A power station derating determination method, electronic equipment and readable storage medium

Abstract

The application discloses a power station de-rating power limiting judgment method, an electronic device and a readable storage medium, relates to the technical field of power station management, and comprises the following steps: acquiring regional power generation efficiencies of a target power station in each target period, and acquiring a historical power generation efficiency set of the target power station in historical days before a current day; determining a reference power generation power range of the target power station in each target period according to the regional power generation efficiencies in each target period and the historical power generation efficiency set; determining each de-rating period according to an actual power generation power set of the target power station in each target period in the current day and the reference power generation power range; performing time sequence feature analysis on each de-rating period to obtain at least one de-rating feature score of the target power station in the current day; each de-rating feature score at least comprises a power stability score, a boundary mutation intensity score, a temperature coupling score and / or a time sequence predictability score; and determining whether there is artificial de-rating power limiting in the current day of the target power station according to each de-rating feature score.

Description

Technical Field

[0001] This application relates to the field of power plant management technology, and in particular to a method for determining derating and curtailment of power plants, an electronic device, and a readable storage medium. Background Technology

[0002] With the rapid development of distributed energy, residential photovoltaic power stations have become an important part of energy supply. In actual operation and maintenance, there is often a deviation between the actual power generation of a photovoltaic power station and the expected power generation. The reasons for the power generation loss are complex and diverse, mainly including natural factors (such as inverter derating caused by high ambient temperature) and human factors (such as peak shaving and curtailment implemented to ensure the stable operation of the power grid).

[0003] Currently, the monitoring and analysis of power generation loss is typically achieved by real-time collection of operating data such as the inverter's internal temperature, voltage, and current. However, this method can only identify derating caused by natural factors, and its accuracy and robustness in determining derating and curtailment are relatively poor. Summary of the Invention

[0004] The main objective of this application is to provide a method, electronic device, and readable storage medium for determining derating and curtailment of power plants, aiming to improve the accuracy and robustness of determining derating and curtailment of power plants.

[0005] This application provides a method for determining derating and curtailment of power plants, the method comprising:

[0006] Obtain the regional power generation efficiency of the area where the target power station is located during each target time period, and obtain the historical power generation efficiency set of the target power station for each target time period for the historical days before the current day. Based on the regional power generation efficiency and historical power generation efficiency set for each target time period, determine the baseline power generation range of the target power plant for each target time period; Based on the actual power generation set and benchmark power generation range of the target power plant on the current day in each of the target time periods, each derated period is selected from each of the target time periods; A time-series feature analysis is performed on each of the aforementioned depreciation periods to obtain at least one depreciation feature score for the target power plant on the current day; each of the aforementioned depreciation feature scores includes at least a power stability score, a boundary abrupt change intensity score, a temperature coupling score, and / or a time-series predictability score; Based on the scores of each of the aforementioned reduction characteristics, it is determined whether the target power station currently experiences artificial reductions or power rationing.

[0007] In one embodiment, the step of determining the reference power generation range of the target power plant in each target time period based on the regional power generation efficiency and historical power generation efficiency set for each target time period includes: Based on the regional power generation efficiency and historical power generation efficiency set for each target time period, determine the power generation efficiency deviation value and the standard deviation value of the power generation efficiency deviation for each target time period of the target power plant; The power generation efficiency deviation value for each target time period is calculated and the sum of the regional power generation efficiency for each target time period is obtained to obtain the baseline power generation efficiency of the target power plant in each target time period. The baseline power generation efficiency of the target power plant in each target time period is calculated as a product of the baseline power generation efficiency and the installed capacity of the target power plant in each target time period. Based on the standard deviation of power generation efficiency during each target time period and the installed capacity, the power fluctuation range of the target power plant during each target time period is calculated. For any target time period, the sum of the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the upper limit of the power range, and the difference between the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the lower limit of the power range, so as to generate the reference power generation range of the target time period.

[0008] In one embodiment, the step of determining the power generation efficiency deviation and standard deviation of the target power plant in each target time period based on the regional power generation efficiency and historical power generation efficiency set for each target time period includes: For any target time period, calculate the difference between each historical power generation efficiency in the historical power generation efficiency set of the target time period and the regional power generation efficiency of the target time period to obtain the deviation value of each sub-power generation efficiency; The average value of each of the sub-power generation efficiency deviation values ​​is taken as the power generation efficiency deviation value of the target power plant in the target time period; The standard deviation of the power generation efficiency of the target power plant in the target period is calculated based on the average value of the deviation values ​​of each sub-power generation efficiency and the historical power generation efficiency of each historical power generation efficiency in the target period.

[0009] In one embodiment, the step of selecting each derated period from each target period based on the actual power generation set of the target power plant on the current day for each target period and the baseline power generation range for each target period includes: For any of the target time periods, calculate the difference between each actual power generation in the actual power generation set of the target time period and the baseline power generation and the lower limit of the power range of the reference power generation range of the target time period, respectively, to obtain the power generation baseline residual value set and the power generation lower limit residual value set of the target time period; If the average value of the baseline residual value set of power generation during the target period is greater than the preset baseline residual threshold corresponding to the target period, and / or the average value of the lower limit residual value set of power generation during the target period is greater than the preset lower limit residual threshold corresponding to the target period, then the target period is designated as the period of deduction.

[0010] In one embodiment, where each of the depreciation characteristic scores includes a power stability score, the step of performing time-series characteristic analysis on each of the depreciation periods to obtain at least one depreciation characteristic score for the target power plant on the current day includes: The mean value of the baseline residual of power generation for each of the aforementioned derated periods is determined based on the actual power generation set and the baseline power generation range of the reference power generation range. Calculate the ratio between the mean of the baseline residual of power generation for each of the aforementioned derated periods and the baseline power generation for each of the aforementioned derated periods within their respective reference power generation ranges, and obtain each first ratio; Calculate the ratio between the actual power generation of each power generation in the actual power generation set of each of the aforementioned derated periods and the installed capacity of the target power plant to obtain each second ratio; The ratio between the average of the first ratios and the average of the second ratios is taken as the power stability score of the target power plant for the current day.

[0011] In one embodiment, when each of the depreciation feature scores includes a boundary abrupt change intensity score, the step of performing time-series feature analysis on each of the depreciation periods to obtain at least one depreciation feature score for the target power plant on the current day includes: Based on each of the aforementioned reduction periods, determine the start and end times of the current day's reduction for the target power plant; Obtain the first set of residual power generation values ​​within a first preset time period before the start time of the derating, and the second set of residual power generation values ​​within a second preset time period after the start time of the derating; obtain the third set of residual power generation values ​​within a third preset time period before the end time of the derating, and the fourth set of residual power generation values ​​within a fourth preset time period after the end time of the derating. Based on the first set of residual power generation values ​​and the second set of residual power generation values, the standard deviation of the initial boundary residual is determined, and based on the third set of residual power generation values ​​and the fourth set of residual power generation values, the standard deviation of the final boundary residual is determined. The maximum value between the standard deviation of the initial boundary residual and the standard deviation of the final boundary residual is taken as the boundary fluctuation value for the day. The ratio between the preset normal boundary fluctuation value and the daily boundary fluctuation value is used as the boundary mutation intensity score of the target power plant on the current day.

[0012] In one embodiment, where each of the derating characteristic scores includes a temperature coupling score, the step of performing time-series characteristic analysis on each of the derating periods to obtain at least one derating characteristic score for the target power plant on the current day includes: Obtain the actual power sequence and actual temperature sequence of the target power plant for each of the aforementioned derated periods on the current day; The actual power sequence and actual temperature sequence for each of the derating periods are differentially processed to obtain the actual power differential sequence and actual temperature differential sequence for each of the derating periods. Based on the actual power difference sequence and actual temperature difference sequence for each of the aforementioned derating periods, the actual correlation coefficient between power and temperature for each of the aforementioned derating periods is determined; Calculate the ratio between the actual correlation coefficient of each derating period and the preset normal correlation coefficient between power and temperature for each derating period to obtain the temperature coupling score for each derating period. Based on the temperature coupling scores for each of the aforementioned reduction periods, the temperature coupling score for the target power plant on the current day is determined.

