CN116418552A - Method and device for detecting false data invasion of power grid and computer equipment - Google Patents
Method and device for detecting false data invasion of power grid and computer equipment Download PDFInfo
- Publication number
- CN116418552A CN116418552A CN202211488249.2A CN202211488249A CN116418552A CN 116418552 A CN116418552 A CN 116418552A CN 202211488249 A CN202211488249 A CN 202211488249A CN 116418552 A CN116418552 A CN 116418552A
- Authority
- CN
- China
- Prior art keywords
- data
- power grid
- neural network
- false
- network model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000009545 invasion Effects 0.000 title abstract description 28
- 238000003062 neural network model Methods 0.000 claims abstract description 155
- 238000001514 detection method Methods 0.000 claims abstract description 133
- 238000005259 measurement Methods 0.000 claims abstract description 67
- 238000012549 training Methods 0.000 claims abstract description 56
- 238000004590 computer program Methods 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims description 47
- 238000000354 decomposition reaction Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 14
- 239000013598 vector Substances 0.000 description 13
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000002347 injection Methods 0.000 description 6
- 239000007924 injection Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a method, an apparatus, a computer device, a storage medium and a computer program product for detecting network false data intrusion. The method comprises the following steps: collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data; inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value; training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model; inputting data to be detected into the neural network model after training is completed, and obtaining output data; and acquiring measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range. By adopting the method, the detection accuracy of the false data invasion of the power grid can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for detecting a false data intrusion of a power grid.
Background
Along with the development of intelligent technology of the power grid, the complexity of the intelligent technology is gradually increased, and the intelligent technology is easy to invade false data. The intrusion mode of the false data can be changed at will according to the configuration of the power grid, and the network protection can be easily handled, so that serious consequences are caused.
However, the existing method is easy to be interfered by the operation data noise of the novel power system in the false data intrusion detection process, and the collected attack data is single in type, so that the detection accuracy of the false data intrusion of the power grid is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for detecting a network false data intrusion that can improve the accuracy of detecting a network false data intrusion.
In a first aspect, the present application provides a method for detecting a network false data intrusion. The method comprises the following steps:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
Training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
inputting data to be detected into the trained neural network model to obtain output data;
and acquiring measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
In one embodiment, the preprocessing the grid data to obtain preprocessed grid data includes:
determining the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data;
based on the decomposition layer number, screening the different types of power grid data according to a preset threshold range to obtain a screened data set;
and clearing fraudulent data in the screened data set to obtain preprocessed power grid data.
In one embodiment, before inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain the running state predicted value, the method further includes:
Establishing a state estimation model of the novel power system according to the measurement data of the novel power system;
performing state estimation calculation on the novel power system through the state estimation model to obtain state estimation calculation data;
and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as the preset power grid false data intrusion detection model.
In one embodiment, the trained neural network model is obtained by training the following method, including:
acquiring a data sample; the data samples comprise data samples containing false data intrusion and data samples not containing false data intrusion;
inputting the data sample into the preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample;
inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample;
and adjusting model parameters of the neural network model to be trained according to output data corresponding to the data samples to obtain the neural network model after training.
In one embodiment, the method further comprises:
acquiring feedback data of the trained neural network model;
updating the trained neural network model according to the feedback data to obtain an updated neural network model;
inputting the data to be detected into the trained neural network model to obtain output data, wherein the data to be detected comprises:
and inputting the data to be detected into the updated neural network model to obtain corresponding output data.
In one embodiment, the method further comprises:
identifying the data type of the false data under the condition that the false data is contained in the data to be detected;
and generating corresponding network false data intrusion early warning information according to the data type.
In a second aspect, the application also provides a detection device for network false data invasion. The device comprises:
the data processing module is used for acquiring power grid data of the novel power system, preprocessing the power grid data and obtaining preprocessed power grid data;
the data detection module is used for inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
The model training module is used for training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
the data output module is used for inputting the data to be detected into the neural network model after training is completed, so as to obtain output data;
and the result confirmation module is used for acquiring the measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
Inputting data to be detected into the trained neural network model to obtain output data;
and acquiring measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
inputting data to be detected into the trained neural network model to obtain output data;
and acquiring measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
inputting data to be detected into the trained neural network model to obtain output data;
and acquiring measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
The detection method, the detection device, the computer equipment, the storage medium and the computer program product for the false data invasion of the power grid are characterized in that the power grid data of a novel power system are collected and preprocessed to obtain preprocessed power grid data; inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value; then training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model; inputting the data to be detected into the neural network model after training is completed, and obtaining output data; and finally, acquiring measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range. Therefore, the power grid data is preprocessed in advance, so that the detection time consumption can be effectively reduced, the calculation difficulty in the detection process is reduced, and the false data injection detection deviation is reduced as much as possible; inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value, so that the operation state predicted value can be accurately calculated through state estimation; then training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model, so that the neural network model which is qualified in training is accurately obtained by repeatedly and continuously training a neural network algorithm; finally, inputting the data to be detected into the neural network model after training to obtain output data, comparing the output data with the measurement data, and confirming that the data to be detected contains false data under the condition that the difference between the output data and the measurement data exceeds a preset range; the detection method effectively avoids the interference of the noise of the operation data of the novel power system, comprehensively and accurately grasps the data type of the power grid attack, and thereby improves the detection accuracy of the false data invasion of the power grid.
