Power grid safety assessment method based on artificial intelligence

Abstract

The invention discloses a power grid safety assessment method based on artificial intelligence. The method comprises the following steps: firstly, acquiring a time sequence of power grid operation data and a time sequence of external environment information, and then performing time sequence correlation feature extraction on the time sequence of the power grid operation data and the time sequence of the external environment information to obtain a power grid operation parameter time sequence correlation feature graph and an external environment information time sequence correlation feature graph; then, internal and external semantic information interaction is carried out on the power grid operation parameter time sequence correlation feature map and the external environment information time sequence correlation feature map to obtain a power grid operation-external environment semantic interaction feature vector, and finally, a monitoring result is determined based on the power grid operation-external environment semantic interaction feature vector.

Description

Technical Field

[0001] The present disclosure relates to the field of power grid security assessment, and in particular to a power grid security assessment method based on artificial intelligence. Background Art

[0002] With the continuous development of society and the growth of electricity demand, the security and stability of power grid systems have become particularly important. Through power grid security assessment, potential problems and risks can be identified in a timely manner to ensure the continuous and stable operation of the power grid.

[0003] Traditional grid security assessment methods often rely on static models and are unable to capture the dynamic changes in grid operation and the impact of external environmental factors. Therefore, an optimized, artificial intelligence-based grid security assessment method is desired. Summary of the Invention

[0004] The present disclosure is made in view of the above problems. One object of the present disclosure is to provide a power grid security assessment method based on artificial intelligence.

[0005] The present invention provides an artificial intelligence-based power grid security assessment method, which includes:

[0006] Obtain the time series of power grid operation data and the time series of external environment information;

[0007] Extracting time series correlation features from the time series of the power grid operation data and the time series of the external environment information to obtain a power grid operation parameter time series correlation feature graph and an external environment information time series correlation feature graph;

[0008] Performing internal and external semantic information interaction on the power grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph to obtain a power grid operation-external environment semantic interaction feature vector; and

[0009] Based on the power grid operation-external environment semantic interaction feature vector, a monitoring result is determined.

[0010] According to the artificial intelligence-based power grid security assessment method of the embodiment of the present disclosure, it integrates power grid operation data and external environmental information, combines advanced deep learning technology to realize in-depth interactive analysis between power grid operation parameters and external environmental information, thereby comprehensively characterizing the power grid operation status and external environment, and using this to intelligently judge the power grid security level, so as to timely discover potential problems and risks and ensure the continuous and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0012] Figure 1 A schematic diagram of the application architecture of the power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown;

[0013] Figure 2 A flowchart of a power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown;

[0014] Figure 3 A flowchart of sub-step S520 of the power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown;

[0015] Figure 4 A flowchart of sub-step S530 of the power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown;

[0016] Figure 5 A flowchart of sub-step S540 of the power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown;

[0017] Figure 6 A schematic diagram of the structure of an artificial intelligence-based power grid security assessment system in an embodiment of the present disclosure is shown;

[0018] Figure 7 An application scenario diagram of the power grid security assessment method based on artificial intelligence in an embodiment of the present disclosure is shown; and

[0019] Figure 8 A schematic diagram of a storage medium according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present disclosure, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts are also within the scope of protection of the present disclosure.

[0021] The terms used in this specification are those commonly used in the art in view of the functions of the present disclosure, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in such cases, their detailed meanings will be described in the detailed description of the present disclosure. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present disclosure.

[0022] Although the present disclosure makes various references to certain modules in the system according to embodiments of the present disclosure, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0023] Flowcharts are used throughout this disclosure to illustrate the operations performed by systems according to embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps may be processed in reverse order or simultaneously, as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0024] Figure 1 A schematic diagram of the application architecture of the artificial intelligence-based power grid security assessment method in an embodiment of the present disclosure is shown, including a server 100 and a terminal device 200.

[0025] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technologies and / or protocols. The Internet is typically the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network. In some embodiments, technologies and / or formats including Hypertext Markup Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPsec) can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0026] The server 100 can provide various network services to the terminal device 200. The server 100 can be a single server, a server cluster consisting of multiple servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140. The input device 130 may include a keyboard, a mouse, a touch screen, etc. The output device 140 may include a display device such as a liquid crystal display (LCD) or a cathode ray tube (CRT).

