Power transmission line risk monitoring method and device based on learning rate strategy, electronic equipment and storage medium

Abstract

The invention discloses a power transmission line risk monitoring method and device based on a learning rate strategy, electronic equipment and a storage medium, and belongs to the technical field of power transmission line risk monitoring. The method comprises the following steps: acquiring system operation information of a power system, wherein the system operation information comprises real-time meteorological data and line operation data; extracting real-time meteorological characteristics from the real-time meteorological data, extracting line operation characteristics from the line operation data, and constructing vector representation to be measured based on the real-time meteorological characteristics and the line operation characteristics; inputting the to-be-measured vector representation into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model based on a plurality of training samples and updating a self-adaptive learning rate, and the training samples comprise sample vector representations and risk assessment labels corresponding to the sample vector representations. The method can improve the assessment precision of the power transmission line risk, and guarantees the safe and stable operation of a power system.

Description

Technical Field

[0001] The present application belongs to the technical field of transmission line risk monitoring, and in particular, relates to a transmission line risk monitoring method, device, electronic device and storage medium based on a learning rate strategy. Background Art

[0002] In the operation of modern power systems, meteorological conditions have a profound impact on the stable operation of power equipment, and N-1 failures may trigger serious chain reactions, further exacerbating risks. Traditional risk assessment methods have many shortcomings when considering meteorological-equipment risk associations and N-1 failure scenarios. For example, fixed learning rate model training is often used, which makes it difficult to cope with complex data characteristics and failure conditions, resulting in poor accuracy and reliability of risk assessment.

[0003] As the scale of power systems expands and the operating environment becomes more complex and changeable, innovative methods are urgently needed to accurately assess such risks and ensure the safe and stable operation of power systems. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a transmission line risk monitoring method, device, electronic device and storage medium based on a learning rate strategy, which can improve the assessment accuracy of transmission line risks and ensure the safe and stable operation of the power system.

[0005] In a first aspect, the present application provides a transmission line risk monitoring method based on a learning rate strategy, the method comprising:

[0006] Acquiring system operation information of the power system, the system operation information including: real-time meteorological data and line operation data;

[0007] Extracting real-time meteorological features from the real-time meteorological data, extracting line operation features from the line operation data, and constructing a vector representation to be measured based on the real-time meteorological features and the line operation features;

[0008] The vector representation to be tested is input into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model based on multiple training samples and updating the adaptive learning rate, and the training samples include sample vector representations and risk assessment labels corresponding to the sample vector representations.

[0009] According to one embodiment of the present application, before inputting the vector representation to be tested into the risk assessment model, the method further includes:

[0010] Acquiring historical operation data of the power system, wherein the historical operation data includes historical meteorological data and equipment failure records;

[0011] Correct and perform integrity verification on the historical operation data;

[0012] Extract features from the verified historical operation data to obtain sample meteorological features and sample line features;

[0013] Construct a sample vector representation from the sample meteorological features and the sample line features;

[0014] Use the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as a training sample;

[0015] Train the logistic regression model with multiple training samples to obtain the risk assessment model.

[0016] According to an embodiment of the present application, training the logistic regression model with multiple training samples to obtain the risk assessment model includes:

[0017] Divide the multiple training samples into a training set and a validation set;

[0018] Train the logistic regression model with the obtained training set and validate the logistic regression model with the validation set;

[0019] Determine the loss value of the logistic regression model based on the validation set through a loss function, update the learning rate, and use the trained logistic regression model as the risk assessment model.

[0020] According to an embodiment of the present application, the update strategy of the learning rate is:

[0021]

[0022] where α t is the updated learning rate; α t is the initial learning rate; G j is the sum of the squared gradients of the jth feature value in the training sample; ε is a stability factor.

