Electric energy safety management system and method based on cloud platform

Abstract

The invention discloses an electric energy safety management system and method based on a cloud platform, and relates to the technical field of electric energy safety management, and the scheme comprises the steps: collecting the operation data of a micro-grid unit in a power grid, and transmitting the operation data to the cloud platform; judging whether the operation data at each time point is abnormal or not; constructing a topological structure of the power network according to the physical connection between the micro-grid units; dividing all nodes into different areas, calculating a comprehensive evaluation value of each node, and selecting the node with the highest comprehensive evaluation value as a local center node of each area; and when a plurality of micro-grid units in any area have an electric energy safety fault, calculating the priority of each fault node according to the local aggregation coefficient of the fault node and the connectivity between the fault node and the local center node, and performing maintenance according to the priority of the fault node. And comprehensive monitoring and management of the electric energy quality are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy safety management, and in particular to an electric energy safety management system and method based on a cloud platform. Background Art

[0002] With the continuous development of smart grid technology, power safety management has become an important part of power system operation. Traditional power safety management methods mostly rely on manual monitoring and manual control, which is not only inefficient, but also difficult to detect and deal with power quality problems in a timely and accurate manner. Especially in large-scale power networks, due to the decentralization and complexity of microgrid units, traditional power safety management methods have been unable to meet the needs of modern power systems.

[0003] In recent years, the rise of cloud platform technology has provided a new solution for power safety management. The cloud platform has powerful data processing and storage capabilities, and can collect and analyze the operating data of microgrid units in the power grid in real time, thereby realizing comprehensive monitoring and management of power quality. However, the existing cloud platform-based power safety management methods still have some shortcomings. For example, these methods often only focus on the operating status of a single microgrid unit, while ignoring the mutual influence and correlation between microgrid units. In addition, these methods also have certain limitations in fault handling and maintenance scheduling, making it difficult to quickly and accurately locate faults and take corresponding maintenance measures. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a cloud-based power safety management system and method, which can collect and analyze the operation data of microgrid units in the power grid in real time, comprehensively consider the mutual influence and correlation between microgrid units, and realize comprehensive monitoring and management of power quality. At the same time, the method also has efficient fault handling and maintenance scheduling capabilities, and can quickly and accurately locate faults and take corresponding maintenance measures when faults occur, so as to ensure the safe and stable operation of the power system.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: A power safety management method based on a cloud platform, comprising the following steps: Collect the operating data of microgrid units in the power grid and send it to the cloud platform; Obtain the operating data of the microgrid unit from the cloud platform, calculate the power quality indicators corresponding to each power quality parameter, determine whether there are abnormalities in the operating data at each time point, count the number of data points with abnormalities and the corresponding duration, and calculate the stability coefficient of the current microgrid unit; Each microgrid unit is regarded as a node in the power network. Each node has a unique identifier. According to the physical connection between the microgrid units, a connection relationship is established between the nodes. A weight is assigned to each connection relationship, the topological structure of the power network is constructed, and the weight of each node is calculated. According to the geographical location information and administrative division information of all nodes, the k-means++ algorithm is used to divide all nodes into different regions, calculate the comprehensive evaluation value of each node, and select the node with the highest comprehensive evaluation value as the local center node of each region; When power safety faults occur in multiple microgrid units in any area, the neighboring nodes of the faulty node are traversed, and the connection status between the nodes is counted. The local clustering coefficient of the faulty node is calculated, and the connectivity between the faulty node and the local central node is calculated through the degree between the nodes. The local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node are combined to calculate the priority of each faulty node, and maintenance is performed according to the priority of the faulty node.

[0006] Furthermore, the operation data of the microgrid unit is obtained from the cloud platform, and the power quality indicators corresponding to each power quality parameter are calculated, including: Obtain voltage data from the cloud platform and calculate the voltage fluctuation rate UD at each time point: UD=U / U0×100%, where U represents the voltage fluctuation and U0 represents the rated voltage; obtain current data from the cloud platform, use fast Fourier transform to calculate harmonic current and fundamental current, and calculate the current harmonic content: current harmonic content=effective value of harmonic current / effective value of fundamental current×100%; obtain power factor data from the cloud platform and calculate the power factor PF: PF=P / S, where P represents active power and S represents apparent power. The power factor change rate is obtained by calculating the ratio of the difference between the power factors at adjacent time points to the power factor at the previous time point.

