weight of indicator 2, Let n be the static subjective weight of the indicator n.

[0119] In one implementation, the timing sensitivity factor is calculated according to the following formula:

[0120] in, Let i be the time-series sensitivity factor of index i at time t. Let be the real-time value of index i at time t. Let i be the historical mean of the index. The historical standard deviation of index i; Calculate the time-series smoothing propagation coefficient using the following formula:

[0121] in, For time-series smoothing conduction coefficient, For smoothing coefficients, Let be the real-time value of index i at time t. The real-time value of index i at time t is the value of index i at the time preceding time t. The dynamic subjective weight is calculated using the following formula:

[0122] in, Let i be the dynamic subjective weight of index i at time t. Let be the static subjective weight of index i at time t.

[0123] In one implementation, the temporal drift entropy is calculated according to the following formula:

[0124] in, For temporal drift entropy, The time window length, Let represent the time series proportion of index i at time t. To prevent zero smoothing factor; Calculate the conflict coefficient using the following formula:

[0125] in, The conflict coefficient is used to characterize the degree of independence between indicators. The user quantifies the nonlinear relationship between the mutual information of indicator i and indicator j. Based on the time-series drift value and the conflict coefficient, the objective weight is dynamically calculated according to the following formula:

[0126] in, The objective weight of index i is calculated dynamically.

[0127] In one implementation, the weight determination module 405 can specifically calculate the combined weights according to the following formula:

[0128] in, For the final combined weights, For the blending ratio, Subjective weighting, For objective weighting; The current operating scenario includes at least one of the following: normal scenario, extreme weather scenario, power grid maintenance scenario, and peak load scenario.

[0129] In one implementation, the calculation module 406 can calculate the power curtailment probability according to the following formula:

[0130] in, Let be the probability of power outage at time t. To characterize the fuzzy measure of the interaction and coupling between indicators, For the final combined weights, Let i be the standardized value of index i.

[0131] This application also provides a specific implementation of an electronic device capable of implementing all steps in the dynamic determination method for power curtailment probability of new energy power plants in the above embodiments. The electronic device specifically includes: a processor, a memory, a communication interface, and a bus; wherein the processor, memory, and communication interface communicate with each other via the bus; the processor is used to call a computer program in the memory, and when the processor executes the computer program, it implements all steps in the dynamic determination method for power curtailment probability of new energy power plants in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step 1: Collect real-time data from four sources for the target renewable energy power plant: operating status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and construct four-dimensional power curtailment risk assessment index data; Step 2: Perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values; Step 3: Based on multi-expert decision-making and time-series state deviation, dynamically calculate the standardized index values ​​and smoothly update the subjective weights; Step 4: Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, dynamically calculate the objective weights of the standardized indicator values; Step 5: Adaptively determine the fusion ratio of subjective weights and objective weights based on the current operating scenario, and then obtain the final combined weights by solving the game equilibrium based on the fusion ratio, subjective weights, and objective weights. Step 6: Perform nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators to calculate the power curtailment probability at the current moment. The power curtailment probability at the current moment is used to dynamically classify risk levels based on historical risk quantiles and quantify the contribution of each indicator to the power curtailment probability.

[0132] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the dynamic determination method for power curtailment probability of new energy power plants in the above embodiments. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements all steps of the dynamic determination method for power curtailment probability of new energy power plants in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step 1: Collect real-time data from four sources for the target renewable energy power plant: operating status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and construct four-dimensional power curtailment risk assessment index data; Step 2: Perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values; Step 3: Based on multi-expert decision-making and time-series state deviation, dynamically calculate the standardized index values ​​and smoothly update the subjective weights; Step 4: Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, dynamically calculate the objective weights of the standardized indicator values; Step 5: Adaptively determine the fusion ratio of subjective weights and objective weights based on the current operating scenario, and then obtain the final combined weights by solving the game equilibrium based on the fusion ratio, subjective weights, and objective weights. Step 6: Perform nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators to calculate the power curtailment probability at the current moment. The power curtailment probability at the current moment is used to dynamically classify risk levels based on historical risk quantiles and quantify the contribution of each indicator to the power curtailment probability.

