Power grid telecontrol information management optimization method based on big data analysis

Abstract

The invention provides a power grid telecontrol information management optimization method based on big data analysis, and relates to the technical field of power grid telecontrol information management, and the method comprises the steps: constructing a dichotomy model of abnormal data; acquiring telecontrol data of the power grid, inputting the telecontrol data into the dichotomy model, and outputting abnormal telecontrol data of the power grid; analyzing the abnormal telecontrol data of the power grid to obtain representation vocabularies of the data; calculating a severity value of the spatial risk corresponding to the representation vocabulary; calculating a voltage out-of-limit risk index value and a distributed power supply removal risk index value corresponding to the abnormal telecontrol data of the power grid based on the severity value of the spatial risk; calculating a power grid telecontrol information management optimization coefficient based on the voltage out-of-limit risk index value and the distributed power supply removal risk index value; and performing early warning management on the power grid telecontrol information based on the power grid telecontrol information management optimization coefficient. According to the scheme, the problems that abnormal telecontrol data cannot be found in time, so that telecontrol configuration is wrong, and a power grid is seriously lost can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid telecontrol information management, and in particular to a power grid telecontrol information management optimization method based on big data analysis. Background Art

[0002] Telecontrol system is a core system used to collect, transmit, process and store remote equipment data. It is widely used in power systems, industrial automation, traffic monitoring and other fields. Traditional telecontrol systems mainly rely on technologies such as supervisory control and data acquisition. Through real-time monitoring and control of remote equipment, it can realize the factual perception and remote operation of system status. In the power field, the telecontrol information of the power grid can mainly include the equipment status information, operation instruction information, remote control / remote adjustment information, data transmission information and statistical analysis information of the monitored power grid.

[0003] Grid telecontrol information management is an important part of the automated operation and management of power systems. With the rapid development of information technology, grid telecontrol information management has gradually evolved from traditional mechanical and telephone connections to an efficient and real-time information management system using advanced communication technology, computer technology and automatic control technology.

[0004] However, in the existing solutions, abnormal telecontrol data in the telecontrol data of the power grid is often not discovered in time, which leads to errors in telecontrol configuration and causes serious losses to the power grid. Summary of the invention

[0005] In view of this, in response to the above shortcomings, it is necessary to propose a power grid telecontrol information management optimization method based on big data analysis to solve the problem that abnormal telecontrol data in the existing scheme cannot be discovered in time, resulting in errors in telecontrol configuration, which in turn causes serious losses to the power grid.

[0006] The present invention provides a power grid telecontrol information management optimization method based on big data analysis, comprising:

[0007] Construct a binary classification model for detecting abnormal data in power grid telecontrol data;

[0008] Acquire telecontrol data of the power grid, input the data into the binary classification model, and output abnormal telecontrol data of the power grid;

[0009] Analyze the abnormal telecontrol data of the power grid and obtain the data representation vocabulary;

[0010] Calculating the severity value of the spatial risk corresponding to the characterizing vocabulary;

[0011] Based on the severity value of the spatial risk, a voltage over-limit risk index value and a distributed generation removal risk index value corresponding to abnormal telecontrol data of the power grid are calculated;

[0012] Calculating a power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed generation removal risk index value;

[0013] Based on the power grid telecontrol information management optimization coefficient, early warning management of power grid telecontrol information is performed.

[0014] Preferably, the construction of a binary classification model for detecting abnormal data in power grid telecontrol data includes:

[0015] Step S11: Set the number of iterations M, set the current number of iterations m to 0, and initialize the following classifier F0(x):

[0016]

[0017] In the formula, y i represents the prediction target corresponding to the telecontrol data of the ith power grid, and N represents the number of telecontrol data of the power grid for building the model;

[0018] Step S12: Calculate the negative gradient value of the current loss function using the following formula:

[0019]

[0020] In the formula, L(y i ,F(x i )) represents the loss function corresponding to the telecontrol data of the ith power grid, F(x i ) is used to represent the input telecontrol data of the i-th power grid;

[0021] Step S13: Fitting is performed and the parameter r of each leaf node is calculated by the following formula jm :

[0022]

[0023] Among them, R jm is the j leaf node classification tree at the mth iteration;

[0024] Step S14: According to the leaf node parameter r jm Update the classifier with learning rate θ;

[0025] Step S15: Repeat steps S12-S14 until the number of iterations reaches M, and obtain the final binary classification model.

