Intelligent monitoring system for power supply and distribution of power distribution network

Abstract

The invention belongs to the technical field of power distribution network electric power intelligent monitoring, and discloses a power distribution network electric power supply and distribution intelligent monitoring system which comprises the steps of collecting electric power data and state data, and performing data reinforcement on the electric power data to obtain reinforced electric power data; performing waveform analysis on the enhanced power data to obtain a load curve graph, performing state influence on the load curve graph to obtain a load correction graph, and performing feature extraction on the load correction graph to obtain load features; predicting load characteristics based on the constructed fault prediction model to obtain a fault message; load prediction is carried out on the load correction graph to obtain a future load demand, a demand topological graph is constructed based on the future load demand, fault cutting is carried out on the demand topological graph to obtain a local demand graph, power optimization scheduling is carried out on the local demand graph to obtain an optimal scheduling scheme, and the stability of the power supply and distribution system is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of power in a distribution network, and more specifically, to an intelligent monitoring system for power supply and distribution in a distribution network. Background Art

[0002] In the context of industrialization, electricity demand is complex and diverse. The power supply and distribution system is the core facility to ensure stable production operation. With the increase in the number of equipment and the advancement of industrial production automation, the existing power supply and distribution monitoring system of the distribution network has exposed significant deficiencies in functionality and adaptability, and it is difficult to meet the requirements of modern intelligent manufacturing. For example, the dynamic changes in electricity demand for diversified production tasks are becoming more and more significant, resulting in frequent adjustments to the power supply and distribution system. The existing system lacks flexible dynamic regulation capabilities. The supply and distribution strategy is usually only targeted at local optimization, ignoring the global nature of the supply and distribution network, and cannot be quickly updated according to real-time data. Scheduling adjustments often have significant delays, lack of real-time adaptive capabilities and global perspectives, resulting in frequent equipment failures, and greatly reduced production efficiency and safety. In the power supply and distribution system, many faults are lurking without causing immediate power outages, but these hidden faults are usually weak fluctuations or intermittent anomalies of power signals. These fluctuations cannot be effectively captured in normal monitoring systems. Once hidden faults evolve into explicit faults, they usually have caused irreversible damage to the equipment, which often leads to production stagnation, equipment damage and expensive maintenance costs.

[0003] In view of this, the present invention proposes an intelligent monitoring system for power supply and distribution in a distribution network to solve the above problems. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an intelligent monitoring system for power supply and distribution of a distribution network, comprising: Data acquisition and processing module: collects power data and status data of distribution network equipment in the same time series, enhances the power data, and obtains enhanced power data; Waveform analysis module: perform waveform analysis on enhanced power data to obtain a load curve diagram, perform state impact on the load curve diagram based on state data to obtain a load correction diagram, perform feature extraction on the load correction diagram to obtain load characteristics; Fault message module: predicts load characteristics based on the constructed fault prediction model, obtains fault messages, and issues fault alarms based on the fault messages; Optimization and dispatching module: includes demand forecasting unit and dispatching unit. The demand forecasting unit performs load forecasting on the load correction diagram to obtain future load demand, builds a demand topology diagram based on future load demand, performs fault cutting on the demand topology diagram based on fault messages to obtain a local demand diagram. The dispatching unit uses an optimization algorithm to perform power optimization dispatching on the local demand diagram to obtain the best dispatching solution.

[0005] Furthermore, the power data includes: device voltage and device current; the status data includes: device temperature.

[0006] Furthermore, the method of enhancing the power data includes: Each type of data in the power data is taken as the original data, and the waveform transformation is performed on the original data to obtain the waveform function. The noise threshold is preset, and the waveform function is smoothed based on the noise threshold to obtain the smoothed value; the maximum and minimum values ​​in the smoothed value are recorded, and the smoothed value at each moment is taken as a neuron data. The smoothed value is enhanced weight learning based on the neuron data to obtain the enhanced weight; the smoothed value at each moment is enhanced based on the enhanced weight, and the enhanced weight at each moment is multiplied by the smoothed value at the corresponding moment to obtain the enhanced data. All enhanced data constitute the enhanced equipment data.

[0007] Furthermore, the formula for performing enhanced weight learning is: ;in, Representative The enhanced weight of the moment, Representative The enhanced weight of the moment, represents the enhanced balance factor, Representative The smoothed value at time, represents the maximum value among the smoothed values, represents the minimum value among the smoothed values, Representative The original data at the moment.

