A classification and identification system and method for new energy output ramping based on multi-level spatial scales

Abstract

This invention discloses a new energy power output ramp-up classification and identification system and method based on multi-level spatial scales, belonging to the field of power grid safety control technology. It includes a data acquisition module for acquiring new energy data corresponding to multi-level spatial data of a target area. The multi-level spatial data includes various new energy power plants and power grid power plants in the target area, and the new energy data is the wind power generation capacity of each new energy power plant. A data analysis module is used to set data scenarios and analyze the new energy data based on these scenarios. The data scenarios include using the wind power generation capacity of each new energy power plant as the data scenario, designating a main power plant among the new energy power plants, and analyzing the correlation between changes in the wind power generation capacity of the main power plant and the output power of the power grid power plant. This invention achieves real-time and accurate identification and prediction of new energy power output ramp-up status by collecting multi-level spatial data from new energy power plants and power grid power plants, accurately extracting key features, and quantifying the patterns of change.

Description

Technical Field

[0001] This invention relates to the field of power grid safety control technology, and in particular to a new energy output ramp-up classification and identification system and method based on multi-level spatial scale. Background Technology

[0002] As the proportion of renewable energy sources increases, their power output fluctuations pose a challenge to grid security. To ensure the stability of grid operation, a coordinated analysis of the impact of grid power variations is necessary.

[0003] Regarding this research, application CN202010885307.X provides a method and system for evaluating renewable energy consumption based on multiple objects and dimensions. The technical solution includes: determining a renewable energy consumption index based on different users, where the index is composed of basic renewable energy consumption indicators; acquiring basic data based on an established power grid zoning model; calculating basic renewable energy consumption indicators for each zone based on the basic data; calculating renewable energy consumption indices for each zone based on the basic indicators and their corresponding weights; and evaluating the renewable energy consumption situation based on these indices. This technical solution can assess and judge the medium- and long-term renewable energy consumption trends, publish different renewable energy indices for different users, and guide relevant users to make correct decisions.

[0004] Another application, CN202110709291.1, provides a method and system for simulating renewable energy output considering both time and spatial scales. This technical solution includes the following steps: 1) dividing the acquired historical renewable energy power generation dataset according to time and spatial scales to obtain corresponding sample datasets; 2) performing time-series simulations on each sample dataset and generating random samples of renewable energy power generation output based on the simulation results; and establishing a probabilistic model of renewable energy output that reflects both time and spatial characteristics based on these random samples. This technical solution improves the practicality and applicability of the renewable energy power generation output probabilistic modeling algorithm.

[0005] However, the above-mentioned technical solutions are all power predictions on a single time scale and lack the ability to conduct collaborative analysis at multiple spatial scales (such as substation level, regional level, and grid level). This single time scale analysis cannot capture the spatiotemporal coupling characteristics of ramp events, which leads to adverse effects on power system operation and power system planning, and makes it impossible to formulate scientific and reasonable dispatch plans. Summary of the Invention

[0006] In view of the problems existing in the field of power grid safety control technology, the present invention is proposed.

[0007] Therefore, one objective of this invention is to provide a new energy power output ramp-up classification and identification system and method based on multi-level spatial scales. By collecting multi-level spatial data from new energy power plants and power grid power plants, it dynamically analyzes the correlation between wind power generation changes and grid output power, accurately extracts key features and quantifies the changes in patterns, and achieves real-time accurate identification and prediction of new energy power output ramp-up status. Moreover, the system can not only effectively assess the impact of new energy power output fluctuations on grid stability, but also has an early warning function, which can predict the changing trend of grid output power in advance, providing a scientific basis for grid dispatch, thereby significantly improving the stability and dispatch efficiency of grid operation.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On the one hand, the present invention provides a new energy output ramp-up classification and identification system based on multi-level spatial scales, comprising:

[0010] The data acquisition module is used to acquire new energy data corresponding to the multi-level space of the target area. The multi-level space includes various new energy power stations and power grid power stations in the target area. The new energy data is the wind power generation power of each new energy power station.

[0011] The data analysis module is used to set data scenarios and analyze the new energy data based on the data scenarios. The data scenarios include taking the wind power generation power of each new energy power station as the data scenario, giving a main power station among the new energy power stations, and analyzing the correlation impact of the changes in the wind power generation power of the main power station on the output power of the power grid power station.

[0012] The feature extraction module responds to the correlation effect and is used to perform feature extraction based on the correlation effect, including extracting the wind power generation power corresponding to the significant decrease in output power in the main station, wherein the significant decrease in output power includes a decrease of 5-10%, and marking the corresponding wind power generation power as the reference wind power generation power.