[0027] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides program instructions and data stored in the memory 120 to the processor 110. In the embodiment of the present disclosure, the memory 120 may be used to store the program of the artificial intelligence-based power grid security assessment method in the embodiment of the present disclosure.

[0028] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the artificial intelligence-based power grid security assessment methods in the embodiments of the present disclosure according to the obtained program instructions.

[0029] In addition, the application architecture diagram in the embodiment of the present disclosure is intended to more clearly illustrate the technical solution in the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Of course, for other application architectures and business applications, the technical solution provided by the embodiment of the present disclosure is also applicable to similar problems.

[0030] The following non-restrictive description of the artificial intelligence-based power grid security assessment method provided according to at least one embodiment of the present disclosure is provided through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present disclosure.

[0031] In response to the above technical problems, the technical concept of this application is to integrate power grid operation data and external environmental information, and combine it with advanced deep learning technology to realize in-depth interactive analysis between power grid operation parameters and external environmental information, so as to comprehensively characterize the power grid operation status and external environment, and use this to intelligently judge the power grid security level, so as to timely discover potential problems and risks and ensure the continuous and stable operation of the power grid.

[0032] Based on this, Figure 2 The flowchart of the power grid security assessment method based on artificial intelligence in the embodiment of the present disclosure is shown. For example, the power grid security assessment method based on artificial intelligence can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 2 As shown, the artificial intelligence-based power grid security assessment method according to the embodiment of the present disclosure includes the steps of: S510, obtaining the time series of power grid operation data and the time series of external environment information; S520, performing time series correlation feature extraction on the time series of the power grid operation data and the time series of the external environment information to obtain a power grid operation parameter time series correlation feature diagram and an external environment information time series correlation feature diagram; S530, performing internal and external semantic information interaction on the power grid operation parameter time series correlation feature diagram and the external environment information time series correlation feature diagram to obtain a power grid operation-external environment semantic interaction feature vector; and, S540, determining the monitoring results based on the power grid operation-external environment semantic interaction feature vector.

[0033] Specifically, in the technical solution of this application, first, a time series of grid operation data and a time series of external environmental information are acquired. The grid operation data includes real-time load, device status, grid frequency, grid voltage, grid current, and power factor, while the external environmental information includes temperature, humidity, wind speed, precipitation, electricity market price, and real-time power consumption. By collecting the time series of grid operation data and the time series of external environmental information, a comprehensive analysis of the grid system's operating status and changes in the external environment over different time periods can be performed, thereby understanding and analyzing the grid's operating status. Specifically, within the time series of grid operation data, real-time load data is a key indicator for understanding the grid's current load situation, helping to assess the grid's load situation and the balance of power supply and demand. Device status reflects the device's operating status in real time. Grid frequency, grid voltage, grid current, and power factor data are important indicators for assessing the grid system's operating status and performance. Monitoring these parameters can reveal problems and risks in grid operation. Within the time series of external environmental information, external environmental factors such as temperature, humidity, wind speed, and precipitation directly affect the operation of grid equipment and power transmission efficiency. Understanding this information helps determine whether the current grid's operating strategy is adapting to changes in the external environment. Electricity market prices are an important reference indicator for electricity trading, and real-time electricity consumption is a representation of electricity demand. This information will affect the adjustment of power grid operation strategies and also affect the safe and stable operation of the power grid.

[0034] Accordingly, in step S510, the grid operation data includes real-time load, equipment status, grid frequency, grid voltage, grid current and power factor, and the external environment information includes temperature, humidity, wind speed, precipitation, electricity market price and real-time electricity consumption.

[0035] Then, the time series of the power grid operation data and the time series of the external environment information are arranged according to the time dimension and parameter sample dimension, respectively, to form a power grid operation parameter time series correlation matrix and an external environment information time series correlation matrix. Arranging the data according to the time dimension and parameter sample dimension thus makes the data structure clearer and more standardized, facilitating subsequent processing and analysis. This integration method helps unify the data format and facilitates data management and processing. Furthermore, integrating the data into a matrix format facilitates subsequent feature extraction and model input. This data structure is more suitable for processing deep learning models, enabling better extraction of important features from the data, thereby improving the accuracy and efficiency of the model.

