Power network communication data encryption method and system

Abstract

The invention discloses a power network communication data encryption method and system, and the method comprises the steps: obtaining power network communication data which comprises all shared communication data of all power system information terminal equipment clusters; according to the method, abnormal value deletion and missing value filling are carried out on acquired power network communication data, power data are segmented and keyword extraction is carried out at the same time, the extracted keywords form a set, a risk matching model is preset in a power system, and the risk matching model is used for matching the risk of the power network communication data. The keyword set is input into the risk matching model to obtain the matching value, the data with the lower matching value is encrypted at a low level, and the data with the lower matching value is not sensitive data of the power enterprise and cannot bring risks to the enterprise even if being stolen, so that the data with the higher matching value is encrypted at a high level by adopting a mode of only disorganizing the data, and the data with the higher matching value is encrypted at a high level; the high-level encryption in the invention is a dual encryption mode, so that lawbreakers are difficult to steal.

Description

Technical Field

[0001] The present invention relates to the technical field of power network communication data encryption, and in particular to a power network communication data encryption method and system. Background Art

[0002] As an indispensable infrastructure in modern society, the stable operation and safety of the power system are of vital importance. With the rapid development of information technology and the advancement of intelligence, the power system is gradually moving towards digitalization and automation, and the importance of network communication in the power system is becoming increasingly prominent. However, compared with the progress of network communication technology, the development of power system network security protection technology lags behind, resulting in the power system facing increasingly serious network security threats.

[0003] However, in the prior art, it is not convenient for the power system to analyze power data and cannot assess the risk level of power data, making it inconvenient to encrypt power data to different degrees according to risk levels, making it difficult to meet the management needs of the power system. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, a method and system for encrypting power network communication data are provided. This technical solution solves the problem proposed in the above-mentioned background technology that the power system is not convenient for analyzing power data, cannot assess the risk level of power data, and is thus not convenient for encrypting power data to different degrees according to risk levels.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for encrypting power network communication data, comprising:

[0007] Acquiring power network communication data, wherein the power network communication data includes all shared communication data of all power system information terminal device clusters;

[0008] Preprocess the power network communication data to obtain complete power network communication data;

[0009] The complete power network communication data is segmented and numbered, and keywords are extracted from each segment of the power network communication data to obtain a keyword set of the complete power network communication data;

[0010] Construct a risk matching model based on a bag of pre-set risk keywords in the power system;

[0011] Input the keyword set into the risk matching model to obtain the risk matching value;

[0012] The power network communication data with higher and lower risk matching values ​​are encrypted at high and low levels respectively.

[0013] Furthermore, in real life, although the intelligent trend of power grids has improved the efficiency of electric energy use and the operating efficiency of power systems, it has also brought a series of hidden dangers to the power system. The data communication of power system information terminal equipment in the power system is vulnerable to attacks by criminals, resulting in the leakage of network communication data and even power paralysis. Therefore, it is necessary to encrypt the network communication data of the power.

[0014] Preferably, the preprocessing of the power network communication data specifically comprises the following steps:

[0015] Performing outlier deletion processing on the power network communication data to obtain first processed data;

[0016] Perform missing value filling processing on the first processed data to obtain second processed data;

[0017] Classification is performed based on the second processed data to obtain complete power network communication data.

[0018] Preferably, the specific calculation formula for performing missing value filling processing is:

[0019]

[0020] Where D i is the filling data; i is the number of filling data; D j are different types of historical data; n is the number of different types of historical data.

[0021] Preferably, the complete power network communication data is segmented and numbered, and keywords are extracted from each segment of the power network communication data to obtain a keyword set of the complete power network communication data, specifically comprising the following steps:

[0022] Segmenting the complete power network communication data;

[0023] The communication data of all power network segments are numbered and recorded as S1, S2, ..... Sn;

[0024] Perform keyword extraction on each numbered power network communication data at the same time, obtain and count each keyword in each numbered power network communication data;

[0025] All keywords are grouped together.

