A photovoltaic power station 5G network security protection device

Abstract

The application discloses a kind of photovoltaic power station 5G network security protection equipment, it is related to network security protection technical field, the equipment includes following component parts: data acquisition module, intelligent fusion analysis and verification system and protection mechanism trigger module;The application can comprehensively collect and in-depth analysis photovoltaic power station operating data, 5G network characteristic parameters, external environmental factors and personnel operation behavior and other multidimensional data by integrating intelligent fusion analysis and verification system, accurately excavate the potential correlation between different factors and mutual influence mechanism, while dynamic correlation rule self-adapting update mechanism can be according to newly collected data and excavated new correlation, real-time adjustment correlation rule, ensure the accuracy and timeliness of analysis result, not only improve the credibility of data, also can discover and respond to network security risk in time.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of network security protection, and particularly relates to a photovoltaic power station 5G network security protection device. BACKGROUND

[0002] With the rapid development of the photovoltaic industry and the wide application of 5G technology, photovoltaic power stations are gradually achieving intelligentization and networking, and the operation of the photovoltaic power station depends on efficient and safe 5G networks for data transmission, remote monitoring and fault warning. However, the photovoltaic power station 5G network faces a complex and changeable network environment, including massive data from different devices and different systems, and the combined influence of external environmental factors and personnel operation behaviors, therefore, how to effectively integrate and analyze these data, ensure the credibility of the data, and timely discover network security risks has become an important issue for the photovoltaic power station 5G network security protection.

[0003] The traditional photovoltaic power station 5G network security protection measures have obvious deficiencies in data correlation analysis and data credibility verification, first, most traditional systems rely on fixed correlation rules for data analysis, which is difficult to adapt to the dynamic changes of data, resulting in inaccurate analysis results and affecting the network security protection effect, second, the traditional method lacks comprehensive and in-depth analysis means when verifying the credibility of the data, and it is difficult to effectively identify the abnormalities or deviations in the data, which may lead to making decisions based on wrong data, in addition, the traditional system lacks an effective fusion mechanism when processing data from different devices and different systems, resulting in serious data island phenomenon and failing to fully play the value of the data.

[0004] In view of the above problems, it is necessary to optimize the existing photovoltaic power station 5G network security protection device, integrate the data correlation analysis and data credibility verification functions, and introduce a dynamic correlation rule self-adaptive updating mechanism to comprehensively improve the security of the photovoltaic power station 5G network, therefore, it is of great significance to develop a photovoltaic power station 5G network security protection device which can comprehensively realize the above characteristics. SUMMARY

[0005] The photovoltaic power station 5G network security protection equipment can comprehensively improve the security of the photovoltaic power station 5G network and the reliability, analysis accuracy and adaptability to environmental changes of data by integrating data correlation analysis and data reliability verification functions and introducing a dynamic correlation rule adaptive updating mechanism.

[0006] The photovoltaic power station 5G network security protection equipment comprises the following components: a data acquisition module, an intelligent fusion analysis and verification system and a protection mechanism triggering module.

[0007] The data acquisition module comprises a photovoltaic power station self-operation data acquisition unit, a 5G network characteristic parameter acquisition unit, an external environmental factor acquisition unit and a personnel operation behavior acquisition unit.

[0008] The photovoltaic power station self-operation data acquisition unit is physically connected or data-communicatively connected with sensors and monitoring devices of devices in the photovoltaic power station, realizes data interaction, collects photovoltaic module power generation efficiency and inverter state data in real time according to a preset sampling frequency, the 5G network characteristic parameter acquisition unit is connected with the photovoltaic power station 5G network by using a network monitoring device, and monitors and collects signal strength, frequency band usage and data transmission rate parameters of the 5G network in real time, the external environmental factor acquisition unit is equipped with a meteorological sensor and an electromagnetic interference monitor, the meteorological sensor collects weather conditions in real time, and the electromagnetic interference monitor continuously monitors surrounding electromagnetic interference intensity, the personnel operation behavior acquisition unit monitors operation records of operation and maintenance personnel logging into the photovoltaic power station 5G network management system by embedding a monitoring program in the photovoltaic power station 5G network management system or by using a network audit tool, records login frequency and operation behavior data of operation instruction types of the operation and maintenance personnel, and arranges collected data and transmits the data to the intelligent fusion analysis and verification system.

[0009] The intelligent fusion analysis and verification system comprises a data preprocessing submodule, a fusion analysis and verification submodule, a risk judgment and protection level adjustment submodule and a dynamic correlation rule adaptive updating submodule.