[0023] According to an embodiment of the present application, the loss function of the logistic regression model is:

[0024]

[0025] where J(θ) is the loss function; θ is the model parameter vector; m is the amount of data in the training sample; y (i) is the risk assessment label of the ith training sample; X (i) is the ith training sample; h θ (X (i)) is the predicted probability of the training sample X by the logistic regression model based on the current model parameter vector θ (i) of the training sample X by the logistic regression model based on the current model parameter vector θ

[0026] According to an embodiment of the present application, before using the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as a training sample, the method includes:

[0027] Based on the device fault record, construct a topological structure representation for the N-1 voltage faults in the power system;

[0028] Extract the risk value of the N-1 voltage faults in the power system from the topological structure representation to obtain a risk assessment label.

[0029] According to an embodiment of the present application, after obtaining the risk assessment result output by the risk assessment model, the method further includes:

[0030] Based on a comprehensive risk assessment criterion, classify the risk assessment result to obtain a risk level;

[0031] When the comprehensive risk value corresponding to the risk assessment result exceeds a risk threshold, trigger a risk warning and push a warning message, where the warning message is determined based on the risk level;

[0032] Analyze the feedback effect of the risk assessment result and the risk warning, and adjust the risk threshold.

[0033] In a second aspect, the present application provides a transmission line risk monitoring device based on a learning rate strategy, and the device includes:

[0034] An acquisition module, configured to acquire system operation information of a power system, where the system operation information includes: real-time meteorological data and line operation data;

[0035] A first processing module, configured to extract real-time meteorological features from the real-time meteorological data, extract line operation features from the line operation data, and construct a vector representation to be measured based on the real-time meteorological features and the line operation features;

[0036] A second processing module, configured to input the vector representation to be measured into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model with multiple training samples and updating the adaptive learning rate, and the training samples include a sample vector representation and a risk assessment label corresponding to the sample vector representation.

[0037] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the transmission line risk monitoring method based on the learning rate strategy as described in the first aspect above.

[0038] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the transmission line risk monitoring method based on the learning rate strategy as described in the first aspect above.

[0039] In a fifth aspect, the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the transmission line risk monitoring method based on the learning rate strategy as described in the first aspect.

[0040] In a sixth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the transmission line risk monitoring method based on the learning rate strategy as described in the first aspect above.

[0041] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application.

[0042] The transmission line risk monitoring method, device, electronic device, and storage medium based on the learning rate strategy provided by the present application have the following beneficial effects compared with the prior art:

[0043] (1) By extracting features from real-time meteorological data and line operation data and performing risk assessment based on a logistic regression model, potential risks existing in the power system can be identified in a timely manner, the risk assessment result of the power system can be obtained quickly, the risk level of the power system can be evaluated in a timely manner, the evaluation accuracy of transmission line risks can be improved, the safe and stable operation of the power system can be guaranteed, a basis for taking preventive measures can be provided, the occurrence of equipment failures and accidents can be effectively reduced, the maintenance cost can be reduced, and the operation efficiency of the power system can be improved.

[0044] (2) Through risk assessment and risk level classification, as well as triggering early warnings and adjusting risk thresholds, risks in the power system can be effectively predicted and managed, the safety and reliability of the system can be ensured. At the same time, through a continuous feedback and optimization mechanism, the risk assessment and early warning system can always maintain high efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and be easily understood from the description of the embodiments in conjunction with the following drawings, where:

[0046] Figure 1 This is a schematic flowchart of a transmission line risk monitoring method based on a learning rate strategy provided in an embodiment of the present application;

[0047] Figure 2 This is a schematic structural diagram of a transmission line risk monitoring device based on a learning rate strategy provided in an embodiment of the present application;

[0048] Figure 3 This is a schematic structural diagram of an electronic device provided in an embodiment of the present application. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0050] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means an "or" relationship between the associated objects before and after.

[0051] Next, in conjunction with the accompanying drawings, the transmission line risk monitoring method based on a learning rate strategy, the transmission line risk monitoring device based on a learning rate strategy, the electronic device, and the readable storage medium provided in the embodiments of the present application will be described in detail through specific embodiments and their application scenarios.

[0052] Among them, the transmission line risk monitoring method based on a learning rate strategy can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

[0053] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablet computers having a touch-sensitive surface (for example, a touch screen display and / or a touchpad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (for example, a touch screen display and / or a touchpad).

