Power system operation safety early warning method and device based on improved timenet

Abstract

The invention discloses an improved timenet-based electric power system operation safety early warning method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring a characteristic signal sequence of a power system; the characteristic signal sequence comprises a voltage signal, a power angle signal and a phase signal; performing feature selection on the feature signal sequence through a Deep Lasso algorithm; filling a missing value in the feature signal sequence after feature selection; predicting the filled feature signal sequence through an improved Timesnet algorithm to obtain a future feature signal sequence; and classifying the future feature sequence through a deep random forest model integrated with xgboost to obtain a classification result, the classification result including a risk result and a risk-free result. According to the invention, more powerful comprehensive risk early warning performance of the operation safety of the power system can be realized.

Description

Technical Field

[0001] This application relates to the technical field of power system operation control, and particularly to a power system operation safety early warning method, device, storage medium and electronic device based on improved TimesNet. Background Art

[0002] In the context of the continuously rising global energy demand, the power system, as a key component of modern social infrastructure, its stability and reliability play a crucial role in promoting economic growth and maintaining the continuity of people's daily lives. The power grid, as the core component of the power system, the safety of its operation directly determines the sustainability and stability of power supply. However, during the operation of the power grid, it inevitably encounters various risk factors, which may cause power supply interruptions and even trigger large-scale power system failures with far-reaching impacts. Grid safety is not only related to the stability of power supply, but also involves public safety and social stability. Power grid failures may lead to service interruptions in multiple fields such as transportation, communication, medical care, and finance, having a serious impact on social and economic activities.

[0003] In the operation management of modern power systems, the stability and reliability of the power grid are key factors in ensuring social and economic activities and the continuity of people's daily lives. Given the increasing complexity of power systems and the widespread integration of renewable energy, the risk factors faced by the power grid have become increasingly diverse and dynamic. Traditional risk assessment methods, usually relying on limited data sets and empirical judgments, have become difficult to fully address the risk challenges in current power grid operations.

[0004] Most current power system risk assessments are achieved by monitoring current signals or voltage signals, making it difficult to perform prediction and risk prevention. Summary of the Invention

[0005] The embodiments of this application provide a power system operation safety early warning method, device, storage medium and electronic device based on improved TimesNet, which can predict risks and prevent them in a timely manner.

[0006] The embodiments of this application provide a power system operation safety early warning method based on improved TimesNet, including: Obtain the characteristic signal sequence of the power system; the characteristic signal sequence includes voltage signals, power angle signals and phase signals; Perform feature selection on the characteristic signal sequence through the Deep Lasso algorithm; Fill in the missing values in the characteristic signal sequence after feature selection; Predict the filled feature signal sequence through the improved Timesnet algorithm to obtain the future feature signal sequence; Classify the future feature sequence through a deep random forest model integrating xgboost to obtain a classification result, where the classification result includes at risk and risk-free.

[0007] Further, in the above power system operation safety warning method based on improved timesnet, where the feature selection of the feature signal sequence through the Deep Lasso algorithm includes: Normalize the data of the feature signal sequence; Input the normalized feature signal sequence into the trained Deep Lasso model for screening to obtain the feature signal sequence after feature selection; where, a Lasso penalty is imposed during the training process of the Deep Lasso model.

[0008] Further, in the above power system operation safety warning method based on improved timesnet, where the Lasso penalty is:

[0009] Where, is the loss function, is the model parameter, is the balance parameter, is the gradient of the feature, is the weighting parameter.

[0010] Further, in the above power system operation safety warning method based on improved timesnet, before the step of filling the missing values in the feature signal sequence, it includes: Analyze the data in the feature signal sequence to obtain the distribution characteristics of the data, the pattern of the missing data, and the correlation between the data.

[0011] Further, in the above power system operation safety warning method based on improved timesnet, where filling the missing values in the feature signal sequence includes: Determine the positions and quantities of the missing values in the feature signal sequence; Use linear interpolation for interpolation.