[0010] The data preprocessing submodule performs data cleaning operations on the received various factor data, and converts the data from different sources into a unified internal data format. The fusion analysis and verification submodule uses big data analysis techniques and intelligent algorithms to perform deep fusion analysis and verification on the preprocessed various factor data. For mining the potential correlation between different factors and the mutual influence mechanism, a data correlation model is constructed, the correlation coefficient between different factors is analyzed based on historical data and real-time collected data, the logical correlation between different factors is mined using association rule mining algorithms, and the complex nonlinear relationship is modeled to accurately capture the potential influence mechanism between different factors. For the multi-source data fusion verification function, the data from different devices and different systems are cross-analyzed, the differences between the same or related data items in different data sources are analyzed, the data comparison operation is performed, and whether the data conforms to the normal situation is judged according to the pre-set physical law and logical relationship. For the abnormal deviation found in the data, the data source tracing program is started to determine the device that has a problem. The risk judgment and protection level adjustment submodule determines the correlation, mutual influence mechanism and data credibility according to the correlation, mutual influence mechanism and data credibility, combines the set network security risk judgment standard, calculates the risk probability value through the risk evaluation model and compares it with the threshold to determine whether there is a network security risk. At the same time, different protection measures are dynamically adjusted according to the data credibility to dynamically adjust the security protection level of the data. The dynamic association rule self-adaptive updating submodule continuously monitors the newly collected data and the new correlation mined by the fusion analysis and verification submodule. With the continuous collection and analysis of new data, when the environmental factors or device running state change, the update of the association rule is triggered. Specifically, when the correlation coefficient between a factor and other factors in the newly collected data changes by more than the threshold R x , the association rule is updated using an update algorithm based on machine learning. Specifically, according to the new data characteristics and the new correlation mined, the weights and thresholds of the factors in the association rule are adjusted to adapt to the new data mode and changes.

[0011] The protection mechanism triggering module includes a data encryption enhancement unit, a network access policy adjustment unit and a warning notification unit.

[0012] After the data encryption enhancement unit receives the signal that the intelligent fusion analysis and verification system determines that there is a network security risk or detects the signal that the data credibility is abnormal, the data encryption enhancement program is automatically started. The network access policy adjustment unit adjusts the access policy of the 5G network according to the specific situation of the risk or the abnormal situation of the data credibility. The warning notification unit sends a warning notification to the operation and maintenance personnel, and the notification content includes the specific information of the network security risk or the data credibility abnormality.

[0013] Further, in the intelligent fusion analysis and verification system, the fusion analysis and verification submodule analyzes the correlation coefficient between different factors based on historical data and real-time collected data, and the calculation formula is: Wherein, x i and y i represent the specific observation values in the data sequence of the two different factors respectively, and are the average values of the data sequence x i and y i , and n represents the number of data points in the data sequence x i and y i .

[0014] Further, in the intelligent fusion analysis and verification system, the fusion analysis and verification submodule uses the association rule mining algorithm to mine the logical association relationship between different factors, and the algorithm formula is: Wherein, R ij represents the comprehensive association relationship strength between factor i and factor j, n represents the number of factor types participating in the calculation of the association relationship, including photovoltaic power station operation data, 5G network characteristic parameters, external environmental factors and personnel operation behaviors, w k is the weight coefficient of the kth factor in the calculation of the association relationship, f k (x ik ,y jk ) is the association function corresponding to the kth factor, x ik is the specific observation value of factor i about the kth factor, and y jk is the specific observation value of factor j about the kth factor.

[0015] Further, in the intelligent fusion analysis and verification system, by comparing the same or related data items in different data sources, the difference is analyzed, the data comparison operation is performed, and according to the pre-set physical law and logical relationship, it is judged whether the data conforms to the normal situation, and the formula is: Wherein, C data represents the data credibility after comprehensive evaluation, M represents the number of data sources participating in data fusion verification, including photovoltaic power station operation data, 5G network characteristic parameters, external environmental factors and personnel operation behaviors, a m is the weight coefficient of the mth data source in evaluating the data credibility, g m (z m ) is the credibility function corresponding to the mth data source, which is used to describe the relationship between the data characteristics of the mth data source and the credibility, z m is the specific data value or data characteristic vector of the mth data source, and by calculating the data credibility, it is judged whether the data conforms to the normal situation.

[0016] Further, in the intelligent fusion analysis and verification system, the risk judgment and protection level adjustment submodule calculates the risk probability value through the risk assessment model and compares it with the threshold value to determine whether there is a network security risk, and the algorithm formula of the risk assessment model is: wherein, P risk represents the network security risk probability value after comprehensive judgment, L represents the number of factors participating in risk judgment, b l is the weight coefficient of the lth factor in judging network security risk, μ l (v l ) is the membership function corresponding to the lth factor, v l is the specific observation value of the lth factor.

[0017] Further, in the intelligent fusion analysis and verification system, the risk judgment and protection level adjustment submodule sets different protection measures according to the data credibility to dynamically adjust the security protection level of the data, and the protection level judgment formula is: wherein, PL adjust represents the dynamically adjusted protection level, C data is the data credibility, C high is the high credibility threshold value, when the data credibility C data is greater than or equal to this threshold value, it means that the data credibility is high, P risk is the network security risk probability value, P low is the low risk threshold value, when the network security risk probability value P risk is less than or equal to this threshold value, it means that the network security risk is low, P mid is the medium risk threshold value, when the network security risk probability value P risk is greater than P low and less than or equal to this threshold value, it means that the network security risk is at a medium level, when the network security risk probability value P risk is greater than P mid , it means that the network security risk is high.