[0008] Furthermore, the manner of influencing the state of the load curve diagram includes: The spline difference method is used to draw a curve for each type of data in the enhanced power data to obtain the equipment voltage curve and the equipment current curve; the equipment voltage curve and the equipment current curve are load fitted to obtain the power load, and the power load at different times constitutes a load curve; Based on the constructed load state influence model, the state data is predicted to obtain the load influence coefficient, the frequency determination function is preset, the frequency determination of the load influence coefficient is performed based on the frequency determination function, the correction frequency is obtained, and the load correction is performed on the load curve based on the load influence coefficient. The formula for load correction is: ;in, Representatives in Correction load at the moment, represents the load shift factor, Representatives in The power load at the moment, Representatives in The load influence coefficient at the time, Representatives in The frequency of time correction, Representative The corrected loads at different times constitute the load correction diagram.

[0009] Furthermore, the method of extracting features from the load correction diagram includes: Integrate the load correction graph over the time series span to obtain the total load value, and divide the total load value by the time series span to obtain the average load; perform difference calculation on the corrected loads at consecutive moments of the load correction graph, subtract the corrected load at the previous moment from the corrected load at the next moment to obtain the load momentary change, calculate the standard deviation of the load momentary change, and divide the standard deviation of the load momentary change by the average load to obtain the load fluctuation rate; calculate the load change rate at each moment in the load correction graph, average the load change rates, and obtain the average change rate; preset a sliding time window to capture short-term fluctuations of the load correction graph, slide the sliding time window at the start time in the load correction graph, calculate the standard deviation of the corrected load in each sliding time window, and obtain the window standard deviation; the load characteristic is composed of the mean of the load fluctuation rate, average load, average change rate and window standard deviation.

[0010] Furthermore, the fault prediction model is constructed in the following manner: Collect historical fault message data and historical equipment load characteristic data, use the historical fault message data and historical equipment load characteristic data as the input of the fault prediction model, use the predicted fault message as the output of the fault prediction model, use the historical fault message as the prediction target of the fault prediction model for model training, and build a fault prediction model. The fault prediction model is a linear regression model. The objective loss function of the fault prediction model is the recall rate function. Minimizing the value of the objective loss function is used as the training goal, and a fault prediction model with the smallest value of the objective loss function is obtained.

[0011] Furthermore, the local demand graph is constructed in the following manner: The load correction graph is predicted based on the trained load forecasting model to obtain the future load demand. The future load demand is used as the load node, and the connection threshold is preset. The correlation between different load characteristics is calculated based on the cosine similarity formula. The correlation is used as the weight of the connected edge, and the load nodes with a correlation greater than or equal to the connection threshold are connected to obtain the demand topology graph. Based on the fault message, the faulty nodes and the edges directly connected to the faulty nodes in the demand topology graph are removed to obtain the local demand graph.

[0012] Furthermore, the method of performing power optimization scheduling on the local demand graph includes: Preset the total load, and evenly distribute each load node in the local demand graph based on the total load to obtain the initial load and preset the load disturbance factor; initialize B ants, and randomly assign each ant to a different graph node in the local demand graph. Initialize the initial pheromone concentration of each edge in the local demand graph to the inverse of the edge weight, and initialize the global fitness to infinitesimal; Each ant performs allocation exploration in the local demand graph, and selects the position to which the ant will move next based on the initial pheromone concentration of each edge. The ant takes the edge with high initial pheromone concentration as the moving direction. When the graph node information of each ant changes, the current position and the previous position of the ant are recorded, and the initial load corresponding to the current position and the previous position is updated based on the load disturbance factor. The load node corresponding to the previous position will reduce the load by the size of the load disturbance factor and allocate it to the load node corresponding to the current position. The allocated value is used as the new initial load of the current position and the previous position, and the load adaptation calculation is performed on the local demand graph at this time to obtain the load fitness; when the load fitness is less than the global fitness, the ant stops moving, and the load fitness at this time is used as the new global fitness. When the load fitness is greater than or equal to the global fitness, the ant returns to the previous position and retracts the load allocation. When all ants stop moving, the current position of the ant is used as the initial position allocation and the allocation exploration is repeated until the number of ants on each load node in the local demand graph no longer changes, and the initial load of each load node in the local demand graph at this time is output as the optimal scheduling solution.