[0054] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0055] The transmission line risk monitoring method based on the learning rate strategy provided in the embodiment of the present application, the execution subject of the transmission line risk monitoring method based on the learning rate strategy can be an electronic device or a functional module or functional entity in the electronic device that can implement the transmission line risk monitoring method based on the learning rate strategy. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras and wearable devices, etc. The transmission line risk monitoring method based on the learning rate strategy provided in the embodiment of the present application is explained below by taking the electronic device as the execution subject as an example.

[0056] like Figure 1 As shown, the transmission line risk monitoring method based on the learning rate strategy includes:

[0057] Step 110: Acquire system operation information of the power system, wherein the system operation information includes: real-time meteorological data and line operation data;

[0058] Step 120: extracting real-time meteorological features from the real-time meteorological data, extracting line operation features from the line operation data, and constructing a vector representation to be measured based on the real-time meteorological features and the line operation features;

[0059] Step 130: input the vector representation to be tested into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model based on multiple training samples and updating the adaptive learning rate, and the training samples include sample vector representations and risk assessment labels corresponding to the sample vector representations.

[0060] Among them, the risk assessment labels are the transmission lines and equipment in the power system, as well as the corresponding risk values.

[0061] In actual implementation, real-time meteorological data of the power system is obtained, for example, temperature, humidity, air pressure, rainfall, wind speed and other meteorological data that can affect the transmission line.

[0062] Acquire real-time line operation data of transmission lines in the power system, including data related to equipment operation and topology, such as line current, voltage, power factor, line load, etc., to reflect the load and health status of transmission lines during actual operation.

[0063] Extract real-time meteorological features from real-time meteorological data. The meteorological features include variables with a relatively high degree of relevance to risk assessment, such as the meteorological change rate of parameters like temperature, wind speed and direction, precipitation change amount, and meteorological anomaly indicators.

[0064] Temperature changes may affect the operating stability of equipment. For example, when the temperature fluctuates violently, the load of power equipment may change. Strong winds or sudden changes in wind speed may cause the breakage or damage of power lines, and changes in wind direction may also affect the stability of the lines.

[0065] Extract line operation features from line operation data. For example, line voltage and current changes, line load changes, and power factor, etc. Sudden changes in current and voltage may be omens of line faults, especially during high-load operation; rapid changes in load may be due to faults or overloads in a certain part of the line; changes in power factor may reflect abnormal operation of equipment, thus affecting the security of the power system.

[0066] For example, 3 real-time meteorological features including temperature, wind speed, and precipitation amount, and 3 line features including current, voltage, and load are extracted. The real-time meteorological features and line operation features are integrated into a vector containing 6 elements in sequence as the representation of the vector to be measured.

[0067] Normalize the features from real-time meteorological features and line operation features and integrate them into a unified vector format as the representation of the vector to be measured and input it into the risk assessment model for processing. The risk assessment model predicts the risk values of transmission lines and equipment in the power system based on the relationship between features and the probability of fault occurrence, and outputs them as the risk assessment results to measure the risk level of the transmission lines.

[0068] Among them, during the training process, adjust the learning rate of the risk assessment model to more effectively reduce errors.

[0069] For example, the risk value is a probability value between 0 and 1, used to characterize the possibility of fault occurrence or safety risk under the current power system state. 0 indicates a very low risk, and 1 indicates a very high risk.

[0070] According to the transmission line risk monitoring method based on the learning rate strategy provided by the embodiments of the present application, by extracting features from real-time meteorological data and line operation data, and based on the risk assessment of the logistic regression model, timely identify potential risks existing in the power system, quickly obtain the risk assessment results of the power system, timely evaluate the risk level of the power system, can improve the assessment accuracy of transmission line risks, ensure the safe and stable operation of the power system, provide a basis for taking preventive measures, effectively reduce the occurrence of equipment failures and accidents, reduce maintenance costs, and improve the operation efficiency of the power system.

