Intelligent monitoring and early warning system of photovoltaic power generation in the substation area based on time series analysis

Abstract

The present invention relates to the field of data monitoring technology, and specifically to an intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis; obtaining power generation fluctuation characteristic values ​​and reference photovoltaic panels according to data fluctuation characteristics of power generation characteristic sequences of all dimensions of photovoltaic panels; obtaining power generation difference characteristic values ​​according to difference characteristics of power generation fluctuation characteristic values ​​between any photovoltaic panel and reference photovoltaic panel, and similar characteristics of power generation characteristic sequences of all dimensions; obtaining fault probability values ​​according to position distance characteristics between any photovoltaic panel and other photovoltaic panels, difference characteristics of power generation difference characteristic values, and power generation difference characteristic values ​​of any photovoltaic panel. The present invention obtains an abnormality index of any photovoltaic panel according to the fault probability value of any photovoltaic panel and the difference characteristics of power generation of any photovoltaic panel and other photovoltaic panels; monitors power generation status according to the abnormality index, improves the monitoring accuracy of photovoltaic panel power generation, and makes the power system run more stably.

Description

Technical Field

[0001] The present invention relates to the field of data monitoring technology, and in particular to an intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis. Background Art

[0002] Photovoltaic power generation in a substation refers to a power generation method that uses photovoltaic technology to convert solar energy into electrical energy in a specific area of ​​the power system. In the process of photovoltaic power generation, it is necessary to monitor the working status of photovoltaic components in real time and conduct data analysis, which helps to timely discover and warn potential faults, thereby reducing operating costs and maintenance risks. Photovoltaic panels are one of the important components in the power generation system. Their quality and working stability affect the power generation efficiency. Photovoltaic panels are prone to dust coverage and line aging when they are outdoors for a long time, which affects the power generation efficiency. Therefore, it is necessary to monitor and analyze the working status of photovoltaic panels during operation to ensure the operating efficiency and reliability of the photovoltaic system. When monitoring the quality and working status of photovoltaic panels, they may be affected by factors such as weather and cloud cover, resulting in interference with the stability and quality assessment of the photovoltaic panels, making the power generation monitoring accuracy of photovoltaic panels low, affecting the operating stability of the power generation system. Summary of the invention

[0003] In order to solve the above-mentioned technical problem that the accuracy of photovoltaic panel power generation monitoring is low due to interference from factors such as weather and clouds, the purpose of the present invention is to provide a photovoltaic power generation intelligent monitoring and early warning system based on time series analysis. The technical solution adopted is as follows:

[0004] The data acquisition module is used to obtain the location of different photovoltaic panels in the area and the power generation characteristic sequences in different dimensions;

[0005] The first data analysis module is used to obtain the power generation fluctuation characteristic value of the photovoltaic panel according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel; obtain the reference photovoltaic panel according to the power generation fluctuation characteristic values ​​of all photovoltaic panels; obtain the power generation difference characteristic value according to the difference characteristics of the power generation fluctuation characteristic value between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequence of all dimensions;

[0006] A second data analysis module is used to obtain a fault probability value according to the position distance characteristics between the arbitrary photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of the arbitrary photovoltaic panels;

[0007] The power generation abnormality monitoring module is used to obtain the abnormality index of the arbitrary photovoltaic panel according to the failure probability value of the arbitrary photovoltaic panel and the difference characteristics of the power generation of the arbitrary photovoltaic panel and other photovoltaic panels; and monitor the power generation state according to the abnormality index.

[0008] Furthermore, the step of obtaining the power generation fluctuation characteristic value of the photovoltaic panel according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel includes:

[0009] The sum of the average absolute error of the power generation characteristic sequence and a preset minimum positive number is calculated to obtain the fluctuation factor of the power generation characteristic sequence; the product of the fluctuation factors of the power generation characteristic sequence of all dimensions of the photovoltaic panel is calculated to obtain the power generation fluctuation characteristic value of the photovoltaic panel.

