Power distribution network fault detection method and device, computer device and storage medium

Abstract

The application relates to the technical field of power grid power, and discloses a power distribution network fault detection method and device, computer equipment and a storage medium. The method comprises the following steps: collecting power grid data of each target node in a distributed power distribution network system in real time through a pre-deployed sensor, and preprocessing the power grid data to obtain preprocessed power grid data; calculating corresponding voltage fluctuation characteristic values according to voltage fluctuation signals of each access node through a pre-constructed voltage fluctuation characteristic model; calculating a net power balance value of the distributed power distribution network system according to the preprocessed power grid data of each target node and the voltage fluctuation characteristic values of each access node through a pre-constructed generalized steady-state interaction model; judging whether the net power balance value is within a preset normal threshold range; if not, it is determined that the distributed power distribution network system has a fault; and thus intelligent detection of the fault of the distributed power distribution network system is realized, and the accuracy and reliability of fault detection are improved.

Description

Technical Field

[0001] This invention relates to the field of power grid technology, and in particular to a method, device, computer equipment, and storage medium for detecting faults in distribution networks. Background Technology

[0002] Driven by the rapid rise in global energy demand and the increasing prevalence of renewable energy, the complexity and scale of modern power distribution networks continue to expand, prompting traditional power systems to accelerate their transformation towards intelligence and automation. Against this backdrop, fault detection technology, as a core element in ensuring the reliable operation and stable supply of power systems, has attracted widespread attention from the industry.

[0003] Fault detection in power systems primarily relies on traditional methods such as current and voltage protection devices. However, when faced with large-scale and complex fault scenarios, these traditional methods reveal limitations such as insufficient sensitivity and response lag, making it difficult to meet the demands of modern power grids for efficient and accurate fault detection. Summary of the Invention

[0004] Based on this, it is necessary to address the inefficiency and slow response of existing traditional power distribution network fault detection methods by proposing a power distribution network fault detection method, device, computer equipment, and storage medium.

[0005] A first aspect of the present invention provides a method for detecting faults in a power distribution network, the method comprising:

[0006] The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0007] By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0008] The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0009] Determine whether the net power balance value is within a preset normal threshold range;

[0010] If not, then the distributed power distribution system is determined to have malfunctioned.

[0011] Furthermore, after the step of determining that a fault has occurred in the distributed distribution network system, the method further includes:

[0012] The voltage fluctuation signals of each load node are input into the voltage fluctuation feature model, and the voltage fluctuation feature values ​​corresponding to each load node are output.

[0013] Determine whether the voltage fluctuation characteristic value of each target node exceeds the preset voltage fluctuation threshold.

[0014] If so, the target node that exceeds the preset voltage fluctuation threshold will be regarded as a potential fault node;

[0015] A traveling wave signal is injected into the potential fault node at the current measurement point using the traveling wave injection method;

[0016] Measure the propagation speed of the traveling wave signal and the time difference between the transmission and return of the traveling wave signal;

[0017] The distance between the potential fault node and the current measurement point is calculated based on the propagation speed and the time difference.

[0018] Based on the distance, the location of the potential fault point is determined.

[0019] Furthermore, after determining the location of the potential fault point based on the distance, the method further includes:

[0020] An operation report is generated, which includes the preprocessed power grid data, voltage fluctuation characteristics, and the location of the potential fault points.

[0021] Further, the step of calculating the voltage fluctuation characteristic value corresponding to each of the access nodes based on the voltage fluctuation signal of each access node using a pre-constructed voltage fluctuation characteristic model includes:

[0022] Selected voltage fluctuation signals within a preset frequency band are extracted from each of the voltage fluctuation signals;

[0023] Analyze and extract the spectral parameters of the selected voltage fluctuation signal, including the voltage peak location, voltage amplitude, voltage phase, and corresponding time point;

[0024] Determine whether the change in at least one of the spectral parameters exceeds a preset change threshold;

[0025] If so, the corresponding voltage fluctuation characteristic value is calculated based on the voltage amplitude of the selected voltage fluctuation signal using a pre-constructed voltage fluctuation characteristic model.

[0026] Furthermore, the pre-constructed voltage fluctuation characteristic model is expressed as:

[0027]

[0028] Among them, V s,i (t) represents the voltage amplitude of the voltage fluctuation signal of the i-th access node at time point t, α i and β i These are the parameters for adjusting the response sensitivity, F(V) s,i (t) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t.