[0013] Furthermore, the formula for performing load adaptation calculation is: ;in, represents load fitness, Represents the number of load nodes in the local demand graph, represents the equilibrium weight, Representative The initial load of each load node, represents the average load of all load nodes, represents the adaptation weight, Representative The future load demand of each load node.

[0014] The technical effects and advantages of the intelligent monitoring system for power supply and distribution of a distribution network of the present invention are as follows: The present invention fully considers the key factors in power supply and distribution by collecting multiple data, which helps to comprehensively monitor the operating status of equipment; by strengthening the power data, it effectively removes mutation data, improves the accuracy of data, strengthens the time series characteristics, and optimizes the system's perception of instantaneous fluctuations; by affecting the state of the load curve graph, it realizes real-time load correction based on equipment status and load fluctuations, effectively copes with complex load change scenarios, and improves the accuracy of load monitoring; through the fault message module, it quickly issues an alarm, responds to potential equipment failures in a timely manner, and reduces the operating risks of the power supply and distribution system of the distribution network; through the construction of a local demand graph, the reliability of subsequent optimization scheduling is ensured; by performing power optimization scheduling on the local demand graph, the distribution of each load node is dynamically adjusted to ensure the balance and adaptability of load distribution, reduce equipment failure rate and energy waste, improve power resource utilization, and reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of an intelligent monitoring system for power supply and distribution in a power distribution network of the present invention; Figure 2 It is a schematic diagram of an intelligent monitoring method for power supply and distribution in a distribution network according to the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1

[0018] See also Figure 1 As shown, this embodiment provides an intelligent monitoring system for power supply and distribution of a distribution network, including: Data acquisition and processing module: collects power data and status data of distribution network equipment in the same time series, enhances the power data, and obtains enhanced power data; Waveform analysis module: perform waveform analysis on enhanced power data to obtain a load curve diagram, perform state impact on the load curve diagram based on state data to obtain a load correction diagram, perform feature extraction on the load correction diagram to obtain load characteristics; Fault message module: predicts load characteristics based on the constructed fault prediction model, obtains fault messages, and issues fault alarms based on the fault messages; Optimization and dispatching module: including demand forecasting unit and dispatching unit. The demand forecasting unit performs load forecasting on the load correction diagram to obtain future load demand, builds a demand topology diagram based on future load demand, performs fault cutting on the demand topology diagram based on fault messages to obtain a local demand diagram, and the dispatching unit uses an optimization algorithm to perform power optimization dispatching on the local demand diagram to obtain the best dispatching solution; The modules are connected to each other via wired and / or wireless means to achieve data transmission between modules.

[0019] Power data includes: equipment voltage, equipment current and equipment rated power; status data includes: equipment temperature and equipment vibration; equipment voltage is obtained through a voltage sensor to monitor the voltage fluctuation of the equipment; equipment current is obtained through a current sensor to monitor the current value of the equipment; equipment temperature is obtained through a temperature sensor to monitor the temperature of the equipment. Excessive equipment temperature may easily lead to equipment failure; equipment vibration is obtained through a vibration sensor. Different vibration frequencies of the equipment indicate different states of the equipment.

[0020] Ways to enhance power data include: Each type of data in the power data (referring to the equipment voltage and equipment current) is taken as the original data, and the original data is transformed into a waveform to obtain a waveform function. Common waveform transformations include wavelet transform and Fourier transform. A noise threshold is preset, and the waveform function is smoothed based on the noise threshold. The formula for waveform smoothing is: ;in, Represents the waveform function in The smoothed value at time, Represents the waveform function in The function value at time, represents the symbolic function, when When the value of is greater than zero, the value of the sign function is 1. When the value of is less than zero, the value of the sign function is -1. When the value of is equal to zero, the value of the sign function is 0. Represents the noise threshold. Waveform smoothing can optimize the local characteristics of the original data, accurately predict the instantaneous changes of the original data, and remove the mutation data in the original data. Record the maximum and minimum values ​​of the smoothed value, and use the smoothed value at each moment as a neuron data. Based on the neuron data, the smoothed value is enhanced weighted. The formula for enhanced weight learning is: ;in, Representative The enhanced weight of the moment, Representative The enhanced weight of the moment, Represents the enhancement balance factor, which is used to balance the changes in enhancement weights. Representative The smoothed value at time, represents the maximum value among the smoothed values, represents the minimum value among the smoothed values, Representative The original data of each moment; based on the enhancement weight, the smooth value of each moment is enhanced, and the enhancement weight of each moment is multiplied by the smooth value of the corresponding moment to obtain the enhanced data, and all the enhanced data constitute the enhanced device data; the value enhancement method based on the enhancement weight can adaptively adjust the influence of the smooth value, so that the smooth data of different time periods can be dynamically enhanced, thereby improving the accuracy of data representation.