[0012] Further, in the above power system operation safety warning method based on improved timesnet, where predicting the filled feature signal sequence through the improved Timesnet algorithm to obtain the future feature signal sequence includes: Construct a topological structure matrix based on the topological structure of the power system; Convert the characteristic signal sequence into a two-dimensional matrix; Perform convolution and fusion on the two-dimensional matrix and the topological structure matrix to obtain a first fusion feature; Decouple the first fusion feature into a one-dimensional sequence, and perform prediction based on the one-dimensional sequence to obtain a future characteristic signal sequence.

[0013] Furthermore, in the above power system operation safety warning method based on the improved TimesNet, the integrated deep random forest model of XGBoost includes an XGBoost model and a deep random forest model. Classifying the future feature sequence through the integrated deep random forest model of XGBoost, the obtained classification results include: Input the future characteristic signal sequence into the XGBoost model for prediction to obtain a first prediction probability vector; Input the future characteristic signal sequence into the deep random forest model for prediction to obtain a second prediction probability vector; Perform weighted summation on the first prediction probability vector and the second prediction probability vector to obtain a fusion probability, and determine the classification result based on the maximum value of the fusion probability.

[0014] An embodiment of this application also provides a power system operation safety warning device based on the improved TimesNet, including: A signal acquisition module for acquiring the characteristic signal sequence of the power system; the characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; A feature selection module for performing feature selection on the characteristic signal sequence through the Deep Lasso algorithm; A missing value filling module for filling the missing values in the characteristic signal sequence after feature selection; A prediction module for predicting the filled characteristic signal sequence through an improved TimesNet algorithm to obtain a future characteristic signal sequence; A classification module for classifying the future feature sequence through an integrated deep random forest model of XGBoost to obtain a classification result, and the classification result includes at risk and risk-free.

[0015] An embodiment of this application also provides a computer-readable storage medium, in which multiple instructions are stored, and the instructions are suitable for being loaded by a processor to execute any one of the above power system operation safety warning methods based on the improved TimesNet.

[0016] An embodiment of the present application also provides an electronic device, including a processor and a memory. The processor is electrically connected to the memory. The memory is used to store instructions and data, and the processor is used for the steps in the power system operation safety warning method based on the improved TimesNet as described in any one of the above.

[0017] The power system operation safety warning method, device, storage medium and electronic device based on the improved TimesNet provided by the present application. The present application performs feature selection through an intelligent feature selection algorithm of machine learning; uses linear interpolation to preprocess features to fill in missing values, predicts the selected features through the improved TimesNet algorithm, and uses an integrated xgboost deep random forest model to classify the prediction results, and comprehensively performs risk warning technology on the future operation safety of the power system through the classification results. This method can achieve a more powerful comprehensive risk warning performance for the operation safety of the power system. Brief Description of the Drawings

[0018] The following will clearly show the technical solutions and other beneficial effects of the present application by describing the specific embodiments of the present application in detail with reference to the accompanying drawings.

[0019] Figure 1 It is a flowchart of the power system operation safety warning method based on the improved TimesNet provided by the embodiment of the present application.

[0020] Figure 2 It is a flowchart of filling in missing values provided by the embodiment of the present application.

[0021] Figure 3 It is a flowchart of classification provided by the embodiment of the present application.

[0022] Figure 4 It is a schematic structural diagram of the power system operation safety warning device based on the improved TimesNet provided by the embodiment of the present application.

[0023] Figure 5 It is a schematic structural diagram of the electronic device provided by the embodiment of the present application. Detailed Description of the Embodiments

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0025] The embodiments of the present application provide a power system operation safety warning method, device, storage medium and electronic device based on improved TimesNet. The power system operation safety warning device based on improved TimesNet provided by the embodiments of the present application can be integrated in an electronic device, and the electronic device can be a device such as a terminal, a server, etc. Among them, the terminal can include a tablet computer, a notebook computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0026] Please refer to Figure 1 , Figure 1 which is a flowchart of the power system operation safety warning method based on improved TimesNet provided by the embodiments of the present application. It is applied to an electronic device. The power system operation safety warning method based on improved TimesNet includes the following steps: S1. Obtain the characteristic signal sequence of the power system; the characteristic signal sequence includes voltage signals, power angle signals and phase signals.

