Intelligent power distribution network monitoring and fault detection system

Abstract

The application discloses an intelligent power distribution network monitoring and fault detection system and relates to the technical field of power distribution network detection.The system comprises a power distribution network region division module, a periodic data acquisition and monitoring module, a data preprocessing and feature extraction module, an intelligent load state evaluation module, a sub-region state division module, a conventional monitoring module and a dynamic adjustment and abnormal response module.The power distribution network region division module divides the entire power distribution network into multiple sub-regions to realize more refined monitoring and management.The application can accurately identify local overload and abnormal load and respond to abnormal fluctuations in time by dividing the power distribution network into sub-regions and combining periodic state scanning.The system can evaluate load fluctuations, automatically learn to adapt to load changes, improve the intelligence, flexibility and stability of the system and ensure the safe and reliable power supply by combining LSTM.

Description

Technical Field

[0001] This invention relates to the field of power distribution network detection technology, and more specifically to a smart power distribution network monitoring and fault detection system. Background Technology

[0002] Smart distribution network monitoring and fault detection refers to the use of advanced sensing technologies, data analysis, artificial intelligence (AI), and machine learning to monitor the operational status of the distribution network and automatically detect and identify faults or anomalies. Specifically, smart distribution network monitoring systems can collect data from various devices within the network, including parameters such as voltage, current, power, and load. This data is then analyzed in real time to identify potential equipment failures, line short circuits, overloads, undervoltage, and other problems. Simultaneously, fault detection technology can provide early warnings through comparison with historical data, anomaly pattern recognition, and predictive maintenance, preventing large-scale power outages or system collapses. This intelligent monitoring and fault detection not only improves the reliability and efficiency of the power system but also enables intelligent fault location and rapid recovery, enhancing the grid's self-healing capabilities.

[0003] The existing technology has the following shortcomings:

[0004] Existing smart distribution network monitoring systems typically track the network's status continuously through periodic operational status scans to promptly detect abnormal fluctuations. However, localized overloads, especially those caused by concentrated loads or temporary high loads, may be difficult to identify in a timely manner. Because a distribution network consists of multiple areas, lines, and equipment, localized overloads usually do not immediately affect the entire network's operation; therefore, monitoring systems based on average network data often overlook this issue. Such localized overloads can lead to unstable power supply in certain areas, exacerbated voltage fluctuations, and in severe cases, may trigger protective power outages to prevent equipment damage. Consequently, unstable power supply can cause frequent voltage fluctuations and power outages, and even lead to the entire power system disconnecting from the grid, severely impacting residents' lives and businesses' production, causing inconvenience and significant economic losses for users.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent distribution network monitoring and fault detection system. By dividing the distribution network into multiple sub-regions and introducing periodic operational status scanning, the monitoring system can track and accurately identify local overloads or abnormal loads in real time, especially in the case of sudden load increases or local faults, promptly detecting and responding to abnormal fluctuations. This regionalized management, combined with key characteristics such as reactive power demand and total harmonic distortion, improves the system's accuracy and responsiveness. Utilizing a Long Short-Term Memory (LSTM) network for load fluctuation index assessment, the system automatically learns and adapts to load changes, marking and focusing on monitoring abnormal areas in real time, significantly improving the intelligence, flexibility, and stability of the distribution network, ensuring the safety and reliability of power supply, and thus solving the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent distribution network monitoring and fault detection system, comprising a distribution network area division module, a periodic data acquisition and monitoring module, a data preprocessing and feature extraction module, an intelligent load status assessment module, a sub-area status division module, a conventional monitoring module, and a dynamic adjustment and anomaly response module.

[0008] The power distribution network area division module divides the entire power distribution network into multiple sub-regions to achieve more refined monitoring and management;

[0009] The periodic data acquisition and monitoring module acquires operational data of each sub-region of the distribution network by performing periodic operational status scans, and continuously tracks the operational status of the distribution network.

[0010] The data preprocessing and feature extraction module preprocesses the data acquired from each sub-region and extracts key features reflecting the load status of the sub-region. Under the detection window, the extracted key features are quantitatively analyzed and transformed into numerical indicators reflecting the current load status.

[0011] The intelligent load status assessment module inputs the quantified features into a pre-learned long short-term memory network, and then uses the long short-term memory network to intelligently assess the load status of each sub-region.

[0012] The sub-region status division module, based on the evaluation results of the long short-term memory network, divides all sub-regions into local voltage abnormal loads and regional load normalities. Sub-regions classified as "local voltage abnormal loads" are marked for subsequent key monitoring and handling.

[0013] For sub-regions classified as having normal regional load, the regular monitoring module continues to perform routine monitoring using preset periodic operating status scans to ensure the stable operation of the overall power distribution network.

[0014] The dynamic adjustment and anomaly response module dynamically adjusts the data acquisition frequency for sub-regions marked as having local voltage anomalies, in order to more accurately identify and respond to abnormal conditions.

[0015] Preferably, key features reflecting the load status of a sub-region are extracted from the preprocessed data. These extracted features include reactive power demand within the sub-region and the degree of harmonic distortion in the power system. Under the detection window, the reactive power demand within the sub-region and the degree of harmonic distortion in the power system are analyzed, generating reactive power load reference values ​​and total harmonic distortion reference values, respectively. The reactive power load reference value quantifies the relationship between reactive power demand and total load within the sub-region, while the total harmonic distortion reference value quantifies the ratio of harmonic current to fundamental current in the power system, reflecting the severity of harmonics in the power system.