[0026] Preferably, the specific calculation formula of the risk matching model is:

[0027]

[0028] Among them, Pj is the matching degree between the input keyword set and the pre-set j-th risk level, N j is the total number of historical keyword sets corresponding to the jth risk level, N0 is the total number of features of the input keyword set, N 同 is the total number of identical features between the feature data of the input keyword set and the historical keyword set corresponding to the jth risk level, α' l is the correlation weight between the feature data of the j-th risk level and the l-th input keyword set and the same feature in the historical keyword set corresponding to the j-th risk level, and max() is the maximum value function.

[0029] Preferably, the high-level encryption and low-level encryption of the power network communication data with higher and lower risk matching values ​​respectively specifically include the following steps:

[0030] Compare the obtained risk matching value with the preset threshold;

[0031] If the risk matching value is greater than or equal to the preset threshold, the power network communication data is determined to be high-level risk data;

[0032] If the risk matching value is less than the preset threshold, the power network communication data is determined to be low-level data;

[0033] High-level encryption is used for high-risk data, and low-level encryption is used for low-level data.

[0034] Preferably, the high-level encryption specifically includes the following steps:

[0035] According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data;

[0036] Each segment of power network communication sub-data is segmented according to a fixed length to obtain multiple encoding vectors;

[0037] Generate a dummy encoding vector for each encoding vector;

[0038] According to the virtual coding vector, each webpage coding vector is encrypted based on the local encryption sequence to obtain each encrypted coding vector;

[0039] splicing multiple encrypted coding vectors to obtain each segment of encrypted power network communication sub-data;

[0040] According to the global encryption sequence, each segment of encrypted power network communication sub-data is encrypted to obtain double-encrypted power network communication data.

[0041] Preferably, the low-level encryption specifically includes the following steps:

[0042] According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data;

[0043] Multiple segments of power network communication sub-data are shuffled in a disordered manner to obtain encrypted power network communication data.

[0044] A power network communication data encryption method system, comprising:

[0045] An acquisition module, the acquisition module is used to acquire power network communication data, the power network communication data includes all shared communication data of all power system information terminal device clusters;

[0046] A data processing module, wherein the data processing module is used to pre-process the power network communication data to obtain complete power network communication data;

[0047] A keyword extraction module, the keyword extraction module is used to segment and number the complete power network communication data, and extract keywords from each segment of the power network communication data to obtain a keyword set of the complete power network communication data;

[0048] A model building module, the model building module is used to build a risk matching model based on a pre-set risk keyword bag in the power system;

[0049] An encryption module is used to input a keyword set into a risk matching model, obtain a risk matching value, and perform high-level encryption and low-level encryption on power network communication data with higher and lower risk matching values, respectively.

[0050] Preferably, the data processing module includes a first data processing unit and a second data processing unit, the first data processing unit is used to perform outlier deletion processing on the power network communication data to obtain first processed data, and the second data processing unit is used to perform missing value filling processing on the first processed data to obtain second processed data;

[0051] The encryption module includes a first encryption unit and a second encryption unit, the first encryption unit is used to perform high-level encryption on high-level risk data, and the second encryption unit is used to perform low-level encryption on low-level data.

[0052] Compared with the prior art, the present invention provides a method and system for encrypting power network communication data, which has the following beneficial effects:

[0053] In real life, although the intelligent trend of power grids has improved the efficiency of electric energy use and the operating efficiency of power systems, it has also brought a series of hidden dangers to power systems. The data communication of power system information terminal equipment in the power system is vulnerable to attacks by criminals, resulting in the leakage of network communication data and even power paralysis. Therefore, it is necessary to encrypt the network communication data of power. The present invention first deletes abnormal values ​​and fills missing values ​​for the acquired power network communication data, so that the power network communication data is accurate, and the processing speed of the later power data is accelerated. By segmenting the power data and extracting keywords at the same time, the extraction speed is also accelerated. The extracted keywords are formed into a set. The risk matching model is pre-set in the power system, and the keyword set is input into the risk matching model to obtain a matching value. The low-level encryption is adopted for the data with a lower matching value, because the data with a lower matching value is not sensitive data of the power enterprise, and even if it is stolen, it will not bring risks to the enterprise. Therefore, the low-level encryption method in the present invention is only a data scrambling method, and the high-level encryption is adopted for the higher matching value. The high-level encryption in the present invention is a double encryption method, which is difficult for criminals to steal, thereby meeting the needs of power enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the power network communication data encryption method in the present invention;