[0071] In some embodiments, before inputting the vector representation to be measured into the risk assessment model, it further includes:

[0072] Obtain the historical operation data of the power system, where the historical operation data includes historical meteorological data and equipment failure records;

[0073] Correct and perform integrity verification on the historical operation data;

[0074] Extract features from the verified historical operation data to obtain sample meteorological features and sample line features;

[0075] Construct a sample vector representation from the sample meteorological features and the sample line features;

[0076] Use the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as training samples;

[0077] Train the logistic regression model with multiple training samples to obtain the risk assessment model.

[0078] Among them, the historical meteorological data includes meteorological conditions in the past period of time, including extreme meteorological data that is highly correlated with line failures, such as heavy rain, strong wind, low temperature, etc.

[0079] The equipment failure records include information such as the failure history and failure type of the equipment, such as the outage time of the equipment in the power system, the failure location, and the cause analysis.

[0080] In actual execution, extract the historical operation data of the power system to provide a comprehensive data basis for subsequent processing.

[0081] Perform data cleaning, correction, and integrity verification on the obtained historical operation data to ensure data quality. Use statistical and physical rules to find data that deviates from the normal range, check whether the data is missing or abnormal. If there is missing data, adopt strategies such as interpolation, supplementation, or discarding to process it, and correct the verified data to ensure the consistency of the data in time and space.

[0082] Extract the meteorological change rate from the preprocessed historical operation data as the sample meteorological feature, and extract the equipment failure trend, etc. as the sample line feature. Normalize the sample meteorological feature and the sample line feature to ensure that the values of each feature are in the same magnitude, so as to avoid the influence of some feature values being too large or too small on the training effect of the model, and integrate them into a sample vector representation. The sample vector representation should be able to reflect the operating conditions of the power system, the impact of meteorology on the line, and the health status of the equipment.

[0083] For example, the meteorological change rate includes the temperature change speed, the wind speed change trend, etc., and the equipment failure trend includes the frequency of equipment failure, the equipment load change, etc.

[0084] Considering the impact of single-point failures on the entire power system, the extracted sample meteorological features and sample line features need to have strong correlation and representativeness, and be able to effectively predict the risks of transmission lines.

[0085] In some embodiments, before using the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as a training sample, the method includes:

[0086] Based on the equipment failure records, construct a topological structure representation for the N-1 voltage failures in the power system;

[0087] Extract the risk values of the N-1 voltage failures in the power system from the topological structure representation to obtain risk assessment labels.

[0088] In actual execution, based on the N-1 voltage failure situation, construct a topological structure representation of the power system. The topological structure representation is a one-dimensional vector including relevant features such as node voltages.

[0089] The topological structure representation includes relevant features such as node voltages and is used to simulate the response actions of the power system if a single-point failure (N-1) occurs.

[0090] In addition, based on the topological information in the topological structure representation, generate a graph structure composed of lines, substations, switches, etc. as the topological structure diagram of the power system, and combine real-time operation data to dynamically monitor the power system, evaluate the fault risks of lines, and facilitate subsequent feature analysis.

[0091] The sample vector representation includes meteorological change rate, equipment failure trend, topological structure, line load, etc.

[0092] Among them, the risk value is the risk assessment result based on historical data or the probability of failure occurrence. For example, the risk value may include the overload probability.

[0093] In some embodiments, training the logistic regression model with multiple training samples to obtain the risk assessment model includes:

[0094] Divide the multiple training samples into a training set and a validation set;

[0095] Train the logistic regression model with the obtained training set and validate the logistic regression model with the validation set;

[0096] Determine the loss value of the logistic regression model based on the validation set through the loss function, update the learning rate, and use the trained logistic regression model as the risk assessment model.

[0097] Divide the obtained training samples into a training set and a validation set according to 7:3. The training set is used for training, and the validation set is used for verification.

[0098] If the number of training samples is insufficient, data augmentation techniques such as noise addition and simulation of different meteorological conditions can be used to increase the sample number and improve the generalization ability of the model.

