New energy abnormal data monitoring, identification and optimization method for complex scenarios

Abstract

The present invention discloses a new energy abnormal data monitoring, identification and optimization method for complex scenarios, which relates to the technical field of new energy abnormal data monitoring, and specifically comprises: step one, collecting historical operation data of the new energy power generation side and historical multi-source data of the working scene of the new energy power generation side, screening the time period containing abnormal data, step two, in the time period of abnormal data affecting the new energy power generation, obtaining abnormal feature data by feature extraction, setting an abnormal degree index according to the abnormal feature data, step three, calculating the abnormal degree index of the new energy power generation side in real time, monitoring and identifying whether the data of the new energy power generation side in the current time period is abnormal, and optimizing the new energy abnormal data. The method realizes the accurate identification and efficient processing of the time period containing the new energy abnormal data, and significantly improves the accuracy and availability of the new energy abnormal data monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy abnormal data monitoring, and specifically relates to a new energy abnormal data monitoring, identification and optimization method for complex scenarios. Background Art

[0002] The current background of new energy abnormal data monitoring mainly focuses on the field of wind power generation. As a clean and renewable energy, wind energy has shown great potential in promoting economic development, protecting the environment and ecosystem due to its diverse energy structure characteristics, and its position in the energy structure is becoming increasingly prominent. With the continuous advancement of technology and the continuous support of policies, wind power generation has become an important part of the new energy field.

[0003] However, in the actual operation of wind power generation systems, a series of abnormal situations have emerged, which pose challenges to the stability and reliability of the system. These abnormal situations include, but are not limited to, failure of wind power generation equipment, damage to inverters, and cable breakage. These failures will not only cause a significant decline in the performance of the wind power generation system, but in severe cases will even cause the entire system to stop operating, thus seriously affecting the stability and reliability of power supply.

[0004] The existing method of judging whether the data is abnormal only by the threshold of the power output of the power generation equipment is obviously not accurate enough. This method may not only lead to false positives and false negatives, but also mislead the maintenance and management of the equipment, thereby increasing the operation and maintenance costs and reducing the overall efficiency of the system. At present, it is necessary to develop a more advanced and comprehensive abnormal data monitoring method to achieve accurate identification and timely warning of abnormal situations in new energy power generation. Summary of the invention

[0005] The purpose of the present invention is to provide a new energy abnormal data monitoring, identification and optimization method for complex scenarios, which is used to solve the technical problem that the identification of new energy power generation abnormal data is not accurate enough in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] New energy abnormal data monitoring, identification and optimization methods for complex scenarios, including:

[0008] Step 1: Collect historical operation data of the renewable energy power generation side and historical multi-source data of the working scenes of the renewable energy power generation side, and filter out time periods containing abnormal data;

[0009] Collect historical operation data, real-time operation data and historical multi-source data that affect the load changes on the renewable energy generation side stored in the database on the renewable energy generation side. The operation data includes the voltage, current and power generation of the renewable energy generation side in the operating state. The multi-source data includes the wind speed and light intensity of the renewable energy generation side in the working environment.

[0010] Step 2: During the period when the data affected by new energy power generation is abnormal, abnormal feature data is obtained by feature extraction, and an abnormal degree index is set according to the abnormal feature data;

[0011] Step 3: Calculate the abnormality degree index of the new energy power generation side in real time, monitor and identify whether the data on the new energy power generation side is abnormal by setting the abnormal range matching degree index, and optimize the abnormal data of new energy.

[0012] Furthermore, the time period containing abnormal data is filtered out. The specific method is as follows:

[0013] The time period is divided into T time periods, each time period contains N time points, the time length of adjacent time points is a fixed value, the first time point in each time period is recorded as the starting time point in chronological order, and the last time point is recorded as the ending time point. The formula Yc(t)=k1|lx(t)-sj(t)|*k2|yd(t)-sj(t)| is used to represent the abnormal index of the data affecting new energy power generation, where t represents the t-th time period, Yc(t) represents the abnormal index of the data affecting new energy power generation in the t-th time period, lx(t) represents the ideal power generation on the new energy power generation side in the t-th time period, sj(t) represents the actual power generation on the new energy power generation side in the t-th time period, yd(t) represents the power consumption of the power grid in the t-th time period, k1 represents the weight coefficient of the difference between the ideal power generation and the actual power generation, and k2 represents the weight coefficient of the difference between the actual power generation and the power consumption of the power grid;

[0014] A threshold R for the abnormal index of the data affecting new energy power generation is set. When the abnormal index of the data affecting new energy power generation in a certain time period is greater than or equal to R, the data affecting new energy power generation in this time period is judged to be abnormal. The abnormal index of the data affecting new energy power generation is used to determine the time periods in which all the data affecting new energy power generation are abnormal.