[0021] Waveform analysis methods for enhanced power data include: The spline difference method is used to draw curves for each type of data in the enhanced power data to obtain the equipment voltage curve and the equipment current curve. The equipment voltage curve and the equipment current curve are load fitted, and the load fitting formula is: ;in, represent The power load at the moment, The voltage curve of the representative device is The voltage at the moment, The representative device current curve is The current at the moment, Represents the phase difference between voltage and current, and the power load at different times constitutes the load curve.

[0022] The ways to influence the state of the load curve diagram include: Collect historical equipment status data, historical equipment power data and historical equipment power. The types of historical equipment status data and equipment status data are consistent, and the data class types of historical equipment power data and power data are consistent. Use the spline difference method to draw curves for each type of data in the historical equipment power data to obtain historical voltage curves and historical current curves. Perform load fitting on the historical voltage curves and historical current curves to obtain historical power loads. Use the ratio of historical equipment power to historical power load as the historical load influence coefficient. The historical equipment status data and the historical load influence coefficient are used as the training sample set, the GAN model is used as the initial model, the GAN model is trained using the training sample set, the historical equipment status data is used as the input data of the load status influence model, and the predicted load influence coefficient is used as the output data of the load status influence model; the minimization of the error between the actual historical load influence coefficient and the predicted load influence coefficient is used as the training goal, and the mean square error function is used as the loss function of the load status influence model. When the loss function reaches convergence, the training is stopped to obtain the load status influence model, and the value of the loss function at this time is recorded as the load offset factor; Based on the constructed load state influence model, the state data is predicted to obtain the load influence coefficient, the frequency determination function is preset, the frequency determination of the load influence coefficient is performed based on the frequency determination function, the correction frequency is obtained, and the load correction is performed on the load curve based on the load influence coefficient. The formula for load correction is: ;in, Representatives in Correction load at the moment, represents the load shift factor, Representatives in The power load at the moment, Representatives in The load influence coefficient at the time, Representatives in The frequency of time correction, Representative The corrected loads at different times constitute the load correction diagram; through the introduction of load offset factors and the use of load correction formulas, the system can make real-time adjustments based on equipment status and load fluctuations, effectively respond to load fluctuations and equipment status changes in the power supply and distribution system of the distribution network, and accurately monitor the power of the distribution network.

[0023] Methods for extracting features from load correction diagrams include: Integrate the load correction graph over the time series span to obtain the total load value, and divide the total load value by the time series span to obtain the average load; perform difference calculation on the corrected loads at consecutive moments of the load correction graph, subtract the corrected load at the previous moment from the corrected load at the next moment to obtain the load momentary change, calculate the standard deviation of the load momentary change, and divide the standard deviation of the load momentary change by the average load to obtain the load fluctuation rate; calculate the load change rate at each moment in the load correction graph, average the load change rates, and obtain the average change rate; preset a sliding time window to capture short-term fluctuations in the load correction graph, slide the sliding time window at the start time in the load correction graph, calculate the standard deviation of the corrected load within each sliding time window, and obtain the window standard deviation; the load characteristics are composed of the mean of the load fluctuation rate, average load, average change rate and window standard deviation. It should be noted that the time series span is the collection duration when data is collected.

[0024] The fault prediction model is constructed in the following ways: Collect historical fault message data and historical equipment load characteristic data, use the historical fault message data and historical equipment load characteristic data as the input of the fault prediction model, use the predicted fault message as the output of the fault prediction model, use the historical fault message as the prediction target of the fault prediction model for model training, and build a fault prediction model. The fault prediction model is a linear regression model. The objective loss function of the fault prediction model is the recall rate function. Minimizing the value of the objective loss function is used as the training goal to obtain a fault prediction model with the smallest value of the objective loss function. Predict the load characteristics based on the constructed fault prediction model to obtain fault messages. The historical fault message data is the fault report data that has occurred on the equipment, including the equipment number, fault type, fault occurrence time and fault description. The equipment load characteristic data and the load characteristic data type are consistent.