[0026] Preferably, the loss function is calculated by the following formula:

[0027]

[0028] in, m is the current iteration number.

[0029] Preferably, in step S14, the classifier model is updated by the following calculation formula:

[0030]

[0031] Among them, J is the total number of leaf node classification trees, and I is the update parameter.

[0032] Preferably, the analysis of abnormal telecontrol data of the power grid includes:

[0033] Extracting the field name and field type of abnormal telecontrol data of the power grid;

[0034] Determine the association between fields based on field names and field types based on association rule mining;

[0035] Perform principal component analysis on the associated fields to obtain the data representation vocabulary.

[0036] Preferably, the calculating the severity value of the spatial risk corresponding to the characterizing vocabulary comprises:

[0037] The vocabulary representing the data is formed into a set T, and U is the domain of severity values;

[0038] Based on the fuzzy relation f(t,u), the mapping and semantic conversion from T to U are realized. In which, the domain of severity value is set to U = {0, 1, ..., 100}, then the fuzzy relation f(t,u) can be expressed as:

[0039]

[0040] In the formula, u represents the mapping value of the severity value corresponding to t in the vocabulary set T;

[0041] Substitute the mapping value into the corresponding fuzzy relation f(t,u) expression to obtain the severity value of the spatial risk corresponding to the characterization vocabulary.

[0042] Preferably, the step of calculating the voltage over-limit risk index value corresponding to the abnormal telecontrol data of the power grid based on the severity value of the spatial risk includes:

[0043] The voltage over-limit risk index value is calculated using the following formula:

[0044] R dy =Σ i P(E i )(Σ j P(X s,j Xs,f )S(E i ,X s,j ))

[0045] In the formula, R dy Used to characterize the voltage over-limit risk index value, P(E i ) represents the voltage over-limit accident E corresponding to the abnormal telecontrol data of the power grid i The probability of occurrence, X s,f Used to characterize the expected voltage operating state at time s, X s,j It is used to characterize the estimated voltage operating state caused by abnormal telecontrol data of the power grid at time s, P(X s,j X s,f ) represents the appearance of X at time s s,j The probability of S(E i ,X s,j ) represents the severity value corresponding to the voltage space risk.

[0046] Preferably, the step of calculating the distributed generation removal risk index value corresponding to the abnormal telecontrol data of the power grid based on the severity value of the spatial risk includes:

[0047] The distributed generation removal risk index value is calculated using the following formula:

[0048] R qc =∑ i P(Q i )(∑ j P(X Q,j X Q,f )S(Q i ,X Q,j ))

[0049] In the formula, R qc Used to characterize the risk index value of distributed power generation removal, P(Q i ) represents the distributed generation removal accident corresponding to the abnormal telecontrol data of the power grid Q i The probability of occurrence, X Q,f Used to characterize the expected operating state of distributed power at time s, X Q,j It is used to characterize the operating state of distributed generation caused by abnormal telecontrol data of the power grid at time s, P(X Q,j X Q,f ) represents the appearance of X at time s Q,j The probability of S(Q i ,X Q,j ) represents the severity value corresponding to the risk of distributed generation removal space.

[0050] Preferably, the calculating of the power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed power generation removal risk index value includes:

[0051] The sum of the voltage over-limit risk index value and the distributed generation removal risk index value is determined as the power grid telecontrol information management optimization coefficient.

[0052] Preferably, the early warning management of power grid telecontrol information based on the power grid telecontrol information management optimization coefficient includes:

[0053] Loading power grid telecontrol information management optimization coefficient threshold;

[0054] Determine whether the power grid telecontrol information management optimization coefficient exceeds the loaded power grid telecontrol information management optimization coefficient threshold; if so, generate an early warning signal.