Drawings
FIG. 1 is a flow chart of a method for detecting network false data intrusion in one embodiment;
FIG. 2 is a flow chart illustrating steps for preprocessing grid data in one embodiment;
FIG. 3 is a flow chart illustrating the steps of training a neural network model in one embodiment;
FIG. 4 is a schematic diagram of a neural network algorithm architecture in one embodiment;
FIG. 5 is a flow chart of a method for detecting network false data intrusion in another embodiment;
FIG. 6 is a flow chart of a method for detecting network false data intrusion in yet another embodiment;
FIG. 7 is a block diagram of a device for detecting network spurious data intrusion in one embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a method for detecting network false data intrusion is provided, where this embodiment is applied to a terminal to illustrate the method, and it is understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices; the internet of things equipment can be intelligent sound boxes, intelligent televisions, intelligent air conditioners, intelligent vehicle-mounted equipment and the like; the portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers. In this embodiment, the method includes the steps of:
Step 101, collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data.
The novel power system is a power system with the basic characteristics of cleanness, low carbon, safety, controllability, flexibility, high efficiency, intelligent friendliness and open interaction.
The power grid data refer to data generated by a novel power system in links of power generation, power transmission, power transformation and the like.
Specifically, the terminal receives a detection request for the intrusion of the false power grid data of the novel power system, acquires the power grid data of the novel power system according to the detection request, and performs wavelet threshold denoising processing on the acquired power grid data to obtain preprocessed power grid data.
The terminal receives a detection request for network false data invasion of the novel power system, and acquires the network data of the novel power system according to the detection request; determining the number of decomposition layers required by denoising the power grid data, selecting a threshold value, processing the decomposition coefficient of the original power data, setting a false data detection threshold value, judging whether a threshold function and a residual error of the threshold function are related, and obtaining the actual running state of the novel power system under the condition that the threshold function and the residual error of the threshold function are related, so as to complete data preprocessing and obtain the preprocessed power grid data.
Step S102, the preprocessed power grid data is input into a preset power grid false data intrusion detection model, and an operation state predicted value is obtained.
The network false data intrusion detection model is used for judging whether the network is invaded by false data.
The running state predicted value refers to a predicted value obtained by performing state estimation by a running state prediction model.
Specifically, the terminal acquires preprocessed power grid data, sets a power grid false data intrusion detection model as a target model, and inputs the preprocessed power grid data into the target model to obtain an operation state predicted value of the power grid data.
For example, the terminal acquires the power grid data after the wavelet threshold denoising process, sets the power grid false data intrusion detection model as a target model, and inputs the power grid data after the wavelet threshold denoising process into the target model to obtain the running state predicted value of the power grid data as 2.4.
And step S103, training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model.
The neural network model is a simplified model simulating the information processing mode of the human brain, and the working mode is to simulate a plurality of interconnected processing units similar to the abstract form of neurons, such as a convolutional neural network model, a deep neural network model and the like.
Specifically, the terminal acquires a neural network model to be trained, and trains the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value, so that model parameters of the neural network model are adjusted, and the trained neural network model is obtained.
By way of example, the terminal obtains a neural network model to be trained, obtains a plurality of running state predicted values through the network false data intrusion detection model, and repeatedly trains the obtained running state predicted values to the neural network model to be trained, so that the weight and bias of the neural network model are adjusted, and the neural network model qualified in training is obtained.
And step S104, inputting the data to be detected into the trained neural network model to obtain output data.
The data to be detected refers to the power grid data to be detected, and whether false data are contained or not is unknown.
Wherein, the output data refers to the output value of the state obtained by using the neural network model.