[0010] Furthermore, the step of obtaining a reference photovoltaic panel according to the power generation fluctuation characteristic values ​​of all photovoltaic panels includes:

[0011] The photovoltaic panels whose average values ​​of the power generation characteristic sequences are not a constant of 0 are sorted from small to large according to the power generation fluctuation characteristic values, and the photovoltaic panel ranked first in the sorting is used as the reference photovoltaic panel.

[0012] Furthermore, the step of obtaining the power generation difference characteristic value according to the difference characteristics of the power generation fluctuation characteristic value between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequence in all dimensions includes:

[0013] Calculate the absolute value of the difference between the power generation fluctuation characteristic values ​​of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the fluctuation difference value; calculate the dynamic time warping distance of the power generation characteristic sequence of the same dimension of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the change difference value; calculate the sum of the change difference value and a preset minimum positive number to obtain the change difference characteristic value; calculate the product of all change difference characteristic values ​​of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the comprehensive change difference characteristic value; calculate the product of the comprehensive change difference characteristic value and the fluctuation difference value to obtain the power generation difference characteristic value of the arbitrary photovoltaic panel.

[0014] Furthermore, the step of obtaining the fault probability value according to the position distance characteristics between the arbitrary photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of the arbitrary photovoltaic panels includes:

[0015] Calculate the sum of the Euclidean distances between any photovoltaic panel and all other photovoltaic panels to obtain a comprehensive distance value; calculate the ratio of the Euclidean distance between any photovoltaic panel and any other photovoltaic panel to the comprehensive distance value and negatively correlate and map them to obtain a distance weight coefficient; calculate the sum of the power generation difference characteristic value of any other photovoltaic panel and a preset minimum positive number to obtain a power generation difference characterization value; calculate the ratio of the power generation difference characteristic value of any photovoltaic panel to the power generation difference characterization value of any other photovoltaic panel to obtain a difference factor; calculate the product of the difference factor and the distance weight coefficient to obtain a weighted difference factor between any photovoltaic panel and any other photovoltaic panel; calculate the sum of the weighted difference factors between any photovoltaic panel and all other photovoltaic panels to obtain a comprehensive difference coefficient; calculate the product of the power generation difference characteristic value of any photovoltaic panel and the comprehensive difference coefficient to obtain the fault probability value.

[0016] Furthermore, the step of obtaining the abnormality index of the arbitrary photovoltaic panel according to the failure probability value of the arbitrary photovoltaic panel and the difference characteristics of the power generation of the arbitrary photovoltaic panel and other photovoltaic panels includes:

[0017] The difference between the total power generation of all photovoltaic panels in the area and the power generation of any photovoltaic panel is calculated to obtain an electric energy difference value; the product of the fault probability value and the electric energy difference value is calculated and normalized to obtain an abnormality index of any photovoltaic panel.

[0018] Furthermore, the step of monitoring the power generation state according to the abnormal index includes:

[0019] When the abnormal index of any photovoltaic panel exceeds a preset abnormal threshold, the power generation state of any photovoltaic panel is abnormal.

[0020] Furthermore, the power generation characteristic sequences of different dimensions are current time series and voltage time series respectively.

[0021] The present invention has the following beneficial effects:

[0022] In the present invention, obtaining the power generation fluctuation characteristic value can preliminarily determine the abnormal power generation of the photovoltaic panel according to the fluctuation characteristics of the power generation characteristic sequence; obtaining the reference photovoltaic panel can determine the photovoltaic panel with normal power generation in the substation, which is conducive to analyzing the abnormal degree of other photovoltaic panels and improving the accuracy of power generation monitoring; obtaining the power generation difference characteristic value can determine the difference degree of power generation characteristics between any photovoltaic panel and the normal photovoltaic panel, and improve the accuracy of monitoring abnormal photovoltaic panels. Since the power generation fluctuation of the photovoltaic panel is not only caused by the failure of the photovoltaic panel, but also related to the weather and clouds, in order to further improve the monitoring accuracy, avoid the abnormal power generation of the photovoltaic panel caused by the weather and clouds from being mistaken for power generation failure; thus, a comprehensive analysis is performed based on the location distance characteristics of the photovoltaic panel and the power generation difference characteristic value between the photovoltaic panels to obtain the fault probability value; the fault probability value can further improve the monitoring accuracy and reduce the probability of misjudgment. According to the fault probability value and the power generation, the abnormal photovoltaic panels in the substation can be accurately monitored, reducing the interference of weather and clouds on the power generation monitoring of the photovoltaic panel; improving the monitoring accuracy of photovoltaic panel power generation, making the power system run more stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0024] Figure 1 A block diagram of an intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the intelligent monitoring and early warning system for photovoltaic power generation in the substation area based on time series analysis proposed by the present invention are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0026] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0027] The following is a detailed description of a specific scheme of an intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis provided by the present invention in conjunction with the accompanying drawings.