[0018] Further, in the intelligent fusion analysis and verification system, the dynamic association rule adaptive updating submodule adjusts the weight and threshold value of each factor in the association rule according to the new data characteristics and the new association relationship mined, for weight adjustment, the adjustment formula is: wherein, represents the updated weight value of factor i after the t+1th iteration, is the current weight value of factor i at the tth iteration, α is the learning rate parameter, represents the partial derivative of the loss function L with respect to the current weight , for threshold value updating, the updating formula is: wherein, T t+1 represents the updated threshold value after the t+1th iteration, T t is the current threshold value at the tth iteration, and β is the learning rate, represents the partial derivative of the loss function L with respect to the current threshold value T t .

[0019] Further, in the protection mechanism triggering module, after the data encryption strengthening unit receives the signal that the intelligent fusion analysis and verification system determines that there is a network security risk or detects a signal that the data credibility is abnormal, the data encryption strengthening program is automatically started, and the encryption strength is dynamically adjusted, and the encryption algorithm determination method is: wherein, E upgrade represents the encryption algorithm to be upgraded according to the risk situation and the data importance, and takes values of AES, 3DES or RSA, representing different encryption algorithms of different strengths, P risk is the network security risk probability value, P low is the low risk threshold value, P mid is the medium risk threshold value, when the network security risk probability value P risk is greater than P low and less than or equal to the threshold value, it indicates that the network security risk is at a medium level, I data is a data importance index, which is used to measure the importance degree of the current transmission data for the operation, decision, etc. of the photovoltaic power station, I low is a low data importance threshold value, I mid is a medium data importance threshold value, when the data importance index I dnta is greater than I low and less than or equal to the threshold value, it indicates that the data importance is at a medium level, and when the data importance index I dnta is greater than I mid , it indicates that the data importance is high.

[0020] Further, in the protection mechanism triggering module, the network access strategy adjustment unit dynamically adjusts the encryption strength through the formula S encryptiom =S base +k·(P risk -P ref ) while upgrading the encryption algorithm, wherein S encryptiom is the adjusted encryption strength, S bure is the basic encryption strength, P risk is the network security risk probability value, k is the encryption strength adjustment coefficient, and P ref is the reference risk probability value.

[0021] Compared with the prior art, the photovoltaic power station 5G network security protection equipment has the following beneficial effects:

[0022] One, the present application can comprehensively collect and deeply analyze multi-dimensional data such as photovoltaic power station operation data, 5G network characteristic parameters, external environmental factors, and personnel operation behaviors by integrating intelligent fusion analysis and verification system, accurately mine potential correlation between different factors and mutual influence mechanism, and dynamic correlation rule adaptive updating mechanism can adjust correlation rules in real time according to newly collected data and mined new correlation, ensure accuracy and timeliness of analysis results, not only improve data credibility, but also can discover and respond to network security risks in time.

[0023] Two, the present application can accurately capture and transmit characteristic information of various factor data such as fluctuation amplitude, frequency, and change rate by data feature adaptive sensing and collecting technology, provide more rich and accurate data support for intelligent fusion analysis and verification system, make it can more accurately analyze the influence of environmental factors or equipment operation state change on photovoltaic power station operation and network security, and dynamic correlation rule adaptive updating mechanism can adjust correlation rules in time according to environmental change or equipment state change, ensure accuracy and reliability of analysis results.

[0024] Other advantages, objects and features of the present application will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0026] Figure 1 It is a structural schematic diagram of a photovoltaic power station 5G network security protection device;

[0027] Figure 2 It is a flow operation diagram of a photovoltaic power station 5G network security protection device. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0029] Embodiment

[0030] The embodiment describes in detail the application of a photovoltaic power station 5G network security protection device in the network security protection of a large desert photovoltaic power station. Through the close cooperation of each module, accurate data collection and analysis, and the triggering of targeted protection mechanisms, the security protection capability of the power station 5G network is effectively improved, ensuring the stable and safe operation of the power station under harsh environments and complex operation and maintenance conditions.

[0031] The data collection module includes a photovoltaic power station itself operation data collection unit, a 5G network characteristic parameter collection unit, an external environmental factor collection unit, and a personnel operation behavior collection unit. The photovoltaic power station itself operation data collection unit establishes a physical connection or data communication link with the sensors and monitoring devices of each device in the photovoltaic power station, realizes data interaction, and collects photovoltaic module power generation efficiency and inverter state data in real time according to the preset sampling frequency. The 5G network characteristic parameter collection unit connects the network monitoring device with the photovoltaic power station 5G network and monitors and collects the signal strength, frequency band usage, and data transmission rate parameters of the 5G network in real time. The external environmental factor collection unit is equipped with a meteorological sensor and an electromagnetic interference monitor. The meteorological sensor collects weather conditions in real time, and the electromagnetic interference monitor continuously monitors the surrounding electromagnetic interference intensity. The personnel operation behavior collection unit embeds a monitoring program in the photovoltaic power station 5G network management system or uses a network audit tool to comprehensively monitor the operation records of the operation and maintenance personnel logging into the photovoltaic power station 5G network management system, records the login frequency and operation instruction type operation behavior data of the operation and maintenance personnel, and arranges the collected data and transmits it to the intelligent fusion analysis and verification system.

