User-to-main transformer load convergence method and system based on multi-level tree diagram

Abstract

The invention discloses a user-to-main transformer load convergence method and system based on a multi-level tree diagram. The method comprises the following steps of: acquiring a topological structure and related ledger and power data of each level of equipment from a user to a 220kV main transformer of a power grid as initial data; constructing a power grid topology tree diagram with a 220kV main root and a user leaf, calculating a load convergence value and a deviation rate of each node, and marking convergence participation conditions; and judging whether the deviation rate of the 220kV main transformer is normal or not based on a set threshold value. And if the abnormal main transformer lower-layer equipment is abnormal, marking a deviation label for the abnormal main transformer lower-layer equipment, analyzing a transaction data set by using an FPGrowth algorithm to find out an associated frequent item set, determining a problem topology layer through the maximum confidence coefficient, and carrying out optimization adjustment on the layer to correct load convergence. By implementing the method provided by the invention, hierarchical topology information can be effectively integrated, and refined load analysis and prediction are supported, so that the operation performance of the power distribution network is improved.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and in particular to a user-to-main transformer load aggregation method and system based on a multi-level tree diagram. Background Technology

[0002] In recent years, with the widespread integration of flexible loads such as distributed renewable energy, electric vehicles, and user-side energy storage devices, user electricity consumption patterns have exhibited significant dynamic and fluctuating characteristics. This change has increased the complexity of low-voltage power grid load forecasting and management, posing challenges to power supply reliability and grid operation economy. As a key node connecting the high-voltage transmission network and the low-voltage distribution network, the main transformer (referred to as "main transformer") plays a crucial role in voltage transformation and load distribution.

[0003] However, current traditional methods for main transformer load aggregation mainly rely on a fixed calculation model, which directly aggregates the load data of each user. This flat load aggregation method fails to fully consider the hierarchical topology within the power system, leading to the following problems: First, due to the lack of hierarchical modeling, it is difficult to accurately track the source of errors. When metering errors accumulate gradually from multiple links such as user meters, distribution transformer metering equipment, and main transformer gate meters, the final load aggregation result may deviate significantly from the actual load conditions. Second, the fixed-mode load aggregation method cannot adapt to rapidly changing load conditions, limiting the flexibility and response speed of main transformer operation adjustments, thereby affecting the stability and efficiency of the entire distribution network.

[0004] Therefore, it is necessary to design a new method that can effectively integrate hierarchical topology information, support refined load analysis and forecasting, improve the operating performance of the distribution network, enhance the accuracy of main transformer load aggregation, reduce the uncertainty caused by multi-level metering errors, and enhance the adaptability to dynamic load environments. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a user-to-main transformer load aggregation method and system based on a multi-level tree diagram.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a user-to-main transformer load aggregation method based on a multi-level tree diagram, comprising: Obtain the corresponding topology, user ledger, distribution transformer ledger, line ledger, and main transformer ledger for users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers, and obtain the power data and switch position data of all equipment to obtain the initial data; The user, distribution transformer, feeder, 35kV / 110kV main transformer, and 220kV main transformer equipment are regarded as nodes in the graph, and the connection relationship is regarded as the edge. The 220kV main transformer is the root node and the user is the leaf node. The power grid topology tree diagram with multi-level relationship between user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer is constructed. Using the power grid topology tree diagram and the initial data, calculate the load aggregation value and load aggregation deviation rate of each layer of nodes, and label whether the nodes of the next layer participate in aggregation. Based on the upper and lower limit thresholds of the load convergence deviation rate index, determine whether the deviation rate of the 220kV main transformer is normal. If the deviation rate of the 220kV main transformer is abnormal, then for the 220kV main transformer with abnormal deviation rate, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the label, each device node at the lower level is labeled with a deviation tag, and a deviation transaction dataset is constructed with time period as the transaction unit. The FP_Growth association rule algorithm is used to mine the frequently associated itemsets with the abnormal deviation rate of the main transformer as the target. Calculate the confidence level of the associated frequent itemsets of the 220kV main transformer deviation rate anomaly, and take the lowest topology layer in the power grid topology tree diagram corresponding to the associated frequent itemsets with the highest confidence level as the problem topology layer of the main cause of the 220kV main transformer deviation rate anomaly. The next layer of the problematic topology is pruned or added to correct the convergence of user loads to the main transformer.