[0007] Furthermore, if the power quality index exceeds the preset index threshold, the operation data at the current time point is marked as abnormal data, that is, there is an abnormality, otherwise, there is no abnormality; for each data marked as abnormal, the duration, occurrence time and abnormality type of the abnormal data are recorded; According to the number of abnormal data points and the corresponding duration, the stability coefficient of the current microgrid unit is calculated: stability coefficient = (1-proportion of abnormal data points) × (1-average abnormal duration coefficient), where the proportion of abnormal data points = the number of abnormal data points / the total number of data points, and the average abnormal duration coefficient = [∑ (duration of abnormal data × abnormal severity weight)] / total abnormal duration.

[0008] Furthermore, the calculation of the weight of each node includes: The network topology is represented as a topological matrix, where rows and columns represent nodes respectively. The elements in the matrix represent the connection relationship between nodes and their weights. If there is a connection between two nodes, the element at the corresponding position in the matrix is ​​the connection weight; if there is no connection, the element is 0 or null. According to the topology matrix, the weight of each node is calculated using the following formula: ; in, represents the weight of node i, d represents the damping factor, represents the connection from node j to node i, represents the weight of node j, Represents the number of outbound links of node j.

[0009] Furthermore, the k-means++ algorithm is used to divide all nodes into different areas, including: Initialize the number of clusters K, the maximum number of iterations, and the convergence threshold; randomly select a node from all nodes as the first cluster center, and for each remaining node, calculate the square of the minimum distance between the node and the selected initial cluster center, and use the square of the minimum distance as the probability weight of the node; based on the probability weight, randomly select the next initial cluster center, so that the probability of selecting a node farther away from the selected center as the new center is higher; repeat the above steps until K initial cluster centers are selected.

[0010] Furthermore, the distance from each node to all initial cluster centers is calculated, and each node is assigned to the cluster center with the closest distance. For each cluster, the average coordinate value of all its member nodes is calculated as the new cluster center. Check whether the convergence condition is met: the cluster center has not changed or the change is less than the preset convergence threshold. If the convergence condition is not met, repeat the above steps until the convergence condition is met and stop the iteration; When the algorithm converges, all nodes are assigned to the nearest cluster center according to the final cluster center to form K cluster areas; Furthermore, administrative division information is obtained. When several cluster areas belong to the same administrative area, the cluster areas within the administrative area are merged into one area. When a cluster area contains several administrative areas, it is divided according to the boundaries of the administrative area into several areas corresponding to the administrative areas. The stability coefficient and weight of each node in the same area are obtained, and the comprehensive evaluation value of each node is calculated: comprehensive evaluation value = stability coefficient × weight.

[0011] Furthermore, the local clustering coefficient of the faulty node is calculated using the following formula: ; in, represents the local clustering coefficient of faulty node i, represents the set of neighbor nodes of node i, represents the number of edges that actually exist between neighboring nodes of node i, represents the maximum number of edges between neighboring nodes of node i, Represents a set of neighbor nodes size.

[0012] Furthermore, the connectivity between the faulty node and the local central node is calculated through the degree between the nodes. The calculation formula is as follows: ; in, represents the connectivity between the faulty node i and the local central node j, represents the degree of faulty node i, represents the degree of the local central node j; The priority of each faulty node is calculated based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node: priority = local clustering coefficient × connectivity.