[0055] It can be seen from the above technical scheme that in the power grid telecontrol information management optimization method based on big data analysis provided by the present invention, firstly, a binary classification model for detecting abnormal data in the power grid telecontrol data is constructed, and then the telecontrol data of the power grid is obtained and input into the binary classification model, and the abnormal telecontrol data of the power grid is output; further, the abnormal telecontrol data of the power grid is parsed to obtain the characterization vocabulary of the data, and then the severity value of the spatial risk corresponding to the characterization vocabulary is calculated; further, based on the severity value of the spatial risk, the voltage over-limit risk index value and the distributed power source removal risk index value corresponding to the abnormal telecontrol data of the power grid can be calculated, and the power grid telecontrol information management optimization coefficient can be determined by the voltage over-limit risk index value and the distributed power source removal risk index value, and the power grid telecontrol information can be early warning managed based on the power grid telecontrol information management optimization coefficient. It can be seen that the scheme can timely identify the abnormal data in the power grid telecontrol information through the constructed binary classification model, and further determine the voltage over-limit risk index and the distributed power source removal risk index after parsing the abnormality, and the early warning signal can be further generated by the voltage over-limit risk index and the distributed power source removal risk index. In this way, the anomaly in the power grid telecontrol data can be discovered in time through the early warning signal, thereby avoiding errors in the telecontrol configuration. At the same time, it also avoids the losses caused to the power grid by telecontrol configuration errors, thereby improving the safety of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of a power grid telecontrol information management optimization method based on big data analysis is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] like Figure 1 As shown, the present invention provides a power grid telecontrol information management optimization method based on big data analysis, the method comprising the following steps:

[0059] Step 101: constructing a binary classification model for detecting abnormal data in power grid telecontrol data;

[0060] Step 102: Obtain telecontrol data of the power grid, input the data into a binary classification model, and output abnormal telecontrol data of the power grid;

[0061] Step 103: parsing abnormal telecontrol data of the power grid to obtain a representation vocabulary of the data;

[0062] Step 104: Calculate the severity value of the spatial risk corresponding to the characterizing vocabulary;

[0063] Step 105: Based on the severity value of the spatial risk, the voltage over-limit risk index value and the distributed generation removal risk index value corresponding to the abnormal telecontrol data of the power grid are calculated;

[0064] Step 106: Calculate the power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed generation removal risk index value;

[0065] Step 107: Based on the power grid telecontrol information management optimization coefficient, early warning management is performed on the power grid telecontrol information.

[0066] In this embodiment, the constructed binary classification model can timely identify abnormal data in the power grid telecontrol information, and further determine the voltage over-limit risk index and the distributed power source removal risk index after analyzing the anomaly. The voltage over-limit risk index and the distributed power source removal risk index can further generate an early warning signal. In this way, the anomaly in the power grid telecontrol data can be discovered in time through the early warning signal, thereby avoiding errors in the telecontrol configuration, and also avoiding the losses caused to the power grid by telecontrol configuration errors, thereby improving the safety of power grid operation. Moreover, based on this solution, telecontrol configuration errors can be discovered before acceptance, so that the problem can be solved in advance and the number of actual equipment operations can be reduced.

[0067] For step 101, a binary classification model for detecting abnormal data in power grid telecontrol data is constructed;

[0068] In this step, when constructing a binary classification model, historical power grid telecontrol data is used for iterative training.

[0069] Specifically, the following steps may be included:

[0070] Step S11: Set the number of iterations M, set the current number of iterations m to 0, and initialize the following classifier F0(x):

[0071]

[0072] Where i = 1, 2, ..., N, y i represents the prediction target corresponding to the telecontrol data of the ith power grid, and N represents the number of telecontrol data of the power grid for building the model;

[0073] Step S12: Calculate the negative gradient value of the current loss function using the following formula:

[0074]

[0075] In the formula, L(y i ,F(x i )) represents the loss function corresponding to the telecontrol data of the ith power grid, F(x i ) is used to represent the input telecontrol data of the i-th power grid;

[0076] In this step, for the classification problem, consider using logarithmic loss as the loss function. Specifically, the loss function can be calculated by the following formula:

[0077]

[0078] in, m is the current iteration number.

[0079] Step S13: Fitting is performed and the parameter r of each leaf node is calculated by the following formula jm :

[0080]

[0081] Among them, R jm is the j leaf node classification tree at the mth iteration;

[0082] Step S14: According to the leaf node parameter r jm Update the classifier with learning rate θ;

[0083] In this step, the classifier model can be updated by the following calculation formula:

[0084]

[0085] Among them, J is the total number of leaf node classification trees, and I is the update parameter.

[0086] Step S15: Repeat steps S12-S14, and add 1 to m in each iteration until the number of iterations reaches M. The final binary classification model can be generated at the end of the iteration.