[0007] The further technical solution is as follows: The user, distribution transformer, feeder, 35kV / 110kV main transformer, and 220kV main transformer equipment are considered as nodes in a graph, and the connection relationships are considered as edges. With the 220kV main transformer as the root node and users as leaf nodes, a multi-level power grid topology tree diagram is constructed, comprising: Topology analysis is used to obtain the relationships between low-voltage users, medium-voltage lines, lines and buses, main transformer bus topology, and high-voltage main transformers and low-voltage main transformers in users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers. Using the 220kV main transformer as the root node, the 35kV / 110kV main transformers at the lower level are found through the relationship between the high-voltage and low-voltage main transformers. The 220kV and 35kV / 110kV main transformers are regarded as nodes of the graph, and the connection relationship is regarded as the edge. The first-level power grid topology tree diagram of 220kV main transformer-35kV / 110kV main transformer is constructed. By identifying the feeders below the 35kV / 110kV main transformer through the relationship between the lines and busbars and the main transformer busbar topology, and considering the feeders and 35kV / 110kV main transformer equipment as nodes of the graph and the connection relationship as edges, a second-level power grid topology tree diagram of 35kV / 110kV main transformer-feeder is constructed. By identifying the distribution transformers below the feeder through the relationship between the medium-voltage line and the distribution transformer, and treating the distribution transformers and feeder equipment as nodes in a graph and the connection relationships as edges, a third-level power grid topology tree diagram of feeder-distribution transformer is constructed. By identifying the users at the lower level of the distribution transformer through the relationship between low-voltage users and transformers, and treating users and distribution transformer equipment as nodes of a graph, and the connection relationship as edges, a fourth-level power grid topology tree graph of distribution transformer-user is constructed. A multi-level power grid topology tree diagram is constructed by integrating the first-level, second-level, third-level, and fourth-level power grid topology tree diagrams, showing the relationships between users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers.

[0008] The further technical solution is as follows: Utilizing the power grid topology tree diagram and the initial data, calculating the load aggregation value and load aggregation deviation rate of each layer of nodes, and labeling whether the next layer of nodes participates in aggregation, includes: Using the aforementioned power grid topology tree diagram and the initial data, load aggregation is performed level by level based on user load across four levels: distribution transformer, feeder, 35kV / 110kV main transformer, and 220kV main transformer. Switch opening and closing position data are used to tag the nodes at the next level with whether they participate in aggregation. The user load of all participating nodes at the next level is summarized as the load aggregation value for that level. The distribution transformer load aggregation value is the sum of the user loads of all participating nodes, the feeder load aggregation value is the sum of the distribution transformer load aggregation values ​​of all participating nodes, and so on down to the 220kV main transformer load aggregation value. For the four levels of distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, the load aggregation deviation rate of each node is calculated by subtracting the load aggregation value from the actual load value of each node and dividing by the absolute value of the actual load value of that node plus the absolute value of the load aggregation value.

[0009] The further technical solution is as follows: The method of determining whether the deviation rate of the 220kV main transformer is normal based on the upper and lower limit thresholds of the load convergence deviation rate index includes: Based on the upper and lower limit thresholds of the load convergence deviation rate index, determine whether the deviation rate of the 220kV main transformer is normal. If the deviation rate of the 220kV main transformer is greater than the upper limit threshold, the deviation rate of the 220kV main transformer is high. If the deviation rate of the 220kV main transformer is less than the lower limit threshold, the deviation rate of the 220kV main transformer is low. Otherwise, the deviation rate of the 220kV main transformer is normal.

