New energy power grid risk early warning method, device and equipment and storage medium

Abstract

The invention discloses a new energy power grid risk early warning method, apparatus and device, and a storage medium. The method comprises the steps of determining a weight ratio of a photovoltaic system, a wind power generation system and a hydroelectric power generation system; variable data of monitoring variables corresponding to a photovoltaic system, a wind power generation system and a hydroelectric power generation system and power grid fluctuation data reflecting power grid fluctuation conditions are obtained; calculating the correlation between each monitoring variable and the fluctuation condition of the power grid, and sorting the correlation; taking a preset number of monitoring variables of which the correlation is ranked in the front as target monitoring variables, and calculating Gaussian distribution of variable data of each target monitoring variable; and determining an abnormal threshold value of each target monitoring variable according to the Gaussian distribution, marking the variable data exceeding the abnormal threshold value as abnormal data, and performing risk early warning according to the abnormal data. According to the invention, the operation pressure of the early warning system can be effectively reduced, and the early warning response speed of the system is improved.

Description

Technical Field

[0001] The present invention relates to the field of electrical automation technology, and in particular to a new energy power grid risk early warning method, device, equipment and storage medium. Background Art

[0002] In the rapid development of modern society, the power system, as one of the core infrastructures, plays a vital role. It not only supports the continuous operation of industrial production, but also maintains the orderly development of commercial activities, and provides indispensable energy security for residents' daily lives. The stable operation of the power system has a decisive influence on ensuring the healthy development of the social economy, promoting the progress of science and technology, and improving the quality of people's lives.

[0003] With the enhancement of environmental protection awareness and the in-depth implementation of sustainable development strategies, the development and utilization of renewable energy has gradually become an important direction for the adjustment of the global energy structure. Solar energy, wind energy and hydropower have become the leaders in the renewable energy system with their clean, pollution-free and abundant resources. Renewable energy generation technology, because it does not produce greenhouse gas emissions, helps to reduce dependence on fossil fuels, reduce environmental pollution and combat global climate change, has always been a very promising development direction in the power system. Photovoltaic power generation systems, wind power systems, hydropower systems and other new energy power generation systems, by integrating power generation into the power grid, jointly provide energy security for daily life.

[0004] However, natural energy sources such as solar energy, wind energy, and hydropower have great uncertainty due to their dependence on natural conditions. The unpredictable weather, such as the intensity of sunshine, the size of wind, and the increase or decrease of water flow, may all affect the output of these energy sources. This instability causes the power generation of photovoltaic power generation systems, wind power systems, and hydropower systems to fluctuate at different times and locations, bringing new challenges to the stable operation of the power grid. Therefore, in order to ensure the safety of the power grid system, the industry has added more consideration data to the risk assessment of the operation of the power grid that introduces new energy power generation systems, resulting in a large amount of data for the early warning system, increasing the computing pressure of the early warning system, and also affecting the speed of the early warning response. Summary of the invention

[0005] The present invention provides a new energy power grid risk warning method, device, equipment and storage medium to solve the technical problems of the existing new energy power grid warning system having a large amount of data, increasing the computing pressure of the warning system and affecting the speed of the warning response.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a new energy grid risk early warning method, comprising:

[0007] Determine the weight ratio of photovoltaic systems, wind power generation systems and hydropower generation systems based on the proportion of new energy installed capacity;

[0008] Obtain variable data of monitoring variables corresponding to photovoltaic systems, wind power generation systems and hydropower generation systems, as well as power grid fluctuation data reflecting power grid fluctuation conditions;

[0009] According to the weight ratio, variable data and power grid fluctuation data, respectively calculate the correlation between each monitored variable and the power grid fluctuation situation, and sort the correlation;

[0010] Taking a preset number of monitoring variables ranked first in relevance as target monitoring variables, and calculating the Gaussian distribution of variable data of each of the target monitoring variables;

[0011] The abnormal threshold of each target monitoring variable is determined according to the Gaussian distribution, the variable data exceeding the abnormal threshold is marked as abnormal data, and a risk warning is performed according to the abnormal data.

[0012] As a preferred solution, the monitoring variables include: the power generation of the photovoltaic system, the power generation of the wind power generation system, the power generation of the hydropower generation system, and the DC voltage value, DC current value and power of the photovoltaic system, the wind power generation system and the hydropower generation system;

[0013] The power grid fluctuation data includes: frequency deviation and voltage deviation.