[0013] An electric energy safety management system based on a cloud platform, comprising: Data acquisition module, which collects the operating data of microgrid units in the power grid and sends it to the cloud platform; The power quality analysis module obtains the operating data of the microgrid unit from the cloud platform, calculates the power quality indicators corresponding to each power quality parameter, determines whether there are abnormalities in the operating data at each time point, counts the number of data points with abnormalities and the corresponding duration, and calculates the stability coefficient of the current microgrid unit; The network topology analysis module regards each microgrid unit as a node in the power network. Each node has a unique identifier. According to the physical connection or logical connection between the microgrid units, a connection relationship is established between the nodes, a weight is assigned to each connection relationship, the topology of the power network is constructed, and the weight of each node is calculated; The local center point selection module uses the k-means++ algorithm to divide all nodes into different areas according to the geographical location information and administrative division information of all nodes, calculates the comprehensive evaluation value of each node, and selects the node with the highest comprehensive evaluation value as the local center node of each area; The fault repair module traverses the neighboring nodes of the faulty node and counts the connections between the nodes when a power safety fault occurs in multiple microgrid units in any area. It calculates the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node through the degree between the nodes. It calculates the priority of each faulty node based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node, and performs repairs based on the priority of the faulty node.

[0014] (III) Beneficial effects The present invention provides a cloud platform-based electric energy safety management system and method, which has the following beneficial effects: (1) By obtaining the operating data of the microgrid unit from the cloud platform and calculating the power quality indicators in real time, the power quality problems in the power grid can be discovered in time. Once the power quality indicators exceed the preset threshold, it can be determined whether there are any abnormalities in the operating data, and the number and duration of abnormal data points can be counted. Based on this information, the stability coefficient of the microgrid unit can be calculated, which can more accurately reflect the stability status of the microgrid unit and provide a reliable decision-making basis for operation and maintenance personnel.

[0015] (2) According to the physical or logical connection between microgrid units, connection relationships are established between nodes and weights are assigned to construct the topological structure of the power network. This can clearly show the connection relationship and mutual influence between the nodes in the power network, which helps to better understand the overall structure and operating status of the power network. At the same time, through the analysis of the connection relationship weights, the key nodes and weak links in the power network can be identified, providing strong support for optimizing the power network structure.

[0016] (3) By clustering all nodes (microgrid units) using the k-means++ algorithm, microgrid units with similar geographical locations can be divided into the same area, which helps to achieve more efficient regional management and resource scheduling. In different areas formed by clustering, the node with the highest comprehensive evaluation value is selected as the local central node, which can ensure the representativeness, stability and influence of the node in the region.

[0017] (4) By considering the local clustering coefficient of the faulty node and the degree of connectivity with the local central node, the impact of the fault on the power network can be evaluated more comprehensively. Prioritize the repair of nodes that have a greater impact on network stability, which helps reduce the impact of the fault on the entire power network and enhance the stability of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the structure of the power safety management system based on the cloud platform of the present invention; Figure 2 It is a schematic diagram of the steps of the power safety management method based on the cloud platform of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] See also Figure 1 The present invention provides a power safety management method based on a cloud platform, comprising the following steps: Step 1: Collect the operating data of the microgrid units in the power grid, including power quality parameters, equipment status, and load demand, form a standardized data packet, and send it to the cloud platform; The step 1 includes the following contents: Step 101: Configure a standardized communication protocol (such as IEC 61850 or MQTT) for each microgrid unit and set communication parameters, including IP address, port number, communication frequency, etc., to ensure that the microgrid unit can establish a stable communication connection with the cloud platform; Step 102: The microgrid unit collects power quality parameters (voltage, current, frequency, power factor, etc.), equipment status (such as operating status, fault alarm, etc.), load demand and other operating data through sensors, and packages the collected data according to the requirements of the communication protocol to form a standardized data packet. The microgrid unit sends the packaged data packet to the cloud platform through the configured communication protocol; Step 103: The cloud platform receives data packets from each microgrid, parses the data packets according to the communication protocol, extracts operation data such as power quality parameters, equipment status, and load demand, pre-processes the operation data, such as filtering, denoising, and outlier detection, and stores the pre-processed data in the database of the cloud platform.

[0021] When using, combine the contents of step 101 to step 103: By configuring a standardized communication protocol for each microgrid unit and setting corresponding communication parameters, ensuring that the data from different microgrid units have a unified format and structure, it helps the cloud platform to efficiently receive, parse and process the data, avoiding the processing complexity and error rate caused by inconsistent data formats. By collecting the power quality parameters, equipment status, load demand and other operating data of the microgrid units in real time and sending them to the cloud platform in real time, real-time monitoring of the microgrid units in the power grid can be achieved.