Specifically, the terminal acquires a detection request of false data invasion of the power grid, acquires data to be detected according to the detection request, sets a trained neural network model as a target model, inputs the data to be detected into the target model, and obtains output data through operation of the target model.
Step S105, obtaining measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
The measurement data of the novel power system refers to data acquired by a power management unit, and the data represent real data and data without virtual false values.
Specifically, the terminal acquires output data and measurement data of the novel power system, calculates a difference value between the output data and the measurement data of the novel power system, compares the calculated difference value with a preset range, and confirms that false data is contained in the data to be detected under the condition that the difference value exceeds the preset range.
The terminal obtains output data and measurement data of the novel power system, calculates a difference value between the output data and the measurement data of the novel power system to be 1.2, and the preset range is 0-1; obviously, if the difference value exceeds the preset range, the fact that false data is contained in the data to be detected is confirmed.
According to the detection method for the false data invasion of the power grid, the power grid data of the novel power system are collected, and the power grid data are preprocessed, so that preprocessed power grid data are obtained; inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value; then training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model; inputting the data to be detected into the neural network model after training is completed, and obtaining output data; and finally, acquiring measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range. Therefore, the power grid data is preprocessed in advance, so that the detection time consumption can be effectively reduced, the calculation difficulty in the detection process is reduced, and the false data injection detection deviation is reduced as much as possible; inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value, so that the operation state predicted value can be accurately calculated through state estimation; then training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model, so that the neural network model which is qualified in training is accurately obtained by repeatedly and continuously training a neural network algorithm; finally, inputting the data to be detected into the neural network model after training to obtain output data, comparing the output data with the measurement data, and confirming that the data to be detected contains false data under the condition that the difference between the output data and the measurement data exceeds a preset range; the detection method effectively avoids the interference of the noise of the operation data of the novel power system, comprehensively and accurately grasps the data type of the power grid attack, and thereby improves the detection accuracy of the false data invasion of the power grid.
In one embodiment, the step S102, before inputting the preprocessed power grid data into the preset power grid false data intrusion detection model to obtain the operation state predicted value, further includes: according to the measurement data of the novel power system, a state estimation model of the novel power system is established; performing state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as a preset power grid false data intrusion detection model.
The measurement data of the novel power system refer to data acquired by a power management unit, and the vector representation form is as follows: z= [ Z ] 1 ,Z 2 ,L,Z m ] T Where T represents the measurement period.
The state estimation model is used for carrying out state estimation calculation on the novel power system, and the state estimation model expression is as follows:
P＝[G(Y)] T +R T
wherein Y represents an energy data state vector of the novel power system, R represents a measurement error vector, and G represents a jacobian matrix of the novel power system.
It should be noted that, the state estimation of the novel power system needs to calculate the minimum power system state vector, and the calculation formula of the minimum state vector of the novel power system is obtained on the basis of the weighted least square method:
Wherein W represents a weight value;
the data residual H, i.e. the difference between the existing and estimated measurement vectors, is expressed as:
the accuracy of the measurement vector can be derived with the aid of the empirical threshold using the above equation.
Let new grid false attack data already know matrix G, and this matrix can control most vector P, then the attack vector expression of false data is:
D＝[D 1 ,D 2 ,L,D m ] T
wherein T represents a measurement period;
an attacker can continuously add an error measurement vector P into the power management unit which is already attacked to further obtain false data injection attack, and the running state prediction model of the novel power system is as follows:
P D ＝[G(Y)] T +D T
wherein T represents a measurement period;
the error state vector can be generated after the running state of the novel power system is predicted, and the expression is as follows:
wherein V represents the node voltage of the novel power system;
and then obtaining a real-time measurement error calculation formula as follows:
when the attack vector d=g (V), the deviation H at this time is D The operation state of the novel power system is already attacked by false information, and the novel power system is detected before the state occurs according to the prediction and the result, so that the false data intrusion detection precision can be enhanced.
Specifically, the terminal acquires measurement data of the novel power system, and a state estimation model of the novel power system is established by analyzing and processing the measurement data; then calculating the minimum power system state vector, and carrying out state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and (3) establishing a network false data intrusion detection model by analyzing and calculating the measurement data and the state estimation calculation data.
In the embodiment, state estimation calculation data are obtained by establishing a state estimation model of the novel power system and carrying out state estimation calculation on the novel power system; then, according to the measurement data and the state estimation calculation data, establishing a power grid false data intrusion detection model as the preset power grid false data intrusion detection model; therefore, related data are effectively utilized, a network false data intrusion detection model is accurately established, and the intrusion detection accuracy of the false data is enhanced.
