FDIA detection method, device and terminal for unified control of AC / DC interconnection

Abstract

The present invention provides a FDIA detection method, device and terminal for AC / DC interconnected unified control, wherein the method comprises: constructing a training set; the training set comprises historical data of DC voltage deviation and historical data of AC frequency deviation when an AC / DC microgrid is in steady-state operation; training an initial logistic regression classifier model based on the training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of DC voltage deviation and AC frequency deviation; inputting the real-time data of DC voltage deviation and AC frequency deviation of the AC / DC microgrid into the target logistic regression classifier model to obtain the FDIA detection result of the AC / DC microgrid. The present invention can solve the problem of lack of detection of false data injection attacks in the interconnected unified control of AC / DC microgrids.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an FDIA detection method, device and terminal for unified control of AC and DC interconnection. Background Art

[0002] The AC / DC hybrid microgrid based on distributed control is a typical cyber-physical system (CPS). The interconnection device is a physical interface connecting the AC microgrid and the DC microgrid. When it operates in the flow control mode, it can accept the power control instructions of the upper-layer equipment to achieve the overall economic operation of the AC / DC hybrid microgrid, and at the same time reduce the transient impact caused by load changes. False Data Injection Attacks (FDIA) is a network attack that poses a great threat to the interconnected unified control of AC / DC microgrids. It can cause the unified control of the interconnected devices to deviate from the rated operating point, and even directly cause a power outage in a subnet. Therefore, the detection strategy of false data in the interconnected unified control of AC / DC microgrids is of great significance.

[0003] Currently, there are the following detection methods for false data injection attacks:

[0004] In the field of FDIA detection algorithms for pure DC microgrids and AC microgrids, some scholars mainly consider the dynamic characteristics of local equipment and design a flexible control algorithm for FDIA with constant injection volume. However, this algorithm can only defend against constant value attacks, and false data also causes certain transient fluctuations in the microgrid system. In addition, some scholars have established an electromagnetic transient model of the microgrid and compared the actual operating data with the electromagnetic transient model to detect false data. However, this algorithm is more dependent on the establishment of the microgrid model. However, information such as line impedance and network topology in practice is often difficult to obtain, resulting in poor accuracy of the model.

[0005] There are still few studies in the field of false data detection in unified control of interconnected AC / DC microgrids. Some scholars have adopted a fully distributed control method to achieve balanced operation of multiple interconnected devices. This method studies the FDIA detection and defense problems of control signals and measurement information, adds elastic control items on the basis of distributed control, and analyzes its stability through Lyapunov functional. However, the above method is essentially still the FDIA problem of pure AC or pure DC microgrids, and has not discussed and analyzed the FDIA situation of more complex and more common AC / DC hybrid microgrids. In addition, the addition of interconnected devices will change the operating characteristics of the sub-microgrids.

[0006] Therefore, there is an urgent need for a detection method for false data injection attacks in the interconnected unified control of AC / DC microgrids. Summary of the invention

[0007] The embodiments of the present invention provide a FDIA detection method, device, and terminal for AC / DC interconnected unified control to solve the problem of lack of detection of false data injection attacks in AC / DC microgrid interconnected unified control.

[0008] In a first aspect, an embodiment of the present invention provides a FDIA detection method for unified control of AC / DC interconnection, comprising:

[0009] Constructing a training set; the training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA;

[0010] The initial logistic regression classifier model is trained based on the training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of a DC voltage deviation and an AC frequency deviation;

[0011] The real-time data of DC voltage deviation and AC frequency deviation of the AC / DC microgrid are input into the target logistic regression classifier model to obtain the FDIA detection results of the AC / DC microgrid.

[0012] In a possible implementation, the binary linear function includes:

[0013] x=θ0+θ1ΔV * +θ2Δf * ;

[0014] Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

[0015] In one possible implementation, the logistic regression prediction function includes:

[0016]

[0017] In one possible implementation, the loss function of the initial logistic regression classifier model includes:

[0018]

[0019] Among them, y iis the detection result value corresponding to the i-th DC voltage deviation and AC frequency deviation.

[0020] In a possible implementation, the initial logistic regression classifier model is trained based on the training set to obtain a target logistic regression classifier model including:

[0021] Iteratively train the parameters to be trained of the initial logistic regression classifier model according to the gradient descent method, the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, and the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is subjected to false data injection attack FDIA;

[0022] When the training stop condition is met, the trained model is determined as the target logistic regression classifier model.