[0014] As a preferred solution, the correlation between each monitored variable and the power grid fluctuation situation is calculated according to the weight ratio, variable data and power grid fluctuation data, including:

[0015] Calculate the mutual information between each monitored variable and the power grid fluctuation according to the variable data and the power grid fluctuation data;

[0016] According to the mutual information and the weight ratio, the correlation between the monitored variable and the power grid fluctuation condition is obtained.

[0017] As a preferred solution, the mutual information between each monitored variable and the power grid fluctuation situation is calculated according to the variable data and the power grid fluctuation data, including:

[0018] Calculate the joint probability distribution and marginal probability distribution of each monitored variable and power grid fluctuation according to the variable data and power grid fluctuation data;

[0019] According to the joint probability distribution and the marginal probability distribution, the mutual information between each monitoring variable and the power grid fluctuation is calculated.

[0020] As a preferred solution, the mutual information between each monitored variable and the power grid fluctuation is calculated according to the following formula:

[0021]

[0022] Where log represents the natural logarithm, P(a,x) is the joint probability that the monitoring variable A and the power grid fluctuation data X take the specific values ​​a and x at the same time, and P(a)P(x) is the marginal probability that the monitoring variable A and the power grid fluctuation data X take the values ​​a and x respectively.

[0023] As a preferred solution, the step of calculating the Gaussian distribution of the variable data of each target monitoring variable includes:

[0024] According to a preset discrete data fitting method, the variable data of each target monitoring variable is fitted into continuous variable data; wherein the discrete data fitting method includes: polynomial fitting, spline interpolation, kernel density estimation and midpoint method;

[0025] According to the variable data of each target monitoring variable after fitting, the mean, variance and probability density function of the variable data of each target monitoring variable are calculated to obtain the Gaussian distribution of the variable data of each target monitoring variable.

[0026] As a preferred solution, determining an abnormal threshold of each target monitoring variable according to the Gaussian distribution, and marking variable data exceeding the abnormal threshold as abnormal data, includes:

[0027] Determine the standard deviation of the variable data according to the mean value of the variable data of each target monitoring variable;

[0028] According to the mean, standard deviation and preset Z score, the abnormal threshold of each target monitoring variable is determined, and then the variable data exceeding the abnormal threshold is marked as abnormal data.

[0029] Based on the above embodiment, another embodiment of the present invention provides a new energy grid risk warning device, including: a weight ratio determination module, a data acquisition module, a correlation calculation module, a Gaussian distribution calculation module and a risk warning module;

[0030] The weight ratio determination module is used to determine the weight ratio of the photovoltaic system, the wind power generation system and the hydropower generation system according to the installed capacity ratio of new energy;

[0031] The data acquisition module is used to acquire variable data of monitoring variables corresponding to the photovoltaic system, the wind power generation system and the hydropower generation system, and power grid fluctuation data reflecting power grid fluctuation conditions;

[0032] The correlation calculation module is used to calculate the correlation between each monitoring variable and the power grid fluctuation situation according to the weight ratio, variable data and power grid fluctuation data, and sort the correlation;

[0033] The Gaussian distribution calculation module is used to take the monitoring variables with a preset number of correlation rankings as target monitoring variables, and calculate the Gaussian distribution of the variable data of each of the target monitoring variables;

[0034] The risk warning module is used to determine the abnormal threshold of each target monitoring variable according to the Gaussian distribution, mark the variable data exceeding the abnormal threshold as abnormal data, and issue a risk warning based on the abnormal data.

[0035] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the new energy grid risk warning method described in the above invention embodiment is implemented.

[0036] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the new energy power grid risk warning method described in the above invention embodiment.

[0037] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0038] The present invention provides a new energy power grid risk early warning method, which determines the weight ratio of photovoltaic systems, wind power generation systems and hydropower generation systems according to the proportion of new energy installed capacity; obtains variable data of monitoring variables corresponding to the photovoltaic systems, wind power generation systems and hydropower generation systems, and power grid fluctuation data reflecting power grid fluctuation conditions; calculates the correlation between each monitoring variable and the power grid fluctuation condition according to the weight ratio, variable data and power grid fluctuation data, and sorts the correlations; takes a preset number of monitoring variables ranked first in the correlation as target monitoring variables, and calculates the Gaussian distribution of the variable data of each target monitoring variable; determines the abnormal threshold of each target monitoring variable according to the Gaussian distribution, marks the variable data exceeding the abnormal threshold as abnormal data, and performs risk early warning according to the abnormal data.