[0032] The intelligent fusion analysis and verification system comprises a data preprocessing submodule, a fusion analysis and verification submodule, a risk judgment and protection level adjustment submodule, and a dynamic correlation rule adaptive updating submodule. The data preprocessing submodule comprehensively and preliminarily processes various factor data (data transmitted from a photovoltaic power station self-operation data acquisition unit, a 5G network characteristic parameter acquisition unit, an external environment factor acquisition unit, and a personnel operation behavior acquisition unit) received, first performs a data cleaning operation, removes invalid data according to a set data filtering rule (such as removing obviously incorrect data values, for example, abnormally large or small data values collected due to sensor failure, removing repeated data records to avoid interference with subsequent analysis), and ensures data accuracy. For example, in the data received this time, a temperature value obviously deviating from the normal range is collected due to sand dust invasion of a certain sensor, which is removed through the data cleaning operation. Then, format unification processing is performed, and data of different sources is converted into a pre-defined standard data structure to ensure that all data has consistent format requirements in subsequent analysis and verification processes, improve data processing efficiency and accuracy, such as converting data in JSON format transmitted by the photovoltaic power station self-operation data acquisition unit, data in a specific network data format transmitted by the 5G network characteristic parameter acquisition unit, data in a general environment data format transmitted by the external environment factor acquisition unit, and data in a database table structure form transmitted by the personnel operation behavior acquisition unit into a unified internal data format (such as a structured data format defined for analysis of the system), so that subsequent modules can conveniently process and analyze the data. The fusion analysis and verification submodule uses advanced big data analysis technology and intelligent algorithms to perform deep fusion analysis and verification on various factor data after preprocessing. First, a data correlation model is constructed, and based on historical data and real-time collected data, correlation coefficients between different factors are analyzed, for example, correlation between photovoltaic component power generation efficiency and 5G network signal strength is calculated through statistical analysis. Assuming that relevant data in the past month is collected, the correlation coefficient between the two is calculated, and the calculation formula is as follows: wherein x i and y i represent specific observation values in data sequences of two different factors, for example, x i may be a series of specific measurement values of photovoltaic component power generation efficiency in a certain time period, and y i may be a series of measurement values of 5G network signal strength in the corresponding time period. Through correlation analysis of the data of the two different factors, the potential correlation relationship between them is mined, so that the update of the dynamic correlation rule is triggered according to the change of the correlation relationship, and are data sequences x iand y i The average value is calculated to take the average level of the data sequence as a reference when calculating the correlation coefficient, so as to more accurately measure the deviation of each data point from the average level, thereby more accurately reflecting the degree of correlation between the two groups of data. For example, for the photovoltaic component power generation efficiency data sequence x i , The average value is the average power generation efficiency of all measured values of the power generation efficiency in a specific time period. For the 5G network signal strength data sequence y i , The average value is the average signal strength of all measured values of the signal strength in the corresponding time period. n represents the number of data points in the data sequence x i and y ithe number of data points in the data set, second, using an association rule mining algorithm, the logical association between different factors may exist, for example, when the external environment temperature rises, by analyzing a large number of historical data and real-time collected data, the logical association relationship that the photovoltaic module power generation efficiency may decrease and the 5G network data transmission rate may be affected is mined, specifically, in the analysis process, the support threshold is set to 0.3, and the confidence threshold is set to 0.7, when the threshold conditions are met, it is considered that the association rule with practical significance is mined, through the analysis of different factor combinations, it is found that when the temperature rises to a certain degree (such as more than 40℃), in most cases (satisfying the confidence threshold), the photovoltaic module power generation efficiency will decrease obviously, and the 5G network data transmission rate will also decrease, this association relationship has important significance for comprehensively understanding the operation condition of the power station and the subsequent risk judgment and protection measure formulation, further, a neural network algorithm is used to model the complex nonlinear relationship, to accurately capture the potential influence mechanism between different factors, for example, for the relationship between personnel operation behavior anomaly and photovoltaic power station operation data and network characteristic parameters, a multi-layer perceptron neural network model is constructed, the number of input layer nodes is determined according to the number of input data characteristics, here the input data includes the operation instruction execution time, operation instruction type, login frequency of the operation and maintenance personnel, and the corresponding photovoltaic power station operation data (such as photovoltaic module power generation efficiency, inverter state, etc.) and 5G network characteristic parameters (such as signal strength, frequency band usage, etc.), assuming that the number of input layer nodes is determined to be 10 after feature extraction and screening, the hidden layer can be set to multiple layers, the number of nodes in each layer is determined according to experience and test, here it is set to two layers, the number of nodes in the first layer hidden layer is 8, the number of nodes in the second layer hidden layer is 6, the number of nodes in the output layer is determined according to the number of targets to be predicted, here the target is to predict the influence degree of personnel operation behavior anomaly on the overall operation of the power station (such as whether it will cause a large decrease in power generation efficiency, whether the network will be interrupted, etc.), so the number of nodes in the output layer is set to 2, through the training of a large number of historical data and real-time collected data, the neural network model can learn the complex relationship between different factors, accurately capture the potential influence mechanism between personnel operation behavior anomaly and photovoltaic power station operation data and network characteristic parameters, for example, when the operation and maintenance personnel make some specific misoperation (such as incorrect configuration of network parameters), the model can predict the possible decrease in photovoltaic module power generation efficiency and the fluctuation of 5G network signal strength, at the same time, the comprehensive association relationship strength R between factor i and factor j is calculated by the formula Mining the comprehensive association relationship strength R between factor i and factor j ij wherein n represents the number of factor types participating in the calculation of the association relationship, covering multiple dimensions of various factors, such as photovoltaic module power generation efficiency, 5G network signal strength, external environment temperature, operation instruction execution time of the operation and maintenance personnel, etc., w kis the weight coefficient