[0016] Preferably, the specific steps for analyzing the reactive power demand within a sub-region under the detection window to generate reactive power load reference values ​​are as follows:

[0017] First, reactive power demand data within the sub-region is collected using monitoring equipment. The reactive power within the sub-region is calculated using the phase difference between voltage and current, as shown in the following expression:

[0018]

[0019] In the formula, Q is the reactive power of the sub-region, and I... k It is the current at the k-th load point in the sub-region, V k θ is the voltage at the k-th load point in the sub-region. k The phase difference between the current and voltage at the k-th load point in the sub-region is denoted by sin(θ). k () is the sinusoidal value of the phase difference between current and voltage;

[0020] After collecting the reactive power demand data Q, the dynamic characteristics of the reactive power demand are analyzed to reveal the load change trend of this sub-region. The calculation expression is as follows:

[0021] Q weighted =λ·Q+(1-λ)·Q previous

[0022] In the formula, Q weighted Q is the weighted reactive power demand, λ is the smoothing factor that controls the contribution of current and historical values ​​to the weighted average result. previous It is the reactive power demand value at the previous moment;

[0023] After analyzing the dynamic characteristics of the load, the reactive power demand of the sub-region is combined with the load density of the power system in that region to calculate the load deviation. The expression for calculating the load deviation is as follows:

[0024]

[0025] In the formula, D is the sub-regional load deviation, and A j I is the area of ​​the j-th load point within the sub-region. j It is the current demand of the j-th load point within the sub-region;

[0026] Overall weighted reactive power demand Q weighted The reactive power load reference value is generated based on the sub-regional load deviation D, using the following formula:

[0027] Reactive Power =α·q weighted +β·d

[0028] In the formula, Reactive Power This is the reactive power load reference value, and α is the weighted reactive power demand Q. weighted The weighting coefficient is β, which is the weighting coefficient of the sub-regional load deviation D.

[0029] Preferably, the specific steps for analyzing the degree of harmonic distortion in the power system under the detection window to generate a total harmonic distortion reference value are as follows:

[0030] First, the voltage and current signals of the power system are analyzed by Fast Fourier Transform to extract the harmonic components of the power system. The extraction formula is as follows:

[0031]

[0032] In the formula, X(h) is the amplitude of the h-th harmonic in the frequency domain, called the spectral component, x(m) is the value of the signal at the m-th sampling point, e is the natural base, p is the imaginary unit, 2π is a mathematical constant used to calibrate the periodicity of sine and cosine waves, h is the frequency index, representing the frequency component of the h-th harmonic, m is the sampling point index of the signal in the time domain, and M is the total number of signal sampling points;

[0033] After extracting the harmonic component X(h), the distortion of each harmonic component is quantized using the following formula:

[0034]

[0035] In the formula, HD(h) is the distortion of the h-th harmonic, X(1) is the fundamental amplitude, and ω is the adjustment factor;

[0036] The distortion degree HD(h) of each harmonic is obtained. Based on the sum of the distortion degrees of all harmonic components, the total harmonic distortion reference value is calculated. The calculation expression is as follows:

[0037]

[0038] In the formula, Total Harmonic τ is the total harmonic distortion reference value, H is the maximum value of the harmonic order, τ is the weighting coefficient, and γ is the reference value control parameter.

[0039] Preferably, the quantified reactive power load reference value and total harmonic distortion reference value are input into a pre-learned long short-term memory network, and a load fluctuation index is generated through the long short-term memory network. The load fluctuation index is then used to intelligently evaluate the load status of the sub-region.

[0040] Preferably, the load fluctuation index generated by intelligently assessing the load status of sub-regions through a pre-learned long short-term memory network is compared and analyzed with a pre-set load fluctuation index reference threshold to classify the status of sub-regions of the distribution network. The classification steps are as follows:

[0041] If the load fluctuation index is greater than the preset load fluctuation index reference threshold, the current sub-region will be classified as a local voltage abnormal load.

[0042] If the load fluctuation index is less than or equal to the preset load fluctuation index reference threshold, the current sub-region will be classified as having normal load.

[0043] Preferably, the specific steps for dynamically adjusting the data acquisition frequency for sub-regions marked as having local voltage anomalies to more accurately identify and respond to abnormal states are as follows:

[0044] When the load fluctuation index Load Fluctuation When the load fluctuation index exceeds the reference threshold, the data acquisition frequency is dynamically adjusted to ensure more accurate detection of potential anomalies when drastic load fluctuations occur in a sub-region. The frequency adjustment formula is as follows:

[0045]

[0046] In the formula, f new This is the adjusted data acquisition frequency, f. base It is the original periodic operating state scanning frequency, ρ is the adjustment coefficient, and Load Fluctuation It is the load fluctuation index. ref It is the reference threshold for the load fluctuation index. It is an exponential adjustment factor for the intensity of load fluctuation, Δt avg It is the average duration of the current load fluctuation, Δt ref The reference load fluctuation duration is μ, which is the adjustment factor.

[0047] Adjusted data acquisition frequency f newFurther optimization will be based on the feedback mechanism to adapt to real-time load changes, making frequency changes more flexible and efficient, as shown in the following formula:

[0048]

[0049] In the formula, f adjusted This is the optimized data acquisition frequency, δ is the dynamic adjustment coefficient, and Load avg ζ is the average of the load fluctuation index, and N is the exponential weight of the load fluctuation index. missed N is the number of undetected anomalies. max θ is the maximum allowed number of missed anomalies, and θ is the anomaly missed detection weight index.

[0050] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0051] This invention divides the distribution network into multiple sub-regions, enabling the monitoring system to perform detailed monitoring and management of each sub-region, ensuring independent and real-time tracking of the load status in each region. Unlike traditional monitoring systems based on average data across the entire network, this sub-region division effectively identifies local overloads or abnormal loads, especially during sudden load surges or local equipment failures, allowing for timely detection of abnormal fluctuations. Key features such as reactive power demand and total harmonic distortion (THD) reflect changes in load imbalance, equipment malfunctions, or power quality issues. The system acquires data in real-time through periodic operational status scans and responds rapidly when anomalies are detected, preventing local overloads from causing widespread power system failures. Furthermore, for overload conditions in specific sub-regions, the system dynamically adjusts the data acquisition frequency for more accurate anomaly identification. This precise monitoring and response mechanism significantly improves the stability of the distribution network, reduces voltage fluctuations, power outages, and system crashes, ensuring the reliability and security of power supply.