[0015] Furthermore, an abnormality degree index is set according to the abnormal characteristic data. The specific method is as follows:

[0016] Using the formula Gc(t)=k a *Pl(t)+k a *Dy(t)+k a*Dl(t) represents the abnormality index, where Gc(t) represents the abnormality index of the t-th time period, Pl(t) represents the frequency difference characteristic index of the t-th time period, Dy(t) represents the voltage difference characteristic index of the t-th time period, Dy(t) represents the current difference characteristic index of the t-th time period, and k a Represents the weight coefficient of the frequency difference characteristic index, k b Represents the weight coefficient of voltage difference characteristic index, k c Represents the weight coefficient of the current difference characteristic index.

[0017] Furthermore, the frequency difference characteristic indicators specifically include:

[0018] Using the formula represents the frequency difference characteristic index, where Pl(t) represents the frequency difference characteristic index of the t-th time period, p(t, k) represents the power generation at the k-th time point in the t-th time period, represents the average value of the generated power in the t-th time period, k represents the k-th time point in the t-th time period, k=1 represents the starting time point of the t-th time period, and k=N represents the ending time point of the t-th time period.

[0019] Furthermore, the voltage difference characteristic indicators specifically include:

[0020] Using the formula represents the voltage difference characteristic index, where Dy(t) represents the voltage difference characteristic index in the tth time period, U A (t,k) represents the voltage value of phase A in the three-phase voltage at time point k in the tth time period, U B (t, k) represents the B phase voltage value of the three-phase voltage at the kth time point in the tth time period, U C (t,k) represents the C phase voltage value of the three-phase voltage at the kth time point in the tth time period, It represents the average value of the three-phase voltage in the tth time period.

[0021] Furthermore, the current difference characteristic indicators specifically include:

[0022] Using the formula represents the current difference characteristic index, where Dl(t) represents the voltage difference characteristic index in the tth time period, I A (t,k) represents the current value of phase A in the three-phase current at time point k in the tth time period, I B (t,k) represents the B-phase current value of the three-phase current at the k-th time point in the t-th time period, I C (t,k) represents the C phase current value of the three-phase current at the kth time point in the tth time period, It represents the average value of the three-phase current in the tth time period.

[0023] Furthermore, an abnormal range matching degree index is set, and the specific method is as follows:

[0024] Based on the historical operation data of the new energy power generation side, determine the abnormality index of the time period containing abnormal data in the historical time period, obtain the abnormality index set with the abnormality index as an element, determine the range interval of the abnormality index in the abnormality index set according to the size relationship and release status of the abnormality index, and record the range interval as the historical abnormality range;

[0025] Based on the real-time collection of the operating status data of the renewable energy power generation side, the abnormality index of the renewable energy power generation side in the current time period is calculated, and the abnormality range of the current time period is determined, which is recorded as the real-time abnormality range;

[0026] The real-time abnormality degree range and the historical abnormality degree range are combined to establish an abnormality range matching degree index, and the formula Dl(t)=(L(t)+B)*(h(t)+A) is used to represent the abnormality range matching degree index, where Dl(t) represents the abnormality range matching degree index of the t-th time period, L(t) represents the range length of the public abnormality degree range of the t-th time period, h(t) represents the number of public abnormality degree indicators contained in the public abnormality degree range of the t-th time period, the public abnormality degree range refers to the range jointly included by the real-time abnormality degree range and the historical abnormality degree range, the number of public abnormality degree indicators refers to the number of elements in the historical abnormality degree indicator set contained in the public abnormality degree range, and A and B are both constant values.