of the kth factor in calculating the correlation relationship, which is set according to the importance degree of different factors to the correlation relationship mining, assuming that for the photovoltaic module power generation efficiency factor, the weight coefficient w1=0.4, for the 5G network signal strength factor, the weight coefficient w2=0.3, for the external environment temperature factor, the weight coefficient w3=0.2, and for the operation personnel operation instruction execution time factor, the weight coefficient w4=0.1, f k (x ik , y jk ) is the correlation function corresponding to the kth factor, which is used to describe the mutual relationship between factor i and factor j at the kth factor level, for example, for the correlation function of the photovoltaic module power generation efficiency and the 5G network signal strength at the external environment temperature factor level, the corresponding function relationship can be established according to the actual data and physical principles, x ik is the specific observation value of factor i about the kth factor, for example, when i is the photovoltaic module power generation efficiency and k is the external environment temperature, x ik is the observed value of the photovoltaic module power generation efficiency at a certain moment corresponding to the external environment temperature value, y jk is the specific observation value of factor j about the kth factor, through the formula, the potential correlation between the factors can be considered comprehensively, and the potential correlation between the factors can be quantified, which provides an accurate basis for mining potential correlation, for example, through calculation, the comprehensive correlation relationship strength R ij between the photovoltaic module power generation efficiency and the 5G network signal strength considering the external environment temperature, operation personnel operation instruction execution time and other factors is 0.5, indicating that there is a certain degree of correlation between them, and the correlation is affected by multiple factors. Finally, the formula is used to evaluate the data credibility C data after comprehensive evaluation, wherein M represents the number of data sources participating in data fusion verification, including data of different devices and systems, such as photovoltaic module monitoring data, inverter data, weather station data, 5G network tester data, and operation personnel operation record data, a m is the weight coefficient of the mth data source in evaluating the data credibility, which is set according to the importance degree of different data sources to the data credibility, assuming that for the photovoltaic module monitoring data, the weight coefficient a1=0.3, for the inverter data, the weight coefficient a2=0.25, for the weather station data, the weight coefficient a3=0.2, for the 5G network tester data, the weight coefficient a4=0.15, and for the operation personnel operation record data, the weight coefficient a5=0.1, g m (z m) is the credibility function corresponding to the mth data source, which is used to describe the relationship between the data characteristics of the mth data source and the credibility, for example, for photovoltaic component monitoring data, the credibility function can be established according to the accuracy of the sensor, the stability of data acquisition and other factors, z m is the specific data value or data feature vector of the mth data source, which can accurately reflect the credibility of the data through the formula, and provide an important basis for subsequent judgment of data reliability, for example, through calculation, the data credibility C data after comprehensive evaluation is 0.65, indicating that the credibility of the overall data is at a medium level, which needs to be considered in the subsequent risk judgment and protection measure adjustment, the risk judgment and protection level adjustment submodule judges whether there is a network security risk according to the correlation relationship, mutual influence mechanism and data credibility mined by the fusion analysis and verification submodule, and combines the pre-set network security risk judgment standard (such as setting the risk level threshold corresponding to different factor combinations), for example, in the case of extreme high temperature weather and abnormal personnel operation behavior, the network security risk probability value P is calculated by formula risk increases significantly and exceeds the medium risk threshold, wherein L represents the number of factors participating in risk judgment, these factors include correlation relationship strength, data deviation degree and various factors related to network security risk, assuming that the correlation relationship strength between photovoltaic component power generation efficiency and 5G network signal strength, the deviation degree of photovoltaic component power generation efficiency data from the normal level, the deviation degree of 5G network signal strength data from the normal level, and the abnormality degree evaluation value of operation personnel operation instruction execution time are considered, that is, L = 4, b l is the weight coefficient of the lth factor in judging network security risk, which is set according to the importance degree of different factors in risk judgment, assuming that the weight coefficient of the correlation relationship strength between photovoltaic component power generation efficiency and 5G network signal strength is b1 = 0.3, and the weight coefficient of the deviation degree of photovoltaic component power generation efficiency data from the normal level is b2 = 0.25, the network security risk probability value P risk increases significantly and exceeds the medium risk threshold, according to formula , the security protection level of the data is dynamically adjusted to PL3, and the corresponding enhanced protection measures are taken, wherein C duta is the data credibility, here C duta = 0.65, P risk is the network security risk probability value, which has been calculated to exceed the medium risk threshold, C high is the high credibility threshold, which is determined according to the requirements of photovoltaic power station on data accuracy and reliability and the analysis of historical data, assuming that C high = 0.8, P lowThe low-risk threshold is determined according to the tolerance of the photovoltaic power station to network security risks and analysis of historical data, assuming that P low = 0.2, P mid is a medium-risk threshold, also determined according to the tolerance of the photovoltaic power station to network security risks and analysis of historical data, assuming that P mid = 0.5, so, according to the above conditions, the case of C data ≥ C high and P risk > P mid occurs, so the protection level is adjusted to PL3, the dynamic correlation rule adaptive updating submodule continuously monitors newly collected data and the new correlation relationships mined by the fusion analysis and verification submodule, and as new data is continuously collected and analyzed, the update of the correlation rules is triggered when the environmental factors or the equipment operating state changes. Specifically, the trigger condition for updating the correlation rules is set, when the correlation coefficient between a factor and other factors in the newly collected data changes by more than a threshold R x , an update algorithm based on machine learning is used to update the correlation rules. Specifically, according to the new data characteristics and the new correlation relationships mined, the weights and thresholds of the factors in the correlation rules are adjusted to adapt to the new data patterns and changes. For weight adjustment, the adjustment formula is: wherein, represents the updated weight value of factor i after the t+1 iteration, is the current weight value of factor i at the t iteration, and a is the learning rate parameter, represents the partial derivative of the loss function L with respect to the current weight . For threshold updating, the update formula is: wherein, T t+1 represents the updated threshold after the t+1 iteration, T t is the current threshold at the t iteration, and b is the learning rate, represents the partial derivative of the loss function L with respect to the current threshold T t .