[0087] For step 102, the telecontrol data of the power grid is obtained, and the data is input into a binary classification model to output abnormal telecontrol data of the power grid;

[0088] In this step, the telecontrol data of the power grid can mainly include telemetry data and remote control data. Among them, telemetry data refers to data measured remotely, and the values ​​of the measured variables are transmitted through communication technology. In the power system, telemetry data mainly includes current, voltage, power, etc. Remote control data refers to remote operation data performed by operating equipment with two determined states. In the power system, remote control data is mainly used to realize remote operation and switching. For example, there are circuit breaker opening and closing operations, and the opening and closing states of the circuit breaker are controlled by remote commands to realize circuit switching and fault isolation; for example, there is transformer tap adjustment, and the transformer tap position is adjusted by remote commands to realize voltage adjustment and stabilization; for example, the switching of reactive power compensation devices, the switching of reactive power compensation devices is controlled by remote commands to realize reactive power balance and voltage stability of the power system.

[0089] Step 103: parsing abnormal telecontrol data of the power grid to obtain a representation vocabulary of the data;

[0090] In this step, when parsing the abnormal telecontrol data of the power grid, the field name and field type of the abnormal telecontrol data of the power grid can be extracted first, and then the correlation between the field names and field types can be determined according to the association rules, and the associated fields can be further subjected to principal component analysis to obtain the representation vocabulary of the data.

[0091] Specifically, first, prepare the data. Select the data set to be analyzed and ensure the data quality; determine the fields to be analyzed, which are numerical, categorical, or intrinsic. Perform necessary preprocessing on the data, such as data cleaning, conversion, and discretization.

[0092] Then, support and execution are defined. Support is the probability of an item set appearing in all transactions. In field correlation analysis, it can be understood as the probability of two or more field values ​​appearing at the same time. And confidence is the conditional probability that Y is also included in the transaction containing X. In field correlation analysis, it can be understood as the probability that field Y takes a certain value when field X takes a certain value.

[0093] Furthermore, association rule mining algorithms are applied. Association rule mining algorithms such as Apriori and FP-Growth are used to identify frequent item sets and generate association rules. Based on association rule mining, the association between field names and field types is determined.

[0094] Furthermore, the principal component analysis is performed on the associated fields to obtain the data representation vocabulary. Specifically, the associated fields can be formed into a matrix B, and the covariance matrix C of the samples of the matrix B is calculated; then the eigenvectors e1, e2, ..., e n And eigenvalue k=1,2,...,n; further using the formula Project the data into the space of feature vectors, BV k is the value of the corresponding dimension in the original sample. Through the above process, the data set can be parsed to obtain the data representation vocabulary.

[0095] The goal of principal component analysis PCA is to find r (r < n) new variables that reflect the main characteristics of things, compress the size of the original data matrix, reduce the dimension of the eigenvector, and select the least dimension to summarize the most important characteristics. Each new variable is a linear combination of the original variables, reflecting the comprehensive effect of the original variables and having certain practical significance. These r new variables are called "principal components", which can reflect the influence of the original n variables to a large extent, and these new variables are unrelated and orthogonal. In this embodiment, through principal component analysis, the data space can be compressed, the characteristics of multivariate data can be intuitively represented in a low-dimensional space, and the representation of the data can be intuitively displayed.

[0096] Step 104: Calculate the severity value of the spatial risk corresponding to the characterizing vocabulary;

[0097] In this step, when calculating the severity value of spatial risk, it can be calculated as follows:

[0098] The vocabulary representing the data is formed into a set T, and U is the domain of severity values;

[0099] Based on the fuzzy relation f(t,u), the mapping and semantic conversion from T to U are realized. In which, the domain of severity value is set to U = {0, 1, ..., 100}, then the fuzzy relation f(t,u) can be expressed as:

[0100]

[0101] In the formula, u represents the mapping value of the severity value corresponding to t in the vocabulary set T;

[0102] Substitute the mapping value into the corresponding fuzzy relation f(t,u) expression to obtain the severity value of the spatial risk corresponding to the characterization vocabulary.

[0103] Step 105: Based on the severity value of the spatial risk, the voltage over-limit risk index value and the distributed generation removal risk index value corresponding to the abnormal telecontrol data of the power grid are calculated;

[0104] In this step, the voltage over-limit risk index value is calculated using the following formula:

[0105] R dy =∑ i P(E i )(∑ j P(X s,j X s,f )S(E i ,X s,j ))

[0106] In the formula, R dy Used to characterize the voltage over-limit risk index value, P(E i ) represents the voltage over-limit accident E corresponding to the abnormal telecontrol data of the power grid i The probability of occurrence, X s,f Used to characterize the expected voltage operating state at time s, X s,j It is used to characterize the estimated voltage operating state caused by abnormal telecontrol data of the power grid at time s, P(X s,j X s,f ) represents the appearance of X at time s s,j The probability of S(E i ,X s,j ) represents the severity value corresponding to the voltage space risk.