[0052] This invention enhances the intelligence and adaptability of distribution network monitoring systems by introducing Long Short-Term Memory (LSTM) networks. LSTM can analyze historical data and capture the temporal characteristics of load fluctuations, thereby achieving accurate prediction and intelligent assessment of load status. The system can not only monitor the load status of sub-regions in real time, but also automatically learn and adapt to load changes, seasonal fluctuations, and sudden events. After reactive power load reference values ​​and total harmonic distortion (THD) reference values ​​are input into the LSTM network, the system can generate a load fluctuation index, providing a dynamic assessment of the load status and comparing it with preset thresholds. Once the load fluctuation index exceeds the preset threshold, the system automatically identifies local voltage anomalies, marks the area in real time, and focuses on monitoring it. This adaptive intelligent analysis not only reduces the need for human intervention but also adjusts monitoring strategies according to different changes in power demand. Through this intelligent processing, the distribution network can automatically adjust under changing load conditions, significantly improving the system's flexibility, stability, and fault response capabilities, ultimately ensuring efficient and secure power supply. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0054] Figure 1 This is a schematic diagram of the modules of the intelligent power distribution network monitoring and fault detection system of the present invention. Detailed Implementation

[0055] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0056] This invention provides, for example Figure 1 The intelligent distribution network monitoring and fault detection system shown includes a distribution network area division module, a periodic data acquisition and monitoring module, a data preprocessing and feature extraction module, an intelligent load status assessment module, a sub-area status division module, a routine monitoring module, and a dynamic adjustment and anomaly response module.

[0057] The power distribution network area division module divides the entire power distribution network into multiple sub-regions to achieve more refined monitoring and management;

[0058] Distribution networks typically consist of multiple zones, lines, and equipment, each with potentially significant differences in load characteristics and operating conditions. Firstly, the distribution network is divided into several sub-zones based on factors such as geographical location, load distribution, and equipment characteristics. This division allows the monitoring system to focus more on the specific operating conditions of each sub-zone, rather than relying solely on average data from the entire network. Reasonable zoning not only improves monitoring accuracy but also optimizes resource allocation, ensuring that critical areas receive priority monitoring and management.

[0059] The periodic data acquisition and monitoring module acquires operational data of each sub-region of the distribution network by performing periodic operational status scans, and continuously tracks the operational status of the distribution network.

[0060] "By implementing periodic operational status scans to acquire operational data from each sub-region of the distribution network and continuously track its operational status," means collecting real-time operational data from each sub-region of the distribution network periodically (or at preset time intervals) to monitor and analyze its current state. In existing technologies, distribution networks typically acquire real-time data through sensors (such as current, voltage, and power sensors) installed at various key locations. These sensors periodically transmit data to a central monitoring system, which continuously updates this data to reflect real-time information such as load, equipment operation, and power quality in each sub-region. Periodic scanning not only helps the monitoring system track the daily operation of the distribution network but also detects potential abnormal fluctuations in each sub-region, such as localized overloads and load imbalances. In this way, the system can promptly identify problems that may affect power stability, providing a basis for subsequent handling and adjustments, thereby preventing power outages or equipment damage caused by overloads, faults, etc.

[0061] These data, including key parameters such as voltage, current, power, and load, reflect the real-time operating status of the distribution network. Periodic scanning ensures that the system can promptly capture changes and potential anomalies during operation, providing fundamental data for subsequent analysis and processing. The period setting should be optimized based on the specific needs and operating characteristics of the distribution network to balance the frequency of data acquisition with the consumption of system resources.

[0062] The data preprocessing and feature extraction module preprocesses the data acquired from each sub-region and extracts key features reflecting the load status of the sub-region. Under the detection window, the extracted key features are quantitatively analyzed and transformed into numerical indicators reflecting the current load status.

[0063] The acquired operational data typically contains noise, missing values, and outliers, thus requiring preprocessing. Preprocessing steps include data denoising, data cleaning, missing value imputation, and time synchronization. These processes ensure data quality and consistency, making subsequent feature extraction and analysis more accurate and reliable. High-quality data is the foundation for intelligent evaluation and fault detection. The preprocessing process may also involve data standardization and normalization to ensure different features have the same scale, improving model performance.

[0064] Key features reflecting the load status of sub-regions are extracted from the preprocessed data. These features include reactive power demand within the sub-region and the degree of harmonic distortion in the power system. Under the detection window, the reactive power demand within the sub-region and the degree of harmonic distortion in the power system are analyzed, generating reactive power load reference values ​​and total harmonic distortion reference values. The reactive power load reference value quantifies the relationship between reactive power demand and total load within the sub-region, while the total harmonic distortion reference value quantifies the ratio of harmonic current to fundamental current in the power system, reflecting the severity of harmonics in the power system.

[0065] A rapid increase in reactive power demand within a sub-region typically indicates an overload, especially when the load exceeds normal limits. Reactive power is the energy used in a power system to maintain voltage stability and generate electromagnetic fields; it is primarily consumed by inductive loads (such as motors and transformers). When the load in a sub-region increases, particularly during periods of concentrated or sudden load increases, reactive power demand also increases accordingly. When the load is excessive, the system requires more reactive power to maintain voltage stability and prevent voltage drops or low voltage levels that could malfunction equipment. A rapid increase in reactive power demand is often due to the activation or sudden increase of a large number of inductive loads in the system, exceeding the design capacity or the system's carrying capacity. This situation puts greater pressure on the power system, potentially leading to severe voltage fluctuations or even voltage collapse. Without timely adjustment and control, protective power outages may be triggered to prevent equipment damage. Therefore, a rapid increase in reactive power demand is a critical warning signal, indicating that the current sub-region may have entered an overload state, threatening the stability and reliability of the power system and requiring further analysis and action.