[0028] See also Figure 1 , which shows a block diagram of a photovoltaic power generation intelligent monitoring and early warning system based on time series analysis provided by an embodiment of the present invention, the system includes the following modules:

[0029] The data acquisition module S1 is used to obtain the locations of different photovoltaic panels in the area and the power generation characteristic sequences in different dimensions.

[0030] In the embodiment of the present invention, the implementation scenario is to monitor the power generation status of the photovoltaic panel; first, the location of different photovoltaic panels in the substation and the power generation feature sequences of different dimensions are obtained. In the embodiment of the present invention, the power generation feature sequences of different dimensions are respectively the current time series and the voltage time series; a power generation feature sequence is obtained every 60 minutes, and the implementer can determine the length and acquisition frequency of the power generation feature sequence according to the implementation scenario. Since the photovoltaic panels are arranged outdoors with strong light, they are prone to animal damage, dust obstruction and line aging, which affect the power generation efficiency and stability; therefore, it is necessary to monitor the photovoltaic panels to ensure the power generation efficiency and stability. The power generation, voltage and current of the photovoltaic panels can be used to identify whether the photovoltaic panels are generating electricity normally, but during the monitoring process, factors such as weather and clouds will affect the analysis results. For example, clouds appear to block some photovoltaic panels in the substation, resulting in insufficient light intensity, abnormal characteristics such as power generation and power, so that the blocked photovoltaic panels may be misjudged as faulty photovoltaic panels. Therefore, in order to improve the accuracy of photovoltaic panel monitoring and ensure the stable operation of the power system, it is necessary to analyze the power generation characteristics of photovoltaic panels more comprehensively.

[0031] The first data analysis module S2 is used to obtain the power generation fluctuation characteristic value of the photovoltaic panel according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel; obtain the reference photovoltaic panel according to the power generation fluctuation characteristic values ​​of all photovoltaic panels; obtain the power generation difference characteristic value according to the difference characteristics of the power generation fluctuation characteristic values ​​between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequence of all dimensions.

[0032] When the photovoltaic panel is aged or blocked by dust, the power generation stability of the photovoltaic panel is poor, so the power generation fluctuation characteristic value of the photovoltaic panel is obtained according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel; preferably, in the embodiment of the present invention, the step of obtaining the power generation fluctuation characteristic value includes: calculating the sum of the average absolute error of the power generation characteristic sequence and the preset minimum positive number to obtain the fluctuation factor of the power generation characteristic sequence; it should be noted that the average absolute error belongs to the prior art and is the average of the absolute values ​​of the deviations of all single observations in the sequence from the arithmetic mean; the larger the average absolute error, the more obvious the data fluctuation characteristics of the power generation characteristic sequence and the worse the power generation stability; in the embodiment of the present invention, the preset minimum positive number is 0.01 to avoid the situation of constant 0. Calculate the product of the fluctuation factors of the power generation characteristic sequence of all dimensions of the photovoltaic panel to obtain the power generation fluctuation characteristic value of the photovoltaic panel; in the embodiment of the present invention, it is the current dimension and the voltage dimension, and calculate the product of the fluctuation factors of the current time series and the voltage time series; when the power generation fluctuation characteristic value is larger, it means that the power generation of the photovoltaic panel is more unstable and the failure is more likely to occur.