[0023] In a second aspect, an embodiment of the present invention provides an FDIA detection device for unified control of AC / DC interconnection, including:

[0024] A construction module is used to construct a training set; the training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA;

[0025] A model training module is used to train an initial logistic regression classifier model based on a training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of a DC voltage deviation and an AC frequency deviation;

[0026] The detection module is used to input the real-time data of DC voltage deviation and AC frequency deviation of the AC / DC microgrid into the target logistic regression classifier model to obtain the attack FDIA detection result of the AC / DC microgrid.

[0027] In a possible implementation, the binary linear function includes:

[0028] x=θ0+θ1ΔV * +θ2Δf * ;

[0029] Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

[0030] In a possible implementation, it is characterized in that the logistic regression prediction function includes:

[0031]

[0032] In a possible implementation, it is characterized in that the loss function of the initial logistic regression classifier model includes:

[0033]

[0034] Among them, y i is the detection result value corresponding to the i-th DC voltage deviation and AC frequency deviation.

[0035] In a possible implementation, the model training module is specifically used to:

[0036] Iteratively train the parameters to be trained of the initial logistic regression classifier model according to the gradient descent method, the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, and the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is subjected to false data injection attack FDIA;

[0037] When the training stop condition is met, the trained model is determined as the target logistic regression classifier model.

[0038] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0039] The embodiment of the present invention provides a terminal of an FDIA detection method and device for unified control of AC / DC interconnection. Compared with the prior art, the embodiment of the present invention has the following beneficial effects:

[0040] 1) Different from the previous FDIA detection method in pure AC or pure DC microgrids, the embodiment of the present invention comprehensively considers the operating characteristics of AC and DC microgrids, takes advantage of the fact that local measurement data of DC voltage and AC frequency are difficult to be tampered with, and selects historical data of DC voltage deviation and AC frequency deviation to construct a training set. The embodiment of the present invention uses historical data of DC voltage deviation and AC frequency for training, does not rely on the establishment of an accurate model of the microgrid, and realizes FDIA detection for unified control of AC and DC interconnection.

[0041] 2) Compared with the existing linear regression method, the embodiment of the present invention trains the initial logistic regression classifier model through a binary linear function composed of DC voltage deviation and AC frequency deviation. It only needs to solve the three parameter values ​​in the binary linear function to complete the detection process, which greatly reduces the complexity of the algorithm and memory usage.

[0042] 3) The FDIA detection algorithm provided by the embodiment of the present invention reacts quickly, minimizing the impact of FDIA on the AC / DC interconnected unified control device, and sending FDIA warning signals at the same time, which helps operation and maintenance personnel to find abnormalities and fill network loopholes in time. In addition, the embodiment of the present invention can distinguish between normal load disturbances in the AC / DC microgrid and FDIA of interconnected unified control on the basis of the normal operation of the original microgrid, and the FDIA detection method does not affect the normal operation of the original microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 is a flowchart of the steps of the FDIA detection method for unified control of AC / DC interconnection provided by an embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of the FDIA process in which the DC voltage and AC frequency of the AC / DC microgrid are attacked by false data injection provided by an embodiment of the present invention;

[0046] Figure 3 This is a practical effect diagram of abnormality detection of the FDIA detection method for unified control of AC / DC interconnection provided by an embodiment of the present invention;

[0047] Figure 4 It is an actual effect diagram of the defense strategy of the FDIA detection method for unified control of AC / DC interconnection provided by an embodiment of the present invention;

[0048] Figure 5 is a schematic diagram of a DC voltage and AC frequency curve when a false data injection attack FDIA is performed at the 15th second according to an embodiment of the present invention;

[0049] Figure 6 A schematic diagram of an FDIA detection device for unified control of AC / DC interconnection provided by an embodiment of the present invention;

[0050] Figure 7 A schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0053] like Figure 1 As shown, an FDIA detection method for unified control of AC / DC interconnection provided by an embodiment of the present invention may include the following steps:

[0054] Step S110, constructing a training set; the training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA.

[0055] In some embodiments, historical data in the AC / DC microgrid may be selected in a preset selection manner to construct a training set.

[0056] Specifically, during the selection process, when a load disturbance occurs, an energy shortage occurs in the AC / DC microgrid. The global power sharing feature will make the AC subgrid and the DC subgrid share the load disturbance. FDIA will also cause transient disturbances in the AC / DC microgrid, but at this time there is no power shortage in the AC / DC microgrid, only energy transfer between the AC / DC subgrids. The essential differences between the above two situations lead to inconsistent transient states of the AC / DC microgrid. Therefore, the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, as well as the historical data of DC voltage deviation and AC frequency deviation during FDIA of the AC / DC microgrid are selected to construct the training set.