[0039] The weather and climate in each region have different impacts, and the proportion of new energy power generation types is also different. The present invention analyzes the correlation between each monitoring variable and the power grid fluctuation situation based on the weight ratio of the photovoltaic system, wind power generation system and hydropower generation system, the variable data of the monitoring variables corresponding to the photovoltaic system, wind power generation system and hydropower generation system, and the power grid fluctuation data reflecting the power grid fluctuation situation. Then, the monitoring data with the highest correlation ranking is monitored, and the Gaussian distribution system is used to monitor the data volume during monitoring, and risk warnings are issued for the monitored abnormal data. Through the present invention, there is no need to monitor each monitoring data in real time, only the monitoring data with the highest correlation ranking needs to be monitored, which can effectively reduce the computing pressure of the early warning system and improve the early warning response speed of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a new energy grid risk early warning method provided by an embodiment of the present invention;

[0041] Figure 2 It is a structural schematic diagram of a new energy power grid risk early warning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0044] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0045] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0047] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0048] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0049] Embodiment 1

[0050] Please refer to Figure 1 , is a flow chart of a new energy grid risk early warning method provided by an embodiment of the present invention, comprising the following specific steps:

[0051] S1. Determine the weight ratio of photovoltaic system, wind power generation system and hydropower generation system according to the proportion of new energy installed capacity;

[0052] Specifically, the new energy grid risk early warning method described in the present invention includes the following specific steps:

[0053] (1) First, determine the weight ratio of photovoltaic systems, wind power generation systems, and hydropower generation systems based on the local proportion of new energy installed capacity, for example: 3:1:2.

[0054] S2. Obtain variable data of monitoring variables corresponding to the photovoltaic system, the wind power generation system and the hydropower generation system, and grid fluctuation data reflecting grid fluctuation conditions;

[0055] Preferably, the monitored variables include: the power generation of the photovoltaic system, the power generation of the wind power generation system, the power generation of the hydropower generation system, and the DC voltage value, DC current value and power of the photovoltaic system, the wind power generation system and the hydropower generation system; the grid fluctuation data include: frequency deviation and voltage deviation.

[0056] (2) Count the variable data of the monitoring variables corresponding to the photovoltaic system, wind power generation system and hydropower generation system, for example, the amount of electricity delivered to the power grid by the photovoltaic system, wind power generation system and hydropower generation system every day within a preset time period, such as 12 months. The monitoring variables can be recorded as: photovoltaic system power generation A, wind power system power generation B, hydropower system power generation C. Each data type is a monitoring variable.

[0057] The data for consideration may also include the DC voltage value, DC current value, power, etc. of each system when generating electricity, which are detection variables D, E, F, etc.

[0058] And record the power grid fluctuation situation within the above preset time period, such as within 12 months. The power grid fluctuation data X reflecting the power grid fluctuation situation can generally be selected from: frequency deviation, voltage deviation, at least one of them.

[0059] S3. Calculate the correlation between each monitored variable and the power grid fluctuation situation according to the weight ratio, variable data and power grid fluctuation data, and sort the correlation;

[0060] Preferably, the correlation between each monitored variable and the power grid fluctuation situation is calculated respectively according to the weight ratio, variable data and power grid fluctuation data, including: calculating the mutual information between each monitored variable and the power grid fluctuation situation according to the variable data and the power grid fluctuation data; obtaining the correlation between the monitored variable and the power grid fluctuation situation according to the mutual information and the weight ratio.

[0061] Preferably, the mutual information between each monitored variable and the power grid fluctuation situation is calculated based on the variable data and the power grid fluctuation data, including: calculating the joint probability distribution and marginal probability distribution of each monitored variable and the power grid fluctuation situation based on the variable data and the power grid fluctuation data; and calculating the mutual information between each monitored variable and the power grid fluctuation situation based on the joint probability distribution and the marginal probability distribution.

[0062] Preferably, the mutual information between each monitored variable and the power grid fluctuation is calculated according to the following formula:

[0063]

[0064] Where log represents the natural logarithm, P(a,x) is the joint probability that the monitoring variable A and the power grid fluctuation data X take the specific values ​​a and x at the same time, and P(a)P(x) is the marginal probability that the monitoring variable A and the power grid fluctuation data X take the values ​​a and x respectively.