[0033] Furthermore, when the power generation fluctuation characteristic value is smaller, it means that the power generation of the photovoltaic panel is more stable. The photovoltaic panel can be used as a reference, and a comparison analysis is performed based on the reference photovoltaic panel to determine the degree of abnormality of any photovoltaic panel. Therefore, a reference photovoltaic panel is obtained based on the power generation fluctuation characteristic values ​​of all photovoltaic panels; preferably, in an embodiment of the present invention, the step of obtaining a reference photovoltaic panel includes: sorting the photovoltaic panels whose average value of the power generation characteristic sequence is not a constant 0 from small to large according to the power generation fluctuation characteristic value, and taking the photovoltaic panel in the first place in the sorting as the reference photovoltaic panel. The purpose of selecting photovoltaic panels whose average value of the power generation characteristic sequence is not a constant 0 is to eliminate photovoltaic panels that are completely faulty and do not generate electricity. The power generation fluctuation characteristic value of photovoltaic points that do not generate electricity at all is 0. If they are involved in the sorting, it will affect the subsequent analysis. The reference photovoltaic panel obtained can be considered as a photovoltaic panel with higher power generation efficiency and stability in the entire area. Comparing and analyzing any photovoltaic panel with the reference photovoltaic panel can determine the degree of failure of any photovoltaic panel. The greater the difference between the power generation characteristic sequence of any photovoltaic panel and that of the reference photovoltaic panel, and the greater the power generation fluctuation characteristic value of the arbitrary photovoltaic panel, the more likely that the arbitrary photovoltaic panel will fail; therefore, the power generation difference characteristic value is obtained based on the difference characteristics of the power generation fluctuation characteristic values ​​between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequences in all dimensions, and the arbitrary photovoltaic panel does not include the reference photovoltaic panel.

[0034] Preferably, in an embodiment of the present invention, the step of obtaining the power generation difference characteristic value includes: calculating the absolute value of the difference between the power generation fluctuation characteristic value of any photovoltaic panel and the reference photovoltaic panel to obtain the fluctuation difference value; because the power generation fluctuation characteristic value of the reference photovoltaic panel is the smallest, the larger the fluctuation difference value, the more likely the arbitrary photovoltaic panel is abnormal. Calculate the dynamic time warping distance of the power generation characteristic sequence of the same dimension of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the change difference value; it should be noted that the dynamic time warping distance is obtained by the existing DTW dynamic time warping algorithm, and the specific steps are not repeated. When the difference in the change characteristics of the two sequences is greater, the larger the dynamic time warping distance is, the larger the change difference value is. Calculate the sum of the change difference value and the preset minimum positive number to obtain the change difference characteristic value; the preset minimum positive number is 0.01 to avoid the situation where the change difference value is 0. Calculate the product of all the change difference characteristic values ​​of any photovoltaic panel and the reference photovoltaic panel to obtain the comprehensive change difference characteristic value; when the comprehensive change difference characteristic value is larger, the power generation characteristic sequence of the arbitrary photovoltaic panel and the reference photovoltaic panel is more dissimilar, and the arbitrary photovoltaic panel is more likely to be abnormal. Calculate the product of the comprehensive change difference characteristic value and the fluctuation difference value to obtain the power generation difference characteristic value of the arbitrary photovoltaic panel. The larger the power generation difference characteristic value, the greater the difference between the power generation characteristics of the arbitrary photovoltaic panel and the power generation characteristics of the reference photovoltaic panel, and the more abnormal the arbitrary photovoltaic panel is. The formula for obtaining the power generation difference characteristic value includes:

[0035]

[0036] Where W represents the power generation difference characteristic value of any photovoltaic panel, T represents the power generation fluctuation characteristic value of any photovoltaic panel, and E represents the power generation fluctuation characteristic value of the reference photovoltaic panel. represents the fluctuation difference value, M represents the number of dimensions of the power generation feature sequence, and in the embodiment of the present invention, M is 2, i.e., current and voltage; represents the change difference value of the mth dimension, a represents a preset minimum positive number, represents the change difference eigenvalue, Represents the comprehensive change difference eigenvalue.