[0036] Then, the grid operation parameter time series correlation matrix is ​​passed through a grid operation parameter time series correlation feature extractor based on a first convolutional neural network model to obtain a grid operation parameter time series correlation feature map; and the external environment information time series correlation matrix is ​​passed through an external environment information time series correlation feature extractor based on a second convolutional neural network model to obtain an external environment information time series correlation feature map. Among them, the convolutional neural network (CNN) is a deep learning model that is mainly used to process data with a similar grid structure, such as images. CNN can effectively extract spatial features from data through components such as convolutional layers and pooling layers, and is suitable for pattern recognition and feature extraction tasks in many fields. In the technical solution of this application, it is expected to utilize the excellent feature extraction ability of convolutional neural networks when processing structured data such as images and two-dimensional matrices, and to mine the correlation between parameters and the implicit dynamic change pattern in the time dimension from the grid operation parameter time series correlation matrix and the external environment information time series correlation matrix, so as to understand the changing conditions of the grid operation state and the external environment.

[0037] Accordingly, in step S520, if Figure 3 As shown, the time series correlation features of the power grid operation data and the time series of the external environment information are extracted to obtain a power grid operation parameter time series correlation feature diagram and an external environment information time series correlation feature diagram, including: S521, arranging the time series of the power grid operation data and the time series of the external environment information into a power grid operation parameter time series correlation matrix and an external environment information time series correlation matrix according to the time dimension and the parameter sample dimension respectively; S522, passing the power grid operation parameter time series correlation matrix through a power grid operation parameter time series correlation feature extractor based on a first convolutional neural network model to obtain the power grid operation parameter time series correlation feature diagram; and, S523, passing the external environment information time series correlation matrix through an external environment information time series correlation feature extractor based on a second convolutional neural network model to obtain the external environment information time series correlation feature diagram.

[0038] Taking into account that although the power grid operation parameter time series correlation feature map and the external environment information time series correlation feature map are obtained through the processing of convolutional neural networks, since the time series of the power grid operation data and the time series of the external environment information as source domain data themselves contain a large amount of redundant information, these redundant information may be retained or even amplified during the feature extraction process. Therefore, in the technical solution of the present application, the power grid operation parameter time series correlation feature map and the external environment information time series correlation feature map are respectively passed through a feature screening network to screen and refine the feature distribution, retaining the most representative and important features, thereby obtaining a more compact and effective feature representation, namely, the power grid operation parameter time series distillation correlation feature vector and the external environment information time series distillation correlation feature vector.

[0039] In the actual application scenario of the present application, the operation status of the power grid is jointly affected by internal factors (such as power load, power generation, equipment status, etc.) and external factors (such as weather, temperature, humidity, etc.). If the power grid operation data and external environmental information can be comprehensively utilized, it can be more in line with the actual situation of the power grid operation. Based on this, in the technical solution of the present application, the internal-external factor semantic interaction module is further used to perform semantic interaction analysis on the time-series distillation associated feature vector of the power grid operation parameters and the time-series distillation associated feature vector of the external environmental information to obtain the power grid operation-external environment semantic interaction feature vector. In this way, the semantic information of the power grid operation parameters and the external environmental information can be effectively integrated and interacted through the internal-external factor semantic interaction module to capture the complex relationship and mutual influence between them. This helps to explore the deep information hidden behind the data and improve the understanding of the overall state of the power grid system.

[0040] Accordingly, in step S530, if Figure 4 As shown, internal and external semantic information interaction is performed on the grid operation parameter timing association feature graph and the external environment information timing association feature graph to obtain a grid operation-external environment semantic interaction feature vector, including: S531, feature distillation screening is performed on the grid operation parameter timing association feature graph and the external environment information timing association feature graph to obtain a grid operation parameter timing distillation association feature vector and an external environment information timing distillation association feature vector; and, S532, semantic interaction analysis is performed on the grid operation parameter timing distillation association feature vector and the external environment information timing distillation association feature vector using an internal-external factor semantic interaction module to obtain the grid operation-external environment semantic interaction feature vector.

[0041] In one example, in step S531, feature distillation screening is performed on the grid operation parameter timing correlation feature graph and the external environment information timing correlation feature graph to obtain a grid operation parameter timing distillation correlation feature vector and an external environment information timing distillation correlation feature vector, including: passing the grid operation parameter timing correlation feature graph and the external environment information timing correlation feature graph through a feature screening network respectively to obtain the grid operation parameter timing distillation correlation feature vector and the external environment information timing distillation correlation feature vector.