[0066] The specific steps for analyzing the reactive power demand within a sub-region and generating reactive power load reference values ​​under the detection window are as follows:

[0067] First, reactive power demand data within the sub-region is collected through monitoring equipment. This involves obtaining reactive power information related to the sub-region from the real-time monitoring system. The reactive power within the sub-region is calculated using the phase difference between voltage and current, as shown in the following expression:

[0068]

[0069] In the formula, Q is the reactive power of the sub-region, and I... k It is the current at the k-th load point (transformer, motor, etc.) in the sub-region, V k θ is the voltage at the k-th load point in the sub-region. k The phase difference between the current and voltage at the k-th load point in the sub-region is denoted by sin(θ). k () is the sinusoidal value of the phase difference between current and voltage;

[0070] The collection of this data provides a foundation for subsequent analysis, reflecting the reactive power distribution at various load points within the sub-region.

[0071] After collecting reactive power demand data Q, the dynamic characteristics of reactive power demand are analyzed to reveal the load change trend of this sub-region. At this point, it is not enough to rely solely on simple statistics (such as mean or standard deviation); the instantaneous and sudden nature of load changes must be considered. The exponentially weighted moving average (EWMA) model of load is used to emphasize changes over a time period. The calculation expression is as follows:

[0072] Q weighted =λ·Q+(1-λ)·Q previous

[0073] In the formula, Q weighted This is the weighted reactive power demand, representing an adjusted assessment of the reactive power demand within the current sub-region. It considers both past and current reactive power demand. λ is a smoothing factor that controls the contribution of current and historical values ​​to the weighted average result, and its value ranges from 0 to 1. Q previous It is the reactive power demand value at the previous moment, representing the reactive power demand at the previous point in time in the historical data;

[0074] The purpose of this step is to capture instantaneous load fluctuations by smoothing out recent changes in reactive power demand, while avoiding the influence of historical data from a more distant time period on the current assessment, thereby more accurately identifying abnormal load conditions.

[0075] After analyzing the dynamic characteristics of the load, the reactive power demand of the sub-region is combined with the load density of the power system in that region to calculate the load deviation, further quantifying the abnormal level of reactive power load. The expression for calculating the load deviation is as follows:

[0076]

[0077] In the formula, D is the sub-regional load deviation, and A j I is the area of ​​the j-th load point within the sub-region. jIt is the current demand of the j-th load point within the sub-region;

[0078] Load deviation D reflects the relationship between load density and reactive power demand within a sub-region, revealing situations of load concentration or deviation from normal ranges. A high D value indicates excessive load concentration or uneven load distribution, posing an overload risk. This step helps to gain a deeper understanding of abnormal characteristics in reactive power demand.

[0079] Overall weighted reactive power demand Q weighted The reactive power load reference value generated by the sub-region load deviation D is used to quantify the load status of the sub-region. The generation formula is as follows:

[0080] Reactive Power =α·Q weighted +β,D

[0081] In the formula, Reactive Power This is the reactive power load reference value, and α is the weighted reactive power demand Q. weighted The weighting coefficients are used to measure the weighted reactive power demand Q. weighted In the final reference value Reactive Power The importance of β in the context of reactive power load reference value is measured by the weighting factor of the sub-regional load deviation D. Power The importance of [the subject / method].

[0082] This step generates a reactive power load reference value that not only reflects the current reactive power demand level of the sub-region but also takes into account the potential impact of load density on system stability. When Reactive Power A larger value indicates that the sub-region is in a state of high overload risk, while a smaller value indicates that the load in the region is relatively stable and the overload risk is low.

[0083] A higher reactive power load reference value, generated after analyzing the reactive power demand within a sub-region under a detection window, indicates a greater load demand within that sub-region, especially for inductive loads, which may be approaching or exceeding the system's carrying capacity. Reactive power is primarily used to maintain voltage stability in power systems. When the load demand in a sub-region increases, the reactive power demand also increases, thereby increasing the risk of load and voltage fluctuations in the system. A high reactive power load reference value usually indicates that the region may be approaching an overload state. Overload can lead to voltage drops, increased current fluctuations, and may trigger protective power-off mechanisms. Conversely, a low reactive power load reference value indicates that the load demand in the region is relatively stable, and the risk of overload is lower.

[0084] Severe harmonic distortion in a power system can indeed indicate an overload in a sub-region, especially when the load exceeds the system's design capacity. Harmonic distortion is caused by nonlinear loads (such as power electronic equipment, frequency converters, and switching power supplies), typically occurring when the load is too heavy or unevenly distributed. When the load in a sub-region is too high, especially during concentrated industrial loads or sudden increases in instantaneous load, the proportion of nonlinear loads increases, leading to aggravated harmonic generation and consequently severe harmonic distortion in the power system. During overload, the current and voltage waveforms in the power system are distorted due to load changes, forming high-frequency harmonic components. These harmonics not only affect the stability and power quality of the power system but can also damage distribution equipment, such as causing overheating and insulation aging. Increased harmonic distortion is usually accompanied by an abnormal increase in system load; therefore, elevated total harmonic distortion is often an important signal of system overload.

[0085] The specific steps for analyzing the degree of harmonic distortion in a power system under a detection window to generate a total harmonic distortion reference value are as follows:

[0086] First, the voltage and current signals of the power system are analyzed by Fast Fourier Transform (FFT) to extract the harmonic components of the power system. The frequency and amplitude of each harmonic provide a basis for further analysis. The extraction formula is as follows:

[0087]

[0088] In the formula, X(h) is the amplitude of the h-th harmonic in the frequency domain, called the spectral component. Each X(h) obtained after FFT transformation corresponds to a signal component of a specific frequency. X(h) contains the amplitude and phase information of the frequency component, reflecting the weight and phase difference of the frequency in the original signal. x(m) is the value of the signal at the m-th sampling point, representing the discrete sample value of the time-domain signal of the power system (such as current or voltage signal). e is the natural base, p is the imaginary unit, 2π is a mathematical constant used to calibrate the periodicity of sine and cosine waves, h is the frequency index, representing the frequency component of the h-th harmonic, m is the sampling point index of the time-domain signal. For each sampling point m, the complex exponential function calculates the contribution of that point to the h-th harmonic. M is the total number of signal sampling points.