In one embodiment, as shown in fig. 3, in step S103, the trained neural network model is trained by the following method, which specifically includes the following steps:
Step S301, acquiring a data sample; the data samples include data samples that contain false data intrusions and data samples that do not contain false data intrusions.
Step S302, inputting the data sample into a preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample.
Step S303, inputting the running state predicted value corresponding to the data sample into the neural network model to be trained, and obtaining output data corresponding to the data sample.
And step S304, according to the output data corresponding to the data sample, the model parameters of the neural network model to be trained are adjusted, and the neural network model after training is obtained.
Wherein a data sample refers to a data sample of grid data, whether it contains spurious data is known.
The calculation formula of the result in the output layer of the neural network model is as follows:
wherein K is j Representing the output value, w, of hidden layers in a neural network jc Representing weights between output layer and hidden layer, b c Representing the bias between the output layer and the hidden layer.
The model parameters of the neural network model refer to weights and offsets of the neural network model, and a calculation formula for updating the weights in real time is as follows:
Wherein w is ij Represents the weight, w, between the input layer i and the hidden layer j jc Representing weights, x, between input layer j and hidden layer c i Represents sample data, M is the number of test samples, c represents test samples, α represents network parameters, e c Represents the output value, K j The output value of the hidden layer in the neural network is represented by the following calculation formula:
wherein w is ij Representing the weight, x, between the input layer i and the hidden layer j i Represents sample data, f represents an activation function, a j Representing the bias of the input layer and the hidden layer;
the offset real-time update calculation formula is:
wherein a is j Representing the bias of the input layer from the hidden layer, b c Representing the offset between the output layer and the hidden layer, K j Representing the output value, w, of hidden layers in a neural network jc Represents the weight between the input layer j and the hidden layer c, M is the number of detection samples, c represents the detection samples, e c Represents the output value, alpha represents the network parameter, x i Representing sample data.
The neural network algorithm structure in the neural network model to be trained is shown in fig. 4.
Specifically, a terminal acquires a data sample of power grid data, sets a false data intrusion detection model of the power grid as a target model, and inputs the data sample into the target model for analysis and calculation to obtain a plurality of running state predicted values corresponding to the data sample; inputting the obtained running state predicted value into a neural network model to be trained, and calculating to obtain output data corresponding to the data sample; and repeatedly training the neural network algorithm by utilizing the output data, and adjusting the weight and the bias in the neural network model to finally obtain the neural network qualified in training.
In the embodiment, a data sample is acquired and is input into a preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample; then, inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample; then, according to output data corresponding to the data samples, model parameters of the neural network model to be trained are adjusted, and a neural network model after training is obtained; the neural network algorithm is repeatedly and continuously trained, the weight and the bias in the neural network model are adjusted according to the practical condition of training, and finally the neural network model qualified in training is accurately obtained.
In one embodiment, in step S103, the trained neural network model is further trained by the following method, which specifically includes the following steps: acquiring feedback data aiming at the neural network model after training; updating the trained neural network model according to the feedback data to obtain an updated neural network model; inputting data to be detected into the trained neural network model to obtain output data, wherein the method comprises the following steps of: and inputting the data to be detected into the updated neural network model to obtain corresponding output data.
The feedback data of the neural network model refers to historical output data obtained through processing of the neural network model.
Specifically, the terminal acquires and analyzes feedback data aiming at the neural network model after training, and screens out effective feedback data; updating model parameters of the trained neural network model according to the effective feedback data to obtain an updated neural network model; and inputting the data to be detected into the updated neural network model to obtain more accurate output data.
In the embodiment, feedback data of the neural network model which is completed by training is obtained; updating the trained neural network model according to the feedback data to obtain an updated neural network model; inputting the data to be detected into the updated neural network model to obtain corresponding output data; therefore, the neural network model can be updated and corrected in real time through the latest feedback data, and the neural network model can be obtained more accurately.
In one embodiment, as shown in fig. 2, in the step S101, the power grid data is preprocessed to obtain preprocessed power grid data, which specifically includes the following contents: determining the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data; based on the number of decomposition layers and a preset threshold range, carrying out data screening on different types of power grid data to obtain a screened data set; and deleting deceptive data in the screened data set to obtain preprocessed power grid data.
Wherein, the power grid data comprises three attributes of physical attribute, technical attribute and value attribute; the number of decomposition layers refers to layering according to time scales of milliseconds, minutes, 5 minutes, 15 minutes and the like; fraudulent data refers to data of lower reliability.