[0042] It is worth noting that the feature selection network reduces the dimensionality of the feature vector by reducing the number of features in the feature graph while retaining the most important information, which helps improve model efficiency and reduce computational costs. The feature selection network can remove noise and redundant information in the feature graph, thereby improving the signal-to-noise ratio of the features, which helps the model focus on relevant features related to the prediction task. The feature selection network can extract specific types of features, such as patterns within a specific frequency range or features associated with specific events, which helps the model learn complex relationships and improve prediction accuracy. The feature selection network helps identify the most important features that influence prediction results, providing interpretability of model decisions and allowing engineers to understand how the model makes predictions. By removing irrelevant features, the feature selection network improves the model's generalization ability. This helps the model perform well on unseen data and reduces the risk of overfitting. In summary, the feature selection network plays a crucial role in extracting time-series correlation features from power grid operating parameters and external environmental information, helping to improve model efficiency, accuracy, interpretability, and generalization.

[0043] Specifically, the grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph are respectively passed through a feature screening network to obtain the grid operation parameter time series distillation correlation feature vector and the external environment information time series distillation correlation feature vector, including: performing feature graph expansion on the grid operation parameter time series correlation feature graph to obtain a sequence of grid operation parameter time series correlation feature vectors; processing the sequence of grid operation parameter time series correlation feature vectors using the following feature screening formula to obtain the grid operation parameter time series distillation correlation feature vector; wherein the feature screening formula is:

[0044]

[0045]

[0046] Among them, v i is the ith power grid operation parameter time series correlation feature vector in the sequence of power grid operation parameter time series correlation feature vectors, v jis the jth grid operation parameter time series associated feature vector in the sequence of the grid operation parameter time series associated feature vectors, ||·||1 represents the 1-norm of the feature vector, M is the length of the sequence of the grid operation parameter time series associated feature vectors -1, V k is the representation of the sequence of the time series associated feature vectors of the power grid operation parameters, D i represents the characteristic difference coefficient, exp(·) represents the natural exponential function operation, N s represents the total number of feature difference coefficients, P k A time series distillation correlation feature vector for the power grid operation parameters is obtained.

[0047] In one example, in step S532, using the internal-external factor semantic interaction module, a semantic interaction analysis is performed on the time series distillation association feature vector of the power grid operation parameters and the time series distillation association feature vector of the external environment information to obtain the power grid operation-external environment semantic interaction feature vector, including: processing the time series distillation association feature vector of the power grid operation parameters and the time series distillation association feature vector of the external environment information using the following semantic interaction formula to obtain the power grid operation-external environment semantic interaction feature vector; wherein the semantic interaction formula is:

[0048]

[0049] in, is the time series distillation associated feature vector of the power grid operation parameters, is the temporal distillation associated feature vector of the external environment information, is the grid operation-external environment semantic interaction feature vector, represents the square of the L2 norm of the eigenvector, (·) T Indicates the transpose of the eigenvector, - indicates the element-wise subtraction and difference processing, and + indicates the element-wise addition and summation processing.

[0050] Then, the power grid operation-external environment semantic interaction feature vector is passed through a classifier-based power grid security monitor to obtain a monitoring result, which is a power grid security level label.

[0051] Accordingly, in step S540, Figure 5 As shown, based on the power grid operation-external environment semantic interaction feature vector, the monitoring result is determined, including: S541, performing feature distribution correction on the power grid operation-external environment semantic interaction feature vector to obtain a corrected power grid operation-external environment semantic interaction feature vector; and, S542, passing the corrected power grid operation-external environment semantic interaction feature vector through a classifier-based power grid security monitor to obtain the monitoring result, which is a power grid security level label.

[0052] In the technical solution described above, the grid operation parameter time-series distillation associated feature vector and the external environment information time-series distillation associated feature vector respectively express the local correlation features of the grid operation data and the external environment information in the time-series-sample cross-dimension after feature screening. However, considering the time-series distribution differences and inter-sample correlation differences of the source data of the grid operation data and the external environment information, the grid operation parameter time-series distillation associated feature vector and the external environment information time-series distillation associated feature vector will have significant feature distribution structure differences, so that when the internal-external factor semantic interaction module is used to perform semantic interaction analysis on the grid operation parameter time-series distillation associated feature vector and the external environment information time-series distillation associated feature vector, the grid operation-external environment semantic interaction feature vector obtained based on position-by-position correspondence semantic interaction has a poor semantic interaction fusion effect on the grid operation parameter time-series distillation associated feature vector and the external environment information time-series distillation associated feature vector.