[0010] The further technical solution is as follows: If the deviation rate of the 220kV main transformer is abnormal, then for the 220kV main transformer with abnormal deviation rate, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the label, each lower-level device node is labeled with a deviation tag, and a deviation transaction dataset is constructed with time period as the transaction unit. Using the FP_Growth association rule algorithm, frequent association itemsets targeting abnormal main transformer deviation rate are mined, including: For 220kV main transformers with abnormal deviation rates, based on the upper and lower limit thresholds of the load aggregation deviation rate index and the tags, each device node at the lower level is tagged with a deviation tag indicating high deviation rate, low deviation rate, normal deviation rate, or not participating in aggregation. Obtain historical data on the current time when the main transformer deviation rate is abnormal, and construct a deviation transaction dataset with high deviation rate, low deviation rate, and no aggregation label for device nodes, using time period as the transaction unit; Using the FP_Growth association rule algorithm, a minimum support threshold is set, and frequent association itemsets targeting the current time main variable deviation rate anomaly are mined based on the deviation transaction dataset.

[0011] The further technical solution is as follows: The confidence level of the associated frequent itemsets of the 220kV main transformer deviation rate anomaly is calculated, and the lowest layer of the power grid topology tree corresponding to the associated frequent itemset with the highest confidence level is taken as the problem topology layer of the main cause of the 220kV main transformer deviation rate anomaly, including: Traverse the associated frequent itemsets of the 220kV main transformer deviation rate anomaly, calculate the confidence level of the 220kV main transformer deviation rate anomaly derived from the lower-level associated frequent itemsets of the 220kV main transformer, and use it as the confidence level of each associated frequent itemset of the 220kV main transformer deviation rate anomaly. The most confident frequently associated itemset is selected as the most frequently associated itemset that is the main cause of the abnormal main transformer load convergence deviation rate. According to the hierarchy of the power grid topology tree diagram, the lowest level of the frequently associated topology in the set of the main causes of the abnormal deviation rate of the 220kV main transformer is taken as the problem topology layer of the main causes of the abnormal deviation rate of the 220kV main transformer.

[0012] The further technical solution is as follows: The next layer of the problematic topology layer is pruned or augmented to correct the convergence of user load to the main transformer, including: Based on the problem topology layer, pruning or branching operations are performed on the next layer of equipment nodes according to deviation labels or load contribution, and the progressive load convergence deviation rate and change significance are recalculated. If the load aggregation deviation rate of the 220kV main transformer after pruning or adding branches is normal and the change significance exceeds the threshold, then the corrected step-by-step load aggregation result is output; otherwise, continue to adjust until the optimal node is found or the node that minimizes the absolute value of the deviation rate and maximizes the change significance is selected as the optimization scheme and the result is output.

[0013] The further technical solution is as follows: based on the problem topology layer, the next-level device nodes are sorted by deviation label or load contribution and pruned or added, and the progressive load convergence deviation rate and change significance are recalculated, including: According to the descending order of the deviation labels or load contribution of the equipment nodes in the next layer of the problem topology layer, the equipment nodes in the next layer of the problem topology layer are traversed, pruned, or added. The load is then re-aggregated step by step from the next layer of the problem topology layer to the 220kV main transformer. The main transformer load aggregation deviation rate after pruning or adding and the significance of the change in the main transformer deviation rate before and after pruning or adding are calculated. The significance of the change in the main transformer deviation rate is defined as the absolute value of the difference between the main transformer load aggregation deviation rate before pruning or adding and the main transformer load aggregation deviation rate after pruning or adding, divided by the absolute value of the main transformer load aggregation deviation rate before pruning or adding.