[0033] The protection mechanism triggering module includes a data encryption enhancement unit, a network access policy adjustment unit, and a warning notification unit. Due to the increase in the risk level, the data encryption enhancement unit upgrades the originally used AES encryption algorithm to the 3DES encryption algorithm according to the pre-set encryption strategy, and at the same time of upgrading the encryption algorithm, dynamically adjusts the encryption strength through the formula S encryptiom = S base +k·(P risk -P ref ) to ensure that the data is not stolen or tampered with during transmission, and to ensure the security of the data in the high-risk situation, wherein S bureTo the basic encryption strength, assume set to a fixed value, such as S base = 100 (the value here is only an example, the actual can be determined according to the initial setting of encryption algorithm, etc.), k is the encryption strength adjustment coefficient, according to the requirement of data security and the safety policy of photovoltaic power station, specific setting, assume k = 0.5; P risk is the network security risk probability value, has been calculated to exceed the medium risk threshold, P ref is the reference risk probability value, can be set according to historical data or experience, assume P ref = 0.3, through the calculation can get S encryption = 100 + 0.5·(P risk - 0.3), the specific P risk Value is substituted into to obtain the adjusted encryption strength, so as to realize the dynamic adjustment of data encryption strength, to adapt to the high risk network environment, network access strategy adjustment unit for suspicious IP address access, through the network firewall limits the access of related IP address, and increases the fingerprint verification and face recognition and other identity verification link, for example, in monitoring there is suspicious IP address tries to frequently access the key network resources of power station, network firewall immediately block the access request of this IP address, at the same time, pop up fingerprint verification and face recognition window, require the access to carry on the identity verification, only through the verification of the access can continue to access related resources, at the same time, according to the data credibility situation, limit the accessible range of part of low credibility data, only allow specific operation and maintenance personnel role to access related data, effectively prevent unauthorized access and data leakage risk, for example, for those data credibility is lower than a certain threshold (such as C data <0.5) operation and maintenance data, such as some temporary record device debugging parameters, only allow high level operation and maintenance personnel (such as power station technical director, etc.) to access, ordinary operation and maintenance personnel can't access these data, so as to ensure the safety and secrecy of data, early warning notification unit determines the early warning level as high risk, through the form of short message to all operation and maintenance personnel immediately send early warning notice, the notification content details the existing network security risk situation, including the influence of extreme high temperature weather on photovoltaic module power generation efficiency and 5G network, personnel operation behavior abnormal situation and data encryption and network access strategy adjustment situation, etc., so that operation and maintenance personnel can take corresponding measures in time to deal with, such as on-site inspection equipment, troubleshooting, etc., operation and maintenance personnel can clearly understand the current situation of power station and the measures to be taken, so as to effectively deal with network security risk, guarantee the normal operation of power station.