[0037] The second data analysis module S3 is used to obtain a fault probability value according to the position distance characteristics between any photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of any photovoltaic panel.

[0038] After obtaining the power generation difference characteristic values ​​of all photovoltaic panels, it is necessary to determine the reasons for the power generation difference with the reference photovoltaic panel; because the cloud covers some photovoltaic panels in the substation area, it will also cause differences in the power generation characteristics of this type of photovoltaic panel and the reference photovoltaic panel, and this type of photovoltaic panel usually appears in a small area; and photovoltaic panels with faults such as dust coverage and line aging often appear randomly, so the location characteristics of the photovoltaic panels can be combined for further analysis. Therefore, the fault probability value is obtained based on the location distance characteristics between any photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of any photovoltaic panel.

[0039] Preferably, in an embodiment of the present invention, the step of obtaining a fault probability value includes: calculating the sum of the Euclidean distances between the arbitrary photovoltaic panel and all other photovoltaic panels to obtain a comprehensive distance value; calculating the ratio of the Euclidean distance between the arbitrary photovoltaic panel and any other photovoltaic panel to the comprehensive distance value and negatively correlating and mapping them to obtain a distance weight coefficient; the closer any other photovoltaic panel is to the arbitrary photovoltaic panel, the larger the distance weight coefficient is, and the more reference-based the power generation characteristics of the arbitrary other photovoltaic panel are. Calculate the sum of the power generation difference characteristic value of the arbitrary other photovoltaic panel and a preset minimum positive number to obtain a power generation difference characterization value; the preset minimum positive number is 0.01 to avoid the situation where the power generation difference characteristic value is 0. Calculate the ratio of the power generation difference characteristic value of the arbitrary photovoltaic panel to the power generation difference characterization value of any other photovoltaic panel to obtain a difference factor; the larger the difference factor is, the more abnormal the power generation characteristics of the arbitrary photovoltaic panel are. Calculate the product of the difference factor and the distance weight coefficient to obtain the weighted difference factor between the arbitrary photovoltaic panel and any other photovoltaic panel; when the weighted difference factor is larger, it means that the distance between the arbitrary photovoltaic panel and the arbitrary photovoltaic panel is closer, and the power generation difference characterization value of the arbitrary photovoltaic panel is greater than the power generation difference characterization value of the arbitrary photovoltaic panel, the arbitrary photovoltaic panel is more likely to be abnormal power generation caused by line aging and dust coverage. On the contrary, if the cloud is blocked and any other photovoltaic panel is normal, the more similar the power generation difference characterization value of the arbitrary photovoltaic panel and any other photovoltaic panel with a closer distance is, the closer the difference factor is to 1, and the smaller the weighted difference factor is. Calculate the sum of the weighted difference factors of the arbitrary photovoltaic panel and all other photovoltaic panels to obtain the comprehensive difference coefficient; when the comprehensive difference coefficient of the arbitrary photovoltaic panel is larger, it means that the difference factors of the arbitrary photovoltaic panel and other photovoltaic panels around it and at a longer distance are larger, and the arbitrary photovoltaic panel is more likely to be unstable power generation caused by line aging and dust coverage. Calculate the product of the power generation difference characteristic value of any photovoltaic panel and the comprehensive difference coefficient to obtain the fault probability value; the larger the fault probability value, the more likely it is that the power generation of any photovoltaic panel is unstable due to line aging and dust coverage. The formula for obtaining the fault probability value includes:

[0040]

[0041] In the formula, represents the failure probability value of any ith photovoltaic panel, represents the power generation difference characteristic value of the i-th arbitrary photovoltaic panel, N represents the number of photovoltaic panels other than the arbitrary photovoltaic panel, represents the power generation difference characteristic value of the nth other photovoltaic panel, a represents a preset minimum positive number, represents the power generation difference characterization value, represents the difference factor, It represents the Euclidean distance between any photovoltaic panel and the nth photovoltaic panel, S represents the comprehensive distance value, represents the distance weight coefficient, represents the weighted difference factor, represents the comprehensive coefficient of variation.