[0133] As described above, this application embodiment constructs four-dimensional power curtailment risk assessment index data by collecting four types of multi-source real-time data: the operating status of the target new energy power station, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints. Outlier truncation and adaptive segmentation of the index data are performed to obtain standardized index values. Subjective weights are dynamically calculated and smoothly updated based on multi-expert decision-making and time-series state deviation. Objective weights are dynamically calculated based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between indicators. The ratio of subjective to objective weight fusion is adaptively determined according to the current operating scenario, and the final combined weight is obtained through game equilibrium solution. Then, nonlinear weighted aggregation is performed by combining the final combined weight with the coupling relationship between indicators to obtain the power curtailment probability at the current moment. Simultaneously, risk levels are dynamically classified based on historical risk quantiles, and the contribution of each indicator to the power curtailment probability is quantified. By employing the aforementioned synergistic technical means, key factors of power curtailment risk can be covered, abnormal data interference can be eliminated, and the impact of dimensional differences can be removed. This allows subjective weights to align with the inertia of power grid operation and reflect risk changes in real time, while objective weights can uncover data time-series patterns and nonlinear correlations. Combining weights with expert experience and data characteristics makes the calculation of power curtailment probability more closely aligned with the actual risk transmission mechanism. Ultimately, this achieves real-time, dynamic, and accurate assessment of power curtailment probability, effectively solving the technical problem of existing schemes being unable to accurately and efficiently determine power curtailment probability, and achieving the technical effect of accurate and efficient power curtailment probability prediction.

[0134] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The collection, use and processing of the relevant data shall comply with relevant laws, regulations and standards, and corresponding operation entry points shall be provided for users to choose to authorize or refuse.

[0135] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0136] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0137] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0138] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0139] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0140] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0141] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0146] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0147] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0148] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0150] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0151] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A method for dynamically determining a power curtailment probability of a new energy plant, characterized in that, The method includes: Collect real-time data from four sources—operation status, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints—for the target renewable energy power plants to construct a four-dimensional power curtailment risk assessment index. Outlier truncation and adaptive segmentation dimensionless processing were performed on the four-dimensional power curtailment risk assessment index data to obtain standardized index values. Based on multi-expert decision-making and time-series state deviation, the standardized index values ​​are dynamically calculated and the subjective weights are smoothly updated. Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, the objective weights of the standardized indicator values ​​are dynamically calculated. The fusion ratio of subjective and objective weights is adaptively determined based on the current operating scenario, and the final combined weights are obtained by solving the game equilibrium based on the fusion ratio, subjective weights, and objective weights. The probability of power curtailment at the current moment is calculated by nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators. The probability of power curtailment at the current moment is used to dynamically classify risk levels according to historical risk quantiles and quantify the contribution of each indicator to the probability of power curtailment.

2. The method of claim 1, wherein, The system collects real-time data from four sources: the operating status of the target renewable energy power plants, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints. This data is used to construct a four-dimensional power curtailment risk assessment index, including: Real-time operation data, power grid constraint data, meteorological forecast data, and spatiotemporal correlation data are collected from the station monitoring system, power grid dispatching system, meteorological platform, and regional cluster management system, respectively. The collected data is cleaned, verified, and completed. Based on four dimensions—station operation, power grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints—quantitative features strongly correlated with power curtailment are extracted to form secondary indicators. Each indicator is labeled as either a positive risk indicator or a negative risk indicator, thus completing the construction of a four-dimensional indicator system.

3. The method of claim 1, wherein, Based on multi-expert decision-making and time-series state deviation, the standardized index values ​​are dynamically calculated and subjective weights are smoothly updated, including: Based on the optimal and worst indicators determined by multi-expert decision-making, the static subjective weights are obtained. Calculate the time-series sensitivity factor based on the degree of deviation between the real-time value and the historical average of the indicator; Calculate the time-series smoothing transmission coefficient based on the magnitude of changes in indicators at adjacent time points; The static subjective weight, time-sensitive factor, and smoothing transmission coefficient are fused together, and the dynamic subjective weight is obtained by dynamically calculating and smoothly updating.

4. The method according to claim 3, characterized in that, Based on the optimal and worst-case indicators determined by multi-expert decision-making, the static subjective weights are obtained, including: Obtain the importance vector of the best indicator relative to other indicators for the current expert, and the importance vector of other indicators relative to the worst indicator. Establish an expert consensus model by constructing optimization objectives and constraints to ensure maximum consistency and minimum bias among all experts' judgments: in, This is the total deviation value. For the number of experts, For the number of indicators, The optimal index selected for the m-th expert. The worst-case indicator selected for the m-th expert. Let represent the importance of the optimal indicator relative to indicator i. The importance of the worst-case indicator relative to indicator i. The static subjective weight of index i, The static subjective weight of the optimal indicator selected for the m-th expert. The static subjective weight of the worst-case indicator selected by the m-th expert. Solving the aforementioned expert consensus model yields a static subjective weight vector: in, This is a static subjective weight vector. The static subjective weight of indicator 1, The static subjective weight of indicator 2, Let n be the static subjective weight of the indicator n.