[0053] Therefore, the applicant of the present application performs a fusion correction on the time series distillation associated feature vectors of the power grid operation parameters and the time series distillation associated feature vectors of the external environment information.

[0054] Accordingly, in one example, in step S541, feature distribution correction is performed on the power grid operation-external environment semantic interaction feature vector to obtain a corrected power grid operation-external environment semantic interaction feature vector, including: fusing and correcting the power grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector to obtain a corrected feature vector; and, fusing the corrected feature vector and the power grid operation-external environment semantic interaction feature vector to obtain the corrected power grid operation-external environment semantic interaction feature vector.

[0055] Specifically, fusing and correcting the grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector to obtain a corrected feature vector includes: fusing and correcting the grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector using the following fusion correction formula to obtain the corrected feature vector; wherein the fusion correction formula is:

[0056]

[0057] Among them, V1 is the time series distillation associated feature vector of the power grid operation parameters, V2 is the time series distillation associated feature vector of the external environment information, v 1i ∈V1,v 2i ∈V2,v 1iis the eigenvalue of the ith position in the time series distillation associated eigenvector of the power grid operation parameters, v 2i is the eigenvalue of the ith position in the temporal distillation associated feature vector of the external environment information, the eigenvectors V1 and V2 have the same length L, α and β are scale hyperparameters, and ε is the distance difference hyperparameter, represents vector multiplication, (·) T represents the transpose operation, v c i ′ is the eigenvalue of the i-th position in the corrected eigenvector.

[0058] Here, in view of the difficulty in reconstructing the interaction of the manifold network structure caused by the manifold distribution distance between the time series distillation associated feature vector V1 of the power grid operation parameter and the time series distillation associated feature vector V2 of the external environment information in the feature fusion scenario, the low-order mesoscale Hilbert space primitive structure is used to effectively approximate the network substructure in the complex manifold network structure to construct the low-order mesoscale submanifold interaction behavior based on distance representation, so as to understand the abnormal submanifold interaction in the network at the network interaction level and improve the feature fusion representation effect of the time series distillation associated feature vector V1 of the power grid operation parameter and the time series distillation associated feature vector V2 of the external environment information. In this way, the v c i By fusing the correction feature vector composed of ′ with the power grid operation-external environment semantic interaction feature vector, the semantic interaction fusion effect of the power grid operation-external environment semantic interaction feature vector on the power grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector can be improved, thereby improving the accuracy of the classification result obtained by the classifier of the power grid operation-external environment semantic interaction feature vector.

[0059] Furthermore, in step S542, the corrected power grid operation-external environment semantic interaction feature vector is passed through a classifier-based power grid security monitor to obtain the monitoring result, which is a power grid security level label, including: using the fully connected layer of the classifier-based power grid security monitor to fully connect encode the corrected power grid operation-external environment semantic interaction feature vector to obtain an encoded classification feature vector; and inputting the encoded classification feature vector into the Softmax classification function of the classifier-based power grid security monitor to obtain the monitoring result.

[0060] It should be understood that the role of a classifier is to use given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression and SVM are commonly used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-class classification. However, this is prone to errors and is inefficient. A commonly used multi-classification method is the Softmax classification function.

[0061] Based on the above embodiments, see Figure 6 , which is a schematic diagram of the structure of an artificial intelligence-based power grid security assessment system 800 according to an embodiment of the present disclosure. The artificial intelligence-based power grid security assessment system 800 includes: a data acquisition module 810 for acquiring a time series of power grid operation data and a time series of external environment information; a time series correlation feature extraction module 820 for performing time series correlation feature extraction on the time series of the power grid operation data and the time series of the external environment information to obtain a power grid operation parameter time series correlation feature graph and an external environment information time series correlation feature graph; an internal and external semantic information interaction module 830 for performing internal and external semantic information interaction on the time series correlation feature graph of the power grid operation parameters and the time series correlation feature graph of the external environment information to obtain a power grid operation-external environment semantic interaction feature vector; and a monitoring result analysis module 840 for determining a monitoring result based on the power grid operation-external environment semantic interaction feature vector.