[0027] Furthermore, the data on the renewable energy power generation side is monitored and identified to be abnormal, and the abnormal data on renewable energy is optimized. The specific methods are as follows:

[0028] A threshold value W of the abnormal range matching index is set. If the abnormal range matching index at the current moment is greater than W, the data on the new energy power generation side in the current time period is judged to be abnormal. By dynamically adjusting the output power of the generator, the distribution between different energy sources is optimized according to real-time weather data and energy supply conditions to ensure the maximization of the overall power generation efficiency. When abnormal new energy data is detected in the current time period, whether the new energy power generation is excessive or insufficient is detected. When the new energy power generation is excessive, the excess electric energy is stored; when the power generation is insufficient, the stored electric energy is released from the energy storage system to maintain the stable operation of the power grid.

[0029] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0030] 1. The present invention helps to accurately identify abnormal time periods by setting an abnormal index threshold R and comparing abnormal indicators in each time period, thereby avoiding false alarms or missed alarms that may be caused by a single threshold judgment. The method of the present invention not only considers operating data such as voltage, current and power generation on the renewable energy power generation side, but also incorporates multi-source data such as wind speed and light intensity, thereby being able to more comprehensively reflect the working status and external environment of the renewable energy power generation side, thereby improving the comprehensiveness of monitoring;

[0031] 2. The present invention quantifies the degree of abnormality in each time period by setting an abnormality degree index, thereby achieving a comprehensive and accurate assessment of the operating status of the renewable energy power generation side. By determining the real-time abnormality degree range and the historical abnormality degree range, it can quickly and accurately determine whether the data on the renewable energy power generation side is abnormal. At the same time, by introducing the abnormal range matching degree index, this method can further refine the accuracy of abnormal monitoring and ensure accurate identification of time periods containing new energy abnormal data. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A step diagram of a new energy abnormal data monitoring, identification and optimization method for complex scenarios is shown;

[0034] Figure 2 A step diagram of the abnormality degree index calculation method is shown. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] like Figure 1 , Figure 2 The new energy abnormal data monitoring, identification and optimization method for complex scenarios shown in the figure specifically includes the following steps:

[0037] Step 1: Collect historical operation data of the renewable energy power generation side and historical multi-source data of working scenarios of the renewable energy power generation side, and filter out time periods containing abnormal data.

[0038] Collect historical operation data, real-time operation data and historical multi-source data that affect the load change on the new energy generation side stored in the database on the new energy generation side, where the operation data includes the voltage, current and power generation on the new energy generation side in the operation state, and the multi-source data includes the wind speed and light intensity on the new energy generation side in the working environment, and process the collected data, such as: filling in missing values, normalization, and collectively refer to the processed historical operation data and historical multi-source data as new energy generation impact data;

[0039] The time period is divided into T time periods, each time period contains N time points, and the time length of adjacent time points is a fixed value. The first time point in each time period is recorded as the starting time point in chronological order, and the last time point is recorded as the ending time point. The impact data of renewable energy power generation in each time period is classified and analyzed. The power consumption on the grid side in each time period is determined by pre-setting the electric meter equipment on the grid side. The actual power generation on the renewable energy power generation side in each time period is determined based on the voltage, current and power generation on the renewable energy power generation side in each time period. According to the relationship between the power generation on the renewable energy power generation side and the wind speed and light intensity under ideal conditions, the ideal power generation on the renewable energy power generation side in different time periods is obtained. The abnormal index of renewable energy power generation impact data is set by comprehensively considering the ideal power generation on the renewable energy power generation side, the actual power generation and the power consumption on the grid side. The specific formula of the abnormal index of renewable energy power generation impact data is as follows:

[0040] Yc(t)=k1lx(t)-sj(t)|*k2|yd(t)-sj(t)|;

[0041] Wherein, t represents the t-th time period, Yc(t) represents the abnormal index of the data affecting renewable energy power generation in the t-th time period, lx(t) represents the ideal power generation on the renewable energy power generation side in the t-th time period, sj(t) represents the actual power generation on the renewable energy power generation side in the t-th time period, yd(t) represents the power consumption of the power grid in the t-th time period, k1 represents the weight coefficient of the difference between the ideal power generation and the actual power generation, and k2 represents the weight coefficient of the difference between the actual power generation and the power consumption of the power grid.