[0013] A data fusion processing module, comprising an acquisition unit, a calculation unit, and a judgment unit;

[0014] The acquisition unit is used to acquire the time corresponding to the output power dropping to 5%, and based on the time, a time period is set, and within the time period, a time period corresponding to the output power dropping from 1% to 5% is divided, and the time period is marked as a reference time period.

[0015] The calculation unit responds to the acquisition unit and is used to calculate the regular change of the wind power generation power of the main station when the output power decreases by 1% as a calculation target.

[0016] The judgment unit is used to make relevant judgments based on the changes in the pattern. The relevant judgments include: when the output power is decreasing, if the wind power generation power does not decrease and shows an increasing trend, then the system determines that the wind power generation power of each new energy power station is in a ramp-up state; otherwise, no judgment is made.

[0017] In a preferred embodiment of the present invention, the data analysis module analyzes the correlation between changes in the wind power generation capacity of the main field and the output power of the power grid station. The analysis steps are as follows:

[0018] Data cleaning is performed on the wind power generation capacity of each new energy power station and the output power of the power grid power station obtained in the target area. The data cleaning includes removing missing values, outliers or erroneous data from the power generation capacity and output power.

[0019] Determine the time window for analyzing the correlation between changes in wind power generation and the output power of power grid substations;

[0020] A safety threshold is set based on the changes in wind power generation during the home game;

[0021] Within the selected time window, obtain the power variation of the wind power generation at the main station at adjacent time points or different time nodes.

[0022] Statistical analysis was performed on the calculated power changes, and characteristic parameters were extracted.

[0023] Based on the set safety thresholds, the changes in wind power generation at the main power station are divided into different intervals. The division method includes dividing the wind power generation into a small increase interval and a large increase interval when the wind power generation increases; and dividing the wind power generation into a small decrease interval and a large decrease interval when the wind power generation decreases.

[0024] The changes in the wind power generation of the main power station are correlated and matched with the output power of the power grid power station. The correlation and matching includes ensuring that the correspondence between the changes in the wind power generation of the main power station and the output power of the power grid power station is analyzed within the same time window.

[0025] To determine the correlation between changes in wind power generation at the main power station and the output power of the power grid power station;

[0026] Based on the aforementioned correlation, the impact of the wind power generation capacity of the main power station on the output power of the power grid power station in different ranges is analyzed.

[0027] In a preferred embodiment of the present invention, the calculation unit calculates the regular change in the wind power generation power of the main station when the output power decreases by 1%, taking each 1% decrease as a calculation target, and calculates the result according to the following formula:

[0028] ; ;

[0029] In the formula, This indicates that the wind power generation capacity of the main wind farm is at the [number]th [year]. The rate of change when the price decreases by 1%;

[0030] Indicates the output power of the power grid station in the th... The rate of change when the price decreases by 1%;

[0031] and The wind power generation capacity of the main station is respectively in the 1st Power values ​​at the beginning and end of a 1% decrease;

[0032] and The output power of the power grid station is respectively in the th The power values ​​at the beginning and end of a 1% decrease.

[0033] In a preferred embodiment of the present invention, the following formula is also included:

[0034] ;

[0035] In the formula, This indicates the wind power generation capacity of the home game. and the output power of power grid stations covariance;

[0036] and The wind power generation capacity of the main wind farm and the output power of the grid station are respectively the wind power generation capacity of the main wind farm and the output power of the grid station in the th year. The value that can be obtained when the decrease is 1%;

[0037] and These are the average values ​​of the wind power generation capacity of the main wind farm and the output power of the grid-connected wind farm, respectively, when the wind power generation capacity decreases by 1%.

[0038] This indicates a decrease of 1%.

[0039] In a preferred embodiment of the present invention, the correlation between the change in wind power generation at the main power station and the output power of the power grid power station is obtained by calculation according to the following formula:

[0040] ;

[0041] In the formula, This indicates the wind power generation capacity of the home game. Output power of power grid stations The correlation coefficient between them;

[0042] Indicates the home game in the Wind power generation at each observation time;

[0043] Indicates the power grid station at the first Output power at each observation time, and correspond;

[0044] Indicates the wind power generation capacity of the main station The sample mean;

[0045] Indicates the output power of the power grid station The sample mean;

[0046] This indicates the total number of observed data.

[0047] In a preferred embodiment of the present invention, the wind intensity is obtained according to the calculation result, wherein the wind intensity is the wind intensity at which the output power decreases from 1% to 5%, and the wind intensity is marked as the reference wind intensity; when the output power of the power grid station decreases in the future, if the wind intensity corresponding to the decrease from 1% to 5% is lower than the reference wind intensity, the system determines that the wind power generation of each new energy station in the target area is in a downward trend; otherwise, no determination is made.