[0065] (3) According to the weight ratio, variable data and power grid fluctuation data, mutual information is used to calculate the correlation between each monitoring variable and the power grid fluctuation situation, and the correlations are sorted to evaluate which monitoring variable has a higher correlation with the power grid fluctuation situation.

[0066] In a specific embodiment, the above steps specifically include:

[0067] 3-1. Calculate the joint probability distribution P(A, X) of variables A and X, the marginal probability distributions P(A) and P(X), and the mutual information I(A, X) of two random variables A and X is defined as:

[0068]

[0069] Where log represents the natural logarithm. The numerator P(a,x) in the above formula is the joint probability that variables A and X take the specific values ​​a and x at the same time, while the denominator P(a)P(x) is the marginal probability that variables A and X take the values ​​a and x respectively. The specific value to be taken depends on the research needs. If you think that the value obtained from the weather on a certain day, or the median or mode in statistics is more in line with local research needs, you can choose this value.

[0070] 3-2. Similarly, calculate the mutual information I(B,X) between variables B and X, calculate the mutual information I(C,X) between variables C and X, and so on.

[0071] 3-3. Comparing all mutual information, the larger the mutual information value, the stronger the interdependence between the two variables, that is, the more information they share, the higher the correlation, and the sorting is based on the correlation:

[0072] If I(A,X)>I(B,X), then the correlation between A and X is considered to be higher than the correlation between B and X;

[0073] Furthermore, I(B,X)<I(C,X), which means the correlation between B and X is lower than the correlation between C and X. Then the correlation ranking is: A, C, B.

[0074] 3-4. Assuming that the mutual information of different power generation systems is the same, the ones with larger weights will be given priority according to the weight ratio:

[0075] If the weight ratio of photovoltaic power generation system in a region is greater than that of wind power generation system, and I(A,X)=I(B,X), then the correlation ranking is: A, B.

[0076] S4, taking a preset number of monitoring variables ranked first in relevance as target monitoring variables, and calculating the Gaussian distribution of variable data of each of the target monitoring variables;

[0077] Preferably, the calculation of the Gaussian distribution of the variable data of each target monitoring variable includes: fitting the variable data of each target monitoring variable into continuous variable data according to a preset discrete data fitting method; wherein the discrete data fitting method includes: polynomial fitting, spline interpolation, kernel density estimation and midpoint method; based on the variable data of each target monitoring variable after fitting, calculating the mean, variance and probability density function of the variable data of each target monitoring variable to obtain the Gaussian distribution of the variable data of each target monitoring variable.

[0078] (4) 4-1. For the top ranked data (in actual application, the top few data, which can be balanced based on time cost and warning accuracy), multiple discrete statistical data are first fitted into continuous data; there are many methods for fitting discrete data into continuous curves, which can use polynomial fitting, spline interpolation, kernel density estimation, midpoint method, etc.

[0079] 4-2. Calculation of Gaussian distribution of photovoltaic system power generation data set

[0080] First, calculate the mean and variance of the photovoltaic system power generation data set;

[0081] Then calculate the probability density function of the photovoltaic system power generation A.

[0082] S5. Determine an abnormal threshold value of each target monitoring variable according to the Gaussian distribution, mark variable data exceeding the abnormal threshold value as abnormal data, and issue a risk warning based on the abnormal data.

[0083] Preferably, determining the abnormal threshold of each target monitoring variable according to the Gaussian distribution and marking the variable data exceeding the abnormal threshold as abnormal data includes: determining the standard deviation of the variable data according to the mean of the variable data of each target monitoring variable; determining the abnormal threshold of each target monitoring variable according to the mean, standard deviation and a preset Z score, and then marking the variable data exceeding the abnormal threshold as abnormal data.

[0084] (5) Using the above Gaussian separation and setting a threshold, samples with probability density values ​​below the threshold are marked as abnormal. According to the normal distribution table, the threshold at the 95% confidence level is found, which means that on the normal distribution curve, approximately 95% of the data falls within the interval of the mean plus or minus two standard deviations (i.e., -2σ to +2σ). This interval is also called the "95% confidence interval." Set the threshold to the mean plus or minus 1.96 times the standard deviation (Z = 1.96 corresponds to a confidence level of approximately 95%), then any data point below this lower limit or above this upper limit may be considered abnormal.