[0029] Further, the step of calculating the net power balance value of the distributed distribution network system based on the pre-constructed generalized steady-state interaction model, according to the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node, includes:

[0030] The actual output power A(t) of the access node at time point t is calculated using the output power calculation formula, which is:

[0031]

[0032] Where F(Vs,i(t)) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. λ represents the natural decay of the output power of the i-th access node with time t. i Let P be the attenuation coefficient of the i-th distributed power access node. s,i (t) represents the output power of the i-th access node at time t, and m is the total number of access nodes;

[0033] The actual power consumption B(t) of the load node at time point t is calculated using the power consumption calculation formula, which is:

[0034]

[0035] Among them, I l,j (t) represents the current value of the j-th load node at time t, k j Let be the current response sensitivity of the j-th load node. Let V be the hyperbolic tangent function in a nonlinear function, where τ is the integration variable and V is the integrator. l,j (τ) represents the voltage value of the load node in the time integral variable τ, dτ represents the small change in the integral variable, and γ j P is the hysteresis coefficient of the load node to voltage fluctuations. l,j (t) represents the power consumed by the j-th load node at time t, and n is the total number of load nodes;

[0036] The net power balance value P of the distributed distribution network system at time point t is calculated using a pre-constructed generalized steady-state interaction model. s,l (t), represented as:

[0037]

[0038] Where T is the entire time interval and dt is the time increment.

[0039] Furthermore, in the step of determining whether the net power balance value is within the preset normal threshold range, the preset normal threshold range is greater than or equal to 0.

[0040] A second aspect of the present invention provides a power distribution network fault detection device, the device comprising:

[0041] The power grid data acquisition module is used to collect power grid data from various target nodes in a distributed distribution network system in real time through pre-deployed sensors, and to preprocess the power grid data to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals;

[0042] The voltage fluctuation feature calculation module is used to calculate the voltage fluctuation feature value corresponding to each of the access nodes based on the voltage fluctuation signal of each access node through a pre-constructed voltage fluctuation feature model.

[0043] The net power balance value calculation module is used to calculate the net power balance value of the distributed distribution network system based on the preprocessed grid data of each target node and the voltage fluctuation characteristic value of each access node through a pre-built generalized steady-state interaction model.

[0044] The first judgment module is used to determine whether the net power balance value is within a preset normal threshold range;

[0045] The fault determination module is used to determine that the distributed power distribution system has failed if the fault is not within the preset normal threshold range.

[0046] A third aspect of the invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0047] The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0048] By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0049] The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0050] Determine whether the net power balance value is within a preset normal threshold range;

[0051] If not, then the distributed power distribution system is determined to have malfunctioned.

[0052] A fourth aspect of the present invention provides a computer device including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0053] The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0054] By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0055] The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0056] Determine whether the net power balance value is within a preset normal threshold range;

[0057] If not, then the distributed power distribution system is determined to have malfunctioned.

[0058] This invention utilizes pre-deployed sensors to collect real-time grid data from various target nodes in a distributed distribution network system. This data is pre-processed to obtain pre-processed grid data. A pre-built voltage fluctuation characteristic model is then used to calculate voltage fluctuation characteristic values ​​corresponding to each access node based on its voltage fluctuation signals. Furthermore, a pre-built generalized steady-state interaction model is used to calculate the net power balance value of the distributed distribution network system based on the pre-processed grid data from each target node and the voltage fluctuation characteristic values ​​from each access node. If the net power balance value is not within a preset normal threshold range, a fault is determined to have occurred in the distributed distribution network system. This achieves intelligent fault detection in the distributed distribution network system, improving the accuracy and reliability of fault detection, reducing reliance on manual intervention, and significantly increasing detection efficiency. Simultaneously, by monitoring and analyzing grid data in real time, potential faults can be promptly identified and addressed, effectively ensuring the safe and stable operation of the distribution network system. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] in:

[0061] Figure 1 This is an application environment diagram of a power distribution network fault detection method in one embodiment;

[0062] Figure 2 Here is a flowchart of a power distribution network fault detection method in one embodiment;

[0063] Figure 3 This is a structural block diagram of a power distribution network fault detection device in one embodiment;

[0064] Figure 4 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0065] 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.

[0066] Figure 1 This is a diagram illustrating the application environment of a power distribution network fault detection method in one embodiment. (Refer to...) Figure 1 This distribution network fault detection method is applied to a distribution network fault detection system. The system includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal; a mobile terminal can be at least one of a mobile phone, tablet, or laptop. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to collect power grid data from various target nodes in the distributed distribution network system, and the server 120 is used to analyze the power grid data according to the distribution network fault detection method.

[0067] like Figure 2 As shown, in one embodiment, a method for detecting power distribution network faults is provided. This method can be applied to both terminals and servers; this embodiment uses terminal application as an example. The power distribution network fault detection method specifically includes the following steps:

[0068] S1: Real-time acquisition of power grid data from various target nodes in the distributed power distribution network system through pre-deployed sensors, and preprocessing of the power grid data to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals;

[0069] S2: Using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0070] S3: Using a pre-constructed generalized steady-state interaction model, the net power balance value of the distributed distribution network system is calculated based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0071] S4: Determine whether the net power balance value is within a preset normal threshold range;

[0072] S5: If not, then the distributed power distribution network system is determined to have a fault.