[0025] The methods of performing load forecasting on the load correction diagram include: A sample window is preset, and the load correction graph is cut with the sample window to obtain a sample load sequence. Each sample load data is normalized to obtain standard sample data. A classification algorithm is used to cluster the training samples to obtain sample clusters. Commonly used classification algorithms include K-Means clustering algorithm and hierarchical clustering algorithm. The load forecasting model is preset as an LSTM model, and standard sample data is used as the input and time scale of the load forecasting model. The predicted future load demand is used as the output of the load forecasting model. The output probability is preset, and the output of each prediction is selected with the output probability. The Adam optimizer is used as the model optimizer of the load forecasting model, and the cross entropy function is used as the loss function of the load forecasting model. The load forecasting model is cyclically trained based on the sample clusters, and the parameters of the load forecasting model are optimized with the Adam optimizer. The mean of the loss function value of each round of cyclic training is calculated as the loss mean. When the loss mean converges, the load forecasting model at this time is output as the optimal load forecasting model. The load correction graph is predicted based on the trained load forecasting model to obtain future load demand. The sample window is a window with a fixed time span. Assuming that the time span is three hours, the window cutting is to divide the load correction diagram into time spans of three hours.

[0026] Methods for performing fault cutting on the demand topology graph include: Taking the future load demand as the load node, the connection threshold is preset, and the correlation between different load characteristics is calculated based on the cosine similarity formula. The correlation is used as the weight of the connected edge, and the load nodes with a correlation greater than or equal to the connection threshold are connected to obtain a demand topology map. Based on the fault message, the faulty nodes and the edges directly connected to the faulty nodes in the demand topology map are removed (the system shuts down the faulty equipment at the same time) to obtain a local demand map.

[0027] The methods for optimizing power dispatch for local demand graphs include: Preset the total load, and evenly distribute each load node in the local demand graph based on the total load to obtain the initial load and preset the load disturbance factor; initialize B ants, where the value of B is greater than the number of load nodes in the local demand graph, and randomly assign each ant to a different graph node in the local demand graph. Initialize the initial pheromone concentration of each edge in the local demand graph to be the inverse of the edge weight, and initialize the global fitness to be infinitesimal; Each ant performs distribution exploration in the local demand graph, and selects the position to which the ant will move next based on the initial pheromone concentration of each edge. The ant uses the edge with high initial pheromone concentration as the moving direction. When the graph node information of each ant changes, the ant's current position and previous position are recorded, and the initial load corresponding to the current position and previous position is updated based on the load disturbance factor. The load node corresponding to the previous position will reduce the load of the load disturbance factor and allocate it to the load node corresponding to the current position. The allocated value is used as the new initial load of the current position and previous position, and the load adaptation calculation is performed on the local demand graph at this time. The formula for load adaptation calculation is: ;in, represents load fitness, Represents the number of load nodes in the local demand graph, Represents the balancing weight, which is used to balance the proportion of load balancing in load fitness. Representative The initial load of each load node, represents the average load of all load nodes, Represents the adaptation weight, which is used to balance the proportion of future load demand in load fitness. The larger the adaptation weight, the more likely the initial load assigned to the node is to be close to the future load demand. Representative The future load demand of each load node in the local demand graph is obtained; when the load fitness is less than the global fitness, the ants stop moving and use the load fitness at this time as the new global fitness. When the load fitness is greater than or equal to the global fitness, the ants return to the previous position and take back the load allocation. When all ants stop moving, the current ant position is used as the initial position allocation to repeat the allocation exploration until the number of ants on each load node in the local demand graph no longer changes. The initial load of each load node in the local demand graph at this time is output as the optimal scheduling solution.

[0028] This embodiment fully considers the key factors in power supply and distribution by collecting multiple data, which helps to comprehensively monitor the operating status of equipment; by strengthening the power data, it effectively removes mutation data, improves the accuracy of data, strengthens the time series characteristics, and optimizes the system's perception of instantaneous fluctuations; by affecting the state of the load curve, it realizes real-time load correction based on equipment status and load fluctuations, effectively copes with complex load change scenarios, and improves the accuracy of load monitoring; through the fault message module, it quickly issues alarms, responds to potential equipment failures in a timely manner, and reduces the operating risks of the power supply and distribution system of the distribution network; through the construction of a local demand graph, it ensures the reliability of subsequent optimization and scheduling; through the power optimization scheduling of the local demand graph, it dynamically adjusts the distribution of each load node to ensure the balance and adaptability of load distribution, reduce equipment failure rate and energy waste, improve power resource utilization, and reduce operating costs.