[0089] This step allows for the precise acquisition of the amplitude value of each harmonic, providing crucial data for harmonic distortion analysis.

[0090] After extracting the harmonic component X(h), the distortion of each harmonic component is quantified. The distortion is expressed as the ratio between each harmonic and the fundamental frequency (main frequency component), as shown in the following formula:

[0091]

[0092] In the formula, HD(h) is the distortion of the h-th harmonic, X(1) is the fundamental amplitude, that is, the amplitude of the first harmonic. The fundamental is usually the signal component in the power system whose frequency is closest to the grid frequency (e.g., 50Hz or 60Hz), and ω is an adjustment factor used to weight the distortion of higher harmonics.

[0093] The purpose of this step is to quantify the distortion of each harmonic in a nonlinear manner, thereby highlighting the impact of higher-order harmonics on the power quality of the power system.

[0094] The distortion degree HD(h) of each harmonic is obtained. Based on the sum of the distortion degrees of all harmonic components, the total harmonic distortion reference value is calculated. This reference value is used to measure the degree of harmonic pollution in the entire system. To eliminate bias towards larger harmonic frequencies, the calculation expression is as follows:

[0095]

[0096] In the formula, Total Harmonic τ is the total harmonic distortion reference value, H is the maximum harmonic order, referring to the maximum harmonic order within the range of harmonic calculations considered, τ is the weighting coefficient, used to nonlinearly weight the influence of each harmonic, and γ is the reference value control parameter, which is the parameter for nonlinearly controlling the entire harmonic distortion reference value result.

[0097] This step enhances the impact of high-frequency harmonics through weighted and nonlinear methods to reflect the severe impact of higher-order harmonics on the power system when the load increases, thereby more accurately quantifying the harmonic pollution of the system.

[0098] A higher total harmonic distortion (THD) reference value, generated by analyzing the harmonic distortion level in a power system within a detection window, indicates a greater risk of overload in the current sub-region. Harmonic distortion is caused by nonlinear loads (such as power electronic equipment and frequency converters). When the load exceeds the design capacity of the power system, the harmonic content in the system increases significantly, leading to distortion of voltage and current waveforms and causing power quality problems. A high THD reference value means that there are more harmonic components in the system, usually indicating an overload or imbalance, suggesting that the power system is under stress and increasing the risk of faults and equipment damage. Therefore, a high THD reference value indicates a greater risk of overload in the current sub-region, while a low THD value indicates a more balanced system load and a lower risk of overload.

[0099] The intelligent load status assessment module inputs the quantified features into a pre-learned long short-term memory network, and then uses the long short-term memory network to intelligently assess the load status of each sub-region.

[0100] The quantified reactive power load reference value and total harmonic distortion reference value are input into a pre-learned long short-term memory network. The long short-term memory network generates a load fluctuation index, which is then used to intelligently assess the load status of the sub-region.

[0101] A pre-trained Long Short-Term Memory Network (LSTM) is a deep learning model trained on a large amount of historical data before the system is put into actual operation. LSTM is a special type of recurrent neural network (RNN) that excels at processing time-series data. Its characteristics include the ability to capture long-term dependencies and effectively prevent the gradient vanishing problem. In smart distribution network monitoring systems, LSTM is used to process and analyze various dynamically changing data in the distribution network, such as reactive power load reference values ​​and total harmonic distortion (THD) reference values. These data typically have time-series characteristics, reflecting the evolution and fluctuations of the system state. Therefore, the LSTM model can use past data information to predict future load changes and anomalies, thereby achieving intelligent assessment of the load state of sub-regions of the distribution network. By training on historical operating data, LSTM learns the potential patterns and complex time-series characteristics of distribution network operation, enabling the model to intelligently assess the current load state based on new input data (such as reactive power load reference values ​​and THD reference values).

[0102] During training, the LSTM network continuously adjusts its weights and biases to optimize its predictive capabilities. By inputting a large amount of historical data, the model can identify potential patterns in load changes across different sub-regions of the distribution network. For example, it can determine whether an increase in reactive power under specific conditions indicates local overload, or whether an increase in harmonic distortion reference values ​​is related to equipment load imbalance. This historical data-based learning process makes the LSTM network highly adaptable, enabling real-time intelligent assessment of the distribution network based on different time periods and load conditions. In this way, LSTM can generate an index reflecting load fluctuations—the load fluctuation index—by inputting real-time data such as reactive power load reference values ​​and total harmonic distortion reference values. This index quantifies the current load status of a sub-region, helping the system make more accurate judgments and timely responses. Compared to traditional monitoring methods, LSTM, with its powerful time-series modeling capabilities, enables the system to make more accurate and efficient predictions when facing complex and dynamically changing power loads, thereby improving the stability and reliability of the distribution network.

[0103] Long Short-Term Memory (LSTM) networks are not limited here, but can be used to reactivate reactive power load reference values. Power Total Harmonic Distortion Reference Value HarmonicAfter analysis, a load fluctuation index is generated. Fluctuation Any long short-term memory network can be used. To achieve the technical solution of this invention, this invention provides a specific implementation method.

[0104] Load fluctuation index Fluctuation The formula for generating the formula is as follows:

[0105]

[0106] In the formula, f1 and f2 are the reactive power load reference values. Power Total Harmonic Distortion Reference Value Harmonic The preset proportional coefficients, and both f1 and f2 are greater than 0.

[0107] As can be seen from the load fluctuation index, the larger the reactive power load reference value generated after analyzing the reactive power demand in the sub-region under the detection window, and the larger the total harmonic distortion reference value generated after analyzing the harmonic distortion degree in the power system under the detection window, the larger the load fluctuation index generated by the intelligent assessment of the load status of the sub-region through the pre-learned long short-term memory network, the greater the probability of the current sub-region being overloaded. Conversely, the smaller the load fluctuation index, the smaller the probability of the current sub-region being overloaded.