[0085] In a specific embodiment, the above steps specifically include:

[0086] 5-1. Estimation of parameters: First, we need to estimate the mean (μ) and standard deviation (σ) of the data.

[0087] 5-2. Determine the threshold: Use the Z score to determine the threshold. For a 95% confidence level, the Z score is usually 1.96 (corresponding to 2.5% for each of the two tails).

[0088] 5-3. Calculate the threshold: Multiply the Z score by the standard deviation, and then subtract and add this value from the mean to get two thresholds:

[0089] Lower threshold: μ-1.96σ, upper threshold: μ+1.96σ.

[0090] 5-4. Mark outliers: Any data point below the lower threshold or above the upper threshold is considered an outlier.

[0091] (6) Real-time monitoring and early warning: Based on the marked abnormal data, determine whether an abnormal situation has occurred, trigger the early warning mechanism, and notify relevant personnel to take appropriate measures.

[0092] (7) Model optimization and update: Based on actual conditions, the performance of the Gaussian distribution model can be regularly checked, and the model can be optimized and updated based on new data to maintain the accuracy and effectiveness of the model. The data can be iterated every six months, with the latest 12 months as the statistical data, and the mutual trust can be recalculated to find the data types with the highest relevance ranking.

[0093] It can be seen that the present invention provides a new energy power grid risk warning method. The weather and climate influences in each region are different, and the proportion of new energy power generation types is also different. The present invention analyzes the correlation between each monitoring variable and the power grid fluctuation situation according to the weight ratio of the photovoltaic system, wind power generation system and hydropower generation system, the variable data of the monitoring variables corresponding to the photovoltaic system, wind power generation system and hydropower generation system, and the power grid fluctuation data reflecting the power grid fluctuation situation. Then, the monitoring data with the highest correlation ranking is monitored, and the Gaussian distribution system is used to monitor the data volume during monitoring, and the monitored abnormal data is given a risk warning. Through the present invention, there is no need to monitor each monitoring data in real time, only the monitoring data with the highest correlation ranking needs to be monitored, which can effectively reduce the computing pressure of the early warning system and improve the early warning response speed of the system.

[0094] Embodiment 2

[0095] Please refer to Figure 2 , is a schematic diagram of the structure of a new energy grid risk warning device provided by an embodiment of the present invention, the device comprising: a weight ratio determination module, a data acquisition module, a correlation calculation module, a Gaussian distribution calculation module and a risk warning module;

[0096] The weight ratio determination module is used to determine the weight ratio of the photovoltaic system, the wind power generation system and the hydropower generation system according to the installed capacity ratio of new energy;

[0097] The data acquisition module is used to acquire variable data of monitoring variables corresponding to the photovoltaic system, the wind power generation system and the hydropower generation system, and power grid fluctuation data reflecting power grid fluctuation conditions;

[0098] The correlation calculation module is used to calculate the correlation between each monitoring variable and the power grid fluctuation situation according to the weight ratio, variable data and power grid fluctuation data, and sort the correlation;

[0099] The Gaussian distribution calculation module is used to take the monitoring variables with a preset number of correlation rankings as target monitoring variables, and calculate the Gaussian distribution of the variable data of each of the target monitoring variables;

[0100] The risk warning module is used to determine the abnormal threshold of each target monitoring variable according to the Gaussian distribution, mark the variable data exceeding the abnormal threshold as abnormal data, and issue a risk warning based on the abnormal data.

[0101] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0102] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0103] Embodiment 3

[0104] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the new energy grid risk warning method described in the above-mentioned embodiment of the invention when executing the computer program.

[0105] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0106] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0107] Embodiment 4

[0108] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the new energy power grid risk warning method described in the above-mentioned embodiment of the invention.

[0109] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0110] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0111] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A new energy power grid risk early warning method, characterized in that: include: Determine the weight ratio of photovoltaic systems, wind power generation systems and hydropower generation systems based on the proportion of new energy installed capacity; Obtain variable data of monitoring variables corresponding to photovoltaic systems, wind power generation systems and hydropower generation systems, as well as power grid fluctuation data reflecting power grid fluctuation conditions; According to the weight ratio, variable data and power grid fluctuation data, respectively calculate the correlation between each monitored variable and the power grid fluctuation situation, and sort the correlation; Taking a preset number of monitoring variables ranked first in relevance as target monitoring variables, and calculating the Gaussian distribution of variable data of each of the target monitoring variables; The abnormal threshold of each target monitoring variable is determined according to the Gaussian distribution, the variable data exceeding the abnormal threshold is marked as abnormal data, and a risk warning is performed according to the abnormal data.