[0027] Specifically, use a voltage transformer to collect part of the voltage signals of the power system, use an optical fiber current transformer to collect part of the current signals of the power system, and use a synchronous phasor measurement unit to collect the phase signals of the power system.

[0028] S2. Perform feature selection on the characteristic signal sequence through the Deep Lasso algorithm.

[0029] In one embodiment, step S2 includes the following steps: S21. Standardize the data of the characteristic signal sequence; S22. Input the standardized characteristic signal sequence into the trained Deep Lasso model for screening to obtain the characteristic signal sequence after feature selection; among them, Lasso penalty is imposed during the training process of the Deep Lasso model.

[0030] The Lasso penalty is:

[0031] Among them, is the loss function, is the model parameter, is the balance parameter, is the gradient of the feature, is the weighting parameter.

[0032] S3. Fill in the missing values in the characteristic signal sequence after feature selection.

[0033] Before the step of filling in the missing values in the characteristic signal sequence, it includes: analyzing the data in the characteristic signal sequence to obtain the distribution characteristics of the data, the pattern of missing data, and the correlation between the data.

[0034] In one embodiment, step S3 includes the following steps: S31, determining the positions and quantities of the missing values in the characteristic signal sequence; S32, performing interpolation using the linear interpolation method.

[0035] S4, predicting the filled characteristic signal sequence through an improved Timesnet algorithm to obtain the future characteristic signal sequence.

[0036] Figure 2 This is the flowchart for filling in the missing values provided by the embodiment of the present application. As Figure 2 shown, step S4 includes the following steps: S41, constructing a topological structure matrix based on the topological structure of the power system.

[0037] Among them, the topological structure matrix represents the connection structure of the power system. In the topological structure matrix, 1 represents connection and 0 represents non - connection.

[0038] S42, converting the characteristic signal sequence into a two - dimensional matrix.

[0039] Through Timesnet, the time - series data in the one - dimensional characteristic signal sequence is converted into a two - dimensional representation to enhance the model's analysis and prediction capabilities. This process usually starts with splitting the continuous time series into multiple small segments, and then extracting key features from each segment, such as statistics, frequency - domain features, or model - based features. Next, these features are re - organized into a two - dimensional matrix form for further processing. Timesnet uses an embedding layer to map the time steps into a high - dimensional space, ultimately achieving the conversion of feature data into two - dimensional data.

[0040] S43, performing convolution and then fusion on the two - dimensional matrix and the topological structure matrix to obtain the first fusion feature.

[0041] Performing convolution and then fusion on the two - dimensional matrix and the topological structure matrix to obtain the two - dimensional first fusion feature. The information on the changes in the front - and - back topological structures is fused into the two - dimensional data through convolution.

[0042] S44, decoupling the first fusion feature into a one - dimensional sequence, and performing prediction based on the one - dimensional sequence to obtain the future characteristic signal sequence.

[0043] Using the two - dimensional - to - one - dimensional conversion algorithm of Timesnet, the first fusion feature that has fused topological features is decoupled into a one - dimensional sequence.

[0044] Furthermore, Timesnet includes a fine-grained enhancement module that predicts the decoupled one-dimensional sequence through the fine-grained enhancement module, and finally obtains the predicted result.

[0045] S5. Classify the future feature sequence through the deep random forest model integrating xgboost to obtain the classification result, where the classification result includes risky and risk-free.

[0046] Figure 3 This is the flowchart of the classification provided by the embodiment of the present application. As Figure 3 shown, the deep random forest model integrating xgboost includes an xgboost model and a deep random forest model. Step S5 includes the following steps: S51. Input the future feature signal sequence into the xgboost model for prediction to obtain the first predicted probability vector.

[0047] Configure XGBoost hyperparameters, including the maximum tree depth D1, learning rate η, and L2 regularization coefficient λ. Input the future feature signal sequence into the xgboost model, train the classifier through the gradient boosting algorithm, and output the first predicted probability vector.