[0108] The preset proportional coefficients (f1 and f2) here refer to the different reference values ​​(reactive power load reference value) used in the formula for balancing and weighting. Power Total Harmonic Distortion Reference Value Harmonic Load fluctuation index Fluctuation The load fluctuation index (FFI) is a crucial parameter. Specifically, these coefficients reflect the relative importance and contribution ratio of the two reference values ​​in the calculation. In practical applications, the impact of reactive power load and harmonic distortion on load fluctuations may differ. For example, changes in reactive power demand may have a more direct impact on system load fluctuations, while the impact of harmonic distortion may be more evident in load imbalances under specific conditions. Therefore, f1 and f2 are pre-set weights used to adjust the formula to more accurately reflect the actual system conditions. These coefficients are typically determined through historical data analysis, expert experience, or model optimization methods to ensure that the formula's results closely match the actual load fluctuation state. In short, the pre-set proportional coefficients are a way to quantify and weight the importance of various reference values ​​during the FFI generation process.

[0109] The sub-region status division module, based on the evaluation results of the long short-term memory network, divides all sub-regions into local voltage abnormal loads and regional load normalities. Sub-regions classified as "local voltage abnormal loads" are marked for subsequent key monitoring and handling.

[0110] The load fluctuation index generated by the intelligent assessment of the load status of sub-regions using a pre-learned long short-term memory network is compared and analyzed with a pre-set load fluctuation index reference threshold to classify the status of sub-regions of the distribution network. The classification steps are as follows:

[0111] If the load fluctuation index is greater than the preset load fluctuation index reference threshold, the current sub-region will be classified as a local voltage abnormal load.

[0112] If the load fluctuation index is less than or equal to the preset load fluctuation index reference threshold, the current sub-region will be classified as having normal load.

[0113] Local voltage abnormality refers to the phenomenon where the voltage deviates from the normal range in a sub-area of ​​the distribution network due to excessive load or uneven distribution; normal regional load means that the load in a sub-area of ​​the distribution network is operating stably and all electrical parameters (such as voltage, current, reactive power, and harmonics) fluctuate within the design range.

[0114] The purpose of marking sub-regions classified as "local voltage anomaly loads" is to accurately identify problem areas within the entire distribution network, enabling subsequent focused monitoring and rapid response. Through marking, the system can clearly identify which sub-regions have voltage anomalies or overload issues, prioritizing resource allocation for dynamic data acquisition, high-frequency monitoring, and fault diagnosis in these areas. This allows for timely identification of the root cause and implementation of targeted measures (such as load shifting, equipment maintenance, or reactive power compensation). This marking mechanism not only improves monitoring efficiency and avoids wasting network-wide monitoring resources but also effectively prevents localized problems from escalating into network-wide faults, ensuring the overall stability and power quality of the distribution network.

[0115] For sub-regions classified as having normal regional load, the regular monitoring module continues to perform routine monitoring using preset periodic operating status scans to ensure the stable operation of the overall power distribution network.

[0116] For sub-regions classified as having normal load, routine monitoring continues with pre-set periodic operational status scans. The primary purpose is to maintain the continuous and stable operation of the distribution network and ensure the timely detection of potential load fluctuations or system anomalies. Even if these sub-regions are performing normally under current load, periodic monitoring remains necessary because power load and system status are dynamic, and sudden load increases or unexpected faults can lead to power system instability. Periodic scans allow for continuous tracking of the operational status of each sub-region, enabling timely detection of potential abnormal fluctuations, such as minor voltage fluctuations, load imbalances, or equipment operational deviations. This not only helps prevent potential overload risks but also provides real-time operational data to the system, supporting more precise scheduling and management, and ensuring that the overall distribution network remains in a safe and stable operating state.

[0117] The dynamic adjustment and anomaly response module dynamically adjusts the data acquisition frequency for sub-regions marked as having local voltage anomalies, in order to more accurately identify and respond to abnormal conditions.

[0118] The specific steps for dynamically adjusting the data acquisition frequency to more accurately identify and respond to abnormal states in sub-regions marked as having local voltage anomalies are as follows:

[0119] When the load fluctuation index Load Fluctuation When the load fluctuation index exceeds the reference threshold, the data acquisition frequency is dynamically adjusted to ensure more accurate detection of potential anomalies when drastic load fluctuations occur in a sub-region. The frequency adjustment formula is as follows:

[0120]

[0121] In the formula, f new This is the adjusted data acquisition frequency, f. base This refers to the original periodic operating state scanning frequency. ρ is an adjustment coefficient used to control the degree of influence of the load fluctuation index on the data acquisition frequency. It determines how the frequency is adjusted when the load fluctuation intensity increases. Fluctuation It is the load fluctuation index. ref It is the reference threshold for the load fluctuation index. It is an exponential adjustment factor for load fluctuation intensity, used to control the load fluctuation index. Fluctuation The nonlinear effect of adjusting the data acquisition frequency, Δt avg It is the average duration of the current load fluctuation, Δt ref It is the reference load fluctuation duration, which is usually set based on historical data and the operating characteristics of the power grid. It is used to standardize the impact of the load fluctuation duration. μ is an adjustment coefficient that controls the impact of the load fluctuation duration on the data acquisition frequency.

[0122] In the steps, This indicates how the intensity of load fluctuations affects the acquisition frequency in a weighted manner; while The time characteristics of load fluctuations are taken into account. When the load fluctuation intensity is large and the fluctuation duration is long, the data acquisition frequency will increase significantly, thereby improving the system's response capability to local voltage anomalies.

[0123] Adjusted data acquisition frequency f new Further optimization based on the feedback mechanism will be implemented to adapt to real-time load changes. In particular, when frequent load fluctuations or abnormal states fail to be accurately captured, an adaptive gain function can be introduced to adjust the update rate of the scanning frequency, making frequency changes more flexible and efficient. The formula is as follows:

[0124]

[0125] In the formula, f adjusted This is the optimized data acquisition frequency, where δ is the dynamic adjustment coefficient used to control the sensitivity of the dynamic adjustment frequency. Load avg ζ is the average value of the load fluctuation index, and ζ is the load fluctuation index.