[0099] Use the training set to train the logistic regression model, evaluate the performance of the model through the validation set, calculate the loss value of the model on the validation set using the loss function, adjust the learning rate according to the validation set loss value, and adopt an adaptive learning rate strategy to optimize the model, so that the learning rate is adaptively adjusted during the training process to improve the convergence speed and effect of the model.

[0100] With logistic regression as the core architecture, dynamically adjust the learning rate according to a specific strategy, and intelligently expand features to capture complex relationships, jointly constructing an adaptable model framework;

[0101] Logistic regression model prediction formula:

[0102]

[0103] where, θ = [θ1, θ2, …, θ n is the model parameter vector, and X = [x1, x2, …, x n is the input of the model.

[0104] During the process of adaptive learning rate adjustment, first calculate the gradient of each sample:

[0105]

[0106] where, y (i) is the risk assessment label of the i-th training sample (0 represents low risk, 1 represents high risk), h θ (X (i) ) is the predicted probability of the logistic regression model based on the current model parameter vector θ for the training sample X (i) , is the j-th feature of the training sample X (i) .

[0107] Then calculate the sum of the squares of the gradients of each feature value in the training samples:

[0108]

[0109] where, m is the number of training samples.

[0110] In some embodiments, the update strategy of the learning rate is as follows:

[0111]

[0112] where α t is the updated learning rate; α t is the initial learning rate; G j is the sum of the squares of the gradients of the j-th eigenvalue in the training samples; ε is the stability factor.

[0113] where α is the initial learning rate, which is a positive number set in advance and determines the step size of parameter update in the initial stage of model training.

[0114] ε is a very small positive number (such as 10-8), and its function is to prevent the denominator from being 0 and ensure the stability of the calculation.

[0115] In some embodiments, the loss function of the logistic regression model is:

[0116]

[0117] where J(θ) is the loss function; θ is the model parameter vector; m is the data volume of the training samples; y (i) is the risk assessment label of the i-th training sample; X (i) is the i-th training sample; h θ (X (i) ) is the predicted probability of the logistic regression model for the sample X (i) based on the current model parameter vector θ.

[0118] In addition, the key parameters of the model can also be adjusted according to the monitoring feedback to optimize the model performance through iteration.

[0119] The loss function is used to measure the difference between the prediction results and the true labels of the risk assessment model for the entire training set and validation set under the given parameter θ. The goal of model training is to minimize the value of this loss function by adjusting the model parameter vector θ, and the adjustment mechanism of the adaptive learning rate is also to update the parameters more effectively towards this minimization goal.

[0120] In some embodiments, after obtaining the risk assessment result output by the risk assessment model, the method further includes:

[0121] Based on the comprehensive risk assessment criteria, classifying the risk assessment result to obtain a risk level;

[0122] When the comprehensive risk value corresponding to the risk assessment result exceeds the risk threshold, a risk warning is triggered and a warning message is pushed, and the warning message is determined based on the risk level;

[0123] Analyze the feedback effects of the risk assessment result and the risk warning, and adjust the risk threshold.

[0124] Among them, the risk assessment result can be a numerical value (such as the probability of a fault occurring) or a category (such as low risk, medium risk, high risk).

[0125] In actual implementation, the risk values of each device and line in the risk assessment result are weighted and calculated to obtain a comprehensive risk value. According to the numerical value of the comprehensive risk value, the risk level of the risk assessment result is divided to present the real-time risk status of the power system;

[0126] Compare the comprehensive risk value with the risk threshold. When the risk threshold is exceeded, a warning is triggered, and a warning message including the risk level, detailed risk analysis and countermeasure suggestions is sent to the operation and maintenance personnel through various sound, light and electrical signals to ensure timely awareness and response to risks;

[0127] Analyze the warning effect, adjust the risk threshold, optimize the model and warning strategy according to the risk assessment result, and continuously improve the system performance to ensure the safety of the power system.

[0128] Record the risk assessment results and their corresponding risk levels at each time point for subsequent analysis and decision-making support.