[0013] In one embodiment, where each of the depreciation feature scores includes a time-predictable score, the step of performing time-series feature analysis on each of the depreciation periods to obtain at least one depreciation feature score for the target power plant on the current day includes: For any of the aforementioned reduction periods, the reduction period is divided into a first sub-period and a second sub-period; Based on the actual power sequence of the target power plant on the current day in the first sub-period, the training model is iteratively optimized to generate a power prediction model; The power generation power of the target power plant at each time point in the second sub-period is predicted using the power prediction model to obtain the predicted power sequence; Calculate the mean power deviation between the predicted power sequence and the actual power sequence of the second sub-period; The ratio between the mean power deviation and the mean of the actual power sequence in the second sub-period is calculated to obtain the temporal predictability score of the depreciation period; Based on the predictable time series scores for each of the aforementioned reduction periods, the predictable time series score for the target power plant on the current day is determined.

[0014] In one embodiment, the step of determining whether the target power station has experienced artificial power rationing on the current day based on the scores of each of the rationing characteristics includes: The scores of each of the reduction features are normalized to obtain the normalized scores of each reduction feature. If the average score of each reduction feature after normalization is less than a preset threshold, it is determined that the target power station is experiencing artificial reduction in power consumption on the current day.

[0015] In one embodiment, the step of obtaining the regional power generation efficiency of the area where the target power plant is located during each target time period includes: Obtain the operating data of each normally operating power station in the area where the target power station is located during each target time period; Based on the operating data of each normally operating power station in each of the target time periods, the normalized power generation efficiency of each normally operating power station in each of the target time periods is determined; Based on the normalized power generation efficiency of each of the normally operating power plants in each of the target time periods, the regional power generation efficiency of the area where the target power plant is located in each of the target time periods is determined.

[0016] In addition, to achieve the above objectives, this application also provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power plant rationing determination method as described above.

[0017] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the power plant rationing determination method as described above.

[0018] This application provides a method for determining power rationing and curtailment of a power plant, comprising: obtaining the regional power generation efficiency of the area where the target power plant is located during each target time period, and obtaining the historical power generation efficiency set of the target power plant for each target time period on historical days prior to the current day; determining the baseline power generation range of the target power plant during each target time period based on the regional power generation efficiency and the historical power generation efficiency set for each target time period; selecting each rationing period from each target time period based on the actual power generation set and the baseline power generation range of the target power plant on the current day during each target time period; performing time series feature analysis on each rationing period to obtain at least one rationing feature score for the target power plant on the current day; each rationing feature score includes at least a power stability score, a boundary abrupt change intensity score, a temperature coupling score, and / or a time series predictability score; and determining whether there is artificial rationing and curtailment of the target power plant on the current day based on each rationing feature score.

[0019] Therefore, the technical solution provided in this application constructs a benchmark power generation range that objectively reflects the true power generation capacity of the power station by utilizing the regional power generation efficiency of the area where the target power station is located and the historical power generation efficiency of the target power station itself on historical days. By comparing the actual power generation of the target power station on the current day with this benchmark power generation range, the derating period in which the actual power generation deviates abnormally can be accurately located, and the time window that needs to be analyzed can be clearly identified. Compared with the existing technology that only focuses on the power station's own data or only focuses on natural factors, the technical solution provided in this application can reduce misjudgments caused by common factors such as weather changes and ambient temperature changes, thereby improving the accuracy of identifying derating periods.

[0020] Furthermore, the technical solution provided in this application, after identifying the derating period, does not simply make a derating determination, but performs time-series characteristic analysis on the derating period to calculate derating characteristic scores from multiple dimensions such as power stability, boundary change intensity, temperature coupling relationship, and time-series predictability. This clearly distinguishes between two different types of derating caused by human-induced power curtailment and derating caused by natural factors, effectively improving the robustness and accuracy of derating cause determination.

[0021] In summary, the technical solution provided in this application can improve the accuracy and robustness of determining power rationing and curtailment for power plants. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the power plant derating and curtailment determination method provided in the first embodiment of this application; Figure 2 A flowchart illustrating the power plant derating and curtailment determination method provided in the second embodiment of this application; Figure 3 A flowchart illustrating the power plant derating and curtailment determination method provided in the third embodiment of this application; Figure 4 A flowchart illustrating the power plant derating and curtailment determination method provided in the fourth embodiment of this application; Figure 5 A flowchart illustrating the power plant derating and curtailment determination method provided in the fifth embodiment of this application; Figure 6 This is a schematic diagram of the hardware operating environment involved in the embodiments of this application.

[0025] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0026] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0027] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0028] With the rapid development of distributed energy, residential photovoltaic power stations have become an important part of energy supply. In actual operation and maintenance, there is often a deviation between the actual power generation of a photovoltaic power station and the expected power generation. The reasons for the power generation loss are complex and diverse, mainly including natural factors (such as inverter derating caused by high ambient temperature) and human factors (such as peak shaving and curtailment implemented to ensure the stable operation of the power grid).

[0029] Currently, the monitoring and analysis of power generation loss is typically achieved by real-time collection of operating data such as the inverter's internal temperature, voltage, and current. However, this method can only identify derating caused by natural factors, and its accuracy and robustness in determining derating and curtailment are relatively poor.

[0030] Based on this, this application provides a method for determining power rationing and curtailment of a power plant, comprising: obtaining the regional power generation efficiency of the area where the target power plant is located in each target time period, and obtaining the historical power generation efficiency set of the target power plant in each target time period for historical days prior to the current day; determining the baseline power generation range of the target power plant in each target time period based on the regional power generation efficiency and the historical power generation efficiency set for each target time period; selecting each rationing period from each target time period based on the actual power generation set and the baseline power generation range of the target power plant in each target time period on the current day; performing time series feature analysis on each rationing period to obtain at least one rationing feature score for the target power plant on the current day; each rationing feature score includes at least a power stability score, a boundary abrupt change intensity score, a temperature coupling score, and / or a time series predictability score; and determining whether there is artificial rationing and curtailment of the target power plant on the current day based on each rationing feature score.

[0031] Therefore, the technical solution provided in this application constructs a benchmark power generation range that objectively reflects the true power generation capacity of the power station by utilizing the regional power generation efficiency of the area where the target power station is located and the historical power generation efficiency of the target power station itself on historical days. By comparing the actual power generation of the target power station on the current day with this benchmark power generation range, the derating period in which the actual power generation deviates abnormally can be accurately located, and the time window that needs to be analyzed can be clearly identified. Compared with the existing technology that only focuses on the power station's own data or only focuses on natural factors, the technical solution provided in this application can reduce misjudgments caused by common factors such as weather changes and ambient temperature changes, thereby improving the accuracy of identifying derating periods.

[0032] Furthermore, the technical solution provided in this application, after identifying the derating period, does not simply make a derating determination, but performs time-series characteristic analysis on the derating period to calculate derating characteristic scores from multiple dimensions such as power stability, boundary change intensity, temperature coupling relationship, and time-series predictability. This clearly distinguishes between two different types of derating caused by human-induced power curtailment and derating caused by natural factors, effectively improving the robustness and accuracy of derating cause determination.

[0033] In summary, the technical solution provided in this application can improve the accuracy and robustness of determining power rationing and curtailment for power plants.

[0034] The execution subject of the power plant rationing determination method in this application can be an electronic device with data processing, network communication and program operation functions. For example, it can be a control system or control circuit that can realize the above functions, or it can be the power plant itself. This embodiment does not specifically limit it.