[0107] Consider using the following calculation formula to calculate the distributed generation removal risk index value:

[0108] R qc =∑ i P(Q i )(∑ j P(X Q,j X Q,f )S(Q i ,X Q,j ))

[0109] In the formula, R qc Used to characterize the risk index value of distributed power generation removal, P(Q i ) represents the distributed generation removal accident corresponding to the abnormal telecontrol data of the power grid Q i The probability of occurrence, X Q,f Used to characterize the expected operating state of distributed power at time s, X Q,j It is used to characterize the operating state of distributed generation caused by abnormal telecontrol data of the power grid at time s, P(X Q,j X Q,f ) represents the appearance of X at time s Q,j The probability of S(Q i ,X Q,j ) represents the severity value corresponding to the risk of distributed generation removal space.

[0110] Step 106: Calculate the power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed generation removal risk index value;

[0111] In this embodiment, when calculating the power grid telecontrol information management optimization coefficient, the sum of the voltage over-limit risk index value and the distributed power generation removal risk index value can be determined as the power grid telecontrol information management optimization coefficient. Of course, in one embodiment, the weighted sum of the voltage over-limit risk index value and the distributed power generation removal risk index value can be determined as the power grid telecontrol information management optimization coefficient.

[0112] Step 107: Based on the power grid telecontrol information management optimization coefficient, early warning management is performed on the power grid telecontrol information.

[0113] In this step, when performing early warning management on the power grid telecontrol information, first load the power grid telecontrol information management optimization coefficient threshold; then determine whether the power grid telecontrol information management optimization coefficient exceeds the loaded power grid telecontrol information management optimization coefficient threshold; if so, generate an early warning signal, if not, do not generate an early warning signal. In this way, the early warning signal can be used to timely discover telecontrol configuration errors, and then solve the problem in advance, which can not only reduce the number of actual equipment operations, but also avoid power grid losses caused by telecontrol configuration errors, and improve the safety of power grid operation.

[0114] The present specification also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute a method in any one of the embodiments in the specification.

[0115] The present specification also provides a computing device, including a memory and a processor, wherein executable codes are stored in the memory, and when the processor executes the executable codes, a method in any embodiment of the present specification is implemented.

[0116] The modules or units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. The above disclosure is only the preferred embodiment of the present invention, and of course it cannot be used to limit the scope of the rights of the present invention. Those skilled in the art can understand that all or part of the processes of the above embodiment are implemented, and the equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A power grid telecontrol information management optimization method based on big data analysis, characterized in that: include: Construct a binary classification model for detecting abnormal data in power grid telecontrol data; Acquire telecontrol data of the power grid, input the data into the binary classification model, and output abnormal telecontrol data of the power grid; Analyze the abnormal telecontrol data of the power grid and obtain the data representation vocabulary; Calculating the severity value of the spatial risk corresponding to the characterizing vocabulary; Based on the severity value of the spatial risk, a voltage over-limit risk index value and a distributed generation removal risk index value corresponding to abnormal telecontrol data of the power grid are calculated; Calculating a power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed generation removal risk index value; Based on the power grid telecontrol information management optimization coefficient, early warning management of power grid telecontrol information is performed.

2. The power grid telecontrol information management optimization method based on big data analysis according to claim 1 is characterized in that: The method of constructing a binary classification model for detecting abnormal data in power grid telecontrol data includes: Step S11: Set the number of iterations M, set the current number of iterations m to 0, and initialize the following classifier F0(x): In the formula, y i represents the prediction target corresponding to the telecontrol data of the ith power grid, and N represents the number of telecontrol data of the power grid for building the model; Step S12: Calculate the negative gradient value of the current loss function using the following formula: In the formula, L(y i ,F(x i )) represents the loss function corresponding to the telecontrol data of the ith power grid, F(x i ) is used to represent the input telecontrol data of the i-th power grid; Step S13: Fitting is performed and the parameter r of each leaf node is calculated by the following formula jm : Among them, R jm is the j leaf node classification tree at the mth iteration; Step S14: According to the leaf node parameter r jm Update the classifier with learning rate θ; Step S15: Repeat steps S12-S14 until the number of iterations reaches M, and obtain the final binary classification model.