[0057] Step S120, training the initial logistic regression classifier model based on the training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of a DC voltage deviation and an AC frequency deviation.

[0058] In one possible implementation, the independent variable of the logistic regression prediction function can be:

[0059] x=θ0+θ1ΔV * +θ2Δf * ;

[0060] Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

[0061] In one possible implementation, the initial logistic regression classifier model can be:

[0062]

[0063] Specifically, h θ (x) function is an odd function, h θ (x) The function value threshold is (0, 1), h θ (x) The function graph is smooth and easy to differentiate. When x is greater than 0, h θ (x) approaches 1. On the contrary, when x is less than 0, h θ The value of (x) is close to 0. The initial logistic regression classifier model completes the classification of the two target situations, h θ The extreme value characteristics of (x) effectively restrict logical judgment and narrow the range of numerical judgment of binary classification problems. The initial logistic regression classifier model is artificially defined, with class 1 as normal results and class 0 as abnormal results.

[0064] In one possible implementation, the initial logistic regression classifier model can use the following loss function:

[0065]

[0066] Among them, the number of training set samples in the initial logistic regression classifier model is 2n, and the 2n samples include n historical data of DC voltage deviation and n historical data of AC frequency deviation. The n historical data of DC voltage deviation include the historical data of DC voltage deviation when the AC / DC microgrid is in steady-state operation and the historical data of DC voltage deviation when the AC / DC microgrid is subjected to FDIA. The n historical data of AC frequency deviation include the historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation and the historical data of AC frequency deviation when the AC / DC microgrid is subjected to FDIA. n>0, y0, y1...y n They are marked class 1 or class 0 observations, respectively. Class 1 is the normal result when the AC / DC microgrid is in steady-state operation, and class 0 is the abnormal result when the AC / DC microgrid is subjected to FDIA.

[0067] In a possible implementation, the following training method can be used to train the initial logistic regression classifier model: according to the gradient descent method, the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, and the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is subjected to false data injection attack FDIA, the parameters to be trained of the initial logistic regression classifier model are iteratively trained; when the training stop condition is met, the trained model is determined as the target logistic regression classifier model.

[0068] Specifically, the loss function J(θ0,θ1) is a continuous differentiable function, and the function graph trend is smooth and easy to differentiate. For solving the loss function J(θ0,θ1), there are relatively classic numerical solution methods, most of which use the gradient descent method.

[0069] Step S130: input the real-time data of the DC voltage deviation and the real-time data of the AC frequency deviation of the AC / DC microgrid into the target logistic regression classifier model to obtain the FDIA detection result of the AC / DC microgrid.

[0070] In a possible implementation, the initial logistic regression classifier model completes offline training to obtain θ0, θ1 and θ2, and obtains the target logistic regression classifier model. The real-time data of the DC voltage deviation and the real-time data of the AC / DC microgrid are input into h θ (x) function, the target logistic regression classifier model builds an abnormal data logistic regression model from h θ The network attack is judged in the output of the (x) function, and the FDIA detection results of the AC / DC microgrid are obtained to achieve rapid and real-time early warning.

[0071] In order to better understand the FDIA detection method for unified control of AC / DC interconnection provided in the above embodiment, an implementation method is provided below, which includes the following steps:

[0072] like Figure 2As shown in the figure, when the AC or DC load changes, the change characteristics of the DC voltage and AC frequency of the AC / DC microgrid are quite different from those of FDIA, and the effect of using the initial logistic regression classifier model for discrimination is more obvious. When the DC load increases suddenly, the AC subnet and the DC subnet effectively support the disturbance of the AC / DC microgrid at the same time, which is specifically manifested in that when the DC voltage drops, the AC frequency also decreases, and the data mapping relationship satisfies the one-to-one correspondence. At this time, the power growth direction of the interconnected device is from the AC subnet to the DC subnet. When the AC load increases suddenly, the AC subnet and the DC subnet also effectively support the disturbance of the AC / DC microgrid at the same time, which is specifically manifested in that when the AC frequency drops, the DC voltage also decreases. At this time, the power growth direction of the interconnected device is from the DC subnet to the AC subnet. When FDIA transmitted to the interconnected device occurs, there is no source-load mismatch in the AC / DC microgrid at this time. Forcibly injecting power into one of the subnets will inevitably lead to an imbalance in the overall output power, which is specifically manifested in that the DC voltage increases / decreases while the AC frequency decreases / increases.

[0073] 1) Select the historical data of DC voltage deviation and AC frequency deviation of each disturbance process, as well as the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, to construct a training set.