[0048] S52. Input the future feature signal sequence into the deep random forest model for prediction to obtain the second predicted probability vector.

[0049] First-layer random forest training: Input the future feature signal sequence into XGBoost, train N1 decision trees, with the maximum depth of each tree being D2, and output the class probability distribution.

[0050] Second-layer feature enhancement: Concatenate the class probability distribution output by the first layer with the original features to form an enhanced feature matrix; Train the second-layer random forest (N2 trees, maximum depth D3), and output the second predicted probability vector.

[0051] S53. Perform weighted summation on the first predicted probability vector and the second predicted probability vector to obtain the fusion probability, and determine the classification result based on the maximum value of the fusion probability.

[0052] The predicted class can be determined according to the maximum value of the fusion probability, or a threshold can be set for binary classification judgment.

[0053] According to the method described in the above embodiments, this embodiment will be further described from the perspective of a power system operation safety warning device based on improved TimesNet. This power system operation safety warning device based on improved TimesNet can be specifically implemented as an independent entity, or integrated in an electronic device, which can be a device such as a terminal, a server, etc. Among them, the terminal can include a tablet computer, a notebook computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0054] Please refer to Figure 4 , Figure 4 Specifically described is the power system operation safety warning device based on improved TimesNet provided by the embodiments of the present application, which is applied to an electronic device. This power system operation safety warning device based on improved TimesNet may include: A signal acquisition module, configured to acquire a characteristic signal sequence of the power system; the characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; A feature selection module, configured to perform feature selection on the characteristic signal sequence through the Deep Lasso algorithm; A missing value filling module, configured to fill the missing values in the characteristic signal sequence after feature selection; A prediction module, configured to predict the filled characteristic signal sequence through an improved TimesNet algorithm to obtain a future characteristic signal sequence; A classification module, configured to classify the future feature sequence through a deep random forest model integrating XGBoost to obtain a classification result, and the classification result includes at risk and risk-free.

[0055] In specific implementation, each of the above modules and / or units can be implemented as an independent entity, or can be combined arbitrarily to be implemented as the same or several entities. For the specific implementation of each of the above modules and / or units, reference can be made to the foregoing method embodiments. For the specific beneficial effects that can be achieved, reference can also be made to the beneficial effects in the foregoing method embodiments, which will not be elaborated herein.

[0056] In addition, the embodiments of the present application further provide an electronic device, which can be a device such as a computer or a tablet computer. This electronic device can implement the steps in any of the embodiments of the power system operation safety warning method based on improved TimesNet provided by the embodiments of the present application. Therefore, it can achieve the beneficial effects that can be achieved by any of the power system operation safety warning methods based on improved TimesNet provided by the embodiments of the present invention. For details, please refer to the foregoing embodiments, which will not be elaborated herein.

[0057] Figure 5 The specific structural block diagram of the electronic device provided by the embodiment of the present invention is shown. This electronic device can be used to implement the power system operation safety warning method based on the improved timesnet provided in the above embodiment. The electronic device 500 can be a terminal, a server, or other devices. Among them, the terminal can include a tablet computer, a notebook computer, a personal computer (PC), a microprocessing box, or other devices, etc.

[0058] The RF circuit 510 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. The RF circuit 510 can include various existing circuit elements for performing these functions. For example, antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, subscriber identity module (SIM) cards, memories, and so on. The RF circuit 510 can communicate with various networks such as the Internet, enterprise intranets, wireless networks, or communicate with other devices through a wireless network. The above-mentioned wireless network can include a cellular phone network, a wireless local area network, or a metropolitan area network. The above-mentioned wireless network can use various communication standards, protocols, and technologies, including but not limited to the Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as the Institute of Electrical and Electronics Engineers standards IEEE 802.11a, IEEE 802.11b, IEEE802.11g, and / or IEEE802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging, and short messages, and any other suitable communication protocols, and even can include those protocols that have not been developed yet.