[0126] Exponential weights are used to control The exponential coefficient of the degree of influence on frequency adjustment, n missed N represents the number of undetected anomalies, indicating the number of abnormal events that were not detected in a timely manner during the current sub-region monitoring process. max θ represents the maximum allowed number of missed anomalies, indicating the maximum number of times an anomaly can be missed as set by the system. It is used to standardize the handling of missed anomalies. θ is the anomaly missed detection weighting index, used to control... The degree of impact on the adjustment frequency.

[0127] Through this feedback mechanism, when load fluctuations are frequent and abnormal states cannot be successfully captured, the system automatically increases the data acquisition frequency, thereby improving the accuracy of anomaly identification. Conversely, if abnormal states are already being effectively monitored, the increase in frequency will be suppressed to avoid excessive resource waste and system burden. This dynamic adjustment mechanism can respond more precisely to load changes, ensuring effective monitoring of the system under various complex conditions.

[0128] The step of dynamically adjusting the data acquisition frequency for sub-areas marked as having localized voltage anomalies aims to monitor localized voltage anomalies with higher accuracy and real-time performance by increasing the frequency of data collection. This allows for timely identification and response to potential overloads or other anomalies. In distribution network operation, localized voltage anomalies are often precursors to load overloads or voltage fluctuations caused by factors such as sudden load increases or power system imbalances. When voltage anomalies occur in certain areas of the distribution network, conventional periodic data acquisition may fail to capture sudden short-term voltage fluctuations and rapidly changing load conditions in a timely manner, leading to delayed detection of the anomalies and affecting system response and processing.

[0129] By dynamically adjusting the data acquisition frequency, the system can flexibly adjust the monitoring accuracy and frequency based on the current grid status and load changes in the sub-region. For example, when a local voltage anomaly load is detected, the system will identify this abnormal signal and automatically increase the data acquisition frequency to more precisely track key parameters such as voltage fluctuations, current changes, and power factor. This high-frequency data acquisition not only captures instantaneous voltage deviations in real time but also provides more detailed load fluctuation data, helping the system quickly determine whether the load has entered an overload state and avoiding missing abnormal moments due to excessively long sampling periods.

[0130] Furthermore, dynamically adjusting the data acquisition frequency helps the system better predict load change trends and take proactive control measures, such as adjusting voltage, allocating load, or activating backup equipment. This ensures that the power system can react quickly to localized overloads or voltage problems. This effectively reduces the failure rate of the distribution network, lowers the risk of power outages, improves system stability and security, and ensures that users' power supply is not severely affected. Through this flexible monitoring strategy, the distribution network can continuously optimize its operating efficiency in a dynamic environment, ensuring power quality and high system reliability.

[0131] This invention divides the power distribution network into multiple sub-regions, enabling the monitoring system to perform detailed monitoring and management of each sub-region, ensuring independent and real-time tracking of the load status in each region. Unlike traditional monitoring systems based on average data across the entire network, this sub-regional division effectively identifies local overloads or abnormal loads, especially during sudden load surges or local equipment failures, allowing for timely detection of abnormal fluctuations. Key features such as reactive power demand and total harmonic distortion (THD) reflect changes in load imbalance, equipment malfunctions, or power quality issues. The system acquires data in real-time through periodic operational status scans and responds rapidly upon detecting anomalies, preventing local overloads from triggering widespread power system failures. Furthermore, for overload conditions in specific sub-regions, the system dynamically adjusts the data acquisition frequency for more accurate anomaly identification. This precise monitoring and response mechanism significantly improves the stability of the power distribution network, reduces voltage fluctuations, power outages, and system crashes, ensuring the reliability and security of power supply.

[0132] This invention enhances the intelligence and adaptability of distribution network monitoring systems by introducing Long Short-Term Memory (LSTM) networks. LSTM can analyze historical data and capture the temporal characteristics of load fluctuations, thereby achieving accurate prediction and intelligent assessment of load status. The system can not only monitor the load status of sub-regions in real time, but also automatically learn and adapt to load changes, seasonal fluctuations, and sudden events. After reactive power load reference values ​​and total harmonic distortion (THD) reference values ​​are input into the LSTM network, the system can generate load fluctuation indices. These indices provide a dynamic assessment of load status and can be compared with preset thresholds. Once the load fluctuation index exceeds the preset threshold, the system automatically identifies local voltage anomalies, marks the area in real time, and focuses on monitoring it. This adaptive intelligent analysis not only reduces the need for human intervention but also adjusts monitoring strategies according to different changes in power demand. Through this intelligent processing, the distribution network can automatically adjust under changing load conditions, significantly improving the system's flexibility, stability, and fault response capabilities, ultimately ensuring efficient and secure power supply.