[0022] Step 2: Obtain the operating data of the microgrid unit from the cloud platform, calculate the power quality index corresponding to each power quality parameter, determine whether there is an abnormality in the operating data at each time point, count the number of data points with abnormalities and the corresponding duration, and calculate the stability coefficient of the current microgrid unit; The step 2 includes the following contents: Step 201: Obtaining the operation data of the microgrid unit from the cloud platform, and calculating the power quality indicators corresponding to each power quality parameter, including but not limited to: obtaining voltage data from the cloud platform, and calculating the voltage fluctuation rate at each time point: UD=U / U0×100%, where U represents the voltage fluctuation amount, and U0 represents the rated voltage; obtaining current data from the cloud platform, using fast Fourier transform to calculate the harmonic current and fundamental current, and calculating the current harmonic content: current harmonic content=effective value of harmonic current / effective value of fundamental current×100%; obtaining power factor data from the cloud platform, and calculating the power factor: PF=P / S, where P represents active power, and S represents apparent power. According to the continuous power factor data, the power factor change rate is calculated, that is, the ratio of the difference between the power factors at adjacent time points to the power factor at the previous time point; Step 202: according to the national power quality standards (such as GB / T 14549-1993, GB / T 18481-2001, etc.), set the index threshold corresponding to each power quality index, compare the power quality index at each time point with the preset index threshold, and judge whether the operation data at each time point is abnormal. If the power quality index exceeds the preset index threshold, the operation data at the current time point is marked as abnormal data, that is, there is an abnormality. Otherwise, there is no abnormality. Step 203: for each data marked as abnormal, i.e., abnormal data point, calculate the duration of the abnormal data, i.e., the time period from the data point to the restoration of the normal value (i.e., below the threshold), and record the duration, occurrence time, and abnormal type (i.e., the corresponding power quality indicator) of the abnormal data; Step 204: Calculate the stability coefficient of the current microgrid unit according to the number of abnormal data points and the corresponding duration, and determine the stability of the current microgrid unit. The calculation formula is as follows: stability coefficient = (1-proportion of abnormal data points) × (1-average abnormal duration coefficient), where the proportion of abnormal data points = the number of abnormal data points / the total number of data points, and the average abnormal duration coefficient = [∑ (duration of abnormal data × abnormal severity weight)] / total abnormal duration; It should be noted that the abnormality severity weight is set according to the severity of the abnormality type (such as voltage fluctuation, current harmonics, power factor change, etc.), which is usually determined through expert evaluation or historical data analysis. According to the calculated stability coefficient, the stability of the current microgrid unit can be determined. The higher the stability coefficient, the more stable the microgrid unit, and vice versa. When used, combine the contents of step 201 to step 204: By obtaining the operating data of the microgrid unit from the cloud platform and calculating the power quality indicators in real time, power quality problems in the power grid can be discovered in a timely manner. Once the power quality indicators exceed the preset threshold, it can be determined whether there are abnormalities in the operating data, and the number and duration of abnormal data points can be counted. The stability coefficient of the microgrid unit can be calculated based on this information, which can more accurately reflect the stability status of the microgrid unit and provide a reliable decision-making basis for operation and maintenance personnel.