2. The new energy grid risk early warning method according to claim 1, characterized in that: The monitoring variables include: the power generation of the photovoltaic system, the power generation of the wind power generation system, the power generation of the hydropower generation system, and the DC voltage value, DC current value and power of the photovoltaic system, the wind power generation system and the hydropower generation system; The power grid fluctuation data includes: frequency deviation and voltage deviation.

3. The new energy grid risk early warning method according to claim 1, characterized in that: The calculating the correlation between each monitoring variable and the power grid fluctuation situation according to the weight ratio, variable data and power grid fluctuation data respectively includes: Calculate the mutual information between each monitored variable and the power grid fluctuation according to the variable data and the power grid fluctuation data; According to the mutual information and the weight ratio, the correlation between the monitored variable and the power grid fluctuation condition is obtained.

4. The new energy grid risk early warning method according to claim 3, characterized in that: The calculating the mutual information between each monitored variable and the power grid fluctuation situation according to the variable data and the power grid fluctuation data includes: Calculate the joint probability distribution and marginal probability distribution of each monitored variable and power grid fluctuation according to the variable data and power grid fluctuation data; According to the joint probability distribution and the marginal probability distribution, the mutual information between each monitoring variable and the power grid fluctuation is calculated.

5. The new energy grid risk early warning method according to claim 4, characterized in that: The mutual information between each monitored variable and the power grid fluctuation is calculated according to the following formula: Where log represents the natural logarithm, P(a,x) is the joint probability that the monitoring variable A and the power grid fluctuation data X take the specific values ​​a and x at the same time, and P(a)P(x) is the marginal probability that the monitoring variable A and the power grid fluctuation data X take the values ​​a and x respectively.

6. The new energy grid risk early warning method according to claim 1, characterized in that: The calculating of the Gaussian distribution of the variable data of each target monitoring variable comprises: According to a preset discrete data fitting method, the variable data of each target monitoring variable is fitted into continuous variable data; wherein the discrete data fitting method includes: polynomial fitting, spline interpolation, kernel density estimation and midpoint method; According to the variable data of each target monitoring variable after fitting, the mean, variance and probability density function of the variable data of each target monitoring variable are calculated to obtain the Gaussian distribution of the variable data of each target monitoring variable.

7. The new energy grid risk early warning method according to claim 1, characterized in that: The step of determining an abnormal threshold of each target monitoring variable according to the Gaussian distribution and marking variable data exceeding the abnormal threshold as abnormal data includes: Determine the standard deviation of the variable data according to the mean value of the variable data of each target monitoring variable; According to the mean, standard deviation and preset Z score, the abnormal threshold of each target monitoring variable is determined, and then the variable data exceeding the abnormal threshold is marked as abnormal data.

8. A new energy grid risk early warning device, characterized in that: include: Weight ratio determination module, data acquisition module, correlation calculation module, Gaussian distribution calculation module and risk warning module; The weight ratio determination module is used to determine the weight ratio of the photovoltaic system, the wind power generation system and the hydropower generation system according to the installed capacity ratio of new energy; The data acquisition module is used to acquire variable data of monitoring variables corresponding to the photovoltaic system, the wind power generation system and the hydropower generation system, and power grid fluctuation data reflecting power grid fluctuation conditions; The correlation calculation module is used to calculate the correlation between each monitoring variable and the power grid fluctuation situation according to the weight ratio, variable data and power grid fluctuation data, and sort the correlation; The Gaussian distribution calculation module is used to take the monitoring variables with a preset number of correlation rankings as target monitoring variables, and calculate the Gaussian distribution of the variable data of each of the target monitoring variables; The risk warning module is used to determine the abnormal threshold of each target monitoring variable according to the Gaussian distribution, mark the variable data exceeding the abnormal threshold as abnormal data, and issue a risk warning based on the abnormal data.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the new energy power grid risk warning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the new energy power grid risk early warning method as described in any one of claims 1 to 7.

Images