[0035] The following description uses an electronic device as the execution subject to illustrate the various embodiments.

[0036] This application proposes a method for determining derating and curtailment of power plants according to a first embodiment. Please refer to [link / reference]. Figure 1 The method for determining power plant rationing may include steps S10 to S50: Step S10: Obtain the regional power generation efficiency of the area where the target power station is located during each target time period, and obtain the historical power generation efficiency set of the target power station for each target time period for the historical days before the current day. It should be noted that the target power station refers to the residential photovoltaic power station to be tested for whether it has been subject to artificial throttling and curtailment. The target power station's location refers to the geographical area where it is situated, which can be defined based on grid topology, geographical location, or administrative region, such as the same distribution area, the same feeder, or a group of power stations within a radius of several kilometers. The target time period refers to a continuous time unit obtained by dividing the day's power generation time into fixed time intervals, such as every 15 minutes, every 30 minutes, or every hour. Regional power generation efficiency is an indicator used to reflect the overall power generation level of normally operating power stations within a region. It is usually expressed as a statistical value of normalized efficiency (i.e., the ratio between actual power generation and the installed capacity of the power station), used to eliminate the impact of common factors such as weather changes and ambient temperature variations on power generation. Historical days refer to several days prior to the current date, typically selecting normal operating days with no faults and no power outages recorded by the target power station in the past. The historical power generation efficiency set is the data set consisting of the power generation efficiency of the target power station at each sampling time within the target time period within the historical days.

[0037] In one feasible implementation, the step of obtaining the regional power generation efficiency of the area where the target power plant is located during each target time period may include steps S11-S13: Step S11: Obtain the operating data of each normally operating power station in the area where the target power station is located during each target time period; It should be noted that a normally operating power station refers to a power station within the area that is in normal working condition, without fault alarms, and without missing or abnormal data. Operating data may include, but is not limited to, the power station's real-time power generation, installed capacity, current, and / or voltage, etc., but this embodiment does not impose specific limitations on these.

[0038] When acquiring the operating data of each normally operating power station in the target power station area during each target time period, one can first acquire the operating data of all power stations in the target power station area during each target time period; then, through data cleaning, the operating data of power stations that are abnormal due to faults, shutdowns, or missing data are removed, thus obtaining the operating data of all normally operating power stations during each target time period.

[0039] Step S12: Based on the operating data of each normally operating power station in each target time period, determine the normalized power generation efficiency of each normally operating power station in each target time period. It should be noted that the normalized power generation efficiency is the ratio of the actual power generation of a power plant to its installed capacity during a target time period. When determining the normalized power generation efficiency of each normally operating power plant in each target time period based on its operating data, for each sampling moment within each target time period, the ratio between the actual power generation of the power plant and its installed capacity at that sampling moment can be directly calculated to obtain the instantaneous normalized efficiency at that sampling moment. If there are multiple sampling moments within a time period, the average of the instantaneous normalized efficiencies at these sampling moments can be taken as the normalized power generation efficiency for that sampling period. Alternatively, for each target time period, the integral or average value of the actual power generation within that target time period can be calculated first, and then divided by the product of the power plant's installed capacity and the duration of the target time period to obtain the normalized power generation efficiency of the power plant in that target time period. This embodiment does not specifically limit the implementation method of step S12.

[0040] Step S13: Determine the regional power generation efficiency of the area where the target power station is located during each target time period based on the normalized power generation efficiency of each normally operating power station during each target time period.

[0041] When determining the regional power generation efficiency of the area where the target power station is located in each target time period based on the normalized power generation efficiency of each normally operating power station in each target time period, for each target time period, the median, average, or weighted average of the normalized power generation efficiency of all normally operating power stations in that target time period can be used as the regional power generation efficiency of the area where the target power station is located in that target time period. This embodiment does not make specific limitations on this.

[0042] In this implementation, firstly, normally operating power plants are screened to ensure the reliability of input data from the source, eliminating interference from faulty or abnormal equipment on the overall statistics. Then, normalization processing eliminates differences in installed capacity between power plants, enabling comparisons of power plants of different sizes on the same scale, laying the foundation for regional aggregation. Next, by aggregating the normalized efficiencies of each power plant, a regional power generation efficiency sequence that objectively and accurately reflects the overall power generation capacity of the target region at different times can be obtained. Therefore, this regional power generation efficiency sequence not only provides reliable regional reference data for establishing subsequent benchmark power generation ranges but also minimizes interference from regional common factors such as weather changes and ambient temperature variations, ensuring the accuracy of subsequent derating period identification and manual derating determination.

[0043] Step S20: Determine the baseline power generation range of the target power plant in each target time period based on the regional power generation efficiency and historical power generation efficiency set for each target time period. It should be noted that the benchmark power generation range is the reasonable power generation range that the target power station should achieve in each target period, calculated based on the regional power generation efficiency and the historical performance of the target power station.

[0044] In one feasible implementation, step S20 may include steps S21 to S25: Step S21: Based on the regional power generation efficiency and historical power generation efficiency set for each target time period, determine the power generation efficiency deviation value and the standard deviation value of the power generation efficiency deviation of the target power plant for each target time period. It should be noted that the power generation efficiency deviation value is the statistical average difference between the historical power generation efficiency of the target power plant during a target period and the regional power generation efficiency during the same period. It is used to quantify the inherent characteristics of the target power plant relative to the overall regional power generation level during the target period. The standard deviation of the power generation efficiency deviation is a statistical measure of the dispersion of the historical power generation efficiency deviation value of the target power plant during a target period. It reflects the fluctuation range of the historical power generation characteristics of the target power plant relative to the regional benchmark during the target period.

[0045] When determining the power generation efficiency deviation and standard deviation of the target power plant in each target period based on the regional power generation efficiency and historical power generation efficiency set for each target period, for any target period, the difference between each historical power generation efficiency in the historical power generation efficiency set of the target period and the regional power generation efficiency of the target period is calculated to obtain the sub-power generation efficiency deviation value; the average value of each sub-power generation efficiency deviation value is taken as the power generation efficiency deviation value of the target power plant in the target period; based on the average value of each sub-power generation efficiency deviation value and each historical power generation efficiency in the historical power generation efficiency set of the target period, the standard deviation of the power generation efficiency of the target power plant in the target period is calculated.

[0046] Understandably, by calculating the sub-efficiency deviation value between each historical power generation efficiency and the corresponding regional power generation efficiency, the system accurately captures each individual fluctuation of the target power plant relative to the regional benchmark during that period. Then, the average of each sub-efficiency deviation value is used as the final power generation efficiency deviation value, effectively offsetting the impact of random fluctuations in a single historical data point. This objectively reflects the inherent efficiency difference of the target power plant relative to the overall regional efficiency, ensuring the stability and representativeness of the deviation value. Finally, based on the average of each sub-efficiency deviation value and the standard deviation of each historical power generation efficiency, the dispersion of this inherent difference is quantified to clearly define the normal fluctuation range of the target power plant's historical power generation characteristics. This not only avoids the random interference of a single data sample but also achieves accurate quantification of efficiency deviation-related parameters, providing accurate and reliable core foundational data for subsequent calculations of baseline power generation efficiency, power fluctuation amplitude, and benchmark power generation range. This ensures the accuracy and reliability of subsequent derating period identification and manual derating determination.

[0047] Step S22: Calculate the sum between the power generation efficiency deviation value of each target time period and the regional power generation efficiency of each target time period to obtain the baseline power generation efficiency of the target power plant in each target time period. It should be noted that the baseline power generation efficiency is the expected power generation efficiency that the target power station should achieve in a certain target period under the condition that no abnormal factors are affected, calculated by combining the overall power generation level of the region and the inherent characteristics of the target power station.