[0073] In this embodiment, a power distribution network fault refers to a physical state that prevents power distribution equipment (components) from operating normally as required. Power distribution network faults are generally categorized into line faults, equipment faults, faults caused by natural disasters, and faults caused by human factors. Furthermore, power distribution line faults are generally classified into three types: single-phase grounding, phase-to-phase short circuits, and grounding-to-phase short circuits. Specifically, these include phase-to-phase short circuits caused by foreign objects, bird strikes, and lightning strikes. These fault types each have their own characteristics; for example, single-phase grounding faults are relatively difficult to locate, while phase-to-phase short circuit faults may be caused by foreign objects, lightning strikes, or reduced equipment insulation.

[0074] In step S1 above, the distributed distribution network system includes multiple target nodes, which are further divided into access nodes and load nodes. Access nodes are nodes connected to distributed power sources in the distributed distribution network system, thereby providing power to the system. Load nodes are nodes connected to loads in the power grid system; each electrical device can be considered a load node, which consumes electrical energy within the system. High-frequency sensors are deployed at each access node and load node in the distributed distribution network system to collect real-time power grid data, such as voltage and current. This data is preprocessed to remove noise and fill in missing values, resulting in preprocessed power grid data. High-frequency sensors can collect and process voltage and current fluctuation signals in real time, ensuring the capture of short-term, high-frequency transient waveforms and harmonic interference. Through high-frequency sampling, common fault types in the power grid system can be accurately detected, facilitating precise judgment of fault type and severity, and significantly improving the sensitivity and accuracy of fault detection.

[0075] In step S2 above, the voltage fluctuation signal of the access node of the distributed distribution network system is analyzed by using discrete Fourier transform. The calculated voltage fluctuation characteristic value is used to intuitively understand the voltage change of the access node in the distributed distribution network system, and is used for subsequent steps to determine the existence of faults.

[0076] In steps S3-S5 above, the net power balance value is used to assess the overall operating status of the distributed distribution network system. When a fault occurs in the distributed distribution network system, the net power balance value can quickly reflect the existence of power imbalance, thereby quickly identifying the fault in the distribution network system.

[0077] This embodiment achieves intelligent fault detection in distributed distribution network systems through the above steps, improving the accuracy and reliability of fault detection, reducing reliance on manual intervention, and significantly increasing detection efficiency. Simultaneously, by monitoring and analyzing power grid data in real time, potential faults can be promptly identified and addressed, effectively ensuring the safe and stable operation of the distribution network system.

[0078] In one specific embodiment, after step S5 of determining that a fault has occurred in the distributed distribution network system, the method further includes:

[0079] S6: Input the voltage fluctuation signal of each load node into the voltage fluctuation feature model respectively, and output the voltage fluctuation feature value corresponding to each load node.

[0080] S7: Determine whether the voltage fluctuation characteristic value of each target node exceeds the preset voltage fluctuation threshold;

[0081] S8: If so, the target node that exceeds the preset voltage fluctuation threshold is regarded as a potential fault node;

[0082] S9: Inject a traveling wave signal into the potential fault node at the current measurement point using the traveling wave injection method;

[0083] S10: Measure the propagation speed of the traveling wave signal and the time difference between the transmission and return of the traveling wave signal;

[0084] S11: Calculate the distance between the potential fault node and the current measurement point based on the propagation speed and the time difference;

[0085] S12: Determine the location of the potential fault point based on the distance.

[0086] In this embodiment, in the event of a fault in the distributed distribution network system, the voltage fluctuations of all nodes are further examined to determine the location of the fault.

[0087] In step S6 above, the same method as in step S2 is used to perform spectral analysis on the voltage fluctuation signals of each load node in the distributed distribution network system by using discrete Fourier transform.

[0088] In steps S7-S8 above, the preset voltage fluctuation threshold can be set by those skilled in the art based on the normal operation experience of the distribution network and voltage fluctuation standards. By comparing the voltage fluctuation characteristics of each target node with the preset voltage fluctuation threshold, potential faulty nodes are initially screened out.

[0089] In steps S9-S12 above, the traveling wave injection method is a high-precision technology for fault location in power distribution network systems. It utilizes the propagation characteristics of electromagnetic waves in power lines to determine the location of the fault point by injecting a traveling wave signal after a fault occurs and measuring the propagation time and speed of the signal.

[0090] The traveling wave injection method is used to inject a traveling wave signal from the current measurement point to the potential fault node. The propagation speed and time difference of the traveling wave signal are measured, the distance between the potential fault point and the measurement point is calculated, and the location of the potential fault point is determined. The specific formula is as follows:

[0091] D = v·s

[0092] Where D is the distance between the potential fault point and the current measurement point, v is the propagation speed of the traveling wave signal, and s is the time difference of the traveling wave signal propagation.