Wherein, the calculation formula of the decomposition layer number is:
n＝log 2 m-5
in the formula, n is the number of decomposition layers required by wavelet threshold denoising, and m represents the number of novel power grid data attributes.
In the detection process, comparing the power grid data reconstructed after denoising with the reduction degree of useful information in the original data, determining the suitability of the number of decomposition layers, measuring whether the number of decomposition layers is good or not according to the signal-to-noise ratio and the root mean square error of the power data, and determining that the number of decomposition layers is optimal if the power data meets the conditions of large signal-to-noise ratio and small root mean square error;
the signal-to-noise ratio calculation formula of the power data is as follows:
the root mean square error calculation formula of the power data is:
where x (N) represents the raw power data, x% (N) represents the denoised power data, and N represents the raw power data set.
Specifically, the terminal acquires the acquired power grid data of the novel power system, and determines the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data; then setting a threshold range, and processing the decomposition coefficient of the original power data; setting a false data detection threshold value, and judging whether a relation exists between a threshold function and residual errors of the threshold function; under the condition that a relation exists between the threshold function and the residual error, the actual running state of the novel power system is obtained, and finally, the data preprocessing is completed.
In this embodiment, by preprocessing the power grid data, the detection time consumption can be effectively reduced, the calculation difficulty in the detection process is reduced, and the false data injection detection deviation is reduced as much as possible.
In one embodiment, the method specifically further comprises the following steps: under the condition that the data to be detected contains false data, the data type of the false data is identified; and generating corresponding network false data intrusion early warning information according to the data type.
Wherein the data type refers to the data type that the grid may be attacked by spurious data.
The intrusion early warning information refers to early warning information generated corresponding to the type of data of the power grid possibly attacked by false data.
Specifically, the terminal judges whether the data to be detected contains false data or not through the trained neural network model, and analyzes and identifies the data type of the false data under the condition that the data to be detected contains the false data, and generates corresponding intrusion early warning information of the false data of the power grid according to the data type.
In this embodiment, the data type of the dummy data is identified by confirming that the data to be detected contains the dummy data; generating corresponding network false data intrusion early warning information according to the data type; therefore, the network false data intrusion early warning information aiming at a certain data type is accurately obtained, and the detection efficiency of network false data intrusion is improved.
In one embodiment, as shown in fig. 5, another method for detecting network false data intrusion is provided, which specifically includes the following steps:
step S501, collecting power grid data of a novel power system, and determining the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data; based on the number of decomposition layers and a preset threshold range, carrying out data screening on different types of power grid data to obtain a screened data set; and deleting deceptive data in the screened data set to obtain preprocessed power grid data.
Step S502, a state estimation model of the novel power system is established according to the measurement data of the novel power system; performing state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as a preset power grid false data intrusion detection model.
Step S503, obtaining a data sample; the data samples include data samples containing false data intrusions and data samples not containing false data intrusions; and inputting the data sample into the preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample.
Step S504, inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample; and adjusting model parameters of the neural network model to be trained according to the output data corresponding to the data samples to obtain the neural network model after training.
Step S505, obtaining feedback data for the trained neural network model; and updating the trained neural network model according to the feedback data to obtain an updated neural network model.
And step S506, inputting the data to be detected into the updated neural network model to obtain corresponding output data.
Step S507, obtaining measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
Step S508, under the condition that the false data is contained in the data to be detected, the data type of the false data is identified; and generating corresponding network false data intrusion early warning information according to the data type.
According to the detection method for the false data invasion of the power grid, the power grid data of the novel power system are collected and preprocessed in advance, so that the detection time consumption can be effectively reduced, the calculation difficulty in the detection process is reduced, and the false data injection detection deviation is reduced as much as possible; then, according to the measured data and the state estimation calculation data, a power grid false data intrusion detection model is established and used as a preset power grid false data intrusion detection model, so that the power grid false data intrusion detection model is accurately established according to related known data; then inputting the acquired data sample into the preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample, so that the operation state predicted value can be accurately calculated through state estimation; inputting the running state predicted value corresponding to the data sample into the neural network model to be trained to obtain output data corresponding to the data sample, and adjusting model parameters of the neural network model to be trained according to the output data corresponding to the data sample to obtain a trained neural network model, so that the neural network model is effectively trained through a neural network algorithm, and meanwhile, the model parameters in the neural network model are adjusted according to the actual condition of training to accurately obtain a qualified neural network model; then, acquiring feedback data aiming at the trained neural network model, and updating the trained neural network model according to the feedback data to obtain an updated neural network model, so that a more accurate neural network model is obtained by updating the neural network model; finally, inputting the data to be detected into the updated neural network model to obtain corresponding output data, acquiring measurement data of the novel power system, and confirming that false data are contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range; in addition, under the condition that the data to be detected contains the false data, the data type of the false data is identified, and corresponding network false data intrusion early warning information is generated according to the data type, so that relevant personnel can efficiently and accurately deal with the network false data intrusion condition.