[0042] The power generation abnormality monitoring module S4 is used to obtain the abnormality index of any photovoltaic panel according to the fault probability value of any photovoltaic panel and the difference characteristics of the power generation of any photovoltaic panel and other photovoltaic panels; and monitor the power generation state according to the abnormality index.

[0043] After obtaining the fault probability value of the photovoltaic panels in the substation, the photovoltaic panels that may be abnormal can be further comprehensively judged in combination with the power generation of the photovoltaic panels. Therefore, the abnormal index of any photovoltaic panel is obtained according to the fault probability value of any photovoltaic panel and the difference characteristics of the power generation of any photovoltaic panel and other photovoltaic panels; preferably, in the embodiment of the present invention, the step of obtaining the abnormal index includes: calculating the difference between the total power generation of all photovoltaic panels in the substation and the power generation of any photovoltaic panel, and obtaining the electric energy difference value; it should be noted that the power generation can be obtained according to the current time series and the voltage time series, and the specific steps are not repeated. Since the clouds will move, the short-term cloud cover will not cause the power generation of the photovoltaic panel to drop too much. Therefore, when the electric energy difference value is larger, it means that the arbitrary photovoltaic panel is more likely to be caused by line aging, dust cover and other situations. Power generation abnormality, timely warning and maintenance are required. Calculate the product of the fault probability value and the electric energy difference value and normalize them to obtain the abnormal index of the arbitrary photovoltaic panel; when the abnormal index is larger, it means that the arbitrary photovoltaic panel is more likely to be caused by line aging, dust cover and other situations. Power generation abnormality, rather than weather and cloud problems.

[0044] Furthermore, the power generation state can be monitored according to the abnormal index, specifically including: when the abnormal index of any photovoltaic panel exceeds the preset abnormal threshold, the power generation state of any photovoltaic panel is abnormal, and the photovoltaic panel with abnormal power generation state needs to be warned and maintained in time; in the embodiment of the present invention, the preset abnormal threshold is 0.6, which can be determined by the implementer according to the implementation scenario. Monitoring the power generation process of the photovoltaic panel according to the abnormal index improves the accuracy of power generation monitoring and makes the operation of the power generation system more stable.

[0045] In summary, the embodiment of the present invention provides a smart monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis; the power generation fluctuation characteristic value and the reference photovoltaic panel are obtained according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel; the power generation difference characteristic value is obtained according to the difference characteristics of the power generation fluctuation characteristic value between any photovoltaic panel and the reference photovoltaic panel, and the similar characteristics of the power generation characteristic sequence of all dimensions; the fault probability value is obtained according to the position distance characteristics between any photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic value, and the power generation difference characteristic value of any photovoltaic panel. The present invention obtains the abnormal index of any photovoltaic panel according to the fault probability value of any photovoltaic panel and the difference characteristics of the power generation of any photovoltaic panel and other photovoltaic panels; the power generation status is monitored according to the abnormal index, which improves the monitoring accuracy of photovoltaic panel power generation and makes the power system operation more stable.