[0048] In a preferred embodiment of the present invention, the following steps are taken: The wind intensity before the output power decreases by 1% is obtained, the wind intensity includes the wind intensity within 10 minutes before the output power decreases by 1%, and the 6 to 10 most frequent wind intensities occurring before the output power decreases by 1% within those 10 minutes are obtained. The order of these 6 to 10 most frequent wind intensities is obtained based on time sequence, and the time interval between adjacent wind intensities is obtained based on this order. This time interval is marked as a reference time interval. When a wind intensity equal to the first wind intensity appears in the target area at a future time, if the same wind intensity as the second wind intensity appears at a slower time than the reference time interval, the system determines that the output power of the power grid station will decrease slowly at a future time. Conversely, if the same wind intensity as the second wind intensity appears at a faster time than the reference time interval, the system determines that the output power of the power grid station will decrease rapidly at a future time.

[0049] In a preferred embodiment of the present invention, if a wind intensity equal to the second and third wind intensities occurs faster than the reference time interval, but the output power of the power grid station does not decrease, the system determines that the output power of the power grid station will not decrease in the future; otherwise, no determination is made.

[0050] On the other hand, the present invention provides a method for applying to a new energy output ramp-up classification and identification system based on multi-level spatial scales as described above, comprising the following steps:

[0051] Acquire new energy data corresponding to a multi-level space in the target area, wherein the multi-level space includes various new energy power stations and power grid power stations in the target area, and the new energy data is the wind power generation power of each new energy power station;

[0052] A data scenario is set, and the new energy data is analyzed based on the data scenario. The data scenario includes taking the wind power generation of each new energy power station as the data scenario, giving a main power station in each new energy power station, and analyzing the correlation impact of the change in the wind power generation of the main power station on the output power of the power grid power station.

[0053] Based on the aforementioned correlation, feature extraction is performed, including extracting the wind power generation power corresponding to the significant decrease in output power from the main power station, wherein the significant decrease in output power includes a decrease of 5% to 10%, and marking the corresponding wind power generation power as the reference wind power generation power.

[0054] Collect the time taken for the output power to drop to 5%, and set a time period based on the time taken. Divide the time period into time periods corresponding to the output power dropping from 1% to 5%, and mark the time periods as reference time periods.

[0055] The wind power generation power of the main station is calculated as a calculation target for each 1% decrease in output power;

[0056] The system makes relevant judgments based on the aforementioned pattern of change. These judgments include determining that if the wind power generation does not decrease and shows an increasing trend when the output power is decreasing, the system determines that the wind power generation of each new energy power station is in a ramp-up state; otherwise, no judgment is made.

[0057] Beneficial effects:

[0058] 1. By acquiring multi-level spatial data of various new energy power plants and power grid power plants in the target area, the system has achieved comprehensive monitoring of new energy output. Furthermore, by setting data scenarios, especially based on the wind power generation of each new energy power plant, the system can more accurately identify the ramp-up status of new energy output. This scenario setting helps to eliminate other interference factors and make the identification results more reliable.

[0059] 2. By analyzing the correlation between changes in wind power generation at the main power station and the output power of the power grid, and by determining the time window, the system can accurately assess the impact of changes in new energy output on the stability of the power grid. Furthermore, by extracting characteristic parameters, such as the amount of power change and the range of change, the system further refines the analysis of the correlation. These parameters provide strong support for subsequent judgments and improve the accuracy and effectiveness of the assessment.

[0060] 3. The system extracts the wind power generation corresponding to the significant decrease in output power and further refines the judgment criteria for the ramp-up state by calculating the regular changes in the wind power generation of the main station for every 1% decrease. This calculation method can more accurately reflect the changing trend of new energy output and improve the scientific nature of the judgment.

[0061] 4. By referencing wind intensity, the system provides a basis for predicting changes in the output power of power grid stations in the future. Furthermore, by acquiring the time interval of wind intensity before the output power decreases, the system provides an early warning of the rate of change in output power in the future. When similar wind intensity changes occur in the future, the system can predict the rate of change in output power based on the reference value of the time interval, thereby taking countermeasures in advance. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the modular structure of the new energy output ramp-up classification and identification system based on multi-level spatial scale according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention;

[0063] The diagram is labeled as follows: 110 - Data acquisition module; 120 - Data analysis module; 130 - Feature extraction module; 140 - Data fusion processing module; 1401 - Acquisition unit; 1402 - Calculation unit; 1403 - Judgment unit. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0065] Since existing technical solutions are all based on power prediction at a single time scale and lack the ability to conduct collaborative analysis at multiple spatial scales, they have an adverse impact on power system operation and planning, and cannot formulate scientific and reasonable dispatch plans.