[0048] Step S23: Calculate the product between the baseline power generation efficiency and the installed capacity of the target power plant for each target time period to obtain the baseline power generation of the target power plant for each target time period. It should be noted that baseline power generation is the expected power output of the target power plant during a certain target period under the condition that no abnormal factors are present, obtained by converting baseline power generation efficiency into power dimension.

[0049] Step S24: Calculate the power fluctuation range of the target power plant in each target period based on the standard deviation of the power generation efficiency deviation and the installed capacity for each target period. It should be noted that the power fluctuation amplitude is the range of power fluctuation calculated based on the degree of fluctuation of historical power generation efficiency deviation (i.e., the standard deviation of power generation efficiency deviation).

[0050] When calculating the power fluctuation range of the target power plant in each target period based on the standard deviation of power generation efficiency and the installed capacity in each target period, the product of the installed capacity of a preset multiple (e.g., 2 times) and the standard deviation of power generation efficiency in each target period can be used as the power fluctuation range of the target power plant in each target period. The preset multiple can be a default value or can be flexibly set by the user according to the actual situation. This embodiment does not make specific limitations on this.

[0051] Step S25: For any target time period, the sum of the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the upper limit of the power range, and the difference between the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the lower limit of the power range, so as to generate the reference power generation range of the target time period.

[0052] This implementation method eliminates systematic deviations caused by the inherent characteristics of power plants through historical data statistics. By utilizing the standard deviation of power generation efficiency during the target period and the installed capacity of the target power plant, it provides sufficient tolerance for errors in the benchmark range, effectively avoiding misjudgments due to random fluctuations under normal operating conditions. Therefore, the final generated benchmark power generation range can accurately reflect the normal power generation capacity of the target power plant, thereby improving the accuracy of identifying periods of derated generation.

[0053] This embodiment does not specifically limit the implementation of step S20. For example, in other feasible implementations, a quantile regression model can be constructed using regional power generation efficiency, temperature, humidity, etc., as features, and the historical power generation of the target power station as a label; then, the model is trained to predict the 10th and 90th quantiles of the power generation of the target power station under given features, which are used as the lower and upper limits of the benchmark power range, respectively, to construct the benchmark power generation range.

[0054] Step S30: Based on the actual power generation set and benchmark power generation range of the target power plant in each target time period on the current day, select each derated time period from each target time period; It should be noted that the actual power generation set is the data set comprising the power generation efficiency of the target power plant at each moment during the target time period on the current day. The derated period is the target time period in which the actual power generation is significantly lower than the lower limit of the benchmark power generation range or the baseline power generation.

[0055] In one feasible implementation, step S30 may include steps S31-S32: Step S31: For any target time period, calculate the difference between each actual power generation in the actual power generation set of the target time period and the baseline power generation and the lower limit of the power range of the benchmark power generation range of the target time period, respectively, to obtain the power generation baseline residual value set and the power generation lower limit residual value set of the target time period. It should be noted that the baseline residual value of power generation is the difference between the actual power generation and the baseline power generation, and the lower limit residual value of power generation is the difference between the actual power generation and the lower limit of the power range.

[0056] Step S32: If the average value of the baseline residual value set of power generation in the target period is greater than the preset baseline residual threshold corresponding to the target period, and / or the average value of the lower limit residual value set of power generation in the target period is greater than the preset lower limit residual threshold corresponding to the target period, then the target period is designated as the period of reduced credit.

[0057] It should be noted that the average value of the power generation baseline residual set is the arithmetic mean of all power generation baseline residual values ​​within the set, and it is used to reflect the degree to which the overall power output deviates from the baseline power generation output during the corresponding target period. Similarly, the average value of the power generation lower limit residual set is the arithmetic mean of all power generation lower limit residual values ​​within the set, and it is used to reflect the degree to which the overall power output deviates from the lower limit of the power range during the corresponding target period.

[0058] The preset baseline residual threshold can be a default value or can be flexibly set by the user according to the actual situation. This embodiment does not impose specific limitations on this. For example, the average historical power baseline residual of the target power plant on the historical day in each target time period can be determined first by using the historical power generation set of the target power plant on the historical day in each target time period and the benchmark power generation range of each target time period; then, the standard deviation of the historical power baseline residual of the target power plant on the historical day in each target time period can be determined by using the historical power generation set of each target time period and the average historical power baseline residual; then, the standard deviation of the historical power baseline residual of the target power plant on the historical day in each target time period can be directly used as the preset baseline residual threshold.

[0059] The preset lower limit residual threshold can be a default value or can be flexibly set by the user according to the actual situation. This embodiment does not impose specific limitations on this. For example, the historical power generation set of the target power plant on the historical day in each target time period and the benchmark power generation range of each target time period can be used to determine the average value of the historical power lower limit residual of the target power plant on the historical day in each target time period; then, the standard deviation value of the historical power lower limit residual of the target power plant on the historical day in each target time period can be determined using the historical power generation set of each target time period and the average value of the historical power lower limit residual; then, the standard deviation value of the historical power lower limit residual can be directly used as the preset lower limit residual threshold.

[0060] Understandably, if the average value of the baseline residual value set of power generation during the target period is greater than the preset baseline residual threshold corresponding to the target period, it indicates that the actual power generation during the target period deviates from the baseline power generation by a margin exceeding the normal range. In other words, the actual power generation is consistently lower than the expected power generation level, indicating a significant decline in power generation capacity. Therefore, the target period can be designated as a period for deduction. Conversely, if the average value of the lower limit residual value set of power generation during the target period is greater than the preset lower limit residual threshold corresponding to the target period, it indicates that the actual power generation during the target period has fallen below the lower limit of normal fluctuations, resulting in a significant abnormal deduction. Therefore, the target period can also be designated as a period for deduction.

[0061] This implementation method constructs two sets of judgment indicators: baseline residual and lower limit residual of power generation. It then performs a two-dimensional comparison based on the mean of the residuals and a preset threshold. This allows for the accurate and robust identification of abnormal periods where the actual power generation is significantly lower than the baseline power generation range. It effectively distinguishes between normal fluctuations and genuine rationing. This not only avoids misjudgments caused by single-point instantaneous anomalies but also prevents missed detections due to slight and persistent low power levels. This ensures the accuracy and reliability of the determined rationing periods, thereby further improving the accuracy and robustness of the power rationing and curtailment judgment for power plants.

[0062] This embodiment does not specifically limit the implementation of step S30. For example, in other feasible implementations, it is also possible to determine only the baseline residual value or the lower limit residual value of power generation for each target time period, or to further consider the upper limit residual value of power generation for each target time period, in order to complete the determination of the derated period.

[0063] Step S40: Perform time series feature analysis on each depreciation period to obtain at least one depreciation feature score for the target power plant on the current day; each depreciation feature score includes at least the power stability score, boundary change intensity score, temperature coupling score and / or time series predictability score; It should be noted that the power stability score reflects the stability of power fluctuations during the derating period. During artificial power curtailment, power fluctuations typically remain stable at a low level, while natural derating exhibits larger fluctuations. The boundary abrupt change intensity score reflects the drastic power changes at the start and end of the derating period. Artificial power curtailment often begins and ends abruptly, while natural derating is gradual. The temperature coupling score reflects the correlation between power and temperature during the derating period. During natural derating, power and temperature are strongly correlated. The time-series predictability score reflects the predictability of power change patterns during the derating period. During artificial power curtailment, the power curve exhibits strong regularity (e.g., a horizontal straight line) and is easily predicted.

[0064] Step S50: Based on the scores of each reduction characteristic, determine whether there is any artificial reduction in power supply for the target power station on the current day.

[0065] In one feasible implementation, step S50 may include steps S51-S52: Step S51: Normalize the scores of each reduction feature to obtain the normalized scores of each reduction feature. When normalizing the scores of each reduction feature to obtain the normalized scores, the normalization function shown in Formula 1 can be used to normalize the scores of each reduction feature, resulting in the normalized scores of each reduction feature. Alternatively, extreme value normalization can be used to map each reduction feature score to a preset interval to obtain the normalized scores of each reduction feature. This embodiment does not specifically limit the implementation method of step S51.