[0034] In summary, the above-mentioned embodiments effectively improve the security protection capability of the power station 5G network through the close cooperation of each module, accurate data collection and analysis, and targeted protection mechanism triggering, guarantee the stable and safe operation of the power station under harsh environment and complex operation and maintenance conditions, and fully embody the practicability and effectiveness of the application in the specific application field.

[0035] It will be obvious to a person skilled in the art that the application is not limited to the details of the above-described exemplary embodiments, but that the application can be implemented in other concrete forms without departing from the spirit or essential characteristics of the application. The embodiments should, therefore, be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalents of the claims are therefore intended to be embraced therein. Any reference signs in the claims should not be construed as limiting the claims concerned.

Claims

1. A photovoltaic power plant 5G network security protection device, characterized in that, The device comprises the following components: a data acquisition module, an intelligent fusion analysis and verification system, and a protection mechanism triggering module. The data acquisition module comprises a photovoltaic power station self-operation data acquisition unit, a 5G network characteristic parameter acquisition unit, an external environmental factor acquisition unit, and a personnel operation behavior acquisition unit. The photovoltaic power station self-operation data acquisition unit is physically connected or data communication linked with sensors and monitoring devices in the photovoltaic power station, realizes data interaction, collects photovoltaic module power generation efficiency and inverter state data in real time according to a preset sampling frequency, the 5G network characteristic parameter acquisition unit is connected with the photovoltaic power station 5G network by using a network monitoring device, and monitors and collects signal strength, frequency band usage, and data transmission rate parameters of the 5G network in real time, the external environmental factor acquisition unit is equipped with a meteorological sensor and an electromagnetic interference monitor, the meteorological sensor collects weather conditions in real time, and the electromagnetic interference monitor continuously monitors surrounding electromagnetic interference intensity, the personnel operation behavior acquisition unit is embedded with a monitoring program in the photovoltaic power station 5G network management system or uses a network audit tool to comprehensively monitor operation records of operation and maintenance personnel logging into the photovoltaic power station 5G network management system, records login frequency and operation behavior data of operation instruction types of the operation and maintenance personnel, and arranges collected data and transmits the data to the intelligent fusion analysis and verification system. The intelligent fusion analysis and verification system comprises a data preprocessing submodule, a fusion analysis and verification submodule, a risk judgment and protection level adjustment submodule, and a dynamic correlation rule adaptive updating submodule. The data preprocessing submodule performs data cleaning operations on received various factor data, and converts data of different sources into a unified internal data format. The fusion analysis and verification submodule uses big data analysis technology and intelligent algorithms to perform deep fusion analysis and verification on the preprocessed various factor data. For mining the potential correlation between different factors and the mutual influence mechanism, a data correlation model is constructed, the correlation coefficient between different factors is analyzed based on historical data and real-time collected data, the logical correlation between different factors is mined using association rule mining algorithm, and the complex nonlinear relationship is modeled to accurately capture the potential influence mechanism between different factors. For the multi-source data fusion verification function, cross analysis is performed on data from different devices and different systems, the differences between the same or related data items in different data sources are analyzed, data comparison operations are performed, whether the data conforms to the normal situation is judged based on the pre-set physical law and logical relationship, and for the data found to have abnormal deviation, a data source tracing program is started to determine the device that has problems. The risk judgment and protection level adjustment submodule calculates the risk probability value through a risk assessment model and compares it with a threshold to determine whether there is a network security risk according to the correlation relationship, mutual influence mechanism and data credibility, combines the set network security risk judgment standard, and dynamically adjusts the security protection level of the data according to the data credibility. The dynamic association rule self-adaptive updating submodule continuously monitors newly collected data and the new correlation relationship mined by the fusion analysis and verification submodule. With the continuous collection and analysis of new data, when the environmental factors or device running state change, the update of the association rule is triggered. Specifically, the trigger condition for updating the association rule is set. When the correlation coefficient between a factor and other factors in the newly collected data changes by more than a threshold , an updating algorithm based on machine learning is used to update the association rule. Specifically, according to the new data characteristics and the new correlation relationship mined, the weights and thresholds of the factors in the association rule are adjusted to adapt to the new data mode and changes. The data preprocessing submodule performs data cleaning operations on received various factor data, and converts data of different sources into a unified internal data format. The fusion analysis and verification submodule uses big data analysis technology and intelligent algorithms to perform deep fusion analysis and verification on the preprocessed various factor data. For mining the potential correlation between different factors and the mutual influence mechanism, a data correlation model is constructed, the correlation coefficient between different factors is analyzed based on historical data and real-time collected data, the logical correlation between different factors is mined using association rule mining algorithm, and the complex nonlinear relationship is modeled to accurately capture the potential influence mechanism between different factors. For the multi-source data fusion verification function, cross analysis is performed on data from different devices and different systems, the differences between the same or related data items in different data sources are analyzed, data comparison operations are performed, whether the data conforms to the normal situation is judged based on the pre-set physical law and logical relationship, and for the data found to have abnormal deviation, a data source tracing program is started to determine the device that has problems. The risk judgment and protection level adjustment submodule calculates the risk probability value through a risk assessment model and compares it with a threshold to determine whether there is a network security risk according to the correlation relationship, mutual influence mechanism and data credibility, combines the set network security risk judgment standard, and dynamically adjusts the security protection level of the data according to the data credibility. The dynamic association rule self-adaptive updating submodule continuously monitors newly collected data and the new correlation relationship mined by the fusion analysis and verification submodule. With the continuous collection and analysis of new data, when the environmental factors or device running state change, the update of the association rule is triggered. Specifically, the trigger condition for updating the association rule is set. When the correlation coefficient between a factor and other factors in the newly collected data changes by more than a threshold , an updating algorithm based on machine learning is used to update the association rule. Specifically, according to the new data characteristics and the new correlation relationship mined, the weights and thresholds of the factors in the association rule are adjusted to adapt to the new data mode and changes. The protection mechanism triggering module comprises a data encryption enhancement unit, a network access strategy adjustment unit, and a pre-warning notification unit. After receiving a signal indicating that there is a network security risk or a signal indicating that data credibility is abnormal, the data encryption enhancement unit automatically starts a data encryption enhancement program, the network access strategy adjustment unit adjusts the access strategy of the 5G network according to specific circumstances of the risk or abnormal data credibility, and the pre-warning notification unit sends a pre-warning notification to the operation and maintenance personnel, and the notification content comprises specific information about the network security risk or the abnormal data credibility.