[0066] Based on this, the present invention proposes a new energy power output ramp-up classification and identification system and method based on multi-level spatial scale. By collecting multi-level spatial data of new energy power stations and power grid power stations, it dynamically analyzes the correlation between wind power generation power changes and power grid output power, accurately extracts key features and quantifies the regular changes, and realizes real-time accurate identification and prediction of new energy power output ramp-up status.

[0067] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0068] Reference Figures 1 to 2 This is one embodiment of the present invention, which provides a new energy output ramp-up classification and identification system based on multi-level spatial scales, including:

[0069] The data acquisition module 110 is used to acquire new energy data corresponding to the multi-level space of the target area. The multi-level space includes various new energy power stations and power grid power stations in the target area. The new energy data is the wind power generation power of each new energy power station.

[0070] Through multi-level spatial data acquisition, the system can cover a wider range of new energy power generation scenarios and improve the representativeness of the data;

[0071] Furthermore, by acquiring wind power generation data, timely support is provided for subsequent analysis, enhancing the system's responsiveness to changes in new energy output.

[0072] In reality, the power output of different renewable energy power plants in a region is usually different. The main factors causing this situation are the scale and installed capacity of the power plants, differences in renewable energy resources, and operating strategies and control methods.

[0073] For example, there are significant differences in the installed capacity of different new energy power plants, both in terms of scale and capacity. A large wind farm may have dozens or even hundreds of high-capacity wind turbines, with an installed capacity of hundreds of megawatts; while a small distributed photovoltaic power station may consist of only a few dozen photovoltaic panels, with an installed capacity of only tens of kilowatts.

[0074] Even within the same type of renewable energy power plant, the number of devices and the capacity of individual units can affect the total power output. For example, if two photovoltaic power plants use the same type of photovoltaic panels, but one plant has 1,000 panels while the other has only 500, then the former's power output will typically be twice that of the latter.

[0075] Regarding the differences in new energy resources, wind energy resources vary significantly across different geographical locations within wind farms. Factors such as wind speed, wind direction, and air density all affect the output power of wind turbine generators. For example, coastal areas and inland plateau regions typically have higher wind speeds and abundant wind energy resources, resulting in potentially higher power output for wind farms; while some valleys and basins have lower wind speeds, leading to relatively lower power output for wind farms.

[0076] Therefore, acquiring new energy data corresponding to multiple spatial scales is of practical significance;

[0077] The data analysis module 120 is used to set data scenarios and analyze new energy data based on these scenarios. The data scenarios include using the wind power generation capacity of each new energy power station as the data context, specifying a main power station within each new energy power station, and analyzing the correlation between changes in the wind power generation capacity of the main power station and the output power of the power grid power station. The analysis steps are as follows:

[0078] Data cleaning is performed on the wind power generation capacity (including the main station) and the output power of the grid station obtained in the target area. Data cleaning includes removing missing values, outliers or erroneous data from the power generation capacity and output power.

[0079] Determine the time window for analyzing the correlation between changes in wind power generation and the output power of power grid substations (the choice of time window should be based on the fluctuation characteristics of wind power generation and the response time of the power grid substations' output power. For example, for the analysis of rapid fluctuations in wind power generation, a shorter time window (such as a few minutes) can be selected; while for analyzing its long-term impact on the output power of power grid substations, a longer time window (such as a few hours or a day) can be selected).

[0080] A safety threshold is set based on the changes in wind power generation during home games.

[0081] Within the selected time window, obtain the power variation of the wind power generation at the main station at adjacent time points or different time nodes.

[0082] Statistical analysis is performed on the calculated power changes, and characteristic parameters are extracted (such as average rate of change, maximum rate of change, and variance of the rate of change; these characteristic parameters can describe the overall trend and fluctuation of the wind power generation at the main power station. For example, the average rate of change can reflect the average rate of change of the wind power generation at the main power station over a period of time; the maximum rate of change can reflect the extreme cases of power change; and the variance of the rate of change can measure the dispersion of power change).

[0083] Based on the set safety thresholds, the changes in wind power generation at the main power station are divided into different intervals. The division method includes dividing the increase in wind power generation into a small increase interval and a large increase interval; and dividing the decrease in wind power generation into a small decrease interval and a large decrease interval (explanation) (this allows for a more detailed analysis of the impact of different degrees of change on the output power of the power grid power station).

[0084] The changes in wind power generation at the main power station are correlated and matched with the output power of the power grid power station. The correlation and matching includes ensuring that the correspondence between the changes in wind power generation at the main power station and the output power of the power grid power station is analyzed within the same time window.