[0014] The further technical solution is as follows: If the load aggregation deviation rate of the 220kV main transformer after pruning or branching is normal and the change significance exceeds the threshold, then the corrected step-by-step load aggregation result is output; otherwise, the adjustment continues until the optimal node is found or the node that minimizes the absolute value of the deviation rate and maximizes the change significance is selected as the optimization scheme and the result is output, including: If the load aggregation deviation rate of the 220kV main transformer after pruning or adding branches is normal and the change is significant enough to exceed the threshold, then find the next layer of equipment node in the problem topology layer that meets the conditions, and output the step-by-step load aggregation correction result based on user load: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer. Otherwise, repeat the process of pruning or adding branches to the next-level equipment nodes according to the deviation label or load contribution based on the problem topology layer, and recalculate the step-by-step load aggregation deviation rate and change significance until the next-level equipment node of the problem topology layer that meets the conditions is found, and output the corrected step-by-step load aggregation result based on user load: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer. If the conditions cannot be met, the equipment nodes in the next layer of the problem topology layer are selected according to the principle of having the smallest absolute value of the main transformer load aggregation deviation rate after pruning or adding branches and the largest significant change in the main transformer deviation rate. The corrected load aggregation results of distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on user load are then output.

[0015] This invention also provides a user-to-main transformer load aggregation system based on a multi-level tree diagram, comprising: The data acquisition unit is used to acquire the corresponding topology, user ledger, distribution transformer ledger, line ledger, and main transformer ledger of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, and to acquire the power data and switch position data of all equipment to obtain the initial data. The tree diagram construction unit is used to treat users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers as nodes in a graph, and the connection relationships as edges. With the 220kV main transformer as the root node and users as leaf nodes, a multi-level power grid topology tree diagram with user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationship is constructed. The calculation unit is used to calculate the load aggregation value and load aggregation deviation rate of each layer node using the power grid topology tree diagram and the initial data, and to label whether the next layer node participates in aggregation. The judgment unit is used to determine whether the deviation rate of the 220kV main transformer is normal based on the upper and lower limit thresholds of the load convergence deviation rate index. The mining unit is used to, if the deviation rate of the 220kV main transformer is abnormal, then for the 220kV main transformer with abnormal deviation rate, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the label, to label each device node at the lower level, and to construct a deviation transaction dataset with time period as transaction unit, and to mine the frequently associated itemsets with the main transformer deviation rate abnormality as the target using the FP_Growth association rule algorithm. The topology layer construction unit is used to calculate the confidence level of the associated frequent itemsets of the 220kV main transformer deviation rate anomaly, and take the lowest topology layer in the power grid topology tree diagram corresponding to the associated frequent itemsets with the highest confidence level as the problem topology layer of the main cause of the 220kV main transformer deviation rate anomaly. The adjustment unit is used to prune or add branches to the next layer of the problem topology layer to correct the convergence of user load to the main transformer.

[0016] The advantages of this invention compared to existing technologies are as follows: This invention constructs a multi-level power grid topology tree diagram with relationships between users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers. It then uses initial data to calculate the load aggregation value and deviation rate of each level node, marks the aggregation participation status of each level, and determines the operating status of the 220kV main transformer based on the load aggregation deviation rate threshold. For cases of abnormal deviations, the FP_Growth algorithm is used to mine frequently associated itemsets to identify the main causes of the deviations, thereby optimizing and adjusting the problematic topology layer to achieve accurate load aggregation from users to main transformers. This method effectively integrates hierarchical topology information, supports refined load analysis and forecasting, improves the operating performance of the distribution network and the accuracy of main transformer load aggregation, reduces the uncertainty caused by multi-level metering errors, and enhances the system's adaptability to dynamic load environments.

[0017] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the user-to-main transformer load aggregation method based on a multi-level tree diagram provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of a power grid topology tree diagram provided in an embodiment of the present invention; Figure 3 A schematic block diagram of a user-to-main transformer load aggregation system based on a multi-level tree diagram, provided in another embodiment of the present invention; Figure 4 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] Please see Figure 1 , Figure 1 This is a flowchart illustrating the user-to-transformer load aggregation method based on a multi-level tree diagram provided in this invention. This method, applied to a server, integrates the topology and ledger information from users to all levels of equipment on the 220kV main transformer. It uses the power grid topology tree diagram to calculate the load aggregation value and load aggregation deviation rate for each node, marking participation in aggregation. For abnormal deviation rates, the FP_Growth algorithm is used to mine frequently associated itemsets to identify the main causes, and the problematic layers are pruned or augmented to optimize load aggregation. This method effectively integrates hierarchical topology information, supports refined load analysis and forecasting, improves the operating performance of the distribution network and the accuracy of main transformer load aggregation, reduces the uncertainty caused by multi-level metering errors, and enhances the system's adaptability to dynamic load environments. Through detailed load aggregation calculations and intelligent adjustment strategies, this method ensures the efficient and stable operation of the power system.