[0042] A threshold R for the abnormal index of the data affecting new energy power generation is set. When the abnormal index of the data affecting new energy power generation in a certain time period is greater than or equal to R, the data affecting new energy power generation in this time period is judged to be abnormal. The abnormal index of the data affecting new energy power generation is used to determine the time periods in which all the data affecting new energy power generation are abnormal.

[0043] Step 2: During the time period when the new energy power generation affects the data abnormality, abnormal feature data is obtained through feature extraction, and an abnormal degree index is set according to the abnormal feature data.

[0044] According to the new energy power generation impact data in the period of time when the new energy power generation impact data is abnormal, the change of the historical operation data of the new energy power generation side over time is determined. In combination with the power quality indicators and the technical specifications of the power grid, the abnormal feature data is extracted, and the abnormal degree index is set based on the abnormal feature data. The specific calculation formula of the abnormal degree index is as follows:

[0045] Gc(t)=k a *Pl(t)+k a *Dy(t)+k a *Dl(t);

[0046] Among them, Gc(t) represents the abnormality index of the t-th time period, Pl(t) represents the frequency difference characteristic index of the t-th time period, Dy(t) represents the voltage difference characteristic index of the t-th time period, Dy(t) represents the current difference characteristic index of the t-th time period, k a Represents the weight coefficient of the frequency difference characteristic index, k b Represents the weight coefficient of voltage difference characteristic index, k c Represents the weight coefficient of the current difference characteristic index.

[0047] Furthermore, the specific calculation formula of the frequency difference characteristic index is as follows:

[0048]

[0049] Among them, Pl(t) represents the frequency difference characteristic index of the t-th time period, p(t, k) represents the power generation at the k-th time point in the t-th time period, represents the average value of the generated power in the t-th time period, k represents the k-th time point in the t-th time period, k=1 represents the starting time point of the t-th time period, and k=N represents the ending time point of the t-th time period.

[0050] The specific calculation formula of the voltage difference characteristic index is as follows:

[0051]

[0052] Where Dy(t) represents the voltage difference characteristic index in the tth time period, U A (t,k) represents the voltage value of phase A in the three-phase voltage at time point k in the tth time period, U B (t, k) represents the B phase voltage value of the three-phase voltage at the kth time point in the tth time period, U C (t,k) represents the C phase voltage value of the three-phase voltage at the kth time point in the tth time period, It represents the average value of the three-phase voltage in the tth time period.

[0053] The specific calculation formula of the current difference characteristic index is as follows:

[0054]

[0055] Where Dl(t) represents the voltage difference characteristic index in the tth time period, I A (t,k) represents the current value of phase A in the three-phase current at time point k in the tth time period, I B (t,k) represents the B-phase current value of the three-phase current at the k-th time point in the t-th time period, I C (t,k) represents the C phase current value of the three-phase current at the kth time point in the tth time period, It represents the average value of the three-phase current in the tth time period.

[0056] Determine the abnormality index of each abnormal time period of the new energy power generation impact data, establish an abnormality index set with the abnormality index as an element, and record it as the historical abnormality index set. According to the size relationship and release status of the abnormality index, determine the range interval of the abnormality index in the abnormality index set, and require that the ratio of the number of abnormality indicators in the range interval to the total number of abnormality indicators is M%. In this embodiment, M=86 is set, and the abnormality range obtained from the historical operating status data is recorded as the historical abnormality range.

[0057] Step 3: Calculate the abnormality degree index of the new energy power generation side in real time, monitor and identify whether the data on the new energy power generation side is abnormal by setting the abnormal range matching degree index, and optimize the abnormal data of new energy.