[0023] Step 3: Consider each microgrid unit as a node in the power network. Each node has a unique identifier. According to the physical connection or logical connection between the microgrid units, a connection relationship is established between the nodes. A weight is assigned to each connection relationship, the topological structure of the power network is constructed, and the weight of each node is calculated. The step three includes the following contents: Step 301: each microgrid unit is regarded as a node in the power network, each node has a unique identifier (such as an IP address, microgrid unit number, etc.), and contains basic information of the microgrid unit, such as geographical location, capacity, type of distributed energy connected, etc.; Step 302: According to the physical connection (such as transmission line, communication line) or logical connection (such as energy dispatching protocol, information sharing protocol) between microgrid units, a connection relationship is established between nodes to form a topological structure of the power network, and a weight is assigned to each connection relationship; It should be noted that these connection relationships constitute the topological structure of the network. The connection relationship can be directed (such as the direction of power flow) or undirected (such as only indicating the existence of a connection). The weight of the connection relationship reflects its importance or influence. The weight is determined by the hierarchical analysis method based on a variety of factors, including the capacity, transmission efficiency, stability, and communication speed of the connection line. The larger the weight, the greater the role of the connection in the network. Step 303: The network topology structure is represented as a topology matrix, where rows and columns represent nodes respectively, and the elements in the matrix represent the connection relationship between nodes and their weights. If there is a connection between two nodes, the element at the corresponding position in the matrix is ​​the connection weight; if there is no connection, the element is 0 or a null value; Step 304: Calculate the weight of each node according to the topology matrix. The calculation formula is as follows: ; in, represents the weight of node i, d represents the damping factor, represents the connection from node j to node i, represents the weight of node j, represents the number of outbound links of node j (i.e., the number of other nodes to which node j links). The above weight formula is iterated until the weight of each node converges; When used, combine the contents of step 301 to step 304: According to the physical or logical connection between microgrid units, connection relationships are established between nodes, and weights are assigned to construct the topological structure of the power network. This can clearly display the connection relationships and mutual influences between nodes in the power network, which helps to better understand the overall structure and operating status of the power network. At the same time, through the analysis of the connection relationship weights, the key nodes and weak links in the power network can be identified, providing strong support for optimizing the power network structure.

[0024] Step 4: Based on the geographical location information and administrative division information of all nodes, use the k-means++ algorithm to divide all nodes into different regions, calculate the comprehensive evaluation value of each node, and select the node with the highest comprehensive evaluation value as the local center node of each region; The step 4 includes the following contents: Step 401: Obtain the geographic location information of all nodes (microgrid units), including but not limited to latitude and longitude coordinates, and the region where they are located. Collect administrative division information, including the boundaries and names of administrative regions at all levels, and use the k-means++ algorithm to divide all nodes into different regions, including: Step 4011: Initialize the number of clusters K, and determine the number of regions K that you want to divide based on prior knowledge of administrative divisions or actual needs; set the maximum number of iterations of the algorithm, and set a reasonable maximum number of iterations to avoid infinite loops; set a convergence threshold for cluster center changes to determine whether the algorithm has converged; The convergence threshold can be set based on experience to set a reasonable threshold, set a smaller threshold (such as 0.001 or smaller) to ensure that the cluster center can stabilize during the iteration process, or adjust the convergence threshold through experiments. By running the algorithm multiple times and observing the changes in the clustering results, a suitable threshold range can be gradually found; Step 4012: Randomly select a node from all nodes as the first cluster center. For each remaining node, calculate the square of the minimum distance (the distance is the physical distance based on the geographical location, the same below) between the node and the selected initial cluster center, and use the square of the minimum distance as the probability weight of the node. Step 4013: randomly select the next initial cluster center according to the probability weight, so that the probability of selecting a node far from the selected center as the new center is higher; Step 4014: repeat the above steps 4012-4013 until K initial cluster centers are selected; Step 4015: Calculate the distance between each node and all initial cluster centers, and assign each node to the cluster center with the closest distance; Step 4016: For each cluster, calculate the average coordinate value of all its member nodes as the new cluster center; Step 4017: Check whether the convergence condition is met: the cluster center has not changed or the change is less than the preset convergence threshold. If the convergence condition is not met, repeat steps 4015-4016 until the convergence condition is met and stop iteration; Step 4018: When the algorithm converges, all nodes are assigned to the nearest cluster center according to the final cluster center to form K cluster regions; Step 402: Identify the boundaries between cluster regions and administrative divisions. When several cluster regions belong to the same administrative region, merge the cluster regions in the administrative region into one region. When one cluster region contains several administrative regions, divide them according to the boundaries of the administrative regions into several regions corresponding to the administrative regions. Step 403: Obtain the stability coefficient and weight of each node (i.e., microgrid unit) in the same area, calculate the comprehensive evaluation value of each node: comprehensive evaluation value = stability coefficient * weight, sort the comprehensive evaluation values ​​of all nodes in the same area, and select the node with the highest comprehensive evaluation value as the local central node according to the sorting result; When used, combine the contents of step 401 to step 403: By clustering all nodes (microgrid units) using the k-means++ algorithm, microgrid units with similar geographical locations can be divided into the same area, which helps to achieve more efficient regional management and resource scheduling. In different areas formed by clustering, the node with the highest comprehensive evaluation value is selected as the local central node, which can ensure the representativeness, stability and influence of the node in the region.