[0029] Example 2

[0030] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a method for intelligent monitoring of power supply and distribution in a distribution network is provided, including: S1. Collect power data and status data of distribution network equipment in the same time series, enhance the power data, and obtain enhanced power data; S2. Perform waveform analysis on the enhanced power data to obtain a load curve diagram, perform state influence on the load curve diagram based on the state data to obtain a load correction diagram, perform feature extraction on the load correction diagram to obtain load features; S3. Predict the load characteristics based on the constructed fault prediction model, obtain the fault message, and issue a fault alarm based on the fault message; S4. Perform load forecasting on the load correction diagram to obtain future load demand, construct a demand topology diagram based on the future load demand, perform fault cutting on the demand topology diagram based on the fault message to obtain a local demand diagram, use an optimization algorithm to perform power optimization scheduling on the local demand diagram to obtain the best scheduling solution.

[0031] Example 3

[0032] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the above-mentioned intelligent monitoring method for power supply and distribution in a distribution network is implemented.

[0033] Since the electronic device introduced in this embodiment is an electronic device used to implement a distribution network power supply and distribution intelligent monitoring method in the embodiment of this application, based on the distribution network power supply and distribution intelligent monitoring method introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the distribution network power supply and distribution intelligent monitoring method in the embodiment of this application, it belongs to the scope of protection of this application.

[0034] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0035] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent monitoring system for power supply and distribution in a distribution network, characterized in that: include: Data acquisition and processing module: collects power data and status data of distribution network equipment in the same time series, enhances the power data, and obtains enhanced power data; Waveform analysis module: perform waveform analysis on enhanced power data to obtain a load curve diagram, perform state impact on the load curve diagram based on state data to obtain a load correction diagram, perform feature extraction on the load correction diagram to obtain load characteristics; Fault message module: predicts load characteristics based on the constructed fault prediction model, obtains fault messages, and issues fault alarms based on the fault messages; Optimization and dispatching module: includes demand forecasting unit and dispatching unit. The demand forecasting unit performs load forecasting on the load correction diagram to obtain future load demand, builds a demand topology diagram based on future load demand, performs fault cutting on the demand topology diagram based on fault messages to obtain a local demand diagram. The dispatching unit uses an optimization algorithm to perform power optimization dispatching on the local demand diagram to obtain the best dispatching solution.

2. The power distribution network intelligent monitoring system according to claim 1, characterized in that: The power data includes: device voltage and device current; the status data includes: device temperature.

3. The power distribution network intelligent monitoring system according to claim 2 is characterized in that: The method of enhancing the power data includes: Each type of data in the power data is taken as the original data, and the waveform transformation is performed on the original data to obtain the waveform function. The noise threshold is preset, and the waveform function is smoothed based on the noise threshold to obtain the smoothed value; the maximum and minimum values ​​in the smoothed value are recorded, and the smoothed value at each moment is taken as a neuron data. The smoothed value is enhanced weight learning based on the neuron data to obtain the enhanced weight; the smoothed value at each moment is enhanced based on the enhanced weight, and the enhanced weight at each moment is multiplied by the smoothed value at the corresponding moment to obtain the enhanced data. All enhanced data constitute the enhanced equipment data.

4. The power distribution network intelligent monitoring system according to claim 3 is characterized in that: The formula for enhancing weight learning is: ;in, Representative The enhanced weight of the moment, Representative The enhanced weight of the moment, represents the enhanced balance factor, Representative The smoothed value at time, represents the maximum value among the smoothed values, represents the minimum value among the smoothed values, Representative The original data at the moment.

5. The power distribution network intelligent monitoring system according to claim 4 is characterized in that: The method of influencing the state of the load curve diagram includes: The spline difference method is used to draw a curve for each type of data in the enhanced power data to obtain the equipment voltage curve and the equipment current curve; the equipment voltage curve and the equipment current curve are load fitted to obtain the power load, and the power load at different times constitutes a load curve; Based on the constructed load state influence model, the state data is predicted to obtain the load influence coefficient, the frequency determination function is preset, the frequency determination of the load influence coefficient is performed based on the frequency determination function, the correction frequency is obtained, and the load correction is performed on the load curve based on the load influence coefficient. The formula for load correction is: ;in, Representatives in Correction load at the moment, represents the load shift factor, Representatives in The power load at the moment, Representatives in The load influence coefficient at the time, Representatives in The frequency of time correction, Representative The corrected loads at different times constitute the load correction diagram.