[0062] Here, those skilled in the art will appreciate that the specific functions and operations of each module in the above-mentioned artificial intelligence-based power grid security assessment system 800 have been described in detail in the above reference. Figures 2 to 5 The description of the artificial intelligence-based power grid security assessment method has been introduced in detail, and therefore, its repeated description will be omitted.

[0063] Figure 7 FIG is an application scenario diagram of the power grid security assessment method based on artificial intelligence according to an embodiment of the present disclosure. Figure 7 As shown, in this application scenario, first, the time series of power grid operation data is obtained (for example, Figure 7 D1 as shown in the figure) and the time series of external environmental information (e.g., Figure 7 Then, the time series of the power grid operation data and the time series of the external environment information are input to a server (e.g., Figure 7In S) shown in , the server is capable of using the artificial intelligence-based power grid security assessment algorithm to process the time series of the power grid operation data and the time series of the external environment information to obtain a monitoring result, and the monitoring result is a power grid security level label.

[0064] Based on the above embodiments, the present disclosure also provides another exemplary embodiment of an electronic device. In some possible implementations, the electronic device in the present disclosure may include a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the artificial intelligence-based power grid security assessment method in the above embodiments may be implemented.

[0065] For example, the electronic device is disclosed Figure 1 Taking the server 100 in the example for explanation, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0066] An embodiment of the present disclosure also provides a computer-readable storage medium. Figure 8 1 shows a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present disclosure. Figure 8 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by a processor, the artificial intelligence-based power grid security assessment method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, a flash memory, etc.

[0067] Embodiments of the present disclosure also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the artificial intelligence-based power grid security assessment method according to an embodiment of the present disclosure.

[0068] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented through hardware, software, firmware, or a combination of some or all of the three.

[0069] In addition, although the present disclosure makes various references to certain units in the system according to embodiments of the present disclosure, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the systems and methods can use different units.

[0070] Those skilled in the art will appreciate that all or part of the steps in the above method can be performed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk, or an optical disk. Alternatively, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software functional modules. The present disclosure is not limited to any particular combination of hardware and software.

[0071] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0072] The above is an illustration of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined by the claims. It should be understood that the above is an illustration of the present disclosure and should not be considered as limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

Claims

1. A power grid security assessment method based on artificial intelligence, characterized in that: include: Obtain the time series of power grid operation data and the time series of external environment information; Extracting time series correlation features from the time series of the power grid operation data and the time series of the external environment information to obtain a power grid operation parameter time series correlation feature graph and an external environment information time series correlation feature graph; Performing internal and external semantic information interaction on the power grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph to obtain a power grid operation-external environment semantic interaction feature vector; as well as Based on the power grid operation-external environment semantic interaction feature vector, a monitoring result is determined.

2. The power grid security assessment method based on artificial intelligence according to claim 1 is characterized in that: The grid operation data includes real-time load, equipment status, grid frequency, grid voltage, grid current and power factor, and the external environment information includes temperature, humidity, wind speed, precipitation, electricity market price and real-time electricity consumption.

3. The artificial intelligence-based power grid security assessment method according to claim 2, characterized in that: Extracting time series correlation features from the time series of the power grid operation data and the time series of the external environment information to obtain a power grid operation parameter time series correlation feature graph and an external environment information time series correlation feature graph includes: Arranging the time series of the power grid operation data and the time series of the external environment information into a power grid operation parameter time series correlation matrix and an external environment information time series correlation matrix according to the time dimension and the parameter sample dimension respectively; Passing the power grid operation parameter time series correlation matrix through a power grid operation parameter time series correlation feature extractor based on a first convolutional neural network model to obtain the power grid operation parameter time series correlation feature graph; and The external environment information temporal association matrix is ​​passed through an external environment information temporal association feature extractor based on a second convolutional neural network model to obtain the external environment information temporal association feature graph.