[0066] Formula 1; Where f(x) is the reduced-rate feature score after normalization, e is the natural logarithm, and x is the reduced-rate feature score.

[0067] Step S52: If the average score of each ration reduction feature after normalization is less than the preset threshold, it is determined that there is artificial ration reduction in power supply at the target power station on the current day.

[0068] It should be noted that the preset threshold is the critical value used to distinguish between human-induced power rationing and power rationing caused by natural factors. It can be a default value or it can be flexibly set by the user according to the actual situation. This embodiment does not make specific limitations on it.

[0069] This implementation normalizes the scores of multi-dimensional derating features, eliminating the differences in dimensions and numerical ranges between different features. This allows various scores to be fused and judged under a unified standard. Furthermore, by comparing the average of the normalized scores with a preset threshold, the quantitative judgment of artificial derating and power limiting is achieved, thereby improving the accuracy, robustness, and versatility of the judgment results.

[0070] This embodiment does not specifically limit the implementation of step S50. For example, in other feasible implementations, it can also be determined whether the scores of each derating feature are all less than their respective preset thresholds. If so, it can be determined that the target power station is experiencing artificial derating and power restriction on the current day.

[0071] Based on the above, the technical solution provided in this embodiment constructs a benchmark power generation range that objectively reflects the true power generation capacity of the power station by utilizing the regional power generation efficiency of the area where the target power station is located and the historical power generation efficiency of the target power station itself on historical days. By comparing the actual power generation of the target power station on the current day with this benchmark power generation range, the derating period in which the actual power generation deviates abnormally can be accurately located, and the time window that needs to be analyzed in detail can be identified. Compared with the existing technology that only focuses on the power station's own data or only focuses on natural factors, the technical solution provided in this embodiment can reduce misjudgments caused by common factors such as weather changes and ambient temperature changes, thereby improving the accuracy of identifying derating periods.

[0072] Furthermore, the technical solution provided in this embodiment, after identifying the derating period, does not simply make a derating determination, but performs time-series feature analysis on the derating period to calculate derating feature scores from multiple dimensions such as power stability, boundary change intensity, temperature coupling relationship, and time-series predictability. This clearly distinguishes between two different types of derating caused by human-induced power curtailment and derating caused by natural factors, effectively improving the robustness and accuracy of derating cause determination.

[0073] Therefore, the technical solution provided in this embodiment can improve the accuracy and robustness of determining power rationing for power plants.

[0074] Based on the first embodiment described above, a second embodiment of the power plant derating and curtailment determination method of this application is proposed. In the second embodiment, when each derating characteristic score includes a power stability score, please refer to... Figure 2 Step S40 may include steps S411 to S414: Step S411: Determine the mean value of the baseline residual of power generation for each period of devaluation based on the actual power generation set and the baseline power generation range of the reference power generation range. It should be noted that the mean of the power generation baseline residual is the arithmetic mean of the power generation baseline residual values ​​(i.e., the difference between the actual power generation and the baseline power generation) at all sampling times within the corresponding derated period. It is used to reflect the degree to which the overall power generation deviates from the baseline power generation within the corresponding derated period.

[0075] Step S412: Calculate the ratio between the mean residual value of the power generation baseline for each derated period and the baseline power generation of the respective reference power generation range for each derated period, and obtain each first ratio. It should be noted that the first ratio is used to characterize the relative deviation of the mean residual of the power generation baseline from the baseline power generation during the corresponding reduction period, and it reflects the relative magnitude of the reduction.

[0076] Step S413: Calculate the ratio between the actual power generation of each power generation in the actual power generation concentration of each derated period and the installed capacity of the target power plant to obtain each second ratio. It should be noted that the second ratio is used to characterize the utilization of the actual power generation at the sampling time within the corresponding derated period relative to the maximum power generation capacity of the power station, and it reflects the power generation output level at that sampling time.

[0077] Step S414: The ratio between the average of each first ratio and the average of each second ratio is used as the power stability score of the target power plant for the current day.

[0078] Understandably, a smaller power stability score indicates a smaller relative deviation at lower load levels, a more stable power curve, and is more consistent with the characteristics of artificial power rationing. Conversely, a larger power stability score indicates a larger deviation at the same load level, with more drastic power fluctuations, which is more likely due to natural factors causing rationing.

[0079] In this embodiment, after determining the mean residual value of the power generation baseline for each derated period based on the actual power generation set and the baseline power generation of the benchmark power generation range for each derated period, the ratio between the mean residual value of the power generation baseline for each derated period and the baseline power generation of the benchmark power generation range for each derated period is calculated to eliminate the influence of the difference in baseline levels in different periods, thus obtaining the relative deviation amplitude (i.e., the first ratio). Furthermore, the power generation output level at each moment is obtained by calculating the ratio between the actual power generation set of each derated period and the installed capacity of the target power plant. Thus, the stationarity characteristics of power changes within the derated period are quantitatively characterized from the two dimensions of relative deviation amplitude and power generation output level. This effectively extracts the essential differences in power fluctuation patterns between artificial derated power curtailment, natural derated power curtailment, and equipment failure, providing a stable and reliable basis for subsequent multi-feature fusion judgment, thereby improving the accuracy and reliability of derated cause identification.

[0080] Based on the first and / or second embodiments described above, a third embodiment of the power plant derating and curtailment determination method of this application is proposed. In the third embodiment, when the scores of each derating feature include the boundary abrupt change intensity score, please refer to... Figure 3 Step S40 may include steps S421 to S425: Step S421: Based on each reduction period, determine the start and end times of the current day's reduction for the target power plant; It should be noted that the start time of the credit limit reduction is the earliest start time of all credit limit reduction periods on the current day, sorted by time. The end time of the credit limit reduction is the start time of the latest start time of all credit limit reduction periods on the current day, sorted by time.

[0081] When determining the start and end times of the current day's depreciation for the target power plant based on each depreciation period, the start times of all depreciation periods can be sorted, and the minimum value can be taken as the start time of depreciation; the end times of all depreciation periods can be sorted, and the maximum value can be taken as the end time of depreciation. If the interval between each depreciation period is less than a preset interval length (e.g., 10 minutes), these depreciation periods can also be merged into a continuous period, and the start and end times of this continuous period can be taken as the start and end times of depreciation, respectively. This embodiment does not specifically limit the implementation method of step S421.

[0082] Step S422: Obtain the first power generation residual value set within the first preset time period before the devaluation start time, and the second power generation residual value set within the second preset time period after the devaluation start time; obtain the third power generation residual value set within the third preset time period before the devaluation end time, and the fourth power generation residual value set within the fourth preset time period after the devaluation end time. It should be noted that the first power generation residual value set refers to the power generation residual value set within the first preset time period before the derating start time; the second power generation residual value set refers to the power generation residual value set within the second preset time period after the derating start time; the third power generation residual value set refers to the power generation residual value set within the third preset time period before the derating end time; and the fourth power generation residual value set refers to the power generation residual value set within the fourth preset time period after the derating end time. The first, second, third, and fourth preset time periods can all be default values, or they can be flexibly set by the user according to actual conditions. This embodiment does not impose specific limitations on this. The first, second, third, and fourth preset time periods can be the same or different from each other; this embodiment also does not impose specific limitations on this.

[0083] Step S423: Determine the standard deviation of the initial boundary residual based on the first power generation residual set and the second power generation residual set, and determine the standard deviation of the final boundary residual based on the third power generation residual set and the fourth power generation residual set. It should be noted that the standard deviation of the initial boundary residual is calculated by combining the residual data of the two windows before and after the start of the derating, and it reflects the severity of power fluctuations near the start of the derating. The standard deviation of the final boundary residual is calculated by combining the residual data of the two windows before and after the end of the derating, and it reflects the severity of power fluctuations near the end of the derating.