In order to more clearly illustrate the method for detecting the false data intrusion of the power grid provided by the embodiment of the application, a specific embodiment is used for specifically describing the method for detecting the false data intrusion of the power grid. In one embodiment, as shown in fig. 6, the application further provides a method for detecting false data intrusion of the power grid, which specifically includes the following steps:
step S601, preprocessing grid data.
Step S602, determining the number of decomposition layers required for denoising the dummy data.
Step S603, processing the decomposition coefficients of the original power data in different scales by a threshold selection method.
Step S604, setting the threshold value of false data detection, obtaining the actual running state of the novel power system by comparing the relation between the threshold function and the corresponding residual error, and detecting the result as a diagnosis basis to reduce the detection range.
Step S605, acquiring and analyzing measurement data of a novel power system, and establishing a state estimation model of the novel power system; performing state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and constructing a false data intrusion detection model of the power grid according to the measurement data and the state estimation calculation data.
Step S606, inputting the samples with false data invasion and the samples without false data into a network false data invasion detection model to obtain the running state predicted values of the samples with false data invasion and the samples without false data invasion.
Step S607, inputting the operation state predicted value of the sample with false data invasion and the sample without false data invasion into the neural network model to obtain the output result.
And step 608, continuously updating model parameters of the neural network model according to the difference between the output result and the actual value to obtain the neural network model qualified in training.
Step S609, inputting the data to be detected into the trained neural network to obtain an output value.
In step S610, when the deviation between the output value and the actual threshold is large, it is indicated that there is a false data intrusion in the data to be detected.
According to the detection method for the false data invasion of the power grid, the acquired power grid data are preprocessed, so that the detection time consumption can be effectively reduced, the calculation difficulty in the detection process is reduced, and the false data injection detection deviation is reduced as much as possible; performing state estimation calculation on the novel power system through the state estimation model to obtain state estimation calculation data, and constructing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, so that the related data is effectively utilized, the power grid false data intrusion detection model is accurately built, and the intrusion detection precision of the false data is enhanced; inputting the samples with false data invasion and the samples without false data into a power grid false data invasion detection model to obtain the running state predicted values of the samples with false data invasion and the samples without false data invasion, so that the running state predicted values of the target samples can be accurately calculated through state estimation; inputting the running state predicted values of the samples with false data invasion and the samples without false data invasion into a neural network model to obtain an output result, continuously updating model parameters of the neural network model according to the difference between the output result and the actual value to obtain a neural network model qualified in training, so that the neural network model is effectively trained through a neural network algorithm, and simultaneously, the model parameters in the neural network model are regulated according to the actual condition of training to accurately obtain the neural network model qualified in training; the method has the advantages that the data to be detected is input into the trained neural network to obtain the output value, when the deviation between the output value and the actual threshold value is large, the false data invasion exists in the data to be detected, the interference of the operation data noise of the novel power system is effectively avoided, the data type of the power grid attack is comprehensively and accurately mastered, and therefore the detection accuracy of the false data invasion of the power grid is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a detection device for the network false data invasion, which is used for realizing the detection method for the network false data invasion. The implementation scheme of the device for solving the problem is similar to that described in the above method, so the specific limitation in the embodiment of the device for detecting the false data intrusion of the power grid provided below can be referred to the limitation of the method for detecting the false data intrusion of the power grid hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 7, there is provided a detection apparatus for network false data intrusion, including: a data processing module 701, a data detection module 702, a model training module 703, a data output module 704, and a result determination module 705, wherein:
the data processing module 701 is configured to collect power grid data of the novel power system, and perform preprocessing on the power grid data to obtain preprocessed power grid data.
The data detection module 702 is configured to input the preprocessed power grid data into a preset power grid false data intrusion detection model, so as to obtain an operation state prediction value.
The model training module 703 is configured to train the neural network model to be trained according to the network false data intrusion detection model and the running state prediction value, so as to obtain a trained neural network model.
And the data output module 704 is used for inputting the data to be detected into the trained neural network model to obtain output data.
The result determining module 705 is configured to obtain measurement data of the novel power system, and confirm that the data to be detected contains false data when a difference between the output data and the measurement data exceeds a preset range.