[0059] The memory 520 can be used to store software programs and modules, such as the corresponding program instructions / modules in the above embodiments. The processor 580 executes various functional applications and data processing by running the software programs and modules stored in the memory 520, that is, realizes functions such as taking pictures with the front camera, processing the captured images, and switching the display colors of the display content on the display screen. The memory 520 can include high-speed random access memory, and can also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 520 can further include a memory remotely set relative to the processor 580, and these remote memories can be connected to the electronic device 500 through a network. Examples of the above network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and their combinations.

[0060] The input unit 530 can be used to receive input digital or character information, as well as generate keyboards and mice related to user settings and function controls. The display unit 540 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces, and these graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. The display unit 540 can include a display panel 541. Optionally, the display panel 541 can be configured in the form of an LCD (Liquid Crystal Display) or an OLED (Organic Light-Emitting Diode).

[0061] The audio circuit 560, speaker 561, and microphone 562 can provide an audio interface between the user and the electronic device 500. The audio circuit 560 can transmit the electrical signal converted from the received audio data to the speaker 561, and the speaker 561 converts it into a sound signal for output; on the other hand, the microphone 562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 560 and then converted into audio data. After the audio data is output to the processor 580 for processing, it is sent to another terminal, for example, through the RF circuit 510, or the audio data is output to the memory 520 for further processing. The audio circuit 560 may also include an earphone jack to provide communication between the peripheral earphone and the electronic device 500.

[0062] The electronic device 500 can help the user receive requests, send information, etc. through the transmission module 570 (such as a Wi-Fi module), and it provides the user with wireless broadband Internet access. Although the transmission module 570 is shown in the figure, it can be understood that it does not belong to the essential composition of the electronic device 500 and can be completely omitted within the scope of not changing the essence of the invention according to needs.

[0063] The processor 580 is the control center of the electronic device 500, connecting various parts of the entire mobile phone through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 520, and by invoking the data stored in the memory 520, it performs various functions of the electronic device 500 and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 580 may include one or more processing cores; in some embodiments, the processor 580 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 580 either.

[0064] The electronic device 500 further includes a power supply 590 (such as a battery) for powering each component. In some embodiments, the power supply can be logically connected to the processor 580 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 590 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0065] Although not shown, the electronic device 500 further includes a camera (such as a front camera and a rear camera), a Bluetooth module, etc., which will not be elaborated here. Specifically, in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal further includes a memory, and one or more programs, where one or more programs are stored in the memory and are configured to be executed by one or more processors. One or more programs include instructions for performing the following operations: Obtain the characteristic signal sequence of the power system; the characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; Obtain the characteristic signal sequence of the power system; the characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; Perform feature selection on the characteristic signal sequence through the Deep Lasso algorithm; Fill in the missing values in the characteristic signal sequence after feature selection; Perform prediction on the filled characteristic signal sequence through an improved Timesnet algorithm to obtain a future characteristic signal sequence; Classify the future characteristic sequence through a deep random forest model integrating xgboost to obtain a classification result, and the classification result includes at risk and risk-free.

[0066] In specific implementation, each of the above modules can be implemented as an independent entity, or can be arbitrarily combined and implemented as the same or several entities. For the specific implementation of each of the above modules, reference can be made to the foregoing method embodiments, which will not be elaborated herein.

[0067] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present invention provides a storage medium, in which multiple instructions are stored, and the instructions can be loaded by a processor to execute the steps of any one of the embodiments of the power system operation safety warning method based on the improved timesnet provided by the embodiments of the present invention.

[0068] Among them, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0069] Since the instructions stored in the storage medium can execute the steps of any one of the embodiments of the power system operation safety warning method based on the improved timesnet provided by the embodiments of the present invention, the beneficial effects that can be achieved by any of the power system operation safety warning methods based on the improved timesnet provided by the embodiments of the present invention can be realized. For details, refer to the foregoing embodiments, which will not be elaborated herein.