[0025] Step 5: When multiple microgrid units in any area fail, traverse the neighboring nodes of the faulty node, count the connections between the nodes, calculate the local clustering coefficient of the faulty node, calculate the connectivity between the faulty node and the local central node through the degree between the nodes, and calculate the priority of each faulty node based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node. Repair the faulty node according to its priority.

[0026] The step five includes the following contents: Step 501: When multiple microgrid units in any area fail, all failed nodes are identified through the cloud platform (i.e., the method described in step 2), and specific information of the failure, such as the failure type, occurrence time, etc., is recorded; Step 502: Through the network topology, traverse the neighboring nodes of the faulty node, count the connections between the nodes, and calculate the local clustering coefficient of the faulty node. The calculation formula is as follows: ; in, represents the local clustering coefficient of faulty node i, represents the set of neighbor nodes of node i, represents the number of edges that actually exist between neighboring nodes of node i, represents the maximum number of edges between neighboring nodes of node i, Represents a set of neighbor nodes size.

[0027] It should be noted that the local clustering coefficient reflects the compactness of the network around the faulty node. In the power network, a high local clustering coefficient of a node means that there are more connections between its neighboring nodes, that is, the local network structure where the node is located is relatively dense. This dense network structure may be more likely to spread the fault or affect more nodes when a fault occurs. Therefore, the faulty node with a high local clustering coefficient should have a relatively high repair priority to prevent the fault from spreading further in the network. Step 503: Calculate the connectivity between the faulty node and the local central node through the degree between the nodes. The calculation formula is as follows: ; in, represents the connectivity between the faulty node i and the local central node j, represents the degree of faulty node i, represents the degree of the local central node j; It should be noted that local central nodes refer to nodes with higher comprehensive evaluation values ​​in a certain area. These nodes usually play important roles in the network, such as energy dispatch and information transmission. The connectivity between the faulty node and the local central node reflects the degree of influence of the faulty node on the local central node. The higher the connectivity, the closer the connection between the faulty node and the local central node. Once the faulty node fails, the greater the impact on the local central node and even the entire area. Therefore, the repair priority of the faulty node with high connectivity to the local central node should be increased accordingly. Step 504: The local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node are combined to calculate the priority of each faulty node: priority = local clustering coefficient × connectivity; Step 505: Sort and repair all faulty nodes according to the priority of each faulty node. The higher the priority of the node, the higher the priority of the repair. According to the sorting result, determine the order of repair work. According to the determined repair order, arrange maintenance personnel and equipment to go to the fault site to perform repair work.

[0028] When used, combine the contents of step 501 to step 505: By considering the local clustering coefficient of the faulty node and the connectivity with the local central node, the impact of the fault on the power network can be evaluated more comprehensively, and those nodes that have a greater impact on network stability can be repaired first, which helps reduce the impact of the fault on the entire power network and enhance the stability of the network.