In one embodiment, the detection device for the false data intrusion of the power grid further comprises a model construction module, which is used for constructing a state estimation model of the novel power system according to the measurement data of the novel power system; performing state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as a preset power grid false data intrusion detection model.
In one embodiment, the model training module 703 is further configured to obtain a data sample; the data samples include data samples containing false data intrusions and data samples not containing false data intrusions; inputting the data sample into a preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample; inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample; and adjusting model parameters of the neural network model to be trained according to the output data corresponding to the data samples to obtain the neural network model after training.
In one embodiment, the model training module 703 is further configured to obtain feedback data for the trained neural network model; updating the trained neural network model according to the feedback data to obtain an updated neural network model; and inputting the data to be detected into the updated neural network model to obtain corresponding output data.
In one embodiment, the data processing module 701 is further configured to determine, according to the number of attributes of the grid data, a number of decomposition layers required for denoising the grid data; based on the number of decomposition layers and a preset threshold range, carrying out data screening on different types of power grid data to obtain a screened data set; and deleting deceptive data in the screened data set to obtain preprocessed power grid data.
In one embodiment, the detection device for the network false data intrusion further comprises an early warning information generation module, which is used for identifying the data type of the false data under the condition that the false data is contained in the data to be detected; and generating corresponding network false data intrusion early warning information according to the data type.
The modules in the detection device for the network false data intrusion can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method for detecting network false data intrusion. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
training the neural network model to be trained according to the network false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
inputting data to be detected into the neural network model after training is completed, and obtaining output data;
and acquiring measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range.
In one embodiment, the processor when executing the computer program further performs the steps of: according to the measurement data of the novel power system, a state estimation model of the novel power system is established; performing state estimation calculation on the novel power system through a state estimation model to obtain state estimation calculation data; and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as a preset power grid false data intrusion detection model.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring a data sample; the data samples include data samples containing false data intrusions and data samples not containing false data intrusions; inputting the data sample into a preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample; inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample; and adjusting model parameters of the neural network model to be trained according to the output data corresponding to the data samples to obtain the neural network model after training.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring feedback data aiming at the neural network model after training; updating the trained neural network model according to the feedback data to obtain an updated neural network model; inputting data to be detected into the neural network model after training to obtain output data, wherein the method comprises the following steps: and inputting the data to be detected into the updated neural network model to obtain corresponding output data.
In one embodiment, the processor when executing the computer program further performs the steps of: determining the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data; based on the number of decomposition layers and a preset threshold range, carrying out data screening on different types of power grid data to obtain a screened data set; and deleting deceptive data in the screened data set to obtain preprocessed power grid data.
In one embodiment, the processor when executing the computer program further performs the steps of: under the condition that the data to be detected contains false data, the data type of the false data is identified; and generating corresponding network false data intrusion early warning information according to the data type.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method for detecting network false data intrusion, the method comprising:
collecting power grid data of a novel power system, and preprocessing the power grid data to obtain preprocessed power grid data;
inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
Training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
inputting data to be detected into the trained neural network model to obtain output data;
and acquiring measurement data of the novel power system, and confirming that false data is contained in the data to be detected under the condition that the difference value between the output data and the measurement data exceeds a preset range.
2. The method of claim 1, further comprising, prior to inputting the preprocessed grid data into a predetermined grid dummy data intrusion detection model to obtain the operational state prediction value:
establishing a state estimation model of the novel power system according to the measurement data of the novel power system;
performing state estimation calculation on the novel power system through the state estimation model to obtain state estimation calculation data;
and establishing a power grid false data intrusion detection model according to the measurement data and the state estimation calculation data, and taking the power grid false data intrusion detection model as the preset power grid false data intrusion detection model.
3. The method of claim 1, wherein the trained neural network model is trained by:
acquiring a data sample; the data samples comprise data samples containing false data intrusion and data samples not containing false data intrusion;
inputting the data sample into the preset power grid false data intrusion detection model to obtain an operation state predicted value corresponding to the data sample;
inputting the running state predicted value corresponding to the data sample into a neural network model to be trained to obtain output data corresponding to the data sample;
and adjusting model parameters of the neural network model to be trained according to output data corresponding to the data samples to obtain the neural network model after training.
4. A method according to claim 3, characterized in that the method further comprises:
acquiring feedback data of the trained neural network model;
updating the trained neural network model according to the feedback data to obtain an updated neural network model;
inputting the data to be detected into the trained neural network model to obtain output data, wherein the data to be detected comprises:
And inputting the data to be detected into the updated neural network model to obtain corresponding output data.