[0093] Based on the distance between the potential fault point and the current measurement point, combined with the topology of the distribution network system and known distance information, the specific location of the potential fault point can be determined.

[0094] In one specific embodiment, after step S12 of determining the location of the potential fault point based on the distance, the method further includes:

[0095] S13: Generate an operation report, which includes the preprocessed power grid data, voltage fluctuation characteristic values, and the location of the potential fault point.

[0096] In this embodiment, data is recorded and backed up periodically to generate operation reports. Specifically, after the potential fault point is located, all data during the detection process is recorded in the database. The recorded data includes preprocessed power grid data, voltage fluctuation characteristic values, and the location of potential fault points. The data is backed up periodically, and periodic operation reports are generated based on the operation status of the distribution network. This helps to continuously monitor and improve the power grid operation status, thereby improving the efficiency and reliability of power grid management.

[0097] In one specific embodiment, step S2, which calculates the voltage fluctuation characteristic value corresponding to each of the access nodes based on the voltage fluctuation signal of each access node using a pre-constructed voltage fluctuation characteristic model, includes:

[0098] S201. Extract selected voltage fluctuation signals within a preset frequency band from each of the voltage fluctuation signals;

[0099] S202. Analyze and extract the spectral parameters of the selected voltage fluctuation signal, wherein the spectral parameters include the voltage peak position, voltage amplitude, voltage phase and corresponding time point;

[0100] S203. Determine whether the change of at least one of the spectral parameters exceeds a preset change threshold;

[0101] S204. If so, then the corresponding voltage fluctuation characteristic value is calculated based on the voltage amplitude of the selected voltage fluctuation signal using a pre-constructed voltage fluctuation characteristic model.

[0102] In this embodiment, in steps S201-S202 above, the preset frequency band range is set according to the actual situation of the distribution network and the characteristics of voltage fluctuations. Since voltage fluctuations are abnormally concentrated in the low frequency band, specifically, particularly around 50Hz or 60Hz, for example, in one specific implementation, the preset frequency band range is a frequency range of 0 to 100Hz. The selected voltage fluctuation signal is subjected to spectral analysis to extract its spectral parameters.

[0103] In step S203 above, it is determined whether the changes in one or more spectral parameters exceed preset change thresholds. For example, it is determined whether the offset of the voltage peak position exceeds a preset offset change threshold, or whether the voltage phase change exceeds a preset phase change threshold. The preset change thresholds are set by those skilled in the art based on their experience in the normal operation of the distribution network and the allowable range of voltage fluctuations. By judging whether there are obvious changes in the spectrum (e.g., obvious peak offset and / or obvious phase change), the voltage disturbance is judged, and potentially abnormal voltage fluctuation signals are preliminarily screened out.

[0104] In step S204 above, if the change in the spectral parameters exceeds a preset change threshold, the corresponding voltage fluctuation characteristic value is further calculated based on the voltage amplitude of the selected voltage fluctuation signal using a pre-constructed voltage fluctuation characteristic model. The voltage fluctuation characteristic value is used to more intuitively represent the voltage fluctuation characteristics of the access node.

[0105] Specifically, the pre-constructed voltage fluctuation characteristic model is represented as follows:

[0106]

[0107] Among them, V s,i (t) represents the voltage amplitude of the voltage fluctuation signal of the i-th access node at time point t, α i and β i These are the parameters for adjusting the response sensitivity, F(V) s,i (t) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t, and log is a logarithmic function.

[0108] When α i When the voltage increases, the distribution network system becomes more sensitive to voltage fluctuations, and the voltage change triggers F(V) s,i The change in β(t) is suitable for detecting voltage fluctuations in sensitive devices (such as electronic components). i When the voltage is increased, the amplitude of the voltage fluctuation signal will be significantly amplified, making it easier for the distribution network system to identify faults when there are large voltage fluctuations.

[0109] This embodiment uses Discrete Fourier Transform to perform spectral analysis on the voltage fluctuation signals of the access nodes of the distributed distribution network system, extracts the selected voltage fluctuation signals corresponding to the main frequency components, and establishes a voltage fluctuation feature model. This enables accurate identification of voltage fluctuation anomalies. By adjusting the sensitivity parameters, the response to voltage fluctuations and fault judgment become more sensitive. It is suitable for voltage fluctuation detection of sensitive equipment and can significantly improve the accuracy of fault identification when there are large voltage fluctuations, thereby enhancing the fault detection capability of the distributed distribution network system.