[0029] See also Figure 2 The present invention also provides a power safety management system based on a cloud platform, comprising: a data acquisition module, a power quality analysis module, a network topology analysis module, a local center point selection module and a fault repair module; wherein, Data acquisition module, which collects the operating data of microgrid units in the power grid and sends it to the cloud platform; The power quality analysis module obtains the operating data of the microgrid unit from the cloud platform, calculates the power quality indicators corresponding to each power quality parameter, determines whether there are abnormalities in the operating data at each time point, counts the number of data points with abnormalities and the corresponding duration, and calculates the stability coefficient of the current microgrid unit; The network topology analysis module regards each microgrid unit as a node in the power network. Each node has a unique identifier. According to the physical connection or logical connection between the microgrid units, a connection relationship is established between the nodes, a weight is assigned to each connection relationship, the topology of the power network is constructed, and the weight of each node is calculated; The local center point selection module uses the k-means++ algorithm to divide all nodes into different areas according to the geographical location information and administrative division information of all nodes, calculates the comprehensive evaluation value of each node, and selects the node with the highest comprehensive evaluation value as the local center node of each area; The fault repair module traverses the neighboring nodes of the faulty node and counts the connections between the nodes when a power safety fault occurs in multiple microgrid units in any area. It calculates the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node through the degree between the nodes. It calculates the priority of each faulty node based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node, and performs repairs based on the priority of the faulty node.

[0030] In the application, the several formulas involved are all calculated by removing dimensions and taking their numerical values. The formula is a formula of the most recent real situation obtained by collecting a large amount of data and performing software simulation. The coefficients in the formula are set by technicians in this field according to actual conditions.

[0031] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in combination with electronic hardware, computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0032] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0033] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A power safety management method based on a cloud platform, characterized in that: The following steps are involved: Collect the operating data of microgrid units in the power grid and send it to the cloud platform; Obtain the operating data of the microgrid unit from the cloud platform, calculate the power quality indicators corresponding to each power quality parameter, determine whether there are abnormalities in the operating data at each time point, count the number of data points with abnormalities and the corresponding duration, and calculate the stability coefficient of the current microgrid unit; Each microgrid unit is regarded as a node in the power network. Each node has a unique identifier. According to the physical connection between the microgrid units, a connection relationship is established between the nodes. A weight is assigned to each connection relationship, the topological structure of the power network is constructed, and the weight of each node is calculated. According to the geographical location information and administrative division information of all nodes, the k-means++ algorithm is used to divide all nodes into different regions, calculate the comprehensive evaluation value of each node, and select the node with the highest comprehensive evaluation value as the local center node of each region; When power safety faults occur in multiple microgrid units in any area, the neighboring nodes of the faulty node are traversed, and the connection status between the nodes is counted. The local clustering coefficient of the faulty node is calculated, and the connectivity between the faulty node and the local central node is calculated through the degree between the nodes. The local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node are combined to calculate the priority of each faulty node, and maintenance is performed according to the priority of the faulty node.

2. The power safety management method based on a cloud platform according to claim 1, characterized in that: Obtain the operating data of the microgrid unit from the cloud platform and calculate the power quality indicators corresponding to each power quality parameter, including: Obtain voltage data from the cloud platform and calculate the voltage fluctuation rate at each time point , where U represents the voltage fluctuation and U0 represents the rated voltage; obtain current data from the cloud platform, use fast Fourier transform to calculate harmonic current and fundamental current, and calculate the current harmonic content: current harmonic content = effective value of harmonic current / effective value of fundamental current × 100%; obtain power factor data from the cloud platform, calculate the power factor PF: PF=P / S, where P represents active power and S represents apparent power. The power factor change rate is obtained by calculating the ratio of the difference between the power factors at adjacent time points to the power factor at the previous time point.

3. The power safety management method based on a cloud platform according to claim 2 is characterized in that: If the power quality index exceeds the preset index threshold, the operating data at the current time point is marked as abnormal data, that is, there is an abnormality, otherwise, there is no abnormality; for each data marked as abnormal, the duration, occurrence time and abnormality type of the abnormal data are recorded; According to the number of abnormal data points and the corresponding duration, the stability coefficient of the current microgrid unit is calculated: stability coefficient = (1-proportion of abnormal data points) × (1-average abnormal duration coefficient), where the proportion of abnormal data points = the number of abnormal data points / the total number of data points, and the average abnormal duration coefficient = [∑ (duration of abnormal data × abnormal severity weight)] / total abnormal duration.