[0084] When determining the standard deviation of the initial boundary residuals based on the first set of power generation residuals and the second set of power generation residuals, the first set of power generation residuals and the second set of power generation residuals can be merged into a single sequence to obtain a merged residual sequence; then, the standard deviation of this merged residual sequence is calculated as the standard deviation of the initial boundary residuals. Alternatively, the standard deviations of the first set of power generation residuals and the second set of power generation residuals can be calculated separately, and then the average of the two can be taken as the standard deviation of the initial boundary residuals. This embodiment does not impose specific limitations on this approach.

[0085] Similarly, when determining the standard deviation of the termination boundary residual based on the third and fourth power generation residual sets, the third and fourth power generation residual sets can be merged into a single sequence to obtain a merged residual sequence; then, the standard deviation of this merged residual sequence is calculated as the standard deviation of the termination boundary residual. Alternatively, the standard deviations of the third and fourth power generation residual sets can be calculated separately, and the average of the two can be taken as the standard deviation of the termination boundary residual. This embodiment does not specifically limit this approach. Step S424: Take the maximum value of the standard deviation of the initial boundary residual and the standard deviation of the final boundary residual as the boundary fluctuation value for the day. It should be noted that the daily boundary fluctuation value reflects the maximum volatility of the overall depreciation event at the boundary of the target power plant on that day. In other embodiments, the average of the standard deviation of the initial boundary residual and the standard deviation of the final boundary residual can also be used as the daily boundary fluctuation value; this embodiment does not specifically limit this.

[0086] Step S425: The ratio between the preset normal boundary fluctuation value and the daily boundary fluctuation value is used as the boundary mutation intensity score of the target power station for the current day.

[0087] It should be noted that the normal boundary fluctuation value is the reference value of the boundary residual fluctuation near the boundary of a certain operating period when the target power plant is in normal operation. It can be a default value or it can be flexibly set by the user according to the actual situation. This embodiment does not make specific limitations on this. For example, the standard deviation of the residuals near the start time and the standard deviation of the residuals near the end time of a normal operating cycle of the target power plant can be analyzed, and then the maximum value of the two can be taken as the normal boundary fluctuation value.

[0088] In this embodiment, after determining the start and end times of the derating of the target power plant on a given day based on each derating period, the residual power generation values ​​within a preset time period before and after the start and end times of the derating are extracted and the corresponding boundary residual standard deviation is calculated to quantify the intensity of power fluctuations at the derating boundary, thus obtaining the initial boundary residual standard deviation and the end boundary residual standard deviation. Then, the maximum value between the initial boundary residual standard deviation and the end boundary residual standard deviation is taken as the boundary fluctuation value for the day. Next, the preset normal boundary fluctuation value is compared with the boundary fluctuation value for the day to quantify the abrupt change intensity characteristics during the occurrence and end of the derating process. This effectively extracts the essential differences in power change trends between artificial derating and curtailment, natural temperature derating, and equipment failure, providing a stable and reliable boundary abrupt change characteristic basis for subsequent multi-feature fusion judgment, and improving the accuracy and reliability of derating cause identification.

[0089] Based on the first, second, and / or third embodiments described above, a fourth embodiment of the power plant derating and curtailment determination method of this application is proposed. In the fourth embodiment, when the scores for each derating feature include a temperature coupling score, please refer to... Figure 4 Step S40 may include steps S431 to S435: Step S431: Obtain the actual power sequence and actual temperature sequence of the target power plant for each derated period on the current day; It should be noted that the actual power sequence is a data sequence formed by arranging the actual power generation of the target power plant at each sampling time during the derating period in chronological order, reflecting the real-time change trajectory of power during the derating period. The actual temperature sequence is a data sequence formed by arranging the ambient temperature or inverter temperature at each sampling time during the derating period in chronological order.

[0090] Step S432: Perform differential processing on the actual power sequence and actual temperature sequence for each derating period to obtain the actual power differential sequence and actual temperature differential sequence for each derating period; It should be noted that the actual power difference sequence is the sequence of power changes between adjacent moments within the derating period, reflecting the direction and amplitude of power fluctuations. The actual temperature difference sequence is the sequence of temperature changes between adjacent moments within the derating period, reflecting temperature rises and falls.

[0091] The actual power sequence for each derating period is differentially processed, that is, the difference between the actual power generation at adjacent moments in the actual power sequence is calculated. Similarly, the actual temperature sequence for each derating period is differentially processed, that is, the difference between the actual temperature at adjacent moments in the actual temperature sequence is calculated. The differential processing method can be first-order differential (i.e., the value at the later moment is subtracted from the value at the previous moment), logarithmic differential (i.e., first take the natural logarithm of power and temperature, and then calculate the difference), normalized differential (i.e., divide the difference by the value at the previous moment), etc., and this embodiment does not specifically limit the method.

[0092] Step S433: Determine the actual correlation coefficient between power and temperature for each derating period based on the actual power difference sequence and the actual temperature difference sequence for each derating period. It should be noted that the actual correlation coefficient is a statistic that characterizes the degree of linear correlation between power changes and temperature changes during the period of derated power.

[0093] When determining the actual correlation coefficient between power and temperature for each derating period based on the actual power difference sequence and the actual temperature difference sequence, a Pearson correlation coefficient can be calculated based on the actual power difference sequence and the actual temperature difference sequence, and this Pearson correlation coefficient can be used as the actual correlation coefficient between power and temperature within the derating period. Alternatively, robust statistical methods such as hyperbolic tangent transform or median correlation can be used to calculate the actual correlation coefficient between power and temperature within the derating period. This embodiment does not specifically limit the implementation method of step S433.

[0094] Step S434: Calculate the ratio between the actual correlation coefficient of each derating period and the preset normal correlation coefficient between power and temperature for each derating period to obtain the temperature coupling score for each derating period. It should be noted that the normal correlation coefficient is a statistical measure that characterizes the degree of linear correlation between power changes and temperature changes during a certain operating period of a target power plant under normal operating conditions. It can be a default value or can be flexibly set by the user according to the actual situation. This embodiment does not impose specific limitations on it. For example, the historical power series and historical temperature series of the target power plant under a normal operating cycle can be differentially processed to obtain the historical power differential series and the historical temperature differential series; then, the normal correlation coefficient can be determined based on the historical power differential series and the historical temperature differential series.

[0095] Step S435: Determine the temperature coupling score of the target power plant for the current day based on the temperature coupling score for each derated period.

[0096] When determining the temperature coupling score of the target power plant for the current day based on the temperature coupling scores of each depreciation period, the average of the temperature coupling scores of each depreciation period can be used as the temperature coupling score of the target power plant for the current day; alternatively, the minimum or median of the temperature coupling scores of each depreciation period can be used as the temperature coupling score of the target power plant for the current day; furthermore, different weights can be assigned to each depreciation period based on its duration or the significance of the original correlation coefficient (such as the absolute value of the correlation coefficient), and a weighted average can be calculated as the temperature coupling score of the target power plant for the current day, wherein the longer the duration and the more significant the correlation, the higher the weight. This embodiment does not specifically limit the implementation method of step S435.

[0097] In this embodiment, after obtaining the actual power sequence and actual temperature sequence for each derating period, the power sequence and temperature sequence are differentially processed to highlight their changing trends, resulting in actual power differential sequence and actual temperature differential sequence. Using the actual power differential sequence and actual temperature differential sequence, the actual correlation coefficient between power and temperature within the derating period is determined. Then, the actual correlation coefficient is compared with the preset normal correlation coefficient to obtain the temperature coupling score for each derating period, and finally, the overall temperature coupling score for the day is determined. This quantitatively characterizes the correlation between power anomalies and temperature changes within the derating period from the dimension of the coupling matching degree between power changes and temperature changes. This effectively extracts the essential differences in the causal mechanism between artificial derating and natural temperature derating, providing a stable and reliable temperature coupling feature basis for subsequent multi-feature fusion judgment, and improving the accuracy and reliability of derating cause identification.