[0055] Figure 2 A schematic diagram of a method for preprocessing power network communication data in the present invention;

[0056] Figure 3 A schematic diagram of a method for performing high-level encryption and low-level encryption on power network communication data with higher and lower risk matching values, respectively, in the present invention;

[0057] Figure 4 This is a schematic diagram of a high-level encryption method in the present invention;

[0058] Figure 5 It is a schematic diagram of the low-level encryption method of the present invention. DETAILED DESCRIPTION

[0059] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0060] Example 1

[0061] Please refer to Figure 1-Figure 5 As shown, a method for encrypting power network communication data includes:

[0062] Acquire power network communication data, which includes all shared communication data of all power system information terminal equipment clusters;

[0063] Preprocess the power network communication data to obtain complete power network communication data;

[0064] The complete power network communication data is segmented and numbered, and keywords are extracted from each segment of the power network communication data to obtain a keyword set of the complete power network communication data;

[0065] Construct a risk matching model based on a bag of pre-set risk keywords in the power system;

[0066] Input the keyword set into the risk matching model to obtain the risk matching value;

[0067] The power network communication data with higher and lower risk matching values ​​are encrypted at high and low levels respectively.

[0068] It can be understood by those skilled in the art that in real life, although the intelligent trend of power grids has improved the efficiency of electric energy use and the operating efficiency of power systems, it has also brought a series of hidden dangers to power systems. The data communication of power system information terminal devices in power systems is vulnerable to attacks by criminals, resulting in the leakage of network communication data and even power paralysis. Therefore, it is necessary to encrypt the network communication data of power. The present invention first deletes abnormal values ​​and fills missing values ​​in the acquired power network communication data, so that the power network communication data is accurate, and the processing speed of the later power data is accelerated. By segmenting the power data and extracting keywords at the same time, the extraction speed is also accelerated. The extracted keywords are formed into a set, and a risk matching model is pre-set in the power system. The keyword set is input into the risk matching model to obtain a matching value. A low-level encryption is adopted for a low-level matching value, because the data with a low matching value is not sensitive data of the power enterprise, and even if it is stolen, it will not bring risks to the enterprise. Therefore, the low-level encryption method in the present invention is only a data scrambling method, and a high-level encryption is adopted for a higher matching value. The high-level encryption in the present invention is a double encryption method, which is difficult for criminals to steal, thereby meeting the needs of power enterprises.

[0069] Preprocessing of power network communication data specifically includes the following steps:

[0070] Performing outlier deletion processing on the power network communication data to obtain first processed data;

[0071] Perform missing value filling processing on the first processed data to obtain second processed data;

[0072] Classification is performed based on the second processed data to obtain complete power network communication data.

[0073] The specific calculation formula for filling missing values ​​is:

[0074]

[0075] Where D i is the filling data; i is the number of filling data; D j are different types of historical data; n is the number of different types of historical data.

[0076] The complete power network communication data is segmented and numbered, and keywords are extracted from each segment of the power network communication data. The keyword set of the complete power network communication data is obtained, which specifically includes the following steps:

[0077] Segmenting the complete power network communication data;

[0078] The communication data of all power network segments are numbered and recorded as S1, S2, ..... Sn;

[0079] Perform keyword extraction on each numbered power network communication data at the same time, obtain and count each keyword in each numbered power network communication data;

[0080] All keywords are grouped together.

[0081] The specific calculation formula of the risk matching model is:

[0082]

[0083] Among them, P j is the matching degree between the input keyword set and the pre-set j-th risk level, N j is the total number of historical keyword sets corresponding to the jth risk level, N0 is the total number of features of the input keyword set, N 同 is the total number of identical features between the feature data of the input keyword set and the historical keyword set corresponding to the jth risk level, α' l is the correlation weight between the feature data of the j-th risk level and the l-th input keyword set and the same feature in the historical keyword set corresponding to the j-th risk level, and max() is the maximum value function.

[0084] The specific steps of performing high-level encryption and low-level encryption on power network communication data with high and low risk matching values ​​include the following:

[0085] Compare the obtained risk matching value with the preset threshold;

[0086] If the risk matching value is greater than or equal to the preset threshold, the power network communication data is determined to be high-level risk data;

[0087] If the risk matching value is less than the preset threshold, the power network communication data is determined to be low-level data;

[0088] High-level encryption is used for high-risk data, and low-level encryption is used for low-level data.