4. The power safety management method based on a cloud platform according to claim 1, characterized in that: Calculating the weight of each node includes: The network topology is represented as a topological matrix, where rows and columns represent nodes respectively. The elements in the matrix represent the connection relationship between nodes and their weights. If there is a connection between two nodes, the element at the corresponding position in the matrix is ​​the connection weight; if there is no connection, the element is 0 or null. According to the topology matrix, the weight of each node is calculated using the following formula: ； in, represents the weight of node i, d represents the damping factor, represents the connection from node j to node i, represents the weight of node j, Represents the number of outbound links of node j.

5. The power safety management method based on a cloud platform according to claim 1, characterized in that: Use the k-means++ algorithm to divide all nodes into different areas, including: Initialize the number of clusters K, the maximum number of iterations, and the convergence threshold; randomly select a node from all nodes as the first cluster center, and for each remaining node, calculate the square of the minimum distance between the node and the selected initial cluster center, and use the square of the minimum distance as the probability weight of the node; based on the probability weight, randomly select the next initial cluster center, so that the probability of selecting a node farther away from the selected center as the new center is higher; repeat the above steps until K initial cluster centers are selected.

6. The power safety management method based on a cloud platform according to claim 5, characterized in that: Calculate the distance from each node to all initial cluster centers, and assign each node to the cluster center with the closest distance; for each cluster, calculate the average coordinates of all its member nodes as the new cluster center; Check whether the convergence condition is met: the cluster center has not changed or the change is less than the preset convergence threshold. If the convergence condition is not met, repeat the above steps until the convergence condition is met and stop the iteration; When the algorithm converges, all nodes are assigned to the nearest cluster center according to the final cluster center to form K cluster areas.

7. The cloud platform-based power safety management method according to claim 6, characterized in that: Obtain administrative division information. When several cluster areas belong to the same administrative area, merge the cluster areas within the administrative area into one area. When a cluster area contains several administrative areas, divide it according to the boundaries of the administrative area and divide it into several areas corresponding to the administrative area. Obtain the stability coefficient and weight of each node in the same area, and calculate the comprehensive evaluation value of each node: comprehensive evaluation value = stability coefficient × weight.

8. The power safety management method based on a cloud platform according to claim 1, characterized in that: Calculate the local clustering coefficient of the faulty node. The calculation formula is as follows: ； in, represents the local clustering coefficient of faulty node i, represents the set of neighbor nodes of node i, represents the number of edges that actually exist between neighboring nodes of node i, represents the maximum number of edges between neighboring nodes of node i, Represents a set of neighbor nodes size.

9. The cloud platform-based power safety management method according to claim 8, characterized in that: The connectivity between the faulty node and the local central node is calculated by the degree between the nodes. The calculation formula is as follows: ； in, represents the connectivity between the faulty node i and the local central node j, represents the degree of faulty node i, represents the degree of the local central node j; The priority of each faulty node is calculated based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node: priority = local clustering coefficient × connectivity.

10. A cloud platform-based electric energy safety management system, used to implement the method according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, which collects the operating data of microgrid units in the power grid and sends it to the cloud platform; The power quality analysis module obtains the operating data of the microgrid unit from the cloud platform, calculates the power quality indicators corresponding to each power quality parameter, determines whether there are abnormalities in the operating data at each time point, counts the number of data points with abnormalities and the corresponding duration, and calculates the stability coefficient of the current microgrid unit; The network topology analysis module regards each microgrid unit as a node in the power network. Each node has a unique identifier. According to the physical connection or logical connection between the microgrid units, a connection relationship is established between the nodes, a weight is assigned to each connection relationship, the topology of the power network is constructed, and the weight of each node is calculated; The local center point selection module uses the k-means++ algorithm to divide all nodes into different areas according to the geographical location information and administrative division information of all nodes, calculates the comprehensive evaluation value of each node, and selects the node with the highest comprehensive evaluation value as the local center node of each area; The fault repair module traverses the neighboring nodes of the faulty node and counts the connections between the nodes when a power safety fault occurs in multiple microgrid units in any area. It calculates the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node through the degree between the nodes. It calculates the priority of each faulty node based on the local clustering coefficient of the faulty node and the connectivity between the faulty node and the local central node, and performs repairs based on the priority of the faulty node.

Images