[0085] To determine the correlation between changes in wind power generation at the main power station and the output power of the power grid power station;

[0086] Based on the degree of correlation, the impact of the wind power generation of the main power station on the output power of the power grid power station in different ranges is analyzed respectively;

[0087] Based on the research objectives and practical needs, one or more renewable energy power plants will be selected as the main power plant. Factors such as installed capacity, geographical location, and importance to the power grid can be considered when selecting the main power plant. For example, renewable energy power plants with larger installed capacity and a significant impact on power grid supply can be selected as the main power plant.

[0088] By setting time windows and safety thresholds, the power correlation between the main substation and the power grid substation can be accurately quantified, providing a scientific basis for determining the ramp-up status and improving the system's adaptability to dynamic power environments.

[0089] The feature extraction module 130 responds to the correlation effect and is used to extract features based on the correlation effect, including extracting the wind power generation power corresponding to the significant decrease in output power in the main station. The significant decrease in output power includes a decrease of 5-10%, and marking the corresponding wind power generation power as the reference wind power generation power.

[0090] By marking reference wind power generation capacity, the system can quickly locate key renewable energy power plants that cause a drop in grid output power, thus improving fault location efficiency.

[0091] Furthermore, feature extraction transforms complex data into quantifiable reference metrics, reducing the complexity of subsequent analysis.

[0092] The data fusion processing module 140 includes a data acquisition unit 1401, a calculation unit 1402, and a judgment unit 1403.

[0093] The acquisition unit 1401 is used to acquire the time corresponding to the output power dropping to 5%, and based on the time, a time period is set, and the time period corresponding to the output power dropping from 1% to 5% is divided within the time period, and the time period is marked as the reference time period.

[0094] By dividing the reference time period, the system can quantify the temporal characteristics of changes in new energy output, providing a time benchmark for dynamic response; and the setting of the reference time period provides a data basis for predicting the subsequent rate of decrease in output power.

[0095] The calculation unit 1402 is a response acquisition unit used to calculate the regular change of the wind power generation power of the main station when the output power decreases by 1% as a calculation target.

[0096] By calculating the rate of change, the system can quantify the regularity of changes in new energy output and improve the accuracy of identifying the ramp-up state.

[0097] The regular changes provide a basis for dynamically adjusting power generation plans in power grid dispatching, thereby enhancing system flexibility;

[0098] The judgment unit 1403 is used to make relevant judgments based on the regular changes. The relevant judgments include: when the output power is decreasing, if the wind power generation power does not decrease and shows an increasing trend, then the system determines that the wind power generation power of each new energy power station is in the climbing (rising) state; otherwise, no judgment is made.

[0099] By using the judgment rules, the system can accurately distinguish between the ramp-up state of new energy power output and other states, thus avoiding misjudgment.

[0100] This accurate assessment provides a reliable basis for grid dispatching, helps to adjust power generation plans in advance, and reduces the impact of sudden changes in new energy output on the grid.

[0101] Within the calculation unit, the change in wind power generation at the main power station is calculated based on a 1% decrease in output power, using each 1% decrease as a calculation target. The calculation is performed using the following formula:

[0102] ; ;

[0103] In the formula, This indicates that the wind power generation capacity of the main station is in the [number]th [year]. The rate of change when the price decreases by 1%;

[0104] Indicates the output power of the power grid station in the th... The rate of change when the price decreases by 1%;

[0105] and The wind power generation capacity of the main station is respectively in the 1st Power values ​​at the beginning and end of a 1% decrease;

[0106] and The output power of the power grid station is respectively in the th The power values ​​at the beginning and end of a 1% decrease.

[0107] It also includes calculations based on the following formula:

[0108] ;

[0109] In the formula, Indicates the wind power generation capacity of the home game and the output power of power grid stations covariance;

[0110] and The wind power generation capacity of the main power station and the output power of the grid power station are respectively the wind power generation capacity of the main power station and the output power of the grid power station in the 1st The value that can be obtained when the decrease is 1%;

[0111] and These are the average values ​​of the wind power generation capacity of the main wind farm and the output power of the grid-connected wind farm, respectively, when the wind power generation capacity decreases by 1%.

[0112] This indicates the amount of a 1% decrease (i.e., how many times a 1% decrease occurred).

[0113] In the two calculation formulas mentioned above, the first formula is used to calculate the rate of change between the wind power generation power of the main wind farm and the output power of the grid farm. That is, by quantifying the power change of the two when the power decreases by 1%, it reflects the dynamic response relationship between the output of new energy and the grid load. The second formula calculates the covariance of the two to evaluate the synchronicity and correlation strength of the power change.

[0114] The connection between these two formulas is that the rate of change formula provides dynamic characteristics in the time dimension, while the covariance formula reveals the closeness of the changes between the two from a statistical perspective. The combination of the two can more comprehensively characterize the impact of new energy output on the power grid, thus providing a scientific basis for the system to determine the ramp-up state and predict changes in output power.