[0046] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A smart monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis, characterized in that: The system includes the following modules: The data acquisition module is used to obtain the location of different photovoltaic panels in the area and the power generation characteristic sequences in different dimensions; The first data analysis module is used to obtain the power generation fluctuation characteristic value of the photovoltaic panel according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel; obtain the reference photovoltaic panel according to the power generation fluctuation characteristic values ​​of all photovoltaic panels; obtain the power generation difference characteristic value according to the difference characteristics of the power generation fluctuation characteristic value between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequence of all dimensions; A second data analysis module is used to obtain a fault probability value according to the position distance characteristics between the arbitrary photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of the arbitrary photovoltaic panels; A power generation abnormality monitoring module, used for obtaining an abnormality index of the arbitrary photovoltaic panel according to a failure probability value of the arbitrary photovoltaic panel and a difference characteristic of power generation between the arbitrary photovoltaic panel and other photovoltaic panels; and monitoring a power generation state according to the abnormality index; The step of obtaining the power generation difference characteristic value according to the difference characteristics of the power generation fluctuation characteristic value between any photovoltaic panel and the reference photovoltaic panel and the similar characteristics of the power generation characteristic sequence in all dimensions comprises: Calculate the absolute value of the difference between the power generation fluctuation characteristic values ​​of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the fluctuation difference value; calculate the dynamic time warping distance of the power generation characteristic sequence of the same dimension of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the change difference value; calculate the sum of the change difference value and a preset minimum positive number to obtain the change difference characteristic value; calculate the product of all the change difference characteristic values ​​of the arbitrary photovoltaic panel and the reference photovoltaic panel to obtain the comprehensive change difference characteristic value; calculate the product of the comprehensive change difference characteristic value and the fluctuation difference value to obtain the power generation difference characteristic value of the arbitrary photovoltaic panel; The step of obtaining a fault probability value according to the position distance characteristics between the arbitrary photovoltaic panel and other photovoltaic panels, the difference characteristics of the power generation difference characteristic values, and the power generation difference characteristic values ​​of the arbitrary photovoltaic panels comprises: Calculate the sum of the Euclidean distances between any photovoltaic panel and all other photovoltaic panels to obtain a comprehensive distance value; calculate the ratio of the Euclidean distance between any photovoltaic panel and any other photovoltaic panel to the comprehensive distance value and negatively correlate and map them to obtain a distance weight coefficient; calculate the sum of the power generation difference characteristic value of any other photovoltaic panel and a preset minimum positive number to obtain a power generation difference characterization value; calculate the ratio of the power generation difference characteristic value of any photovoltaic panel to the power generation difference characterization value of any other photovoltaic panel to obtain a difference factor; calculate the product of the difference factor and the distance weight coefficient to obtain a weighted difference factor between any photovoltaic panel and any other photovoltaic panel; calculate the sum of the weighted difference factors between any photovoltaic panel and all other photovoltaic panels to obtain a comprehensive difference coefficient; calculate the product of the power generation difference characteristic value of any photovoltaic panel and the comprehensive difference coefficient to obtain the fault probability value.

2. According to the intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis according to claim 1, it is characterized in that: The step of obtaining the power generation fluctuation characteristic value of the photovoltaic panel according to the data fluctuation characteristics of the power generation characteristic sequence of all dimensions of the photovoltaic panel comprises: The sum of the average absolute error of the power generation characteristic sequence and a preset minimum positive number is calculated to obtain the fluctuation factor of the power generation characteristic sequence; the product of the fluctuation factors of the power generation characteristic sequence of all dimensions of the photovoltaic panel is calculated to obtain the power generation fluctuation characteristic value of the photovoltaic panel.

3. According to the intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis according to claim 1, it is characterized in that: The step of obtaining a reference photovoltaic panel according to the power generation fluctuation characteristic values ​​of all photovoltaic panels comprises: The photovoltaic panels whose average values ​​of the power generation characteristic sequences are not a constant of 0 are sorted from small to large according to the power generation fluctuation characteristic values, and the photovoltaic panel ranked first in the sorting is used as the reference photovoltaic panel.

4. According to the intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis according to claim 1, it is characterized in that: The step of obtaining the abnormality index of the arbitrary photovoltaic panel according to the failure probability value of the arbitrary photovoltaic panel and the difference characteristics of the power generation of the arbitrary photovoltaic panel and other photovoltaic panels comprises: The difference between the total power generation of all photovoltaic panels in the area and the power generation of any photovoltaic panel is calculated to obtain an electric energy difference value; the product of the fault probability value and the electric energy difference value is calculated and normalized to obtain an abnormality index of any photovoltaic panel.

5. According to the intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis according to claim 1, it is characterized in that: The step of monitoring the power generation state according to the abnormal index comprises: When the abnormal index of any photovoltaic panel exceeds a preset abnormal threshold, the power generation state of any photovoltaic panel is abnormal.

6. According to the intelligent monitoring and early warning system for photovoltaic power generation in a substation based on time series analysis according to claim 1, it is characterized in that: The power generation characteristic sequences in different dimensions are current time series and voltage time series respectively.

Images