[0058] Based on the real-time collection of the operating status data of the new energy power generation side, the abnormality index of the new energy power generation side in the current time period is calculated. The abnormality index of the new energy power generation side calculated in the current time period is set as Y. According to the preset abnormality deviation value R, the abnormality range of the current time period is determined to be [YR, Y+R], which is recorded as the real-time abnormality range. The real-time abnormality range and the historical abnormality range are combined to establish the abnormality range matching index. Based on the abnormality range matching index, it is determined whether the data of the new energy power generation side in the current time period is abnormal. The specific calculation formula of the abnormality range matching index is as follows:

[0059] Dl(t)=(L(t)+B)*(h(t)+A);

[0060] Wherein, Dl(t) represents the abnormal range matching degree index of the t-th time period, L(t) represents the range length of the common abnormal degree range of the t-th time period, h(t) represents the number of common abnormal degree indicators contained in the common abnormal degree range of the t-th time period, the common abnormal degree range refers to the range jointly included by the real-time abnormal degree range and the historical abnormal degree range, the number of common abnormal degree indicators refers to the number of elements in the historical abnormal degree indicator set contained in the common abnormal degree range, A and B are both constant values, and in this embodiment, A=4 and B=4 are set.

[0061] Set the abnormal range matching index threshold W. If the abnormal range matching index at the current moment is greater than W, it is judged that the data on the new energy power generation side in the current time period is abnormal, that is, it is detected that there is abnormal new energy data in the current time period, and the power generation strategy in the current time period needs to be adjusted, including: output power adjustment, energy distribution optimization and energy storage system scheduling;

[0062] Output power adjustment specifically refers to dynamically adjusting the output power of the generator to avoid overload or inefficient operation when abnormal new energy data is detected in the current time period;

[0063] Energy allocation optimization specifically means that when abnormal data of new energy sources is detected in the current time period, the allocation between different energy sources is optimized according to real-time weather data and energy supply conditions to ensure the maximization of overall power generation efficiency;

[0064] The energy storage system scheduling specifically refers to detecting whether the power generation of new energy is excessive or insufficient when abnormal data of new energy is monitored in the current time period. When the power generation of new energy is excessive, the excess electricity can be stored; when the power generation is insufficient, the electricity is released from the energy storage system to maintain the stable operation of the power grid.

[0065] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0066] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A new energy abnormal data monitoring, identification and optimization method for complex scenarios, characterized by: include: Step 1: Collect historical operation data of the renewable energy power generation side and historical multi-source data of the working scenes of the renewable energy power generation side, and filter out time periods containing abnormal data; Collect historical operation data, real-time operation data and historical multi-source data that affect the load changes on the renewable energy generation side stored in the database on the renewable energy generation side. The operation data includes the voltage, current and power generation of the renewable energy generation side in the operating state. The multi-source data includes the wind speed and light intensity of the renewable energy generation side in the working environment. Step 2: During the period when the data affected by new energy power generation is abnormal, abnormal feature data is obtained by feature extraction, and an abnormal degree index is set according to the abnormal feature data; Step 3: Calculate the abnormality degree index of the new energy power generation side in real time, monitor and identify whether the data on the new energy power generation side is abnormal by setting the abnormal range matching degree index, and optimize the abnormal data of new energy.

2. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 1 is characterized in that: Filter the time period containing abnormal data as follows: The time period is divided into T time periods, each time period contains N time points, the time length of adjacent time points is a fixed value, the first time point in each time period is recorded as the starting time point in chronological order, and the last time point is recorded as the ending time point. The formula Yc(t)=k1|lx(t)-sj(t)|*k2|yd(t)-sj(t)| is used to represent the abnormal index of the data affecting new energy power generation, where t represents the t-th time period, Yc(t) represents the abnormal index of the data affecting new energy power generation in the t-th time period, lx(t) represents the ideal power generation on the new energy power generation side in the t-th time period, sj(t) represents the actual power generation on the new energy power generation side in the t-th time period, yd(t) represents the power consumption of the power grid in the t-th time period, k1 represents the weight coefficient of the difference between the ideal power generation and the actual power generation, and k2 represents the weight coefficient of the difference between the actual power generation and the power consumption of the power grid; A threshold R for the abnormal index of the data affecting new energy power generation is set. When the abnormal index of the data affecting new energy power generation in a certain time period is greater than or equal to R, the data affecting new energy power generation in this time period is judged to be abnormal. The abnormal index of the data affecting new energy power generation is used to determine the time period in which all the data affecting new energy power generation are abnormal.

3. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 1 is characterized in that: The abnormality degree index is set according to the abnormal characteristic data. The specific method is as follows: Using the formula Gc(t)=k a *Pl(t)+k a *Dy(t)+k a *Dl(t) represents the abnormality index, where Gc(t) represents the abnormality index of the t-th time period, Pl(t) represents the frequency difference characteristic index of the t-th time period, Dy(t) represents the voltage difference characteristic index of the t-th time period, Dy(t) represents the current difference characteristic index of the t-th time period, and k a Represents the weight coefficient of the frequency difference characteristic index, k b Represents the weight coefficient of voltage difference characteristic index, k c Represents the weight coefficient of the current difference characteristic index.

4. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 3 is characterized in that: Frequency difference characteristic indicators, including: Using the formula represents the frequency difference characteristic index, where Pl(t) represents the frequency difference characteristic index of the t-th time period, p(t, k) represents the power generation at the k-th time point in the t-th time period, represents the average value of the generated power in the t-th time period, k represents the k-th time point in the t-th time period, k=1 represents the starting time point of the t-th time period, and k=N represents the ending time point of the t-th time period.

5. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 3 is characterized in that: Voltage difference characteristic indicators, including: Using the formula represents the voltage difference characteristic index, where Dy(t) represents the voltage difference characteristic index in the tth time period, U A (t,k) represents the voltage value of phase A in the three-phase voltage at time point k in the tth time period, U B (t, k) represents the B phase voltage value of the three-phase voltage at the kth time point in the tth time period, U C (t,k) represents the C phase voltage value of the three-phase voltage at the kth time point in the tth time period, It represents the average value of the three-phase voltage in the tth time period.

6. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 3 is characterized in that: Current difference characteristic indicators, including: Using the formula represents the current difference characteristic index, where Dl(t) represents the voltage difference characteristic index in the tth time period, I A (t,k) represents the current value of phase A in the three-phase current at time point k in the tth time period, I B (t,k) represents the B-phase current value of the three-phase current at the k-th time point in the t-th time period, I C (t,k) represents the C phase current value of the three-phase current at the kth time point in the tth time period, It represents the average value of the three-phase current in the tth time period.

7. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 1 is characterized in that: Set the abnormal range matching degree index. The specific method is: Based on the historical operation data of the new energy power generation side, determine the abnormality index of the time period containing abnormal data in the historical time period, obtain the abnormality index set with the abnormality index as an element, determine the range interval of the abnormality index in the abnormality index set according to the size relationship and release status of the abnormality index, and record the range interval as the historical abnormality range; Based on the real-time collection of the operating status data of the renewable energy power generation side, the abnormality index of the renewable energy power generation side in the current time period is calculated, and the abnormality range of the current time period is determined, which is recorded as the real-time abnormality range; The real-time abnormality degree range and the historical abnormality degree range are combined to establish an abnormality range matching degree index, and the formula Dl(t)=(L(t)+B)*(h(t)+A) is used to represent the abnormality range matching degree index, where Dl(t) represents the abnormality range matching degree index of the t-th time period, L(t) represents the range length of the public abnormality degree range of the t-th time period, h(t) represents the number of public abnormality degree indicators contained in the public abnormality degree range of the t-th time period, the public abnormality degree range refers to the range jointly included by the real-time abnormality degree range and the historical abnormality degree range, the number of public abnormality degree indicators refers to the number of elements in the historical abnormality degree indicator set contained in the public abnormality degree range, and A and B are both constant values.

8. The new energy abnormal data monitoring, identification and optimization method for complex scenarios according to claim 1 is characterized in that: Monitor and identify whether the data on the renewable energy power generation side is abnormal, and optimize the abnormal data on renewable energy. The specific methods are as follows: A threshold value W of the abnormal range matching index is set. If the abnormal range matching index at the current moment is greater than W, the data on the new energy power generation side in the current time period is judged to be abnormal. By dynamically adjusting the output power of the generator, the distribution between different energy sources is optimized according to real-time weather data and energy supply conditions to ensure the maximization of the overall power generation efficiency. When abnormal new energy data is detected in the current time period, whether the new energy power generation is excessive or insufficient is detected. When the new energy power generation is excessive, the excess electric energy is stored; when the power generation is insufficient, the stored electric energy is released from the energy storage system to maintain the stable operation of the power grid.

Images