[0115] The correlation between the changes in wind power generation at the main power station and the output power of the power grid power station is calculated using the following formula:

[0116] ;

[0117] In the formula, Indicates the wind power generation capacity of the home game Output power of power grid stations The correlation coefficient between them;

[0118] Indicates the home game in the Wind power generation at each observation time;

[0119] Indicates the power grid station at the first Output power at each observation time, and correspond;

[0120] Indicates the wind power generation capacity of the main station The sample mean;

[0121] The calculation formula is This is used to reflect the average level of wind power generation at the main wind farm throughout the observation period.

[0122] Indicates the output power of the power grid station The sample mean;

[0123] The calculation formula is This is used to reflect the average output power of power grid stations throughout the observation period.

[0124] This indicates the total number of data points observed (i.e., the total number of observation times). For example, if 60 minutes of data were observed, then... =60).

[0125] The corresponding wind intensity is obtained based on the calculation results. The wind intensity is the wind intensity at which the output power decreases from 1% to 5%, and this wind intensity is marked as the reference wind intensity. When the output power of the power grid station decreases in the future, if the wind intensity corresponding to the decrease from 1% to 5% is lower than the reference wind intensity, the system determines that the wind power generation of each new energy station in the target area is on a downward trend; otherwise, no determination is made.

[0126] By referencing wind intensity, the system can predict future trends in renewable energy output and take preventative measures in advance. This prediction helps the power grid dispatch center smooth out fluctuations in renewable energy output and improve the stability of power grid operation.

[0127] The system acquires the wind intensity before the output power decreases by 1%. This includes wind intensity within the 10 minutes preceding the 1% decrease. Within those 10 minutes, it acquires the 6-10 most frequent wind intensities occurring before the 1% decrease. Based on this chronological order, it obtains the sequence of these 6-10 most frequent wind intensities and the time interval between adjacent intensities, marking this time interval as a reference time interval. If, at a future time, the target area experiences a wind intensity equal to the first wind intensity, and this wind intensity is slower than the reference time interval, it becomes the second wind intensity. The system then determines that the power grid station's output power will decrease slowly in the future. Conversely, if the wind intensity is faster than the reference time interval, it becomes the second wind intensity. A rapid decrease is defined as occurring at the same time as the reference time interval; a decrease slower than the reference time interval is considered a slow decrease.

[0128] If a wind intensity equal to the second and third wind intensities occurs faster than the reference time interval, but the output power of the power grid station does not decrease, the system determines that the output power of the power grid station will not decrease in the future; otherwise, no determination is made.

[0129] By using time interval references, the system can provide early warnings of the rate of change in output power, giving the power grid dispatching more time to adjust.

[0130] The early warning function enables the power grid to quickly adjust its operation mode when faced with sudden changes in the output of new energy sources, thereby reducing the impact on the stability of the power grid.

[0131] In reality, there are natural fluctuations in load. Under such natural fluctuations, the grid's output power may not decrease as wind power generation power decreases.

[0132] Electricity load fluctuates naturally with changes in time, season, weather, and other factors. In some cases, the period of reduced wind power generation coincides with the period of natural load decline, during which time the grid's output power may not decrease.

[0133] Furthermore, in addition to natural load fluctuations, the grid's output power will not decrease as wind power generation power decreases due to the grid-side power structure and dispatching, as well as the adjustment effect of the energy storage system.

[0134] Therefore, the determination in this embodiment has practical significance.

[0135] Based on the above, this application achieves real-time and accurate identification and prediction of the power output ramp-up status of new energy power plants by comprehensively collecting multi-level spatial data from both new energy power plants and power grid power plants, dynamically analyzing the correlation between wind power generation changes and grid output power, accurately extracting key features and quantifying the changes in patterns.

[0136] This embodiment, in conjunction with the above-mentioned new energy output ramp-up classification and identification system based on multi-level spatial scales, also proposes a working method for this system, as follows:

[0137] S10: Obtain new energy data corresponding to the multi-level space of the target area. The multi-level space includes each new energy power station and power grid power station in the target area. The new energy data is the wind power generation power of each new energy power station.

[0138] S20: Set up a data scenario and analyze the new energy data based on the data scenario. The data scenario includes taking the wind power generation of each new energy power station as the data scenario, giving a main power station in each new energy power station, and analyzing the correlation impact of the change in the wind power generation of the main power station on the output power of the power grid power station.

[0139] S30: Feature extraction is performed based on the associated impact, including extracting the wind power generation power corresponding to the significant decrease in output power from the main station. The significant decrease in output power includes a decrease of 5-10%, and the corresponding wind power generation power is marked as the reference wind power generation power.