[0110] In one specific embodiment, step S3, which calculates the net power balance value of the distributed distribution network system based on the preprocessed grid data of each target node and the voltage fluctuation characteristic value of each access node using a pre-constructed generalized steady-state interaction model, includes:

[0111] S301. Calculate the actual output power A(t) of the access node at time point t using the output power calculation formula, wherein the output power calculation formula is:

[0112]

[0113] Among them, F(V) s,i (t) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. λ represents the natural decay of the output power of the i-th access node with time t. i Let P be the attenuation coefficient of the i-th distributed power access node. s,i (t) represents the output power of the i-th access node at time t, and m is the total number of access nodes;

[0114] S302. Calculate the actual power consumption B(t) of the load node at time point t using the power consumption calculation formula, wherein the power consumption calculation formula is:

[0115]

[0116] Among them, I l,j (t) represents the current value of the j-th load node at time t, k j Let be the current response sensitivity of the j-th load node. Let V be the hyperbolic tangent function in a nonlinear function, where τ is the integration variable and V is the integrator. l,j (τ) represents the voltage value of the load node in the time integral variable τ, dτ represents the small change in the integral variable, and γ j P is the hysteresis coefficient of the load node to voltage fluctuations. l,j (t) represents the power consumed by the j-th load node at time t, and n is the total number of load nodes;

[0117] S303. Calculate the net power balance value P of the distributed distribution network system at time point t using a pre-constructed generalized steady-state interaction model. s,l (t), represented as:

[0118]

[0119] Where T is the entire time interval and dt is the time increment.

[0120] In this embodiment, in step S301 above, in real-world scenarios, the power output of distributed access nodes (including solar and wind power generation) is not constant; their output power often decays over time and is affected by the natural environment. An exponential decay function is introduced to describe the power decay of distributed power access nodes over time, expressed as:

[0121] in, λ represents the natural decay of the output power of the i-th access node with time t. i Let be the attenuation coefficient of the i-th access node.

[0122] In step S302 above, the power consumption of the load node depends not only on the voltage but also on the current fluctuations. A nonlinear function is introduced to represent the relationship between the power consumption of the load node and the current fluctuations, and the expression is:

[0123] Among them, I l,j (t) represents the current value of the j-th load node at time t, k j Let be the current response sensitivity of the j-th load node, which is obtained through statistical analysis of historical power grid data. The hyperbolic tangent function is a nonlinear function used to describe how the power consumed by a load node changes with current fluctuations.

[0124] By introducing an exponential decay function, the characteristics of the natural decay of distributed power sources over time are accurately described, enhancing the adaptability and accuracy of the model and reflecting the output changes of distributed power sources in real time.

[0125] In some load nodes, power consumption is affected not only by the current voltage but also by the cumulative effect of long-term voltage fluctuations. The cumulative effect of voltage fluctuations can be described by an integral function, expressed as:

[0126] Where τ is the integral variable, used to describe the voltage change at the load node from the initial time to time t, V l,j(τ) represents the voltage value of the load node in the time integral variable τ. The integral term represents the cumulative effect from the initial time to time point t. dτ represents the small change in the integral variable, used to accumulate the voltage fluctuation effect over the calculation period. γ j The hysteresis coefficient is the load node's response to voltage fluctuations, used to describe the load node's sensitivity to long-term voltage fluctuations. The hysteresis coefficient is obtained through experimental measurements at actual load nodes.

[0127] The power consumption of load nodes is not only related to voltage fluctuations but also closely linked to current fluctuations. A nonlinear function is used to describe the relationship between load node power consumption and current fluctuations. The hyperbolic tangent function is used to capture the nonlinear variation characteristics of load consumption, thus more accurately reflecting the dynamics of load response. This is particularly important in complex power grid environments where the dynamic characteristics of the load are crucial. The long-term cumulative effect of load nodes on voltage fluctuations is also considered. An integral function is used to describe the cumulative effect of load nodes on voltage fluctuations over time, effectively capturing the impact of long-term voltage fluctuations on load power consumption. Furthermore, the load's sensitivity to voltage fluctuations is quantified using a hysteresis coefficient, and distributed generation output and load consumption are calculated comprehensively.

[0128] In step S303 above, by constructing a generalized steady-state interaction model, the net power balance value of the distribution network system is calculated. This provides an effective method for dynamically and in real-time evaluating the operating status of the distribution network. The power of the access nodes and load nodes in the distributed distribution network system is calculated separately, allowing power balance calculations to move beyond static assessments and reflect the dynamic changes of the distribution network in real time. The calculation formula of the generalized steady-state interaction model can calculate the net power balance value of the system in real time, which is crucial for the safe operation, fault detection, and emergency response of the power grid. It also considers the actual situation of the power output of distributed sources decaying over time. This not only overcomes the limitations of traditional steady-state models in reflecting dynamic interactions but also provides a more refined evaluation method for complex power grid operations. Through this method, the power supply and demand balance can be monitored in real time, faults or abnormal situations can be quickly identified, thereby improving the safety and stability of power grid operation.