[0098] Based on the first, second, third, and / or fourth embodiments described above, a fifth embodiment of the power plant derating and curtailment determination method of this application is proposed. In the fifth embodiment, when the scores of each derating feature include a time-predictable score, please refer to... Figure 5 Step S40 may include steps S441 to S446: Step S441: For any period of reduced amount, divide the period of reduced amount into a first sub-period and a second sub-period; It should be noted that the first sub-period, which is the portion of the dereasing period used for model training, is usually the first part of the period (e.g., the first 60% of the time length) and is used to capture the power change pattern during the dereasing period. The second sub-period, which is the portion of the dereasing period used for verifying the model's predictive performance, is usually the latter part of the period (e.g., the last 40% of the time length) and is used to evaluate the extrapolability of the pattern.

[0099] When dividing the period for rate reduction, it can be done according to a certain ratio. This ratio can be a default value or can be flexibly set by the user according to the actual situation. This embodiment does not impose specific limitations on this. Alternatively, the period can be divided into two equal halves, with the first half as the first sub-period and the second half as the second sub-period. This embodiment does not impose specific limitations on the implementation method for dividing the period for rate reduction.

[0100] Step S442: Based on the actual power sequence of the target power plant in the first sub-period of the current day, iteratively optimize the model to be trained to generate a power prediction model; It should be noted that the model to be trained can be a linear regression model, such as a first-order autoregressive model or an exponential smoothing model. This embodiment does not impose any specific limitations on this.

[0101] Step S443: Use a power prediction model to predict the power generation of the target power plant at each time point in the second sub-period, and obtain the predicted power sequence; It should be noted that the predicted power sequence is a data sequence formed by arranging the predicted power generation of the target power plant at each time point in the second sub-period of the power prediction model in chronological order.

[0102] When using a power prediction model to predict the power generation of a target power plant at each moment in the second sub-period, the actual power generation at the last moment of the first sub-period can be used as the initial value of the power prediction model to progressively predict the predicted value of the first power generation in the second sub-period. Then, this predicted value is used to continue predicting the next value until the power generation prediction for all moments in the second sub-period is completed.

[0103] Step S444: Calculate the mean power deviation between the predicted power sequence and the actual power sequence of the second sub-period; It should be noted that the mean power deviation is the average of the absolute values ​​of the difference between the predicted power and the actual power at the corresponding time, which reflects the magnitude of the prediction error of the power prediction model.

[0104] Step S445: Calculate the ratio between the mean power deviation and the mean of the actual power sequence in the second sub-period to obtain the time-series predictability score for the derated period; It should be noted that the average value of the actual power series is the arithmetic mean of all actual power generation within the actual power series. The time series predictability score during the derating period reflects the strength of the regularity of power changes within the derating period. The smaller the time series predictability score during the derating period, the stronger the regularity of power changes and the easier it is to predict; the larger the time series predictability score during the derating period, the more complex and difficult it is to predict power changes.

[0105] Step S446: Determine the time-series predictable score of the target power plant for the current day based on the time-series predictable score of each reduction period.

[0106] When determining the time-series predictable score of the target power plant for the current day based on the time-series predictable scores of each reduction period, the average of the time-series predictable scores of each reduction period can be used as the time-series predictable score of the target power plant for the current day; alternatively, the maximum or median of the time-series predictable scores of each reduction period can be used as the time-series predictable score of the target power plant for the current day; or, weights can be assigned based on the duration or amount of training data of each reduction period, and a weighted average can be calculated as the time-series predictable score of the target power plant for the current day, where the longer the duration and the more abundant the data, the higher the weight of the period.

[0107] In this embodiment, after dividing each derating period into a first sub-period and a second sub-period, a power prediction model is trained using the actual power sequence of the first sub-period. Based on this model, the power generation of the second sub-period is predicted to obtain a predicted power sequence. Then, by calculating the average deviation between the predicted power and the actual power, and by comparing the average deviation with the average actual power, the temporal predictability score of each derating period is obtained, and the overall temporal predictability score for the day is finally determined. This quantitatively characterizes the regularity and randomness of power changes within the derating period from the dimension of the predictability of power temporal changes, thereby effectively extracting the essential differences in the causal mechanism between artificial derating and natural temperature-induced derating. This provides a stable and reliable temperature coupling feature basis for subsequent multi-feature fusion judgment, improving the accuracy and reliability of derating cause identification.

[0108] This application also provides an electronic device, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the power plant rationing determination method in the above embodiments.

[0109] The following is for reference. Figure 6 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this application. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0110] like Figure 6As shown, the electronic device may include a processing unit 101 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory 102 or a program loaded from storage device 103 into random access memory 104. Random access memory 104 also stores various programs and data required for the operation of the electronic device. The processing unit 101, read-only memory 102, and random access memory 104 are interconnected via bus 105. Input / output interface 106 is also connected to bus 105. Typically, the following systems can be connected to input / output interface 106: input devices 107 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 108 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 103 including, for example, magnetic tape, hard disks, etc.; and communication devices 109. Communication device 109 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0111] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 103, or installed from read-only memory 102. When the computer program is executed by processing device 101, it performs the functions defined in the methods of the embodiments of this application.

[0112] The electronic device provided in this application adopts the power plant derating and curtailment determination method in the above embodiments, which can improve the accuracy and robustness of power plant derating and curtailment determination. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as the beneficial effects of the power plant derating and curtailment determination method provided in the above embodiments, and other technical features in the electronic device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0113] It should be understood that various parts of the embodiments of this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0114] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the above claims.

[0115] This application also provides a computer-readable storage medium storing a computer program that can run on a processor. The computer program is used to execute the power plant rationing determination method in the above embodiments.

[0116] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0117] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0118] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to: acquire the regional power generation efficiency of the area where the target power plant is located during each target time period, and acquire the historical power generation efficiency set of the target power plant for each target time period on historical days prior to the current day; determine the baseline power generation range of the target power plant during each target time period based on the regional power generation efficiency and the historical power generation efficiency set for each target time period; select each derating period from each target time period based on the actual power generation set and the baseline power generation range of the target power plant on the current day during each target time period; perform time series feature analysis on each derating period to obtain at least one derating feature score for the target power plant on the current day; each derating feature score includes at least a power stability score, a boundary abrupt change intensity score, a temperature coupling score, and / or a time series predictability score; and determine whether there is any artificial derating or curtailment of the target power plant on the current day based on each derating feature score.

[0119] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0121] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0122] The computer-readable storage medium provided in this application embodiment stores computer-readable program instructions for executing the power plant derating and curtailment determination method described above, which can improve the accuracy and robustness of power plant derating and curtailment determination. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application embodiment are the same as the beneficial effects of the power plant derating and curtailment determination method provided in the above embodiments, and will not be repeated here.

[0123] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the power plant derating and curtailment determination method described above.

[0124] The computer program product provided in this application can improve the accuracy and robustness of determining power derating and curtailment for power plants. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the power derating and curtailment determination method for power plants provided in the above embodiments, and will not be repeated here.

[0125] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for determining derating and curtailment of power plants, characterized in that, The method includes: Obtain the regional power generation efficiency of the area where the target power station is located during each target time period, and obtain the historical power generation efficiency set of the target power station for each target time period for the historical days before the current day. Based on the regional power generation efficiency and historical power generation efficiency set for each target time period, determine the baseline power generation range of the target power plant for each target time period; Based on the actual power generation set and benchmark power generation range of the target power plant on the current day in each of the target time periods, each derated period is selected from each of the target time periods; A time-series feature analysis is performed on each of the aforementioned depreciation periods to obtain at least one depreciation feature score for the target power plant on the current day; each of the aforementioned depreciation feature scores includes at least a power stability score, a boundary abrupt change intensity score, a temperature coupling score, and / or a time-series predictability score; Based on the scores of each of the aforementioned reduction characteristics, it is determined whether the target power station currently experiences artificial reductions or power rationing.