[0129] In this embodiment, through risk assessment, risk level division, triggering warnings and adjusting risk thresholds, risks in the power system can be effectively predicted and managed to ensure the safety and reliability of the system. At the same time, through continuous feedback and optimization mechanisms, the risk assessment and warning system can always maintain high efficiency and accuracy.

[0130] For the transmission line risk monitoring method based on the learning rate strategy provided in the embodiments of the present application, the execution subject can be a transmission line risk monitoring device based on the learning rate strategy. In the embodiments of the present application, taking the transmission line risk monitoring device based on the learning rate strategy executing the transmission line risk monitoring method based on the learning rate strategy as an example, the transmission line risk monitoring device based on the learning rate strategy provided in the embodiments of the present application is described.

[0131] The embodiments of the present application also provide a transmission line risk monitoring device based on the learning rate strategy.

[0132] As Figure 2 shown, the transmission line risk monitoring device based on the learning rate strategy includes:

[0133] An acquisition module 210, configured to acquire system operation information of a power system, where the system operation information includes: real-time meteorological data and line operation data;

[0134] A first processing module 220, configured to extract real-time meteorological features from the real-time meteorological data, extract line operation features from the line operation data, and construct a to-be-tested vector representation based on the real-time meteorological features and the line operation features;

[0135] A second processing module 230, configured to input the to-be-tested vector representation into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model based on a plurality of training samples and updating the adaptive learning rate, and the training samples include sample vector representations and risk assessment labels corresponding to the sample vector representations.

[0136] According to the transmission line risk monitoring device based on the learning rate strategy provided in the embodiments of the present application, by extracting features from real-time meteorological data and line operation data, and based on the risk assessment of the logistic regression model, potential risks existing in the power system can be identified in a timely manner, the risk assessment result of the power system can be obtained quickly, the risk level of the power system can be evaluated in a timely manner, the evaluation accuracy of the transmission line risk can be improved, the safe and stable operation of the power system can be guaranteed, a basis for taking preventive measures can be provided, the occurrence of equipment failures and accidents can be effectively reduced, the maintenance cost can be reduced, and the operation efficiency of the power system can be improved.

[0137] The transmission line risk monitoring device based on the learning rate strategy in the embodiments of the present application can be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices other than the terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), or a server, etc., and the embodiments of the present application do not make specific limitations.

[0138] The transmission line risk monitoring device based on the learning rate strategy in the embodiments of the present application can be a device with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, and the embodiments of the present application do not make specific limitations.

[0139] The transmission line risk monitoring device based on the learning rate strategy provided in the embodiments of the present application can implement each process implemented by the transmission line risk monitoring method embodiment based on the learning rate strategy in the above embodiments. To avoid repetition, it will not be elaborated here.

[0140] In some embodiments, such asFigure 3 As shown in Figure 3 , an embodiment of the present application further provides an electronic device 300, which includes a processor 301, a memory 302, and a computer program stored on the memory 302 and executable on the processor 301. When the program is executed by the processor 301, it implements each process of the above embodiment of the transmission line risk monitoring method based on the learning rate strategy and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0141] It should be noted that the electronic device in the embodiment of the present application includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0142] An embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above embodiment of the transmission line risk monitoring method based on the learning rate strategy and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0143] Among them, the processor is the processor in the electronic device in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0144] An embodiment of the present application further provides a computer program product, including a computer program, which implements the above transmission line risk monitoring method based on the learning rate strategy when executed by a processor.

[0145] Among them, the processor is the processor in the electronic device in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs.

[0146] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement each process of the above embodiment of the transmission line risk monitoring method based on the learning rate strategy and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0147] It should be understood that the chip mentioned in the embodiment of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip.

[0148] It should be noted that in this text, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the presence of additional identical elements in the process, method, article or device that includes such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0149] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the power transmission line risk monitoring method based on the learning rate strategy in various embodiments of the present application.

[0150] In the description of the present application, "the first feature", "the second feature" may include one or more of such features.

[0151] In the description of the present application, the meaning of "a plurality of" is two or more.

[0152] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

[0153] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0154] Although the embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and purposes of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A transmission line risk monitoring method based on a learning rate strategy, characterized in that, Including: Obtain the system operation information of the power system, where the system operation information includes: real-time meteorological data and line operation data; Extract real-time meteorological features from the real-time meteorological data, extract line operation features from the line operation data, and construct a representation of the vector to be measured based on the real-time meteorological features and the line operation features; Input the representation of the vector to be measured into the risk assessment model to obtain the risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model with multiple training samples and updating the adaptive learning rate, and the training samples include sample vector representations and risk assessment labels corresponding to the sample vector representations.

2. The transmission line risk monitoring method based on the learning rate strategy according to claim 1, wherein, Before inputting the representation of the vector to be measured into the risk assessment model, it further includes: Obtain the historical operation data of the power system, where the historical operation data includes historical meteorological data and equipment failure records; Correct and perform integrity verification on the historical operation data; Extract features from the verified historical operation data to obtain sample meteorological features and sample line features; Construct a sample vector representation from the sample meteorological features and the sample line features; Use the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as a training sample; Train the logistic regression model with multiple training samples to obtain the risk assessment model.

3. The transmission line risk monitoring method based on a learning rate strategy according to claim 2, wherein Training the logistic regression model with multiple training samples to obtain the risk assessment model includes: Divide the multiple training samples into a training set and a validation set; Train the logistic regression model with the obtained training set and validate the logistic regression model with the validation set; Determine the loss value of the logistic regression model based on the validation set through a loss function, update the learning rate, and use the trained logistic regression model as the risk assessment model.

4. The method for monitoring the risk of a transmission line based on a learning rate strategy according to claim 3, wherein The update strategy of the learning rate is: where α t is the updated learning rate; α t is the initial learning rate; G j is the sum of the squared gradients of the j-th eigenvalue in the training samples; ε is the stability factor.

5. The transmission line risk monitoring method based on the learning rate strategy according to claim 3, characterized in that, The loss function of the logistic regression model is: Among them, J(θ) is the loss function; θ is the model parameter vector; m is the amount of data of the training samples; y (i) is the risk assessment label of the i-th training sample; X (i) is the i-th training sample; h θ (X (i) ) is the predicted probability of the logistic regression model for the training sample X (i) based on the current model parameter vector θ.

6. The power transmission line risk monitoring method based on a learning rate strategy according to claim 2, wherein Before using the combination of the sample vector representation and the risk assessment label corresponding to the sample vector representation as a training sample, the method includes: Based on the equipment failure records, construct a topological structure representation for the N-1 voltage faults in the power system; Extract the risk values of the N-1 voltage faults in the power system from the topological structure representation to obtain risk assessment labels.

7. The transmission line risk monitoring method based on a learning rate strategy according to claim 1, characterized in that After obtaining the risk assessment result output by the risk assessment model, the method further includes: Based on the comprehensive risk assessment criteria, divide the risk assessment result into levels to obtain a risk level; When the comprehensive risk value corresponding to the risk assessment result exceeds the risk threshold, trigger a risk warning and push a warning message, where the warning message is determined based on the risk level; Analyze the feedback effect of the risk assessment result and the risk warning, and adjust the risk threshold.

8. A transmission line risk monitoring device based on a learning rate strategy, characterized in that, Including: An acquisition module for obtaining the system operation information of the power system, where the system operation information includes: real-time meteorological data and line operation data; The first processing module is used to extract real-time meteorological features from the real-time meteorological data, extract line operation features from the line operation data, and construct a vector representation to be measured based on the real-time meteorological features and the line operation features; The second processing module is used to input the vector representation to be measured into a risk assessment model to obtain a risk assessment result output by the risk assessment model; the risk assessment model is obtained by training a logistic regression model based on a plurality of training samples and updating the adaptive learning rate, and the training samples include sample vector representations and risk assessment labels corresponding to the sample vector representations.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the transmission line risk monitoring method based on the learning rate strategy according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the transmission line risk monitoring method based on the learning rate strategy according to any one of claims 1-7.

Images