[0129] In one specific embodiment, the preset normal threshold range in step S4, which determines whether the net power balance value is within a preset normal threshold range, is greater than or equal to 0.

[0130] In this embodiment, if P s,l If (t) < 0, it indicates that the distributed distribution network system has insufficient power supply. Insufficient power supply includes at least one of the following: load exceeding power supply capacity and partial power source failure; if P s,l If (t)≥0, it indicates that the power distribution network system is operating normally.

[0131] like Figure 3 As shown, in one embodiment, a power distribution network fault detection device is provided. The device includes:

[0132] The power grid data acquisition module 10 is used to acquire power grid data of each target node in the distributed distribution network system in real time through pre-deployed sensors, and to preprocess the power grid data to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0133] The voltage fluctuation feature calculation module 20 is used to calculate the voltage fluctuation feature value corresponding to each of the access nodes based on the voltage fluctuation signal of each access node through a pre-constructed voltage fluctuation feature model.

[0134] The net power balance value calculation module 30 is used to calculate the net power balance value of the distributed distribution network system based on the preprocessed grid data of each target node and the voltage fluctuation characteristic value of each access node through a pre-built generalized steady-state interaction model.

[0135] The first judgment module 40 is used to determine whether the net power balance value is within a preset normal threshold range;

[0136] The fault determination module 50 is used to determine that the distributed power distribution system has a fault if it is not within the preset normal threshold range.

[0137] In one specific embodiment, the power distribution network fault detection device further includes:

[0138] The load voltage fluctuation characteristic calculation module is used to input the voltage fluctuation signals of each load node into the voltage fluctuation characteristic model and output the voltage fluctuation characteristic value corresponding to each load node.

[0139] The second judgment module is used to determine whether the voltage fluctuation characteristic value of each target node exceeds the preset voltage fluctuation threshold.

[0140] The potential fault node determination module is used to identify target nodes that exceed a preset voltage fluctuation threshold as potential fault nodes if such nodes exceed the preset voltage fluctuation threshold.

[0141] A traveling wave signal injection module is used to inject a traveling wave signal into the potential fault node at the current measurement point using the traveling wave injection method.

[0142] The measurement module is used to measure the propagation speed of the traveling wave signal and the time difference between the transmission and return of the traveling wave signal;

[0143] The calculation module is used to calculate the distance between the potential fault node and the current measurement point based on the propagation speed and the time difference;

[0144] The location determination module is used to determine the location of the potential fault point based on the distance.

[0145] In one specific embodiment, the power distribution network fault detection device further includes:

[0146] The report generation module is used to generate an operation report, which includes the preprocessed power grid data, voltage fluctuation characteristic values, and the location of the potential fault points.

[0147] In one specific embodiment, the voltage fluctuation characteristic calculation module 20 includes:

[0148] A selected frequency band unit is used to extract selected voltage fluctuation signals within a preset frequency band range from each of the voltage fluctuation signals.

[0149] The parameter extraction unit is used to analyze and extract the spectral parameters of the selected voltage fluctuation signal, including the voltage peak position, voltage amplitude, voltage phase and corresponding time point;

[0150] The first judgment unit is used to determine whether the change of at least one of the spectral parameters exceeds a preset change threshold.

[0151] The first calculation unit is used to calculate the corresponding voltage fluctuation characteristic value based on the voltage amplitude of the selected voltage fluctuation signal by using a pre-constructed voltage fluctuation characteristic model if the voltage fluctuation exceeds a preset change threshold.

[0152] In one specific embodiment, the pre-built voltage fluctuation characteristic model is represented as follows:

[0153]

[0154] Among them, V s,i (t) represents the voltage amplitude of the voltage fluctuation signal of the i-th access node at time point t, α i and β i These are the parameters for adjusting the response sensitivity, F(V) s,i (t) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t.

[0155] In one specific embodiment, the net power balance value calculation module 30 includes:

[0156] The second calculation unit is used to calculate the actual output power A(t) of the access node at time point t using the output power calculation formula, which is:

[0157]

[0158] Where F(Vs,i(t)) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. λ represents the natural decay of the output power of the i-th access node with time t. i Let P be the attenuation coefficient of the i-th distributed power access node. s,i (t) represents the output power of the i-th access node at time t, and m is the total number of access nodes;

[0159] The third calculation unit is used to calculate the actual power consumption B(t) of the load node at time point t using the power consumption calculation formula, which is:

[0160]

[0161] Among them, I l,j (t) represents the current value of the j-th load node at time t, k j Let be the current response sensitivity of the j-th load node. Let V be the hyperbolic tangent function in a nonlinear function, where τ is the integration variable and V is the integrator. l,j (τ) represents the voltage value of the load node in the time integral variable τ, dτ represents the small change in the integral variable, and γ j P is the hysteresis coefficient of the load node to voltage fluctuations. l,j (t) represents the power consumed by the j-th load node at time t, and n is the total number of load nodes;

[0162] The fourth calculation unit is used to calculate the net power balance value P of the distributed distribution network system at time point t using a pre-built generalized steady-state interaction model. s,l (t), represented as:

[0163]

[0164] Where T is the entire time interval and dt is the time increment.