[0074] 2) The initial logistic regression classifier model is trained based on the training set, and the training results of the parameter values ​​θ0, θ1 and θ2 are 7.30, -4.08 and -4.64 respectively.

[0075] 3) The real-time data of DC voltage deviation and AC frequency deviation of the AC / DC microgrid are input into the target logistic regression classifier model to obtain the FDIA detection results of the AC / DC microgrid.

[0076] like Figure 3 , Figure 4 As shown in the figure, the defense strategy of the FDIA detection method for unified control of AC / DC interconnection can be mainly divided into three different operation stages:

[0077] 3-1) 6~10s: DC load disturbance stage.

[0078] At the 6th second, the DC load is put into the DC system. At the initial stage of the disturbance, the DC droop unit quickly supports the DC load. Then the interconnected unified control realizes the power support of the AC subnet to the DC subnet. The AC frequency and DC voltage return to the rated value after a short drop. At this time, the AC / DC microgrid is in a normal load disturbance process, the initial logistic regression classifier model outputs the normal class 0, and the classification result of the FDIA detection algorithm is normal.

[0079] 3-2) 10.1~14s: AC load disturbance stage.

[0080] At 10.1s, the AC load was put into the DC system. At the initial stage of the disturbance, the AC droop unit quickly supported the AC load. Then the interconnected unified control realized the power support of the DC subnet to the AC subnet. The AC frequency and DC voltage returned to the rated value after a short drop. At this time, the AC / DC microgrid also belongs to the normal load disturbance process, and the classification result of the FDIA detection algorithm is normal.

[0081] 3-3) 15~16s: False data injection attack phase.

[0082] At the 15th second, false data with a value of 0.3pu is injected into the communication link. After a short dead time, the FDIA detection algorithm detects that the AC / DC interconnected unified control device is in an abnormal working state. Therefore, the initial logistic regression classifier model outputs the abnormal classification result of class 1 and issues an FDIA early warning signal at the same time. The last correct active power instruction is sent to the AC / DC interconnected unified control device, and the AC / DC microgrid returns to normal operation.

[0083] like Figure 5 As shown in Figure 1, at 15 seconds, the AC / DC microgrid interconnection unified control is controlled by FDIA, and after a short detection delay, the AC / DC microgrid returns to the rated operating state.

[0084] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0085] 1) Different from the previous FDIA detection method in pure AC or pure DC microgrids, the embodiment of the present invention comprehensively considers the operating characteristics of AC and DC microgrids, takes advantage of the fact that local measurement data of DC voltage and AC frequency are difficult to be tampered with, and selects historical data of DC voltage deviation and AC frequency deviation to construct a training set. The embodiment of the present invention uses historical data of DC voltage deviation and AC frequency for training, does not rely on the establishment of an accurate model of the microgrid, and realizes FDIA detection for unified control of AC and DC interconnection.

[0086] 2) Compared with the existing linear regression method, the embodiment of the present invention trains the initial logistic regression classifier model through a binary linear function composed of DC voltage deviation and AC frequency deviation. It only needs to solve the three parameter values ​​in the binary linear function to complete the detection process, which greatly reduces the complexity of the algorithm and memory usage.

[0087] 3) The FDIA detection algorithm provided by the embodiment of the present invention reacts quickly, minimizing the impact of FDIA on the AC / DC interconnected unified control device, and sending FDIA warning signals at the same time, which helps operation and maintenance personnel to find abnormalities and fill network loopholes in time. In addition, the embodiment of the present invention can distinguish between normal load disturbances in the AC / DC microgrid and FDIA of interconnected unified control on the basis of the normal operation of the original microgrid, and the FDIA detection method does not affect the normal operation of the original microgrid.

[0088] Based on the FDIA detection method for unified control of AC / DC interconnection provided in the above embodiment, the present invention also provides a specific implementation of an FDIA detection device for unified control of AC / DC interconnection applied to the FDIA detection method for unified control of AC / DC interconnection. Please refer to the following embodiments.

[0089] like Figure 6 As shown, a FDIA detection device for AC / DC interconnection unified control is provided, the device comprising:

[0090] A construction module 610 is used to construct a training set; the training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA;

[0091] A model training module 620 is used to train an initial logistic regression classifier model based on a training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of a DC voltage deviation and an AC frequency deviation;

[0092] The detection module 630 is used to input the real-time data of the DC voltage deviation and the real-time data of the AC frequency deviation of the AC / DC microgrid into the target logistic regression classifier model to obtain the FDIA detection result of the AC / DC microgrid.