2. The photovoltaic power station 5G network security protection device according to claim 1, characterized in that, The intelligent fusion analysis and verification system, the fusion analysis and verification submodule is based on historical data and real-time collected data, analyzes the correlation coefficient between different factors, and the calculation formula is: Wherein, And Respectively represent the specific observation value in the data sequence of two groups of different factors, And Respectively are the average value of data sequence And , Indicate the number of data points in data sequence And .

3. The photovoltaic power plant 5G network security protection device according to claim 1, characterized in that, In the intelligent fusion analysis and verification system, the fusion analysis and verification submodule utilizes an association rule mining algorithm to uncover the logical relationships between different factors. The algorithm formula is as follows: ,in, Indicator Factors and factors The overall strength of the correlation between them This indicates the number of different types of factors involved in calculating the correlation, including various factors such as the photovoltaic power plant's own operating data, 5G network characteristic parameters, external environmental factors, and personnel operational behaviors. It is the first The weighting coefficients of each factor when calculating the correlation. It is the first The correlation function corresponding to the factors Factors Regarding the first Specific observed values ​​of the factors, Factors Regarding the first Specific observed values ​​of each factor.

4. The photovoltaic power plant 5G network security protection device according to claim 1, characterized in that, In the intelligent fusion analysis and verification system, by comparing the same or related data items in different data sources, the difference is analyzed, the data comparison operation is performed, and whether the data conforms to the normal condition is judged according to the pre-set physical law and logical relationship, and the formula is: Wherein, represents the data credibility after comprehensive evaluation, represents the number of data sources participating in data fusion verification, including various factors such as photovoltaic power station operation data, 5G network characteristic parameters, external environmental factors and personnel operation behavior, is the weight coefficient of the first data source in evaluating data credibility, is the first data source corresponding to the credibility function, used to describe the relationship between the data characteristics of the first data source and the credibility, is the specific data value or data feature vector of the first data source, and the data is judged whether it conforms to the normal condition by calculating the data credibility.

5. The photovoltaic power station 5G network security protection device according to claim 1, characterized in that, The intelligent fusion analysis and verification system, the risk judgment and protection level adjustment submodule calculates the risk probability value through the risk evaluation model and compares with the threshold value to determine whether there is a network security risk, the algorithm formula of the risk evaluation model is: Wherein, represents the network security risk probability value after comprehensive judgment, represents the number of factors participating in risk judgment, is the weight coefficient of the first factor in judging network security risk, is the membership function corresponding to the first factor, is the specific observation value of the first factor.

6. The photovoltaic power plant 5G network security protection device according to claim 1, characterized in that, The intelligent fusion analysis and verification system, risk judgment and protection level adjustment submodule according to data credibility setting different protection measures to dynamically adjust the security protection level of data, its protection level judgment formula is: , wherein represents the dynamically adjusted protection level, is the data credibility, is the high credibility threshold, when the data credibility is greater than or equal to the threshold, it means that the data credibility is high, is the network security risk probability value, is the low risk threshold, when the network security risk probability value is less than or equal to the threshold, it means that the network security risk is low, is the medium risk threshold, when the network security risk probability value is greater than and less than or equal to the threshold, it means that the network security risk is at a medium level, when the network security risk probability value is greater than , it means that the network security risk is high.

7. The photovoltaic power plant 5G network security protection device according to claim 1, characterized in that, In the intelligent fusion analysis and verification system, the dynamic association rule adaptive update submodule adjusts the weights and thresholds of each factor in the association rule based on new data features and newly mined associations. The adjustment formula for the weights is as follows: ,in, Indicates the first Factors after the next iteration The updated weight values, It is in the Factors during the next iteration The current weight value, It is the learning rate parameter. Represents the loss function Regarding the current weight The partial derivative of is used for threshold updates, and the update formula is: ,in, Indicates the first The threshold updated after the next iteration. It is in the The current threshold at the next iteration It's the learning rate. Represents the loss function Regarding the current threshold The partial derivatives of .

8. The photovoltaic power plant 5G network security protection device according to claim 1, characterized in that, In the protection mechanism triggering module, the data encryption strengthening unit automatically starts the data encryption strengthening program and dynamically adjusts the encryption strength after receiving the signal that the intelligent fusion analysis and verification system determines that there is a network security risk or detecting the signal that the data credibility is abnormal, and the encryption algorithm determination method is: wherein, represents the encryption algorithm to be upgraded according to the risk situation and the data importance, and the value is , 3 or , respectively representing different strength encryption algorithms, is a network security risk probability value, is a low risk threshold, is a medium risk threshold, when the network security risk probability value is greater than and less than or equal to the threshold, it indicates that the network security risk is at a medium level, is a data importance index, which is used to measure the importance degree of the current transmission data for the operation, decision, etc. of the photovoltaic power station, is a low data importance threshold, is a medium data importance threshold, when the data importance index is greater than and less than or equal to the threshold, it indicates that the data importance is at a medium level, and when the data importance index is greater than , it indicates that the data importance is high.

9. The photovoltaic power plant 5G network security protection device according to claim 8, characterized in that, In the protection mechanism triggering module, the network access policy adjusting unit adjusts the encryption algorithm in the formula dynamically adjusts the encryption strength, wherein, is the adjusted encryption strength, is the basic encryption strength, is the network security risk probability value, is the encryption strength adjustment coefficient, is the reference risk probability value.

Images