5. The method according to claim 4, characterized in that, Based on the degree of deviation between the real-time value and the historical average of the indicator, a time-series sensitivity factor is calculated, including: Calculate the time-series sensitivity factor using the following formula: in, Let i be the time-series sensitivity factor of index i at time t. Let be the real-time value of index i at time t. Let i be the historical mean of the index. The historical standard deviation of index i; The temporal smoothing propagation coefficient is calculated based on the magnitude of changes in indicators at adjacent time points, including: Calculate the time-series smoothing propagation coefficient using the following formula: in, For time-series smoothing conduction coefficient, For smoothing coefficients, Let be the real-time value of index i at time t. The real-time value of index i at time t is the value of index i at the time preceding time t. The static subjective weights, time-series sensitive factors, and smoothing transmission coefficients are fused together to dynamically calculate and smoothly update the dynamic subjective weights, including: The dynamic subjective weight is calculated using the following formula: in, Let i be the dynamic subjective weight of index i at time t. Let be the static subjective weight of index i at time t.

6. The method according to claim 1, characterized in that, Based on the time-series fluctuation characteristics of the indicators and the degree of nonlinear correlation between the indicators, the objective weights of the standardized indicator values ​​are dynamically calculated, including: Calculate the time drift entropy using the following formula: in, For temporal drift entropy, The time window length, Let represent the time series proportion of index i at time t. To prevent zero smoothing factor; Calculate the conflict coefficient using the following formula: in, The conflict coefficient is used to characterize the degree of independence between indicators. The user quantifies the nonlinear relationship between the mutual information of indicator i and indicator j. Based on the time-series drift value and the conflict coefficient, the objective weight is dynamically calculated according to the following formula: in, The objective weight of index i is calculated dynamically.

7. The method according to claim 1, characterized in that, The fusion ratio of subjective and objective weights is adaptively determined based on the current operating scenario. Then, based on the fusion ratio, subjective weights, and objective weights, the final combined weights are obtained through game equilibrium solution, including: The combined weights are calculated using the following formula: in, For the final combined weights, For the blending ratio, Subjective weighting, For objective weighting; The current operating scenario includes at least one of the following: normal scenario, extreme weather scenario, power grid maintenance scenario, and peak load scenario.

8. The method according to claim 1, characterized in that, Based on the final combined weights and the coupling relationship between indicators, a nonlinear weighted aggregation is performed to calculate the probability of power curtailment at the current moment, including: The probability of power outages is calculated using the following formula: in, Let be the probability of power outage at time t. To characterize the fuzzy measure of the interaction and coupling between indicators, For the final combined weights, Let i be the standardized value of index i.

9. A device for dynamically determining the probability of power curtailment at a new energy power station, characterized in that, include: The data acquisition module is used to collect real-time data from four sources: the operating status of the target new energy power station, grid constraints, meteorological fluctuations, and spatiotemporal coupling constraints, and to construct four-dimensional power curtailment risk assessment index data. The processing module is used to perform outlier truncation and adaptive segmentation dimensionless processing on the four-dimensional power curtailment risk assessment index data to obtain standardized index values. The subjective determination module is used to dynamically calculate the standardized index values ​​and smoothly update the subjective weights based on multi-expert decision-making and time-series state deviation. An objective determination module is used to dynamically calculate the objective weight of the standardized indicator value based on the time-series fluctuation characteristics of the indicator and the degree of nonlinear correlation between the indicators; The weight determination module is used to adaptively determine the fusion ratio of subjective weights and objective weights according to the current operating scenario, and then obtain the final combined weights by solving the game equilibrium based on the fusion ratio, subjective weights and objective weights. The calculation module is used to perform nonlinear weighted aggregation based on the final combined weights and the coupling relationship between indicators to calculate the power curtailment probability at the current moment. The power curtailment probability at the current moment is used to dynamically classify risk levels according to historical risk quantiles and quantify the contribution of each indicator to the power curtailment probability.

10. An electronic device comprising a processor and a memory for storing processor-executable instructions, characterized in that, When the processor executes the instructions, it implements the steps of the method according to any one of claims 1 to 8.

Images