[0093] In a possible implementation, the binary linear function includes:

[0094] x=θ0+θ1ΔV * +θ2Δf * ;

[0095] Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

[0096] In one possible implementation, the logistic regression prediction function includes:

[0097]

[0098] In one possible implementation, the loss function of the initial logistic regression classifier model includes:

[0099]

[0100] Among them, y i is the detection result value corresponding to the i-th DC voltage deviation and AC frequency deviation.

[0101] In a possible implementation, the model training module is specifically used to:

[0102] Iteratively train the parameters to be trained of the initial logistic regression classifier model according to the gradient descent method, the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is in steady-state operation, and the historical data of DC voltage deviation and AC frequency deviation when the AC / DC microgrid is subjected to false data injection attack FDIA;

[0103] When the training stop condition is met, the trained model is determined as the target logistic regression classifier model.

[0104] Figure 7 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 7 As shown, the terminal 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, the steps in the above-mentioned FDIA detection method embodiments for unified control of AC / DC interconnection are implemented. Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0105] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 72 in the terminal 7. For example, the computer program 72 may be divided into Figure 6 Modules / units 610 to 630 are shown.

[0106] The terminal 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of terminal 7 and does not constitute a limitation on terminal 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0107] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] The memory 71 may be an internal storage unit of the terminal 7, such as a hard disk or memory of the terminal 7. The memory 71 may also be an external storage device of the terminal 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 7. Further, the memory 71 may also include both an internal storage unit of the terminal 7 and an external storage device. The memory 71 is used to store the computer program and other programs and data required by the terminal. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0109] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0110] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0112] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0115] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0116] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A FDIA detection method for unified control of AC / DC interconnection, characterized in that: include: Construct a training set; The training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA; The initial logistic regression classifier model is trained based on the training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of a DC voltage deviation and an AC frequency deviation; The real-time data of the DC voltage deviation and the real-time data of the AC frequency deviation of the AC / DC microgrid are input into a target logistic regression classifier model to obtain a FDIA detection result of the AC / DC microgrid.

2. The FDIA detection method for unified control of AC / DC interconnection according to claim 1, characterized in that: The binary linear function comprises: x=θ0+θ1ΔV * +θ2Δf * ; Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

3. The FDIA detection method for unified control of AC / DC interconnection according to claim 2, characterized in that: The logistic regression prediction function includes:

4. The FDIA detection method for unified control of AC / DC interconnection according to claim 3, characterized in that: The loss function of the initial logistic regression classifier model includes: Among them, y i is the detection result value corresponding to the i-th DC voltage deviation and the AC frequency deviation.

5. The FDIA detection method for unified control of AC / DC interconnection according to claim 4, characterized in that: The step of training the initial logistic regression classifier model based on the training set to obtain a target logistic regression classifier model includes: Iteratively train the parameters to be trained of the initial logistic regression classifier model according to the gradient descent method, the historical data of the DC voltage deviation and the historical data of the AC frequency deviation when the AC / DC microgrid is in steady-state operation, and the historical data of the DC voltage deviation and the historical data of the AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA; When the training stop condition is met, the trained model is determined as the target logistic regression classifier model.

6. An FDIA detection device for unified control of AC and DC interconnection, characterized in that: include: A construction module is used to construct a training set; the training set includes historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is in steady-state operation, and historical data of DC voltage deviation and historical data of AC frequency deviation when the AC / DC microgrid is subjected to a false data injection attack FDIA; A model training module, used for training an initial logistic regression classifier model based on the training set to obtain a target logistic regression classifier model; the initial logistic regression classifier model is a logistic regression prediction function, and the independent variable of the logistic regression prediction function is a binary linear function composed of the DC voltage deviation and the AC frequency deviation; The detection module is used to input the real-time data of the DC voltage deviation and the real-time data of the AC frequency deviation of the AC / DC microgrid into the target logistic regression classifier model to obtain the FDIA detection result of the AC / DC microgrid.

7. The FDIA detection device for AC / DC interconnection unified control according to claim 6, characterized in that: The binary linear function comprises: x=θ0+θ1ΔV * +θ2Δf * ; Where, ΔV * is the DC voltage deviation, Δf * is the AC frequency deviation, θ0, θ1 and θ2 are the parameters to be trained of the initial logistic regression classifier model.

8. The FDIA detection device for AC / DC interconnection unified control according to claim 7, characterized in that: The logistic regression prediction function includes:

9. The FDIA detection device for AC / DC interconnection unified control according to claim 8, characterized in that: The loss function of the initial logistic regression classifier model includes: Among them, y i is the detection result value corresponding to the i-th DC voltage deviation and the AC frequency deviation.

10. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

Images