[0133] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0134] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0135] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0136] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0137] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0138] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0141] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0142] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A smart power distribution grid monitoring and fault detection system, characterized by, The power distribution network region division module, the periodic data acquisition and monitoring module, the data preprocessing and feature extraction module, the intelligent load state evaluation module, the sub-region state division module, the conventional monitoring module, and the dynamic adjustment and abnormal response module are included. The power distribution network region division module divides the entire power distribution network into multiple sub-regions to achieve more refined monitoring and management. The periodic data acquisition and monitoring module obtains the operation data of each sub-region of the power distribution network through periodic operation state scanning, and continuously tracks the operation state of the power distribution network. The data preprocessing and feature extraction module preprocesses the data obtained from each sub-region, extracts the key features reflecting the load state of the sub-region, and quantitatively analyzes the extracted key features in the detection window to convert them into numerical indicators reflecting the current load state. The intelligent load state evaluation module inputs the quantized features into the pre-learned long short-term memory network to intelligently evaluate the load state of each sub-region. The sub-region state division module divides all sub-regions into local voltage abnormal load and regional load normal according to the evaluation results of the long short-term memory network, and marks the sub-regions divided as "local voltage abnormal load" for subsequent key monitoring and processing. The conventional monitoring module continues to perform conventional monitoring with the preset periodic operation state scanning for the sub-regions divided as regional load normal to ensure the stable operation of the entire power distribution network. The dynamic adjustment and abnormal response module dynamically adjusts the data acquisition frequency for the sub-regions marked as local voltage abnormal load to more accurately identify and respond to abnormal states. The specific steps for dynamically adjusting the data acquisition frequency for the sub-regions marked as local voltage abnormal load to more accurately identify and respond to abnormal states are as follows: When the load fluctuation index is greater than the load fluctuation index reference threshold, the data acquisition frequency is dynamically adjusted to ensure that potential abnormalities can be more accurately captured when severe load fluctuations occur in the sub-area, and the frequency adjustment formula is as follows: wherein, is the adjusted data acquisition frequency, is the original periodic operating state scan frequency, is the adjustment coefficient, is the load fluctuation index, is the load fluctuation index reference threshold, is the exponential adjustment factor of the load fluctuation intensity, is the average duration of the current load fluctuation, is the reference load fluctuation duration, is the adjustment coefficient; Adjusted data collection frequency Further optimization will be made based on the feedback mechanism to adapt to real-time load changes, making the frequency change more flexible and efficient, as follows: , wherein is the optimized data collection frequency, is the dynamic adjustment factor, is the average of the load fluctuation index, is the exponential weight of the load fluctuation index, is the number of undetected anomalies, is the maximum allowed number of undetected anomalies, is the anomaly undetected weight index.

2. The smart distribution grid monitoring and fault detection system of claim 1, wherein, From the preprocessed key features reflecting the load state of the sub-region, the extracted features include the reactive power demand in the sub-region and the harmonic distortion degree in the power system. In the detection window, the reactive power demand in the sub-region and the harmonic distortion degree in the power system are analyzed to generate a reactive power load reference value and a total harmonic distortion reference value, respectively. The reactive power load reference value quantifies the relationship between the reactive power demand in the sub-region and the total load, and the total harmonic distortion reference value quantifies the ratio of harmonic current to fundamental current in the power system, reflecting the severity of harmonics in the power system.

3. The smart distribution grid monitoring and fault detection system of claim 2, wherein, The specific steps for analyzing the reactive power demand in the sub-region in the detection window to generate a reactive power load reference value are as follows: First, collect the reactive power demand data in the sub-region through the monitoring device. The reactive power in the sub-region is calculated by the phase difference between voltage and current, and the calculation expression is as follows: In the formula, It is the reactive power of the sub-region. It is the first in the sub-region Current at each load point It is the first in the sub-region Voltage at each load point It is the first in the sub-region Phase difference between current and voltage at each load point It is the number of load points within the sub-region. It is the sinusoidal value of the phase difference between current and voltage; After the reactive power demand data is collected The dynamic characteristics of the reactive power demand are then analyzed to reveal the changing trend of the sub-area load, and the expression is calculated as follows: , wherein, is the weighted reactive power demand, is a smoothing factor that controls the degree of contribution of the current value and the historical value to the weighted average result, is the reactive power demand value at the previous time. After analyzing the load dynamic characteristics, combine the reactive power demand of the sub-region with the power system load density of the region to calculate the load deviation, and the load deviation calculation expression is as follows: wherein is the sub-area load deviation, is the area of the sub-area, is the area of the load point number is the current demand of the load point number in the sub-area. The weighted reactive power demand is calculated as follows: And the sub-area load deviation The generated reactive power load reference value is generated according to the following formula: wherein is the reactive power load reference value, is the weighted reactive power demand is the weight coefficient of the reactive power demand is the sub-area load deviation is the weight coefficient of the sub-area load deviation.

4. The smart grid monitoring and fault detection system of claim 2, wherein, The specific steps for analyzing the harmonic distortion degree in the power system in the detection window to generate a total harmonic distortion reference value are as follows: Firstly, the voltage and current signals of the power system are analyzed by fast Fourier transform to extract the harmonic components in the power system, and the extraction formula is as follows: , where is the amplitude of the th harmonic in the frequency domain, called a spectral component, is the value of the signal at the th sample point, is the natural base number, is the imaginary unit, is the mathematical constant used to scale the periodicity of sine and cosine waves, is the frequency index, indicating the th harmonic frequency component, is the sample point index of the time domain signal, is the total number of signal sample points; extracting the harmonic component After that, the distortion degree of each harmonic component is quantified, and the formula is as follows: wherein is the distortion of the second harmonic, is the fundamental amplitude, is the adjustment factor; obtaining the distortion degree of each harmonic calculating the total harmonic distortion reference value from the distortion degrees of all harmonic components, the calculation expression being as follows: wherein is a total harmonic distortion reference value, is a maximum value of the harmonic order, is a weighting coefficient, is a reference value control parameter.

5. The smart grid monitoring and fault detection system of claim 2, wherein, The quantized reactive power load reference value and total harmonic distortion reference value are input into the pre-learned long short-term memory network, and the load fluctuation index is generated through the long short-term memory network. The load fluctuation index is used to intelligently evaluate the load state of the sub-region.

6. The smart distribution grid monitoring and fault detection system of claim 5, wherein, The load fluctuation index generated by the pre-learned long short-term memory network for the intelligent evaluation of the load state of the sub-region is compared and analyzed with the pre-set load fluctuation index reference threshold value, and the distribution network sub-region state is divided, and the division steps are as follows: If the load fluctuation index is greater than the pre-set load fluctuation index reference threshold value, the current sub-region is divided into a local voltage abnormal load; If the load fluctuation index is less than or equal to the pre-set load fluctuation index reference threshold value, the current sub-region is divided into a regional normal load.

Images