2. The method as described in claim 1, characterized in that, The step of determining the baseline power generation range of the target power plant in each target time period based on the regional power generation efficiency and historical power generation efficiency set for each target time period includes: Based on the regional power generation efficiency and historical power generation efficiency set for each target time period, determine the power generation efficiency deviation value and the standard deviation value of the power generation efficiency deviation for each target time period of the target power plant; The power generation efficiency deviation value for each target time period is calculated and the sum of the regional power generation efficiency for each target time period is obtained to obtain the baseline power generation efficiency of the target power plant in each target time period. The baseline power generation efficiency of the target power plant in each target time period is calculated as a product of the baseline power generation efficiency and the installed capacity of the target power plant in each target time period. Based on the standard deviation of power generation efficiency during each target time period and the installed capacity, the power fluctuation range of the target power plant during each target time period is calculated. For any target time period, the sum of the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the upper limit of the power range, and the difference between the baseline power generation of the target time period and the power fluctuation amplitude of the target time period is used as the lower limit of the power range, so as to generate the reference power generation range of the target time period.

3. The method as described in claim 2, characterized in that, The step of determining the power generation efficiency deviation and standard deviation of the target power plant in each target time period based on the regional power generation efficiency and historical power generation efficiency set for each target time period includes: For any target time period, calculate the difference between each historical power generation efficiency in the historical power generation efficiency set of the target time period and the regional power generation efficiency of the target time period to obtain the deviation value of each sub-power generation efficiency; The average value of each of the sub-power generation efficiency deviation values ​​is taken as the power generation efficiency deviation value of the target power plant in the target time period; The standard deviation of the power generation efficiency of the target power plant in the target period is calculated based on the average value of the deviation values ​​of each sub-power generation efficiency and the historical power generation efficiency of each historical power generation efficiency in the target period.

4. The method as described in claim 1, characterized in that, The step of selecting each derated period from each target period based on the actual power generation set of the target power plant on the current day and the baseline power generation range of each target period includes: For any of the target time periods, calculate the difference between each actual power generation in the actual power generation set of the target time period and the baseline power generation and the lower limit of the power range of the reference power generation range of the target time period, respectively, to obtain the power generation baseline residual value set and the power generation lower limit residual value set of the target time period; If the average value of the baseline residual value set of power generation during the target period is greater than the preset baseline residual threshold corresponding to the target period, and / or the average value of the lower limit residual value set of power generation during the target period is greater than the preset lower limit residual threshold corresponding to the target period, then the target period is designated as the period of deduction.

5. The method as described in claim 1, characterized in that, When each of the aforementioned depreciation characteristic scores includes a power stability score, the step of performing time-series characteristic analysis on each of the aforementioned depreciation periods to obtain at least one depreciation characteristic score for the target power plant on the current day includes: The mean value of the baseline residual of power generation for each of the aforementioned derated periods is determined based on the actual power generation set and the baseline power generation range of the reference power generation range. Calculate the ratio between the mean of the baseline residual of power generation for each of the aforementioned derated periods and the baseline power generation for each of the aforementioned derated periods within their respective reference power generation ranges, and obtain each first ratio; Calculate the ratio between the actual power generation of each power generation in the actual power generation set of each of the aforementioned derated periods and the installed capacity of the target power plant to obtain each second ratio; The ratio between the average of the first ratios and the average of the second ratios is taken as the power stability score of the target power plant for the current day.

6. The method as described in claim 1, characterized in that, When each of the aforementioned depreciation feature scores includes a boundary abrupt change intensity score, the step of performing time-series feature analysis on each of the aforementioned depreciation periods to obtain at least one depreciation feature score for the target power plant on the current day includes: Based on each of the aforementioned reduction periods, determine the start and end times of the current day's reduction for the target power plant; Obtain the first set of residual power generation values ​​within a first preset time period before the start time of the derating, and the second set of residual power generation values ​​within a second preset time period after the start time of the derating; obtain the third set of residual power generation values ​​within a third preset time period before the end time of the derating, and the fourth set of residual power generation values ​​within a fourth preset time period after the end time of the derating. Based on the first set of residual power generation values ​​and the second set of residual power generation values, the standard deviation of the initial boundary residual is determined, and based on the third set of residual power generation values ​​and the fourth set of residual power generation values, the standard deviation of the final boundary residual is determined. The maximum value between the standard deviation of the initial boundary residual and the standard deviation of the final boundary residual is taken as the boundary fluctuation value for the day. The ratio between the preset normal boundary fluctuation value and the daily boundary fluctuation value is used as the boundary mutation intensity score of the target power plant on the current day.

7. The method as described in claim 1, characterized in that, When each of the aforementioned depreciation characteristic scores includes a temperature coupling score, the step of performing time-series characteristic analysis on each of the aforementioned depreciation periods to obtain at least one depreciation characteristic score for the target power plant on the current day includes: Obtain the actual power sequence and actual temperature sequence of the target power plant for each of the aforementioned derated periods on the current day; The actual power sequence and actual temperature sequence for each of the derating periods are differentially processed to obtain the actual power differential sequence and actual temperature differential sequence for each of the derating periods. Based on the actual power difference sequence and actual temperature difference sequence for each of the aforementioned derating periods, the actual correlation coefficient between power and temperature for each of the aforementioned derating periods is determined; Calculate the ratio between the actual correlation coefficient of each derating period and the preset normal correlation coefficient between power and temperature for each derating period to obtain the temperature coupling score for each derating period. Based on the temperature coupling scores for each of the aforementioned reduction periods, the temperature coupling score for the target power plant on the current day is determined.

8. The method as described in claim 1, characterized in that, When each of the aforementioned depreciation characteristic scores includes a time-predictable score, the step of performing time-series characteristic analysis on each of the aforementioned depreciation periods to obtain at least one depreciation characteristic score for the target power plant on the current day includes: For any of the aforementioned reduction periods, the reduction period is divided into a first sub-period and a second sub-period; Based on the actual power sequence of the target power plant on the current day in the first sub-period, the training model is iteratively optimized to generate a power prediction model; The power generation power of the target power plant at each time point in the second sub-period is predicted using the power prediction model to obtain the predicted power sequence; Calculate the mean power deviation between the predicted power sequence and the actual power sequence of the second sub-period; The ratio between the mean power deviation and the mean of the actual power sequence in the second sub-period is calculated to obtain the temporal predictability score of the depreciation period; Based on the predictable time series scores for each of the aforementioned reduction periods, the predictable time series score for the target power plant on the current day is determined.

9. The method according to any one of claims 1 to 8, characterized in that, The step of determining whether the target power station has experienced artificial power rationing on the current day based on the scores of each of the aforementioned rationing characteristics includes: The scores of each of the reduction features are normalized to obtain the normalized scores of each reduction feature. If the average score of each reduction feature after normalization is less than a preset threshold, it is determined that the target power station is experiencing artificial reduction in power consumption on the current day.

10. The method according to any one of claims 1 to 8, characterized in that, The step of obtaining the regional power generation efficiency of the area where the target power plant is located during each target time period includes: Obtain the operating data of each normally operating power station in the area where the target power station is located during each target time period; Based on the operating data of each normally operating power station in each of the target time periods, the normalized power generation efficiency of each normally operating power station in each of the target time periods is determined; Based on the normalized power generation efficiency of each of the normally operating power plants in each of the target time periods, the regional power generation efficiency of the area where the target power plant is located in each of the target time periods is determined.

11. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power plant rationing determination method as described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the power plant rationing determination method as described in any one of claims 1 to 10.

Images