5. The method of claim 1, wherein preprocessing the grid data to obtain preprocessed grid data comprises:
determining the number of decomposition layers required by denoising the power grid data according to the attribute quantity of the power grid data;
based on the number of decomposition layers and a preset threshold range, carrying out data screening on different types of power grid data to obtain a screened data set;
and deleting deceptive data in the screened data set to obtain preprocessed power grid data.
6. The method according to any one of claims 1 to 5, further comprising:
identifying the data type of the false data under the condition that the false data is contained in the data to be detected;
and generating corresponding network false data intrusion early warning information according to the data type.
7. A device for detecting network false data intrusion, the device comprising:
the data processing module is used for acquiring power grid data of the novel power system, preprocessing the power grid data and obtaining preprocessed power grid data;
The data detection module is used for inputting the preprocessed power grid data into a preset power grid false data intrusion detection model to obtain an operation state predicted value;
the model training module is used for training the neural network model to be trained according to the power grid false data intrusion detection model and the running state predicted value to obtain a trained neural network model;
the data output module is used for inputting the data to be detected into the neural network model after training is completed, so as to obtain output data;
and the result confirmation module is used for acquiring the measurement data of the novel power system, and confirming that the data to be detected contains false data under the condition that the difference value between the output data and the measurement data exceeds a preset range.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211488249.2A CN116418552A (en) | 2022-11-25 | 2022-11-25 | Method and device for detecting false data invasion of power grid and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211488249.2A CN116418552A (en) | 2022-11-25 | 2022-11-25 | Method and device for detecting false data invasion of power grid and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116418552A true CN116418552A (en) | 2023-07-11 |
Family
ID=87055375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211488249.2A Pending CN116418552A (en) | 2022-11-25 | 2022-11-25 | Method and device for detecting false data invasion of power grid and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116418552A (en) |
-
2022
- 2022-11-25 CN CN202211488249.2A patent/CN116418552A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Biloš et al. | Neural flows: Efficient alternative to neural ODEs | |
| Şalap-Ayça et al. | A meta-modeling approach for spatio-temporal uncertainty and sensitivity analysis: an application for a cellular automata-based urban growth and land-use change model | |
| CN110383298A (en) | Data efficient intensified learning for continuous control task | |
| Tao et al. | Deep learning optimizes data-driven representation of soil organic carbon in Earth system model over the conterminous United States | |
| CN113887845B (en) | Extreme event prediction method, device, equipment and storage medium | |
| CN115795282B (en) | Shock tube dynamic pressure reconstruction method and device, electronic equipment and storage medium | |
| CN113487019A (en) | Circuit fault diagnosis method and device, computer equipment and storage medium | |
| CN114021188A (en) | Method and device for interactive security verification of federated learning protocol and electronic equipment | |
| CN116010226A (en) | Software system reliability simulation evaluation method and device and computer equipment | |
| CN117033039A (en) | Fault detection method, device, computer equipment and storage medium | |
| Shrestha et al. | Deep generative model learning for blind spectrum cartography with NMF-based radio map disaggregation | |
| WO2016037346A1 (en) | Measuring and diagnosing noise in urban environment | |
| CN116738867B (en) | Unmanned aerial vehicle defense simulation method and system based on machine learning | |
| CN117289097A (en) | Power equipment partial discharge detection method, model training method, device and equipment | |
| CN116418552A (en) | Method and device for detecting false data invasion of power grid and computer equipment | |
| CN116306268A (en) | Shield tunneling simulation model parameter identification method system based on federal reinforcement learning | |
| CN115587614A (en) | Implicit full-waveform inversion method and device and electronic equipment | |
| Schmidt et al. | Modeling cloud reflectance fields using conditional generative adversarial networks | |
| Valderrama et al. | Integrating machine learning with pharmacokinetic models: Benefits of scientific machine learning in adding neural networks components to existing PK models | |
| JP2020177508A (en) | Prediction system, prediction method, and prediction program | |
| CN117670878B (en) | VOCs gas detection method based on multi-mode data fusion | |
| CN115577618B (en) | Construction method and prediction method of high-pressure converter valve hall environmental factor prediction model | |
| US20230107271A1 (en) | Modeling bounded rationality in multi-agent simulations using rationally inattentive reinforcement learning | |
| CN118093385A (en) | Training of code quality evaluation model, and code quality evaluation method and device | |
| CN116796280A (en) | Data processing method, apparatus, device, storage medium and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |