An intelligent security situation awareness early warning system and method

Abstract

The application belongs to the technical field of line loss monitoring, and discloses an intelligent security situation awareness early warning system and method; the method comprises the following steps: collecting key data and attributes of a power transmission line in a unit time and environmental key data in the next unit time, obtaining power transmission line data and line environment data through processing; and inputting the two into a threshold prediction model and a line loss prediction model respectively according to line attributes, obtaining a predicted line loss rate threshold and a predicted line loss rate in the next unit time, and generating a predicted line loss rate sequence according to a preset time window; determining a line loss rate abnormal type based on the predicted line loss rate threshold and the sequence, and executing a corresponding automatic adjustment strategy according to the determination result; the application can automatically adjust the power transmission line whose predicted line loss rate exceeds the line loss threshold according to the predicted line loss rate, thereby effectively reducing the line loss rate of the power transmission line, reducing the economic loss of the power grid, and promoting efficient and stable operation of the power grid.

Description

Technical Field

[0001] This invention relates to the field of line loss monitoring technology, and more specifically, to an intelligent security situation awareness and early warning system and method. Background Technology

[0002] The smart grid security situation awareness and early warning system uses a variety of sensors and detection technologies to monitor and analyze the operating status of the power grid, thereby improving the security and stability of the power grid.

[0003] To achieve real-time monitoring of power line status, timely detection and resolution of line loss issues, and improve power grid operation efficiency and safety, Chinese Patent Publication No. CN117763354A proposes a mobile service system and method for line loss monitoring and management, including: a mobile terminal, a cloud platform, and a data acquisition unit; the data acquisition unit uses sensor devices installed on power lines to monitor power data in real time and transmits the data to the cloud platform; the cloud platform includes a data analysis module, a fault location module, an early warning module, a data encryption module, a data storage module, and a data transmission module; the data analysis module performs real-time analysis based on the real-time monitored power data and a line loss prediction model to obtain line loss prediction data; the data storage module includes a monitoring database, a line loss prediction database, and a processing suggestion database; the early warning module determines whether there is a line loss anomaly based on the line loss prediction data obtained by the data analysis module.

[0004] While the above methods can meet the needs of most scenarios, research and practical application of these methods and existing technologies have revealed at least the following shortcomings:

[0005] Existing technologies rely solely on real-time monitored power data to obtain line loss rates, without considering the impact of transmission line attributes and future environmental data on these rates. Transmission line attributes include material, resistivity, radius, and length; environmental data includes temperature, humidity, and wind speed. This results in low accuracy in predicting line loss rates and a lack of automated adjustments for transmission lines with predicted line loss rates exceeding thresholds. Consequently, line loss rates cannot be reduced in a timely and effective manner. On the one hand, a high line loss rate means greater energy loss, leading to greater economic losses for power companies.

[0006] On the other hand, high line loss rates during power transmission from power plants can also cause transmission safety issues and electricity consumption safety problems. For example, excessively high line loss rates are accompanied by increased current in transmission lines. High current can cause conductors to overheat, increasing the risk of line aging and insulation damage. If not controlled in time, this can lead to overload, line breakage, or even fires in transmission lines. For example, excessively high line loss rates can cause voltage drops, preventing terminal equipment from operating normally due to insufficient voltage, thus leading to safety problems such as overheating, damage, or even fires in user equipment.

[0007] In view of this, the present invention proposes an intelligent security situation awareness and early warning system and method to solve the above problems. Summary of the Invention

[0008] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: an intelligent security situation awareness and early warning method, comprising:

[0009] Collect key data and attributes of transmission lines per unit time.

[0010] Collect key environmental data for the next unit of time from the current unit of time;

[0011] The key data of the transmission line and the key data of the environment are analyzed and processed separately to obtain transmission line data and line environment data.

[0012] Transmission line data, line environment data, and transmission line attributes are input into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold.

[0013] Transmission line data, line environment data, and transmission line attributes are input into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit time. The predicted line loss rate for the next unit time is then divided into a predicted line loss rate sequence according to a preset time window.

[0014] The type of line loss rate anomaly is determined based on the predicted line loss rate threshold and the predicted line loss rate sequence; the type of line loss rate anomaly includes persistent line loss anomaly and intermittent line loss anomaly.

[0015] Automated adjustment of transmission lines is performed based on the type of abnormal line loss rate.

[0016] Furthermore, methods for automatically adjusting transmission lines based on the type of line loss anomaly include:

[0017] Obtain the abnormal type of line loss rate;

[0018] If the abnormal line loss rate is of the type of continuous line loss abnormality, then the transmission line will be automatically adjusted for the continuous line loss abnormality.

[0019] If the abnormal line loss rate is of the intermittent line loss type, then the transmission line will be automatically adjusted for the intermittent line loss abnormality.

[0020] Furthermore, methods for automatically adjusting transmission lines in response to persistent line loss anomalies include:

[0021] The power factor data is input into a pre-trained power factor model to obtain the target power factor; the power factor data includes the predicted line loss rate, key environmental data, and transmission line attributes.

[0022] Calculate the reactive power compensation based on the target power factor, active power, and current power factor;

[0023] The target voltage is calculated based on the compensation reactive power, transmission line reactance, and average line voltage.

[0024] Calculate the target current based on the active power, target voltage, and target power factor;

[0025] At the end of the current unit of time, in the next unit of time, the calculated reactive power is compensated using reactive power compensation equipment; the voltage is adjusted to the target voltage using a voltage regulator, and the current is adjusted to the target current using a current regulator.

[0026] Furthermore, methods for automatically adjusting transmission lines in response to intermittent line loss anomalies include:

[0027] Intermittent line loss anomalies are classified and determined based on the predicted line loss rate sequence to obtain the intermittent anomaly type; the intermittent anomaly type includes continuous intermittent anomalies and discrete intermittent anomalies;

[0028] If the intermittent anomaly type is a discrete intermittent anomaly, no processing is required;

[0029] If the intermittent anomaly type is a continuous intermittent anomaly, then the transmission line is automatically adjusted for the continuous intermittent anomaly.

[0030] Furthermore, the method for determining the type of intermittent abnormality includes:

[0031] Mark the time points when the line loss rate exceeds the limit in the predicted line loss rate sequence. The time points when the line loss rate exceeds the limit refer to the time points when the predicted line loss rate is greater than the predicted line loss rate threshold.

[0032] Count the time intervals between all adjacent time points when the line loss rate exceeds the limit, and calculate the average time interval based on all time intervals; count the maximum number of consecutive occurrences of time points when the line loss rate exceeds the limit, and record it as the first duration.

[0033] If the average time interval is less than the preset average time interval threshold, and the first duration is greater than the preset first duration threshold, then the intermittent line loss anomaly will be further determined as a continuous intermittent anomaly.

[0034] If the judgment conditions corresponding to continuous intermittent anomalies are not met, then the intermittent line loss anomaly will be further judged as a discrete intermittent anomaly.

[0035] Furthermore, methods for automatically regulating transmission lines in response to continuous intermittent anomalies include:

[0036] Obtain the first duration number corresponding to the continuous intermittent anomaly, and record the predicted line loss rate of each time point covered by the first duration number as the first predicted line loss rate. Construct all the first predicted line loss rates into a first predicted line loss rate sequence.

[0037] The first predicted line loss rate sequence is time-series aligned with the transmission line data to obtain the first transmission line data; the first predicted line loss rate sequence is time-series aligned with the line environment data to obtain the first line environment data.

[0038] The first predicted line loss rate sequence, the first transmission line data, the first line environment data, and the transmission line attributes are input into the parameter setting model to obtain a set of adjustment parameters; the set of adjustment parameters includes the first compensated reactive power, the first target voltage, and the first target current;

[0039] CK time windows before the start time of the first predicted line loss rate sequence, the set of adjustment parameters is sent to the corresponding equipment for adaptive adjustment; CK is the preset number of time windows.

[0040] Furthermore, the method for determining the abnormal type of line loss rate includes:

[0041] S100: Denote the number of predicted line loss rates in the predicted line loss rate sequence as NUM; let the initial value of num be 1, the value range of num is from 1 to NUM, and num is a loop variable; initialize the number of line loss rates exceeding the limit to 0;

[0042] S101: Obtain the num-th predicted line loss rate from the predicted line loss rate sequence. If the num-th predicted line loss rate is greater than the predicted line loss rate threshold, then subtract the num-th predicted line loss rate from the predicted line loss rate threshold to obtain the line loss rate exceeding the limit, and increment the number of line loss rate exceeding the limit by one. If the num-th predicted line loss rate is less than or equal to the predicted line loss rate threshold, then directly execute S102.

[0043] S102: Let num = num + 1. If num is less than or equal to NUM, return to S101 and continue execution. If num is greater than NUM, execute S103.

[0044] S103: Divide the number of line loss rate exceeding the limit by NUM to obtain the line loss rate exceeding the limit ratio; calculate the average line loss rate exceeding the limit based on all the line loss rate exceeding the limit values;

[0045] Determine whether the line loss rate exceeds the preset threshold and the average line loss rate exceeds the preset threshold. If the conditions are met, the line loss rate anomaly type is determined to be a continuous line loss anomaly. If the conditions are not met, the line loss rate anomaly type is determined to be an intermittent line loss anomaly.

[0046] Furthermore, the key data of the line includes phase angle, initial voltage value, final voltage value, line voltage and line current; the transmission line attributes include transmission line material, line material resistivity, transmission line radius and transmission line length; the key environmental data includes ambient temperature, ambient humidity and ambient wind speed.

[0047] Furthermore, the transmission line data includes reactive power, line voltage difference, average line voltage, line power loss, and average line current; the line environment data includes average ambient temperature, average ambient humidity, and average ambient wind speed.

[0048] An intelligent security situation awareness and early warning system, implementing the aforementioned intelligent security situation awareness and early warning method, includes:

[0049] The first acquisition module is used to collect key data and attributes of the transmission lines within a unit of time.

[0050] The second acquisition module is used to acquire key environmental data for the next unit of time from the current unit of time.

[0051] The first processing module is used to analyze and process the key data of the line and the key data of the environment respectively to obtain the transmission line data and the line environment data.

[0052] The threshold prediction module is used to input transmission line data, line environment data, and transmission line attributes into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold.

[0053] The line loss prediction module is used to input transmission line data, line environment data and transmission line attributes into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit time, and to divide the predicted line loss rate for the next unit time into a predicted line loss rate sequence according to a preset time window.

[0054] The line loss diagnosis module determines the type of line loss rate anomaly based on the predicted line loss rate threshold and the predicted line loss rate sequence; the type of line loss rate anomaly includes persistent line loss anomaly and intermittent line loss anomaly.

[0055] The line loss adjustment module is used to automatically adjust the transmission line according to the abnormal type of line loss rate.

[0056] The technical effects and advantages of the intelligent security situation awareness and early warning system and method of the present invention are as follows:

[0057] By collecting real-time voltage, current, and phase angle data, as well as future ambient temperature, humidity, and wind speed data, this invention comprehensively monitors the factors influencing line losses. Combined with a line loss prediction model, this improves the accuracy of line loss rate prediction. Based on the predicted line loss rate, it determines whether the transmission line requires automated adjustment, and automatically adjusts the lines that do. This invention can automatically adjust transmission lines with predicted line loss rates exceeding a threshold based on real-time data and prediction results, effectively reducing line loss rates, minimizing energy loss, lowering operating costs for power companies, increasing economic benefits, improving the overall efficiency and stability of the power grid, and ensuring power transmission and consumption safety. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of an intelligent security situation awareness and early warning system according to Embodiment 1 of the present invention;

[0059] Figure 2 This is a flowchart of a method for automatically adjusting transmission lines in response to persistent line loss anomalies, according to Embodiment 1 of the present invention.

[0060] Figure 3 This is a flowchart of a method for automatically adjusting transmission lines in response to continuous intermittent anomalies according to Embodiment 1 of the present invention.

[0061] Figure 4 This is a schematic diagram of an intelligent security situation awareness and early warning system according to Embodiment 2 of the present invention;

[0062] Figure 5 This is a flowchart of an intelligent security situation awareness and early warning method according to Embodiment 3 of the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Example 1

[0065] Please see Figure 1As shown in the figure, the intelligent security situation awareness and early warning system described in this embodiment includes a first acquisition module, a second acquisition module, a first processing module, a threshold prediction module, a line loss prediction module, a line loss diagnosis module, and a line loss adjustment module; the above modules are electrically connected to realize data transmission between the modules.

[0066] The first data acquisition module is used to collect key data and attributes of the transmission lines within a unit of time.

[0067] The key data of the line include phase angle, initial voltage value, final voltage value, line voltage, and line current; the phase angle is obtained through a phase measurement unit (PMU); a PMU is a device that can measure the phase angle of voltage and current simultaneously with high precision; the initial voltage value, final voltage value, line voltage, and line current are all obtained through corresponding sensors.

[0068] The initial voltage value is the starting voltage of the transmission line, and the final voltage value is the ending voltage of the transmission line. The initial and final voltage values ​​are collected only once per unit time. The line voltage includes the voltage collected from Z sampling points on the transmission line; the line current includes the current collected from Z sampling points on the transmission line. The line voltage and line current are collected H times per unit time.

[0069] The transmission line attributes include the transmission line material, resistivity of the material, radius, and length. These attributes are obtained through the power system's management system. The transmission line material includes copper and aluminum, among others. Resistivity is an inherent characteristic of the material; different materials have different resistivities, affecting the power loss of the transmission line. The longer the transmission line, the greater its impact on power loss.

[0070] The second acquisition module is used to acquire key environmental data for the next unit of time from the current unit of time. The key environmental data includes ambient temperature, ambient humidity, and ambient wind speed. The ambient temperature, ambient humidity, and ambient wind speed are respectively the ambient temperature, ambient humidity, and ambient wind speed of the environment where the transmission line is located. The ambient temperature, ambient humidity, and ambient wind speed are all obtained from meteorological stations.

[0071] It should be noted that wind speed affects the vibration of transmission lines. When transmission lines vibrate, they change the surrounding electric field distribution, leading to an increase in corona discharge. Corona discharge is a type of reactive power loss, which increases the energy loss during power transmission. Changes in the ambient temperature and humidity of transmission lines also affect their internal resistance, thus impacting energy loss during power transmission.

[0072] The first processing module is used to analyze and process key data of the line and key environmental data respectively to obtain transmission line data and line environmental data.

[0073] The transmission line data includes reactive power, line voltage difference, average line voltage, line power loss, and average line current; the line environment data includes average ambient temperature, average ambient humidity, and average ambient wind speed.

[0074] The method for calculating the line voltage difference is as follows:

[0075] VD = V start -V end ,

[0076] Where VD is the line voltage difference, V start Initial voltage value, V end Final voltage value.

[0077] The method for obtaining the average line voltage includes:

[0078] Establish a line voltage set by collecting voltages from Z sampling points per unit time; calculate the mean line voltage in the line voltage set; the specific method is as follows:

[0079]

[0080] It should be noted that, The average line voltage, V h It represents the h-th line voltage in the line voltage set; the line voltage set contains Z×H line voltages.

[0081] The average line current is obtained using the same method as described above for obtaining the average line voltage.

[0082] The method for obtaining the average ambient temperature includes:

[0083] Create an ambient temperature set based on ambient temperatures within a unit of time; calculate the mean ambient temperature in the set; the specific method is as follows.

[0084]

[0085] It should be noted that, WD is the average ambient temperature. m Let m be the ambient temperature in the m-th time period of the ambient temperature set; the ambient temperature set contains M ambient temperatures.

[0086] The average ambient humidity and average ambient wind speed are obtained using the same method as described above for obtaining the average ambient temperature.

[0087] The specific calculation method for the internal resistance of transmission lines is as follows:

[0088]

[0089] Where R is the internal resistance of the transmission line, δ is the resistivity of the line material, D is the length of the transmission line, and r is the radius of the transmission line.

[0090] The specific calculation method for the line power loss is as follows:

[0091]

[0092] Where PL represents line power loss. This represents the average line current.

[0093] The method for calculating reactive power includes:

[0094] Obtain the phase angle, denoted as φ;

[0095] Calculate the current power factor. The calculation method for the current power factor is as follows:

[0096] CPF = cos(φ).

[0097] Wherein, CPF is the current power factor.

[0098] Calculate the apparent power; the method for calculating the apparent power is as follows:

[0099]

[0100] Where S is the apparent power, This is the average line voltage. This represents the average line current.

[0101] Calculate the active power; the method for calculating the active power is as follows:

[0102]

[0103] Where P is the active power.

[0104] Calculate reactive power; the unit of reactive power is var (Var) or kilovar (kVar); the calculation method for reactive power is as follows:

[0105]

[0106] Where Q represents reactive power.

[0107] The threshold prediction module is used to input transmission line data, line environment data, and transmission line attributes into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold.

[0108] The training method for the threshold prediction model includes:

[0109] A threshold prediction dataset is pre-collected, comprising threshold prediction data and corresponding predicted line loss rate thresholds. The line loss prediction data includes transmission line data, line environment data, and transmission line attributes. The threshold prediction dataset is divided into a training set and a test set. A first classifier is constructed, using the threshold prediction data in the training set as input to the threshold prediction model and the predicted line loss rate thresholds in the training set as output. The first classifier is then trained to obtain an initial first classifier. The initial first classifier is tested using a test set, and the output first classifier that meets a preset accuracy is used as the threshold prediction model. The threshold prediction model is either a long short-term memory network model or a gradient boosting tree model.

[0110] It should be noted that the threshold for abnormal line loss rate varies for different transmission line attributes under different environments. Therefore, a threshold prediction model is adopted to predict the abnormal line loss rate threshold. This allows the line loss prediction model to more comprehensively and accurately reflect the actual operation of transmission lines when facing different actual operating environments. It also enables more reasonable and accurate determination of countermeasures for the predicted line loss rate, thus promoting the efficient and stable operation of the power grid.

[0111] Example table of predicted line loss rate thresholds is shown in Table 1.

[0112] Table 1 Example of Predicted Line Loss Rate Threshold

[0113]

[0114] The line loss prediction module is used to input transmission line data, line environment data and transmission line attributes into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit time, and divide the predicted line loss rate for the next unit time into a predicted line loss rate sequence according to a preset time window.

[0115] The training method for the line loss prediction model includes:

[0116] A line loss prediction dataset is pre-collected, comprising line loss prediction data and corresponding predicted line loss rates. The line loss prediction data includes transmission line data, line environment data, and transmission line attributes. The dataset is divided into a training set and a test set. The line loss prediction data in the training set is used as the input to the line loss prediction model, and the predicted line loss rates in the training set are used as the output. Minimizing the cross-entropy loss function is used as the optimization objective. An early-stop strategy is employed to monitor the performance on the validation set. By continuously adjusting the network parameters, training stops when the prediction accuracy on the test set reaches a prediction accuracy threshold. The line loss prediction model is an autoregressive model. For example, the prediction accuracy threshold can be set to 95% in this application.

[0117] The method for calculating the line loss rate is as follows:

[0118]

[0119] Where RATE is the line loss rate, E start E represents the starting point electrical energy of the transmission line. end The electrical energy is the terminal power of the transmission line; the electrical energy is obtained through an energy metering device.

[0120] It should be noted that the line loss rate is an indicator that measures the loss of electrical energy during power transmission. The direct loss of electrical energy is manifested as voltage drop and power loss. A high line loss rate means that the power company loses more electrical energy, thus causing more economic losses.

[0121] Transmission line data, line environment data, and transmission line attributes encompass the main factors affecting transmission line loss rates. The validity of these data lies in their collective description of different aspects influencing line loss rates. The absence of any one of these factors will lead to a lack of information in the line loss prediction model, affecting the accuracy and reliability of the prediction model.

[0122] For example, the line voltage difference represents the voltage drop across the two ends of a transmission line, directly affecting the line loss rate. The average line voltage and average line current are used to calculate apparent power, active power, and reactive power under actual operating conditions. Reactive power affects voltage stability, reflects the reactive power demand in the power system, and plays a crucial role in predicting the line loss rate. Line power loss is a direct measure of the line loss rate and a key parameter for predicting the target line loss rate. The absence of any one of these transmission line data will prevent the model from accurately reflecting the true operating state of the power system, thus reducing the accuracy of the line loss prediction model.

[0123] For example, temperature affects the resistivity of conductors, which in turn affects the line loss rate; humidity affects the surface characteristics of transmission lines, indirectly impacting the line loss rate; wind speed affects the cooling effect of transmission lines, thus affecting their temperature and resistance, and consequently, the line loss rate. Without this environmental data, the impact of environmental factors on the line loss rate cannot be accurately accounted for, thereby reducing the accuracy of line loss prediction models.

[0124] For example, material, resistivity, radius, and length are fundamental properties of transmission lines that directly affect their electrical performance and line loss rate. The absence of these fundamental properties leads to an incomplete consideration of line characteristics, thereby reducing the accuracy of line loss prediction models.

[0125] Example data for line loss prediction is shown in Table 2.

[0126] Table 2 Example of Line Loss Prediction Data

[0127]

[0128] The line loss diagnosis module determines the type of line loss rate anomaly based on the predicted line loss rate threshold and the predicted line loss rate sequence; the type of line loss rate anomaly includes persistent line loss anomaly and intermittent line loss anomaly.

[0129] The method for determining the abnormal type of line loss rate includes:

[0130] S100: Denote the number of predicted line loss rates in the predicted line loss rate sequence as NUM; let the initial value of num be 1, the value range of num is from 1 to NUM, and num is a loop variable; initialize the number of line loss rates exceeding the limit to 0;

[0131] S101: Obtain the num-th predicted line loss rate from the predicted line loss rate sequence. If the num-th predicted line loss rate is greater than the predicted line loss rate threshold, then subtract the num-th predicted line loss rate from the predicted line loss rate threshold to obtain the line loss rate exceeding the limit, and increment the number of line loss rate exceeding the limit by one. If the num-th predicted line loss rate is less than or equal to the predicted line loss rate threshold, then directly execute S102.

[0132] S102: Let num = num + 1. If num is less than or equal to NUM, return to S101 and continue execution. If num is greater than NUM, execute S103.

[0133] S103: Divide the number of line loss rate exceeding the limit by NUM to obtain the line loss rate exceeding the limit ratio; calculate the average line loss rate exceeding the limit based on all the line loss rate exceeding the limit values;

[0134] The system determines whether the line loss rate exceeds a preset threshold and whether the average line loss rate exceeds a preset threshold. If the conditions are met, the line loss rate anomaly type is classified as a continuous line loss anomaly; if the conditions are not met, the line loss rate anomaly type is classified as an intermittent line loss anomaly. For example, in this application, the line loss rate exceeding threshold is set to... Set the threshold for the line loss rate exceeding the average limit to 5.

[0135] The method for calculating the excessive line loss rate includes:

[0136] CXZ num =XSL num -YZ num

[0137] Among them, CXZ num XSL represents the line loss rate exceeding the limit corresponding to the num-th predicted line loss rate. num Let YZ be the num-th predicted line loss rate. num This is the threshold for predicting line loss rate.

[0138] The calculation method for the excess line loss rate includes:

[0139]

[0140] Wherein, CXBL is the percentage of line loss exceeding the limit, and CXSL is the number of line loss exceeding the limit.

[0141] The line loss adjustment module is used to automatically adjust the transmission line according to the abnormal type of line loss rate.

[0142] Methods for automating transmission line adjustments based on the type of line loss rate anomalies include:

[0143] Obtain the abnormal type of line loss rate;

[0144] If the abnormal line loss rate is of the type of continuous line loss abnormality, then the transmission line will be automatically adjusted for the continuous line loss abnormality.

[0145] If the abnormal line loss rate is of the intermittent line loss type, then the transmission line will be automatically adjusted for the intermittent line loss abnormality.

[0146] like Figure 2 As shown, methods for automatically adjusting transmission lines in response to persistent line loss anomalies include:

[0147] The power factor data is input into a pre-trained power factor model to obtain the target power factor; the power factor data includes the predicted line loss rate, key environmental data, and transmission line attributes.

[0148] Calculate the compensated reactive power; the calculation method for the compensated reactive power is as follows:

[0149] Q need =P×(tan(arccos(CPF))-tan(arccos(APF)))

[0150] Among them, Q need To compensate for reactive power, P is active power, CPF is the current power factor, APF is the target power factor, and the compensated reactive power is the reactive power that the transmission line needs to compensate.

[0151] Calculate the target voltage; the method for calculating the target voltage is as follows:

[0152]

[0153] Among them, V aim For the target voltage, DK is the average line voltage, and DK is the transmission line reactance.

[0154] Calculate the target current; the method for calculating the target current is as follows:

[0155]

[0156] Among them, I aim The target current.

[0157] At the end of the current unit of time, in the next unit of time, the calculated reactive power is compensated using reactive power compensation equipment; the voltage is adjusted to the target voltage using a voltage regulator, and the current is adjusted to the target current using a current regulator. The reactive power compensation equipment includes a static var compensator (SVC) or a static synchronous compensator (STATCOM).

[0158] It should be noted that the line loss rate of transmission lines reflects the proportion of electricity lost during transmission from a power plant. An excessively high line loss rate not only affects the economic efficiency of the power grid but also endangers transmission safety and electricity consumption safety.

[0159] Excessive line loss rate can lead to a significant drop in voltage at the end of the transmission line, affecting the stability of the transmission system. Low voltage can cause equipment to malfunction and trigger large-scale power supply failures.

[0160] High line loss rates can alter the power balance of a power system, leading to power system oscillations or even instability, which in turn can cause large-scale faults in transmission lines, affecting the entire power network.

[0161] High line loss rates increase the current in the line, putting end-user equipment at risk of overload, which can lead to shortened equipment life, frequent failures, and even safety accidents, thus affecting residents' lives, business and industrial activities.

[0162] By adaptively adjusting line losses, the line loss rate can be effectively reduced, thereby ensuring the economy of the power grid, as well as the safety of power transmission and consumption.

[0163] The training method for the power factor model includes:

[0164] A power factor dataset is pre-collected, comprising power factor data and corresponding target power factors, the target power factors being evaluated by power system experts. The power factor dataset is divided into a training set and a test set. A second classifier is constructed, using the power factor data from the training set as input to the power factor model and the target power factors from the training set as output. The second classifier is then trained to obtain an initial second classifier. The initial second classifier is tested using a test set, and the output second classifier that meets a preset accuracy is used as the power factor model. The power factor model is a Long Short-Term Memory (LSTM) network model.

[0165] It is important to note that predicting line loss rates, key environmental data, and transmission line attributes are all crucial for accurately predicting and adjusting the power factor of transmission lines. The absence of any one of these features will prevent the power factor model from fully reflecting the actual situation, thereby reducing the accuracy of predictions and the effectiveness of adjustments. Ensuring the completeness and comprehensiveness of data is a vital prerequisite for achieving efficient power grid management and optimization. For example, the lack of predicted line loss rates makes it impossible to assess losses, thus affecting power factor prediction and adjustment; the lack of key environmental data makes it impossible to assess the impact of environmental data on the power factor, thus affecting power factor prediction and adjustment; and the lack of transmission line attributes makes it impossible to assess the impact of the transmission line's own characteristics on the power factor, thus affecting power factor prediction and adjustment.

[0166] The calculation method for the reactance of the transmission line includes:

[0167] Calculate the inductance of the transmission line; the formula for calculating the inductance of the transmission line is:

[0168]

[0169] Where L is the inductance of the transmission line, D is the length of the transmission line, and r is the radius of the transmission line.

[0170] The inductive reactance of the transmission line is calculated using the following formula:

[0171] GK = 2πfL;

[0172] Where GK is the inductive reactance of the transmission line, and f is the frequency of the transmission line.

[0173] The capacitance of a transmission line is calculated using the following formula:

[0174]

[0175] Where C is the transmission line capacitance and ε is the dielectric constant, typically 8.854 × 10⁻⁶. -12 The unit is F / m.

[0176] The capacitive reactance of the transmission line is calculated using the following formula:

[0177]

[0178] RK represents capacitive reactance.

[0179] The reactance of the transmission line is calculated using the following formula:

[0180] DK = GK - RK;

[0181] Where DK is the reactance of the transmission line.

[0182] It should be noted that when transmission lines require automated regulation, it is usually due to environmental factors that lead to increased line loss rates. Line losses can be reduced by compensating for reactive power and adjusting voltage and current. When reactive power compensation equipment adjusts the reactive power in the transmission line, the power factor changes accordingly, ultimately reaching the target power factor. When the voltage is increased, the current decreases accordingly; as can be seen from the formula for calculating line power loss, power loss is thus reduced.

[0183] For example, assuming the active power is 1000kW, the average line voltage is 10kV, the transmission line reactance is 0.1Ω, the current power factor is 0.8, and the target power factor is 0.85;

[0184] The reactive power that needs to be compensated is:

[0185] Q need =1000×(tan(arccos(0.8))-tan(arccos(0.85)))=130.23kVar

[0186] The target voltage is:

[0187]

[0188] The target current is:

[0189]

[0190] Methods for automatically regulating transmission lines in response to intermittent line loss anomalies include:

[0191] Intermittent line loss anomalies are classified and determined based on the predicted line loss rate sequence to obtain the intermittent anomaly type; the intermittent anomaly type includes continuous intermittent anomalies and discrete intermittent anomalies;

[0192] If the intermittent anomaly type is a discrete intermittent anomaly, no processing is required;

[0193] If the intermittent anomaly type is a continuous intermittent anomaly, then the transmission line is automatically adjusted for the continuous intermittent anomaly.

[0194] The method for determining the type of intermittent abnormality includes:

[0195] Mark the time points when the line loss rate exceeds the limit in the predicted line loss rate sequence. The time points when the line loss rate exceeds the limit refer to the time points when the predicted line loss rate is greater than the predicted line loss rate threshold.

[0196] Count the time intervals between all adjacent time points when the line loss rate exceeds the limit, and calculate the average time interval based on all time intervals; count the maximum number of consecutive occurrences of time points when the line loss rate exceeds the limit, and record it as the first duration.

[0197] If the average time interval is less than the preset average time interval threshold, and the first duration is greater than the preset first duration threshold, then the intermittent line loss anomaly will be further determined as a continuous intermittent anomaly.

[0198] If the judgment conditions corresponding to continuous intermittent anomalies are not met, then the intermittent line loss anomaly will be further judged as a discrete intermittent anomaly.

[0199] It should be noted that the average time interval threshold and the first duration threshold are preset parameters that can be adjusted based on historical operating data or simulation results. For example, in the embodiments of this application, the average time interval threshold can be set to two sampling periods. For instance, when the sampling period is 5 minutes, the corresponding average time interval threshold is 10 minutes. The first duration threshold can be set to 3 times, meaning that when the number of consecutive time points where the predicted line loss rate exceeds the limit exceeds 3 times, the continuous segment is considered to have sufficient continuity. For example, if the average time interval between the time points where the line loss rate exceeds the limit in the predicted line loss rate sequence is 8 minutes, and the maximum number of consecutive exceedances is 4 times, then the conditions of an average time interval less than 10 minutes and a first duration greater than 3 times are met, and it is determined to be a continuous intermittent anomaly. Conversely, if the average time interval is 12 minutes or the maximum number of consecutive exceedances is 2 times, it is determined to be a discrete intermittent anomaly.

[0200] like Figure 3 As shown, methods for automatically regulating transmission lines in response to continuous intermittent anomalies include:

[0201] Obtain the first duration number corresponding to the continuous intermittent anomaly, and record the predicted line loss rate of each time point covered by the first duration number as the first predicted line loss rate. Construct all the first predicted line loss rates into a first predicted line loss rate sequence.

[0202] The first predicted line loss rate sequence is time-series aligned with the transmission line data to obtain the first transmission line data; the first predicted line loss rate sequence is time-series aligned with the line environment data to obtain the first line environment data.

[0203] The first predicted line loss rate sequence, the first transmission line data, the first line environment data, and the transmission line attributes are input into the parameter setting model to obtain a set of adjustment parameters; the set of adjustment parameters includes the first compensated reactive power, the first target voltage, and the first target current;

[0204] CK time windows before the start time of the first predicted line loss rate sequence, the set of adjustment parameters is sent to the corresponding device for adaptive adjustment; CK is the preset number of time windows. For example, in this application, CK is set to 4.

[0205] The training method for the parameter setting model includes:

[0206] A parameter setting dataset is pre-constructed, which includes MX sets of parameter setting data and a set of adjustment parameters corresponding to the MX sets of parameter setting data, where MX is a positive integer; the parameter setting data includes a first predicted line loss rate sequence, first transmission line data, first line environment data, and transmission line attributes; the parameter setting dataset is divided into a training set and a validation set, the training set is used for parameter learning of the parameter setting model, and the validation set is used for real-time monitoring of the generalization performance and overfitting degree of the parameter setting model;

[0207] A deep neural network with a multilayer perceptron as its core is used as the parameter setting model. The parameter setting data is standardized and vectorized before being input into the deep neural network, which consists of an input layer, hidden layers, and an output layer. Each hidden layer uses a non-linear activation function to extract features, and the output layer uses a softmax activation function to obtain the probability distribution corresponding to each set of adjustment parameters. Finally, the set of adjustment parameters corresponding to the highest probability is taken as the prediction result of the parameter setting model. During training, the cross-entropy loss function is used as the optimization objective, and a gradient descent-type optimization algorithm is used to update the network weights. An early stopping strategy is implemented: when the prediction accuracy on the validation set reaches or exceeds the prediction accuracy threshold, the ventilation path priority evaluation model is considered to have converged and training is terminated. For example, the prediction accuracy threshold can be set to 95% in this application.

[0208] It should be noted that in this invention, intermittent line loss anomalies are further divided into continuous intermittent anomalies and discrete intermittent anomalies. This allows for the matching of differentiated adjustment strategies to different anomaly characteristics, thereby improving the targeting and effectiveness of the adjustment. Specifically, continuous intermittent anomalies are typically characterized by the predicted line loss rate continuously exceeding limits within a certain time window for a long duration. They are often related to the phased changes in the operating status of transmission lines or continuous interference from the external environment. If such anomalies are not handled in a timely manner, they may cause significant energy loss and equipment operation risks during the anomaly's duration. Therefore, it is necessary to calculate the adjustment parameters in advance and issue them in a timely manner before the anomaly occurs to achieve proactive intervention. Discrete intermittent anomalies, on the other hand, are characterized by the predicted line loss rate exceeding the limit being scattered along the time axis, with a short duration for each occurrence and a long interval between occurrences. They are mostly caused by transient disturbances or occasional events. Such anomalies have a smaller impact on the overall operation of the system. If the adjustment mode of continuous anomalies is directly adopted, it may lead to frequent start-ups and shutdowns of equipment, increased number of operations, and wear and tear. This application, through this further division, enables the regulation process to perform compensation regulation quickly and accurately in continuous intermittent anomaly scenarios, while avoiding unnecessary actions in discrete intermittent anomaly scenarios. Thus, while ensuring the safe and stable operation of transmission lines, it also takes into account the economy of regulation and equipment lifespan, demonstrating the adaptive and refined advantages of this application in automated regulation strategies.

[0209] Example 2

[0210] Please see Figure 4 As shown, this embodiment provides an intelligent security situation awareness and early warning system, which also includes:

[0211] The power acquisition module is used to collect the starting power and ending power of a power transmission line within a unit of time after the power transmission line that requires automatic adjustment has been automatically adjusted; the power is acquired through power metering equipment.

[0212] The line loss calculation module is used to calculate the line loss rate after automatic adjustment based on the starting and ending electrical energy.

[0213] The method for calculating the line loss rate after automatic adjustment is as follows:

[0214]

[0215] Where XSL is the line loss rate after automatic adjustment, and E qd As the starting point of electrical energy, E zd The final electrical energy.

[0216] The adjustment and diagnosis module is used to compare the line loss rate after automatic adjustment with the predicted line loss rate threshold. If the line loss rate after automatic adjustment is less than or equal to the predicted line loss rate threshold, the automatic adjustment is successful; otherwise, the automatic adjustment fails, fault diagnosis is performed to obtain the fault type, and the fault type is reported.

[0217] The method for obtaining the fault type through fault diagnosis includes: inputting transmission line data and transmission line attributes into the fault diagnosis model to obtain fault diagnosis values, and matching the fault diagnosis values ​​with the fault diagnosis value-fault type mapping table to obtain the specific fault type.

[0218] For example, the fault diagnosis value-fault type mapping table is shown in Table 3.

[0219] Table 3 Fault Diagnosis Values ​​- Fault Type Mapping Table

[0220] 1 abnormal line impedance 2 Grounding fault 3 Phase-to-phase short circuit fault

[0221] The training method for the fault diagnosis model includes:

[0222] A fault diagnosis dataset is pre-collected, comprising fault diagnosis data and corresponding fault diagnosis values. The fault diagnosis data includes transmission line data and transmission line attributes. The dataset is divided into a training set and a test set. The fault diagnosis data in the training set is used as the input to the fault diagnosis model, and the fault diagnosis values ​​in the training set are used as the output. Minimizing the cross-entropy loss function is used as the optimization objective. An early stopping strategy is employed to monitor the performance on the validation set. By continuously adjusting the network parameters, training stops when the prediction accuracy on the test set reaches a prediction accuracy threshold. The fault diagnosis model is either a decision tree model or a random forest model.

[0223] Example 3

[0224] Please see Figure 5 As shown, this embodiment provides an intelligent security situation awareness and early warning method, including:

[0225] Collect key data and attributes of transmission lines per unit time.

[0226] Collect key environmental data for the next unit of time from the current unit of time;

[0227] The key data of the transmission line and the key data of the environment are analyzed and processed separately to obtain transmission line data and line environment data.

[0228] Transmission line data, line environment data, and transmission line attributes are input into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit of time.

[0229] Transmission line data, line environment data, and transmission line attributes are input into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold for the next unit of time.

[0230] Determine whether the transmission line needs automatic adjustment based on the predicted line loss rate and the predicted line loss threshold;

[0231] For transmission lines that require automated regulation, implement automated regulation.

[0232] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0233] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent security situation awareness and early warning, characterized in that, include: Collect key data and attributes of transmission lines per unit time. Collect key environmental data for the next unit of time from the current unit of time; The key data of the transmission line and the key data of the environment are analyzed and processed separately to obtain transmission line data and line environment data. Transmission line data, line environment data, and transmission line attributes are input into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold. Transmission line data, line environment data, and transmission line attributes are input into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit time. The predicted line loss rate for the next unit time is then divided into a predicted line loss rate sequence according to a preset time window. The type of line loss rate anomaly is determined based on the predicted line loss rate threshold and the predicted line loss rate sequence; the type of line loss rate anomaly includes persistent line loss anomaly and intermittent line loss anomaly. Automated adjustment of transmission lines based on the type of abnormal line loss rate; The above-mentioned methods for determining abnormal line loss rates include: S100: Denote the number of predicted line loss rates in the predicted line loss rate sequence as NUM; let the initial value of num be 1, the value range of num is from 1 to NUM, and num is a loop variable; initialize the number of line loss rates exceeding the limit to 0; S101: Obtain the num-th predicted line loss rate from the predicted line loss rate sequence. If the num-th predicted line loss rate is greater than the predicted line loss rate threshold, then subtract the num-th predicted line loss rate from the predicted line loss rate threshold to obtain the line loss rate exceeding the limit, and increment the number of line loss rate exceeding the limit by one. If the num-th predicted line loss rate is less than or equal to the predicted line loss rate threshold, then directly execute S102. S102: Let num = num + 1. If num is less than or equal to NUM, return to S101 and continue execution. If num is greater than NUM, execute S103. S103: Divide the number of line loss rate exceeding the limit by NUM to obtain the line loss rate exceeding the limit ratio; calculate the average line loss rate exceeding the limit based on all the line loss rate exceeding the limit values; Determine whether the line loss rate exceeds the preset threshold and the average line loss rate exceeds the preset threshold. If the conditions are met, the line loss rate anomaly type is determined to be a continuous line loss anomaly. If the conditions are not met, the line loss rate anomaly type is determined to be an intermittent line loss anomaly.

2. The intelligent security situation awareness and early warning method according to claim 1, characterized in that, Methods for automating transmission line adjustments based on the type of line loss rate anomalies include: Obtain the abnormal type of line loss rate; If the abnormal line loss rate is of the type of continuous line loss abnormality, then the transmission line will be automatically adjusted for the continuous line loss abnormality. If the abnormal line loss rate is of the intermittent line loss type, then the transmission line will be automatically adjusted for the intermittent line loss abnormality.

3. The intelligent security situation awareness and early warning method according to claim 2, characterized in that, Methods for automatically adjusting transmission lines in response to persistent line loss anomalies include: The power factor data is input into a pre-trained power factor model to obtain the target power factor; the power factor data includes the predicted line loss rate, key environmental data, and transmission line attributes. Calculate the reactive power compensation based on the target power factor, active power, and current power factor; The target voltage is calculated based on the compensation reactive power, transmission line reactance, and average line voltage. Calculate the target current based on the active power, target voltage, and target power factor; At the end of the current unit of time, in the next unit of time, the calculated reactive power is compensated using reactive power compensation equipment; the voltage is adjusted to the target voltage using a voltage regulator, and the current is adjusted to the target current using a current regulator.

4. The intelligent security situation awareness and early warning method according to claim 2, characterized in that, Methods for automatically regulating transmission lines in response to intermittent line loss anomalies include: Intermittent line loss anomalies are classified and determined based on the predicted line loss rate sequence to obtain the intermittent anomaly type; the intermittent anomaly type includes continuous intermittent anomalies and discrete intermittent anomalies; If the intermittent anomaly type is a discrete intermittent anomaly, no processing is required; If the intermittent anomaly type is a continuous intermittent anomaly, then the transmission line is automatically adjusted for the continuous intermittent anomaly.

5. The intelligent security situation awareness and early warning method according to claim 4, characterized in that, The method for determining the type of intermittent abnormality includes: Mark the time points when the line loss rate exceeds the limit in the predicted line loss rate sequence. The time points when the line loss rate exceeds the limit refer to the time points when the predicted line loss rate is greater than the predicted line loss rate threshold. Count the time intervals between all adjacent time points when the line loss rate exceeds the limit, and calculate the average time interval based on all time intervals; count the maximum number of consecutive occurrences of time points when the line loss rate exceeds the limit, and record it as the first duration. If the average time interval is less than the preset average time interval threshold, and the first duration is greater than the preset first duration threshold, then the intermittent line loss anomaly will be further determined as a continuous intermittent anomaly. If the judgment conditions corresponding to continuous intermittent anomalies are not met, then the intermittent line loss anomaly will be further judged as a discrete intermittent anomaly.

6. The intelligent security situation awareness and early warning method according to claim 4, characterized in that, Methods for automating the regulation of transmission lines in response to continuous intermittent anomalies include: Obtain the first duration number corresponding to the continuous intermittent anomaly, and record the predicted line loss rate of each time point covered by the first duration number as the first predicted line loss rate. Construct all the first predicted line loss rates into a first predicted line loss rate sequence. The first predicted line loss rate sequence is time-series aligned with the transmission line data to obtain the first transmission line data; the first predicted line loss rate sequence is time-series aligned with the line environment data to obtain the first line environment data. The first predicted line loss rate sequence, the first transmission line data, the first line environment data, and the transmission line attributes are input into the parameter setting model to obtain a set of adjustment parameters; the set of adjustment parameters includes the first compensated reactive power, the first target voltage, and the first target current; CK time windows before the start time of the first predicted line loss rate sequence, the set of adjustment parameters is sent to the corresponding equipment for adaptive adjustment; CK is the preset number of time windows.

7. The intelligent security situation awareness and early warning method according to claim 1, characterized in that, The key data for the line include phase angle, initial voltage value, final voltage value, line voltage, and line current; The transmission line attributes include the transmission line material, the resistivity of the material, the transmission line radius, and the transmission line length; the key environmental data include ambient temperature, ambient humidity, and ambient wind speed.

8. The intelligent security situation awareness and early warning method according to claim 1, characterized in that, The transmission line data includes reactive power, line voltage difference, average line voltage, line power loss, and average line current; the line environment data includes average ambient temperature, average ambient humidity, and average ambient wind speed.

9. An intelligent security situation awareness and early warning system, implementing the intelligent security situation awareness and early warning method according to any one of claims 1-8, characterized in that, include: The first acquisition module is used to collect key data and attributes of the transmission lines within a unit of time. The second acquisition module is used to acquire key environmental data for the next unit of time from the current unit of time. The first processing module is used to analyze and process the key data of the line and the key data of the environment respectively to obtain the transmission line data and the line environment data. The threshold prediction module is used to input transmission line data, line environment data, and transmission line attributes into a pre-trained threshold prediction model to obtain the predicted line loss rate threshold. The line loss prediction module is used to input transmission line data, line environment data and transmission line attributes into a pre-trained line loss prediction model to obtain the predicted line loss rate for the next unit time, and to divide the predicted line loss rate for the next unit time into a predicted line loss rate sequence according to a preset time window. The line loss diagnosis module determines the type of line loss rate anomaly based on the predicted line loss rate threshold and the predicted line loss rate sequence; the type of line loss rate anomaly includes persistent line loss anomaly and intermittent line loss anomaly. The line loss adjustment module is used to automatically adjust the transmission line according to the abnormal type of line loss rate.

Images