6. The power distribution network intelligent monitoring system according to claim 5, characterized in that: The method of extracting features from the load correction diagram includes: Integrate the load correction graph over the time series span to obtain the total load value, and divide the total load value by the time series span to obtain the average load; perform difference calculation on the corrected loads at consecutive moments of the load correction graph, subtract the corrected load at the previous moment from the corrected load at the next moment to obtain the load momentary change, calculate the standard deviation of the load momentary change, and divide the standard deviation of the load momentary change by the average load to obtain the load fluctuation rate; calculate the load change rate at each moment in the load correction graph, average the load change rates, and obtain the average change rate; preset a sliding time window to capture short-term fluctuations of the load correction graph, slide the sliding time window at the start time in the load correction graph, calculate the standard deviation of the corrected load in each sliding time window, and obtain the window standard deviation; the load characteristic is composed of the mean of the load fluctuation rate, average load, average change rate and window standard deviation.

7. The intelligent monitoring system for power supply and distribution of distribution network according to claim 6, characterized in that: The fault prediction model is constructed in the following manner: Collect historical fault message data and historical equipment load characteristic data, use the historical fault message data and historical equipment load characteristic data as the input of the fault prediction model, use the predicted fault message as the output of the fault prediction model, use the historical fault message as the prediction target of the fault prediction model for model training, and build a fault prediction model. The fault prediction model is a linear regression model. The objective loss function of the fault prediction model is the recall rate function. Minimizing the value of the objective loss function is used as the training goal, and a fault prediction model with the smallest value of the objective loss function is obtained.

8. The power distribution network intelligent monitoring system according to claim 7, characterized in that: The construction method of the local demand graph includes: The load correction graph is predicted based on the trained load forecasting model to obtain the future load demand. The future load demand is used as the load node, and the connection threshold is preset. The correlation between different load characteristics is calculated based on the cosine similarity formula. The correlation is used as the weight of the connected edge, and the load nodes with a correlation greater than or equal to the connection threshold are connected to obtain the demand topology graph. Based on the fault message, the faulty nodes and the edges directly connected to the faulty nodes in the demand topology graph are removed to obtain the local demand graph.

9. The power distribution network power supply intelligent monitoring system according to claim 8, characterized in that: The method of performing power optimization dispatch on the local demand graph includes: Preset the total load, and evenly distribute each load node in the local demand graph based on the total load to obtain the initial load and preset the load disturbance factor; initialize B ants, and randomly assign each ant to a different graph node in the local demand graph. Initialize the initial pheromone concentration of each edge in the local demand graph to the inverse of the edge weight, and initialize the global fitness to infinitesimal; Each ant performs allocation exploration in the local demand graph, and selects the position to which the ant will move next based on the initial pheromone concentration of each edge. The ant takes the edge with high initial pheromone concentration as the moving direction. When the graph node information of each ant changes, the current position and the previous position of the ant are recorded, and the initial load corresponding to the current position and the previous position is updated based on the load disturbance factor. The load node corresponding to the previous position will reduce the load by the size of the load disturbance factor and allocate it to the load node corresponding to the current position. The allocated value is used as the new initial load of the current position and the previous position, and the load adaptation calculation is performed on the local demand graph at this time to obtain the load fitness; when the load fitness is less than the global fitness, the ant stops moving, and the load fitness at this time is used as the new global fitness. When the load fitness is greater than or equal to the global fitness, the ant returns to the previous position and retracts the load allocation. When all ants stop moving, the current position of the ant is used as the initial position allocation and the allocation exploration is repeated until the number of ants on each load node in the local demand graph no longer changes, and the initial load of each load node in the local demand graph at this time is output as the optimal scheduling solution.

10. The power distribution network intelligent monitoring system according to claim 9, characterized in that: The formula for load adaptation calculation is: ;in, represents load fitness, Represents the number of load nodes in the local demand graph, represents the equilibrium weight, Representative The initial load of each load node, represents the average load of all load nodes, represents the adaptation weight, Representative The future load demand of each load node.

Images