[0070] The above has introduced in detail a power system operation safety warning method, device, storage medium and electronic device based on an improved timesnet of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An early warning method for the operation safety of a power system based on an improved TimesNet, characterized in that, The method includes: Obtaining a characteristic signal sequence of the power system; the characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; Performing feature selection on the characteristic signal sequence through the Deep Lasso algorithm; Filling in the missing values in the characteristic signal sequence after feature selection; Performing prediction on the filled characteristic signal sequence through an improved Timesnet algorithm to obtain a future characteristic signal sequence; Classifying the future characteristic sequence through a deep random forest model integrating xgboost to obtain a classification result, where the classification result includes at risk and risk-free.

2. The power system operation safety warning method based on the improved TimesNet according to claim 1, characterized in that, The performing feature selection on the characteristic signal sequence through the Deep Lasso algorithm includes: Normalizing the data of the characteristic signal sequence; Inputting the normalized characteristic signal sequence into a trained Deep Lasso model for screening to obtain the characteristic signal sequence after feature selection; wherein, a Lasso penalty is imposed during the training process of the Deep Lasso model.

3. The power system operation safety warning method based on the improved timesnet according to claim 2, characterized in that, The Lasso penalty is: Among them, is the loss function, are the model parameters, is the balance parameter, is the gradient of the feature, is the weighting parameter.

4. The power system operation safety warning method based on the improved TimesNet according to claim 1, characterized in that Before the step of filling in the missing values in the characteristic signal sequence, it includes: Analyzing the data in the characteristic signal sequence to obtain the distribution characteristics of the data, the pattern of the missing data, and the correlation between the data.

5. The power system operation safety warning method based on the improved timesnet according to claim 1, characterized in that, Filling in the missing values in the characteristic signal sequence includes: Determining the positions and quantities of the missing values in the characteristic signal sequence; Using linear interpolation for interpolation.

6. The power system operation safety warning method based on the improved timesnet according to claim 1, characterized in that The performing prediction on the filled characteristic signal sequence through an improved Timesnet algorithm to obtain a future characteristic signal sequence includes: Constructing a topology structure matrix based on the topology structure of the power system; Converting the characteristic signal sequence into a two-dimensional matrix; Performing convolution and fusion on the two-dimensional matrix and the topology structure matrix to obtain a first fusion feature; Decoupling the first fusion feature into a one-dimensional sequence and performing prediction based on the one-dimensional sequence to obtain a future characteristic signal sequence.

7. The power system operation safety warning method based on the improved TimesNet according to claim 1, characterized in that, The deep random forest model integrating xgboost includes an xgboost model and a deep random forest model, and the classifying the future characteristic sequence through the deep random forest model integrating xgboost to obtain a classification result includes: Inputting the future characteristic signal sequence into the xgboost model for prediction to obtain a first prediction probability vector; Inputting the future characteristic signal sequence into the deep random forest model for prediction to obtain a second prediction probability vector; Performing weighted summation on the first prediction probability vector and the second prediction probability vector to obtain a fusion probability, and determining the classification result based on the maximum value of the fusion probability.

8. An early warning device for the operation safety of a power system based on an improved TimesNet, characterized in that, It includes: A signal acquisition module for obtaining a characteristic signal sequence of the power system; The characteristic signal sequence includes a voltage signal, a power angle signal, and a phase signal; A feature selection module for performing feature selection on the characteristic signal sequence through the Deep Lasso algorithm; A missing value filling module for filling in the missing values in the characteristic signal sequence after feature selection; A prediction module, configured to predict the filled feature signal sequence through an improved Timesnet algorithm to obtain a future feature signal sequence; A classification module, configured to classify the future feature sequence through a deep random forest model integrating xgboost to obtain a classification result, where the classification result includes at risk and risk-free.

9. A computer-readable storage medium, characterized in that, Multiple instructions are stored in the computer-readable storage medium, and the instructions are adapted to be loaded by a processor to execute the power system operation safety warning method based on the improved timesnet according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a processor and a memory. The processor is electrically connected to the memory. The memory is used to store instructions and data, and the processor is used to execute the steps in the power system operation safety warning method based on the improved timesnet according to any one of claims 1 to 7.

Images