[0165] In one specific embodiment, the preset normal threshold range in the first judgment module 40 is greater than or equal to 0.

[0166] This embodiment enables intelligent fault detection in distributed distribution network systems, improving the accuracy and reliability of fault detection, reducing reliance on manual intervention, and significantly increasing detection efficiency. Simultaneously, by monitoring and analyzing power grid data in real time, potential faults can be promptly identified and addressed, effectively ensuring the safe and stable operation of the distribution network system.

[0167] Figure 4 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a power distribution network fault detection method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement the power distribution network fault detection method. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0168] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0169] The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0170] By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0171] The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0172] Determine whether the net power balance value is within a preset normal threshold range;

[0173] If not, then the distributed power distribution system is determined to have malfunctioned.

[0174] This embodiment enables intelligent fault detection in distributed distribution network systems, improving the accuracy and reliability of fault detection, reducing reliance on manual intervention, and significantly increasing detection efficiency. Simultaneously, by monitoring and analyzing power grid data in real time, potential faults can be promptly identified and addressed, effectively ensuring the safe and stable operation of the distribution network system.

[0175] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0176] The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals.

[0177] By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node.

[0178] The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node.

[0179] Determine whether the net power balance value is within a preset normal threshold range;

[0180] If not, then the distributed power distribution system is determined to have malfunctioned.

[0181] This embodiment enables intelligent fault detection in distributed distribution network systems, improving the accuracy and reliability of fault detection, reducing reliance on manual intervention, and significantly increasing detection efficiency. Simultaneously, by monitoring and analyzing power grid data in real time, potential faults can be promptly identified and addressed, effectively ensuring the safe and stable operation of the distribution network system.

[0182] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0183] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0184] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for detecting faults in a power distribution network, characterized in that, The method includes: The power grid data of each target node in the distributed power distribution network system is collected in real time by pre-deployed sensors, and the power grid data is preprocessed to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals. By using a pre-built voltage fluctuation characteristic model, voltage fluctuation characteristic values ​​corresponding to each access node are calculated based on the voltage fluctuation signals of each access node. The net power balance value of the distributed distribution network system is calculated by using a pre-constructed generalized steady-state interaction model based on the pre-processed grid data of each target node and the voltage fluctuation characteristic value of each access node. Determine whether the net power balance value is within a preset normal threshold range; If not, then the distributed power distribution system is determined to have malfunctioned; The step of calculating voltage fluctuation characteristic values ​​corresponding one-to-one with each access node based on the voltage fluctuation signals of each access node using a pre-constructed voltage fluctuation characteristic model includes: Selected voltage fluctuation signals within a preset frequency band are extracted from each of the voltage fluctuation signals; Analyze and extract the spectral parameters of the selected voltage fluctuation signal, including the voltage peak location, voltage amplitude, voltage phase, and corresponding time point; Determine whether the change in at least one of the spectral parameters exceeds a preset change threshold; If so, the corresponding voltage fluctuation characteristic value is calculated based on the voltage amplitude of the selected voltage fluctuation signal using a pre-constructed voltage fluctuation characteristic model. The pre-constructed voltage fluctuation characteristic model is expressed as follows: Where Vs,i(t) is the voltage amplitude of the voltage fluctuation signal of the i-th access node at time point t, αi and βi are the parameters for adjusting the response sensitivity, and F(Vs,i(t)) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. The step of calculating the net power balance value of the distributed distribution network system using a pre-constructed generalized steady-state interaction model, based on the pre-processed grid data of each target node and the voltage fluctuation characteristic values ​​of each access node, includes: The actual output power A(t) of the access node at time point t is calculated using the output power calculation formula, which is: Where F(Vs,i(t)) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. λ represents the natural decay of the output power of the i-th access node with time t. i Let Ps,i(t) be the attenuation coefficient of the i-th distributed power access node, Ps,i(t) be the output power of the i-th access node at time t, and m be the total number of access nodes. The actual power consumption B(t) of the load node at time point t is calculated using the power consumption calculation formula, which is: Where Il,j(t) is the current value of the j-th load node at time t, and kj is the current response sensitivity of the j-th load node. Let τ be the hyperbolic tangent function in the nonlinear function, Vl,j(τ) be the voltage value of the load node in the time integral variable τ, dτ be the small change of the integral variable, γj be the hysteresis coefficient of the load node to voltage fluctuation, Pl,j(t) be the power consumed by the j-th load node at time t, and n be the total number of load nodes. The net power balance value Ps,l(t) of the distributed distribution network system at time t is calculated using a pre-constructed generalized steady-state interaction model, and is expressed as: Where T is the entire time interval and dt is the time increment.