[0140] S40: Collect the time taken for the output power to drop to 5%, and set a time period based on the time taken. Divide the time period into time periods corresponding to the output power dropping from 1% to 5%, and mark the time period as the reference time period.

[0141] S50: Calculate the regular change in wind power generation at the main station when the output power decreases by 1% as a calculation target;

[0142] S60: Make relevant judgments based on the regular changes. The relevant judgments include: when the output power is decreasing, if the wind power generation power does not decrease and shows an increasing trend, the system determines that the wind power generation power of each new energy power station is in the ramp-up state; otherwise, no judgment is made.

[0143] In summary, this invention, by comprehensively collecting multi-level spatial data from both renewable energy power plants and grid power plants, dynamically analyzes the correlation between wind power generation changes and grid output power, accurately extracts key features and quantifies patterns of change, achieving real-time and accurate identification and prediction of renewable energy output ramp-up status. Furthermore, the system not only effectively assesses the impact of renewable energy output fluctuations on grid stability but also possesses an early warning function, predicting grid output power trends in advance, providing a scientific basis for grid dispatch, thereby significantly improving grid operation stability and dispatch efficiency.

[0144] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A new energy output ramp-up classification and identification system based on multi-level spatial scales, characterized in that, include: The data acquisition module is used to acquire new energy data corresponding to the multi-level space of the target area. The multi-level space includes various new energy power stations and power grid power stations in the target area. The new energy data is the wind power generation power of each new energy power station. The data analysis module is used to set data scenarios and analyze the new energy data based on the data scenarios. The data scenarios include taking the wind power generation power of each new energy power station as the data scenario, giving a main power station among the new energy power stations, and analyzing the correlation impact of the changes in the wind power generation power of the main power station on the output power of the power grid power station. The feature extraction module responds to the correlation effect and is used to perform feature extraction based on the correlation effect, including extracting the wind power generation power corresponding to the significant decrease in output power in the main station, wherein the significant decrease in output power includes a decrease of 5-10%, and marking the corresponding wind power generation power as the reference wind power generation power. A data fusion processing module, comprising an acquisition unit, a calculation unit, and a judgment unit; The acquisition unit is used to acquire the time corresponding to the output power dropping to 5%, and based on the time, a time period is set, and within the time period, a time period corresponding to the output power dropping from 1% to 5% is divided, and the time period is marked as a reference time period. The calculation unit responds to the acquisition unit and is used to calculate the regular change of the wind power generation power of the main station when the output power decreases by 1% as a calculation target. The judgment unit is used to make relevant judgments based on the changes in the pattern. The relevant judgments include: when the output power is decreasing, if the wind power generation power does not decrease and shows an increasing trend, then the system determines that the wind power generation power of each new energy power station is in a ramp-up state; otherwise, no judgment is made.

2. The new energy output ramp-up classification and identification system based on multi-level spatial scale as described in claim 1, characterized in that, In the data analysis module, the correlation impact of changes in wind power generation at the home field on the output power of the power grid substation is analyzed. The analysis steps are as follows: Data cleaning is performed on the wind power generation capacity of each new energy power station and the output power of the power grid power station obtained in the target area. The data cleaning includes removing missing values, outliers or erroneous data from the power generation capacity and output power. Determine the time window for analyzing the correlation between changes in wind power generation and the output power of power grid substations; A safety threshold is set based on the changes in wind power generation during the home game; Within the selected time window, obtain the power variation of the wind power generation at the main station at adjacent time points or different time nodes. Statistical analysis was performed on the calculated power changes, and characteristic parameters were extracted. Based on the set safety thresholds, the changes in wind power generation at the main power station are divided into different intervals. The division method includes dividing the wind power generation into a small increase interval and a large increase interval when the wind power generation increases; and dividing the wind power generation into a small decrease interval and a large decrease interval when the wind power generation decreases. The changes in the wind power generation of the main power station are correlated and matched with the output power of the power grid power station. The correlation and matching includes ensuring that the correspondence between the changes in the wind power generation of the main power station and the output power of the power grid power station is analyzed within the same time window. To determine the correlation between changes in wind power generation at the main power station and the output power of the power grid power station; Based on the aforementioned correlation, the impact of the wind power generation capacity of the main power station on the output power of the power grid power station in different ranges is analyzed.

3. The new energy output ramp-up classification and identification system based on multi-level spatial scale as described in claim 1, characterized in that, In the calculation unit, the change in wind power generation at the main power station is calculated based on a 1% decrease in output power, using this decrease as a calculation target. The calculation is performed according to the following formula: ； ； In the formula, This indicates that the wind power generation capacity of the main wind farm is at the [number]th [year]. The rate of change when the price decreases by 1%; Indicates the output power of the power grid station in the th... The rate of change when the price decreases by 1%; and The wind power generation capacity of the main station is respectively in the 1st Power values ​​at the beginning and end of a 1% decrease; and The output power of the power grid station is respectively in the th The power values ​​at the beginning and end of a 1% decrease.