[0089] High-level encryption specifically includes the following steps:

[0090] According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data;

[0091] Each segment of power network communication sub-data is segmented according to a fixed length to obtain multiple encoding vectors;

[0092] Generate a dummy encoding vector for each encoding vector;

[0093] According to the virtual coding vector, each webpage coding vector is encrypted based on the local encryption sequence to obtain each encrypted coding vector;

[0094] splicing multiple encrypted coding vectors to obtain each segment of encrypted power network communication sub-data;

[0095] According to the global encryption sequence, each segment of encrypted power network communication sub-data is encrypted to obtain double-encrypted power network communication data.

[0096] Low-level encryption specifically includes the following steps:

[0097] According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data;

[0098] Multiple segments of power network communication sub-data are shuffled in a disordered manner to obtain encrypted power network communication data.

[0099] A power network communication data encryption method system, comprising:

[0100] An acquisition module, the acquisition module is used to acquire power network communication data, the power network communication data includes all shared communication data of all power system information terminal equipment clusters;

[0101] A data processing module, which is used to pre-process the power network communication data and obtain complete power network communication data;

[0102] A keyword extraction module, which is used to segment and number the complete power network communication data, and extract keywords from each segment of the power network communication data to obtain a keyword set of the complete power network communication data;

[0103] A model building module, the model building module is used to build a risk matching model based on a pre-set risk keyword bag in the power system;

[0104] The encryption module is used to input the keyword set into the risk matching model, obtain the risk matching value, and perform high-level encryption and low-level encryption on the power network communication data with high and low risk matching values ​​respectively.

[0105] The data processing module includes a first data processing unit and a second data processing unit, the first data processing unit is used to perform an outlier deletion process on the power network communication data to obtain first processed data, and the second data processing unit is used to perform a missing value filling process on the first processed data to obtain second processed data;

[0106] The encryption module includes a first encryption unit and a second encryption unit. The first encryption unit is used to perform high-level encryption on high-level risk data, and the second encryption unit is used to perform low-level encryption on low-level data.

[0107] In summary, in real life, although the intelligent trend of the power grid has improved the utilization efficiency of electric energy and the operation efficiency of the power system, it has also brought a series of hidden dangers to the power system. The data communication of the power system information terminal equipment in the power system is vulnerable to attacks by criminals, resulting in the leakage of network communication data and even the paralysis of power. Therefore, it is necessary to encrypt the network communication data of the power. The present invention first deletes abnormal values ​​and fills missing values ​​for the acquired power network communication data, so that the power network communication data is accurate, and the processing speed of the later power data is accelerated. By adopting the segmentation of the power data and extracting keywords at the same time, the extraction speed is also accelerated. The extracted keywords are formed into a set, and the risk matching model is pre-set in the power system. The keyword set is input into the risk matching model to obtain the matching value. The low matching value adopts low-level encryption, because the data with a lower matching value is not sensitive data of the power enterprise, and even if it is stolen, it will not bring risks to the enterprise. Therefore, the low-level encryption method in the present invention is only a data scrambling method, and the high-level encryption is adopted for the higher matching value. The high-level encryption in the present invention is a double encryption method, which is difficult for criminals to steal, thereby meeting the needs of the power enterprise.

[0108] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for encrypting power network communication data, characterized in that: include: Acquiring power network communication data, wherein the power network communication data includes all shared communication data of all power system information terminal device clusters; Preprocess the power network communication data to obtain complete power network communication data; The complete power network communication data is segmented and numbered, and keywords are extracted from each segment of the power network communication data to obtain a keyword set of the complete power network communication data; Construct a risk matching model based on a bag of pre-set risk keywords in the power system; Input the keyword set into the risk matching model to obtain the risk matching value; The power network communication data with higher and lower risk matching values ​​are encrypted at high and low levels respectively.

2. A method for encrypting power network communication data according to claim 1, characterized in that: The preprocessing of the power network communication data specifically comprises the following steps: Performing outlier deletion processing on the power network communication data to obtain first processed data; Perform missing value filling processing on the first processed data to obtain second processed data; Classification is performed based on the second processed data to obtain complete power network communication data.

3. A method for encrypting power network communication data according to claim 2, characterized in that: The specific calculation formula for the missing value filling process is: Where D i is the filling data; i is the number of filling data; D j are different types of historical data; n is the number of different types of historical data.

4. A method for encrypting power network communication data according to claim 3, characterized in that: The step of segmenting and numbering the complete power network communication data, extracting keywords from each segment of the power network communication data, and obtaining a keyword set of the complete power network communication data specifically includes the following steps: Segmenting the complete power network communication data; The communication data of all power network segments are numbered and recorded as S1, S2, ..... Sn; Perform keyword extraction on each numbered power network communication data at the same time, obtain and count each keyword in each numbered power network communication data; All keywords are grouped together.

5. A method for encrypting power network communication data according to claim 4, characterized in that: The specific calculation formula of the risk matching model is: Among them, P j is the matching degree between the input keyword set and the pre-set j-th risk level, N j is the total number of historical keyword sets corresponding to the jth risk level, N0 is the total number of features of the input keyword set, N 同 is the total number of identical features between the feature data of the input keyword set and the historical keyword set corresponding to the jth risk level, α' l is the correlation weight between the feature data of the j-th risk level and the l-th input keyword set and the same feature in the historical keyword set corresponding to the j-th risk level, and max() is the maximum value function.

6. A method for encrypting power network communication data according to claim 5, characterized in that: The high-level encryption and low-level encryption of the power network communication data with higher and lower risk matching values ​​respectively specifically include the following steps: Compare the obtained risk matching value with the preset threshold; If the risk matching value is greater than or equal to the preset threshold, the power network communication data is determined to be high-level risk data; If the risk matching value is less than the preset threshold, the power network communication data is determined to be low-level data; High-level encryption is used for high-risk data, and low-level encryption is used for low-level data.

7. A method for encrypting power network communication data according to claim 6, characterized in that: The high-level encryption specifically includes the following steps: According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data; Each segment of power network communication sub-data is segmented according to a fixed length to obtain multiple encoding vectors; Generate a dummy encoding vector for each encoding vector; According to the virtual coding vector, each webpage coding vector is encrypted based on the local encryption sequence to obtain each encrypted coding vector; splicing multiple encrypted coding vectors to obtain each segment of encrypted power network communication sub-data; According to the global encryption sequence, each segment of encrypted power network communication sub-data is encrypted to obtain double-encrypted power network communication data.

8. A method for encrypting power network communication data according to claim 7, characterized in that: The low-level encryption specifically includes the following steps: According to the content segments in the power network communication data, the power network communication data is segmented to obtain multiple segments of power network communication sub-data; Multiple segments of power network communication sub-data are shuffled in a disordered manner to obtain encrypted power network communication data.

9. A power network communication data encryption method system, used to implement a power network communication data encryption method as claimed in any one of claims 1 to 8, characterized in that: include: An acquisition module, the acquisition module is used to acquire power network communication data, the power network communication data includes all shared communication data of all power system information terminal device clusters; A data processing module, wherein the data processing module is used to pre-process the power network communication data to obtain complete power network communication data; A keyword extraction module, the keyword extraction module is used to segment and number the complete power network communication data, and extract keywords from each segment of the power network communication data to obtain a keyword set of the complete power network communication data; A model building module, the model building module is used to build a risk matching model based on a pre-set risk keyword bag in the power system; An encryption module is used to input a keyword set into a risk matching model, obtain a risk matching value, and perform high-level encryption and low-level encryption on power network communication data with higher and lower risk matching values, respectively.

10. The method and system for encrypting data in power network communication according to claim 1, characterized in that: The data processing module includes a first data processing unit and a second data processing unit, wherein the first data processing unit is used to perform an outlier deletion process on the power network communication data to obtain first processed data, and the second data processing unit is used to perform a missing value filling process on the first processed data to obtain second processed data; The encryption module includes a first encryption unit and a second encryption unit, the first encryption unit is used to perform high-level encryption on high-level risk data, and the second encryption unit is used to perform low-level encryption on low-level data.

Images