2. The power distribution network fault detection method according to claim 1, characterized in that, After the step of determining that a fault has occurred in the distributed distribution network system, the method further includes: The voltage fluctuation signals of each load node are input into the voltage fluctuation feature model, and the voltage fluctuation feature values ​​corresponding to each load node are output. Determine whether the voltage fluctuation characteristic value of each target node exceeds the preset voltage fluctuation threshold. If so, the target node that exceeds the preset voltage fluctuation threshold will be regarded as a potential fault node; A traveling wave signal is injected into the potential fault node at the current measurement point using the traveling wave injection method; Measure the propagation speed of the traveling wave signal and the time difference between the transmission and return of the traveling wave signal; The distance between the potential fault node and the current measurement point is calculated based on the propagation speed and the time difference. Based on the distance, the location of the potential fault point is determined.

3. The power distribution network fault detection method according to claim 2, characterized in that, After determining the location of the potential fault point based on the distance, the method further includes: An operation report is generated, which includes the preprocessed power grid data, voltage fluctuation characteristics, and the location of the potential fault points.

4. The power distribution network fault detection method according to claim 1, characterized in that, In the step of determining whether the net power balance value is within the preset normal threshold range, the preset normal threshold range is greater than or equal to 0.

5. A power distribution network fault detection device, characterized in that, The device includes: The power grid data acquisition module is used to collect power grid data from various target nodes in a distributed distribution network system in real time through pre-deployed sensors, and to preprocess the power grid data to obtain preprocessed power grid data; the target nodes include multiple access nodes and multiple load nodes; the preprocessed power grid data includes voltage fluctuation signals and current fluctuation signals; The voltage fluctuation feature calculation module is used to calculate the voltage fluctuation feature value corresponding to each of the access nodes based on the voltage fluctuation signal of each access node through a pre-constructed voltage fluctuation feature model. The net power balance value calculation module is used to calculate the net power balance value of the distributed distribution network system based on the preprocessed grid data of each target node and the voltage fluctuation characteristic value of each access node through a pre-built generalized steady-state interaction model. The first judgment module is used to determine whether the net power balance value is within a preset normal threshold range; The fault determination module is used to determine that the distributed power distribution system has failed if the fault is not within the preset normal threshold range. The voltage fluctuation characteristic calculation module includes: A selected frequency band unit is used to extract selected voltage fluctuation signals within a preset frequency band range from each of the voltage fluctuation signals. The parameter extraction unit is used to analyze and extract the spectral parameters of the selected voltage fluctuation signal, including the voltage peak position, voltage amplitude, voltage phase and corresponding time point; The first judgment unit is used to determine whether the change of at least one of the spectral parameters exceeds a preset change threshold. The first calculation unit is used to calculate the corresponding voltage fluctuation characteristic value based on the voltage amplitude of the selected voltage fluctuation signal by using a pre-constructed voltage fluctuation characteristic model if the voltage fluctuation exceeds a preset change threshold. The pre-constructed voltage fluctuation characteristic model is expressed as follows: Among them, V s,i (t) represents the voltage amplitude of the voltage fluctuation signal of the i-th access node at time point t, α i and β i These are the parameters for adjusting the response sensitivity, F(V) s,i (t) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t; The net power balance value calculation module includes: The second calculation unit is used to calculate the actual output power A(t) of the access node at time point t using the output power calculation formula, which is: Where F(Vs,i(t)) represents the voltage fluctuation characteristic value of the voltage fluctuation signal of the i-th access node at time point t. λ represents the natural decay of the output power of the i-th access node with time t. i Let P be the attenuation coefficient of the i-th distributed power access node. s,i (t) represents the output power of the i-th access node at time t, and m is the total number of access nodes; The third calculation unit is used to calculate the actual power consumption B(t) of the load node at time point t using the power consumption calculation formula, which is: Among them, I l,j (t) represents the current value of the j-th load node at time t, k j Let be the current response sensitivity of the j-th load node. Let V be the hyperbolic tangent function in a nonlinear function, where τ is the integration variable and V is the integrator. l,j (τ) represents the voltage value of the load node in the time integral variable τ, dτ represents the small change in the integral variable, and γ j P is the hysteresis coefficient of the load node to voltage fluctuations. l,j (t) represents the power consumed by the j-th load node at time t, and n is the total number of load nodes; The fourth calculation unit is used to calculate the net power balance value P of the distributed distribution network system at time point t using a pre-built generalized steady-state interaction model. s,l (t), represented as: Where T is the entire time interval and dt is the time increment.

6. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the steps of the power distribution network fault detection method as described in any one of claims 1 to 4.

7. A computer device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the power distribution network fault detection method as described in any one of claims 1 to 4.

Images