4. The new energy output ramp-up classification and identification system based on multi-level spatial scale as described in claim 3, characterized in that, It also includes calculations based on the following formula: ； In the formula, This indicates the wind power generation capacity of the home game. and the output power of power grid stations covariance; and The wind power generation capacity of the main wind farm and the output power of the grid station are respectively the wind power generation capacity of the main wind farm and the output power of the grid station in the th year. The value that can be obtained when the decrease is 1%; and These are the average values ​​of the wind power generation capacity of the main wind farm and the output power of the grid-connected wind farm, respectively, when the wind power generation capacity decreases by 1%. This indicates a decrease of 1%.

5. A new energy output ramp-up classification and identification system based on multi-level spatial scales as described in claim 2, characterized in that, The correlation between the changes in wind power generation at the main power station and the output power of the power grid power station is calculated using the following formula: ； In the formula, This indicates the wind power generation capacity of the home game. Output power of power grid stations The correlation coefficient between them; Indicates the home game in the Wind power generation at each observation time; Indicates the power grid station at the first Output power at each observation time, and correspond; Indicates the wind power generation capacity of the main station The sample mean; Indicates the output power of the power grid station The sample mean; This indicates the total number of observed data.

6. A new energy output ramp-up classification and identification system based on multi-level spatial scales as described in any one of claims 3 to 4, characterized in that, The corresponding wind intensity is obtained based on the calculation results. The wind intensity is the wind intensity that decreases from 1% to 5% of the output power. The wind intensity is marked as the reference wind intensity. When the output power of the power grid station decreases in the future, if the wind intensity corresponding to the decrease of 1% to 5% is lower than the reference wind intensity, the system determines that the wind power generation of each new energy station in the target area is in a downward trend. Conversely, no judgment is made.

7. The new energy output ramp-up classification and identification system based on multi-level spatial scale as described in claim 6, characterized in that, The system obtains the wind intensity before the output power decreases by 1%, including the wind intensity within the 10 minutes before the 1% decrease. Within these 10 minutes, it obtains the 6 to 10 most frequent wind intensities that occurred before the 1% decrease. Based on the time sequence, it obtains the order in which these 6 to 10 most frequent wind intensities occur and the time interval between adjacent wind intensities. This time interval is marked as a reference time interval. If, at a future time, a wind intensity equal to the first wind intensity appears in the target area, and a wind intensity equal to the second wind intensity appears at a slower time than the reference time interval, the system determines that the output power of the power grid station will decrease slowly in the future. Conversely, if a wind intensity equal to the second wind intensity occurs faster than the reference time interval, the system determines that the output power of the power grid station will decrease rapidly in the future.

8. The new energy output ramp-up classification and identification system based on multi-level spatial scale as described in claim 7, characterized in that, If a wind intensity equal to the second and third wind intensities occurs faster than the reference time interval, but the output power of the power grid station does not decrease, then the system determines that the output power of the power grid station will not decrease in the future. Conversely, no judgment is made.

9. A method applied to a new energy output ramp-up classification and identification system based on multi-level spatial scales as described in claim 1, characterized in that, Includes the following steps: Acquire new energy data corresponding to a multi-level space in the target area, wherein the multi-level space includes various new energy power stations and power grid power stations in the target area, and the new energy data is the wind power generation power of each new energy power station; A data scenario is set, and the new energy data is analyzed based on the data scenario. The data scenario includes taking the wind power generation of each new energy power station as the data scenario, giving a main power station in each new energy power station, and analyzing the correlation impact of the change in the wind power generation of the main power station on the output power of the power grid power station. Based on the aforementioned correlation, feature extraction is performed, including extracting the wind power generation power corresponding to the significant decrease in output power from the main power station, wherein the significant decrease in output power includes a decrease of 5% to 10%, and marking the corresponding wind power generation power as the reference wind power generation power. Collect the time taken for the output power to drop to 5%, and set a time period based on the time taken. Divide the time period into time periods corresponding to the output power dropping from 1% to 5%, and mark the time periods as reference time periods. The wind power generation power of the main station is calculated as a calculation target for each 1% decrease in output power; The system makes relevant judgments based on the aforementioned pattern of change. These judgments include determining that if the wind power generation does not decrease and shows an increasing trend when the output power is decreasing, the system determines that the wind power generation of each new energy power station is in a ramp-up state; otherwise, no judgment is made.

Images