4. The artificial intelligence-based power grid security assessment method according to claim 3, characterized in that: Performing internal and external semantic information interaction on the power grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph to obtain a power grid operation-external environment semantic interaction feature vector, including: Performing feature distillation screening on the grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph to obtain a grid operation parameter time series distillation correlation feature vector and an external environment information time series distillation correlation feature vector; and An internal-external factor semantic interaction module is used to perform semantic interaction analysis on the grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector to obtain the grid operation-external environment semantic interaction feature vector.

5. The artificial intelligence-based power grid security assessment method according to claim 4, characterized in that: Performing feature distillation screening on the grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph to obtain a grid operation parameter time series distillation correlation feature vector and an external environment information time series distillation correlation feature vector, including: The grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph are respectively passed through a feature screening network to obtain the grid operation parameter time series distillation correlation feature vector and the external environment information time series distillation correlation feature vector.

6. The artificial intelligence-based power grid security assessment method according to claim 5, characterized in that: The power grid operation parameter time series correlation feature graph and the external environment information time series correlation feature graph are respectively passed through a feature screening network to obtain the power grid operation parameter time series distillation correlation feature vector and the external environment information time series distillation correlation feature vector, including: Performing feature graph expansion on the grid operation parameter time series correlation feature graph to obtain a sequence of grid operation parameter time series correlation feature vectors; The sequence of the grid operation parameter time series correlation feature vectors is processed using the following feature screening formula to obtain the grid operation parameter time series distillation correlation feature vectors; wherein the feature screening formula is: Among them, v i is the ith power grid operation parameter time series correlation feature vector in the sequence of power grid operation parameter time series correlation feature vectors, v j is the jth grid operation parameter time series associated feature vector in the sequence of the grid operation parameter time series associated feature vectors, ‖·‖1 represents the 1-norm of the feature vector, M is the length of the sequence of the grid operation parameter time series associated feature vectors -1, V k is the representation of the sequence of the time series associated feature vectors of the power grid operation parameters, D i represents the characteristic difference coefficient, exp(·) represents the natural exponential function operation, N s represents the total number of feature difference coefficients, P k A time series distillation correlation feature vector for the power grid operation parameters is obtained.

7. The artificial intelligence-based power grid security assessment method according to claim 6, characterized in that: Using an internal-external factor semantic interaction module, a semantic interaction analysis is performed on the power grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector to obtain the power grid operation-external environment semantic interaction feature vector, including: The power grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector are processed using the following semantic interaction formula to obtain the power grid operation-external environment semantic interaction feature vector; wherein the semantic interaction formula is: in, is the time series distillation associated feature vector of the power grid operation parameters, is the temporal distillation associated feature vector of the external environment information, is the grid operation-external environment semantic interaction feature vector, represents the square of the L2 norm of the eigenvector, (·) T Indicates the transpose of the eigenvector, ― indicates the bitwise subtraction of the elements, and + indicates the bitwise addition of the elements.

8. The artificial intelligence-based power grid security assessment method according to claim 7, characterized in that: Determining monitoring results based on the power grid operation-external environment semantic interaction feature vector includes: performing feature distribution correction on the power grid operation-external environment semantic interaction feature vector to obtain a corrected power grid operation-external environment semantic interaction feature vector; and The corrected power grid operation-external environment semantic interaction feature vector is passed through a classifier-based power grid security monitor to obtain the monitoring result, which is a power grid security level label.

9. The artificial intelligence-based power grid security assessment method according to claim 8, characterized in that: Performing feature distribution correction on the power grid operation-external environment semantic interaction feature vector to obtain a corrected power grid operation-external environment semantic interaction feature vector, including: Performing fusion correction on the power grid operation parameter time series distillation associated feature vector and the external environment information time series distillation associated feature vector to obtain a corrected feature vector; and The corrected feature vector and the power grid operation-external environment semantic interaction feature vector are fused to obtain the corrected power grid operation-external environment semantic interaction feature vector.

10. The artificial intelligence-based power grid security assessment method according to claim 9, characterized in that: The corrected grid operation-external environment semantic interaction feature vector is passed through a classifier-based grid security monitor to obtain the monitoring result, which is a grid security level label, including: Performing full-connection encoding on the corrected power grid operation-external environment semantic interaction feature vector using the fully connected layer of the classifier-based power grid security monitor to obtain an encoded classification feature vector; and The encoded classification feature vector is input into the Softmax classification function of the classifier-based power grid security monitor to obtain the monitoring result.

Images