3. The power grid telecontrol information management optimization method based on big data analysis according to claim 2 is characterized in that: The loss function is calculated by the following formula: in, m is the current iteration number.

4. The power grid telecontrol information management optimization method based on big data analysis according to claim 2 is characterized in that: In step S14, the classifier model is updated by the following calculation formula: Among them, J is the total number of leaf node classification trees, and I is the update parameter.

5. The power grid telecontrol information management optimization method based on big data analysis according to claim 1 is characterized in that: The analysis of abnormal telecontrol data of the power grid includes: Extracting the field name and field type of abnormal telecontrol data of the power grid; Determine the association between fields based on field names and field types based on association rule mining; Perform principal component analysis on the associated fields to obtain the data representation vocabulary.

6. The power grid telecontrol information management optimization method based on big data analysis according to claim 1 is characterized in that: The calculating the severity value of the spatial risk corresponding to the characterizing vocabulary includes: The vocabulary representing the data is formed into a set T, and U is the domain of severity values; Based on the fuzzy relation f(t,u), the mapping and semantic conversion from T to U are realized. In which, the domain of severity value is set to U = {0, 1, ..., 100}, then the fuzzy relation f(t,u) can be expressed as: In the formula, u represents the mapping value of the severity value corresponding to t in the vocabulary set T; Substitute the mapping value into the corresponding fuzzy relation f(t,u) expression to obtain the severity value of the spatial risk corresponding to the characterization vocabulary.

7. The method for optimizing power grid telecontrol information management based on big data analysis according to claim 1, characterized in that: The calculating, based on the severity value of the spatial risk, a voltage over-limit risk index value corresponding to abnormal telecontrol data of the power grid includes: The voltage over-limit risk index value is calculated using the following formula: R dy =Σ i FOOT i )(Σ j P(X s,j |X s,f )WHETHER i ,X s,j )) In the formula, R dy Used to characterize the voltage over-limit risk index value, P(E i ) represents the voltage over-limit accident E corresponding to the abnormal telecontrol data of the power grid i The probability of occurrence, X s,f Used to characterize the expected voltage operating state at time s, X s,j It is used to characterize the estimated voltage operating state caused by abnormal telecontrol data of the power grid at time s, P(X s,j |X s,f ) represents the appearance of X at time s s,j The probability of S(E i ,X s,j ) represents the severity value corresponding to the voltage space risk.

8. The method for optimizing power grid telecontrol information management based on big data analysis according to claim 1, characterized in that: The step of calculating the distributed power generation removal risk index value corresponding to the abnormal telecontrol data of the power grid based on the severity value of the spatial risk includes: The distributed generation removal risk index value is calculated using the following formula: R qc =Σ i P(Q i )(∑ j P(X Q,j |X Q,f )S(Q i ,X Q,j )) In the formula, R qc Used to characterize the risk index value of distributed power generation removal, P(Q i ) represents the distributed generation removal accident corresponding to the abnormal telecontrol data of the power grid Q i The probability of occurrence, X Q,f Used to characterize the expected operating state of distributed power at time s, X Q,j It is used to characterize the operating state of distributed generation caused by abnormal telecontrol data of the power grid at time s, P(X Q,j X Q,f ) represents the appearance of X at time s Q,j The probability of S(Q i ,X Q,j ) represents the severity value corresponding to the risk of distributed generation removal space.

9. The power grid telecontrol information management optimization method based on big data analysis according to claim 1 is characterized in that: The calculating of the power grid telecontrol information management optimization coefficient based on the voltage over-limit risk index value and the distributed power generation removal risk index value includes: The sum of the voltage over-limit risk index value and the distributed generation removal risk index value is determined as the power grid telecontrol information management optimization coefficient.

10. The power grid telecontrol information management optimization method based on big data analysis according to claim 1, characterized in that: The performing early warning management on the power grid telecontrol information based on the power grid telecontrol information management optimization coefficient includes: Loading power grid telecontrol information management optimization coefficient threshold; Determine whether the power grid telecontrol information management optimization coefficient exceeds the loaded power grid telecontrol information management optimization coefficient threshold; if so, generate an early warning signal.

Images