[0025] Figure 1 This is a flowchart illustrating the user-to-main transformer load aggregation method based on a multi-level tree diagram provided in an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110 to S170.

[0026] S110: Obtain the corresponding topology, user ledger, distribution transformer ledger, line ledger, and main transformer ledger of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, and obtain the power data and switch position data of all equipment to obtain the initial data.

[0027] In this embodiment, the initial data refers to a series of basic information required to execute the user-to-transformer load precise aggregation method based on multi-level tree diagram deviation tracing analysis. This information is crucial for constructing the power grid topology tree diagram and calculating the load aggregation values ​​and deviation rates of equipment at each level. Specifically, the initial data includes the following aspects: Topology: User-Transformer Relationship: Describes the connection between each user's electricity consumption and the corresponding distribution transformer.

[0028] Medium-voltage line-to-transformer relationship: This shows the connection between medium-voltage lines (feeders) and distribution transformers.

[0029] Relationship between lines and busbars: This involves the connection between each feeder and its corresponding busbar.

[0030] Main transformer bus topology: Displays the connection methods of the 35kV / 110kV main transformer and the 220kV main transformer to their respective bus.

[0031] Relationship between high-voltage and low-voltage main transformers: This covers the connection between the 220kV main transformer and the lower-level 35kV / 110kV main transformers.

[0032] Ledger information: User ledger: Records detailed information about all users, such as geographical location and electricity consumption.

[0033] Distribution transformer ledger: contains relevant information about distribution transformers, such as model, installation location, rated power, etc.

[0034] Line ledger: Provides specific parameters of the feeder, including length, type, maximum transmission capacity, etc.

[0035] Main transformer ledger: Lists the attributes of 35kV / 110kV and 220kV main transformers, such as manufacturer, cooling method, voltage level, etc.

[0036] Power data: Power measurement data of various levels of equipment (users, distribution transformers, feeders, 35kV / 110kV main transformers, 220kV main transformers) collected from the D5000 system and the power consumption acquisition system, with a sampling interval of 15 minutes, used for subsequent load aggregation calculation.

[0037] Switch change data: Switch operation records obtained from the main network and distribution network automation system help determine changes in network configuration and are crucial to the accuracy of load aggregation values.

[0038] By comprehensively applying the above information, the multi-layered architecture of the power system can be accurately depicted, enabling detailed load analysis and forecasting. This not only helps identify potential load anomalies but also provides solid data support for optimizing power grid operation strategies. This process emphasizes the accuracy and comprehensiveness of the data, which is fundamental to achieving efficient and reliable power supply.

[0039] S120. Treat users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers as nodes in a graph, and the connection relationships as edges. With the 220kV main transformer as the root node and users as leaf nodes, construct a multi-level power grid topology tree diagram with user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationships.

[0040] In this embodiment, the power grid topology tree diagram refers to a hierarchical structure diagram used to represent the physical connection relationships between various levels of equipment in the power system (including users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers). The diagram is rooted at the 220kV main transformer and connects sequentially downwards to the 35kV / 110kV main transformers, feeders, distribution transformers, and finally the end users, forming a multi-level network. Each level represents different types of equipment and their interconnections.

[0041] In one embodiment, step S120 described above may include steps S121 to S126.

[0042] S121. Obtain the corresponding low-voltage user-transformer relationship, medium-voltage line-transformer relationship, line-bus relationship, main transformer-bus topology relationship, and high-voltage main transformer-low-voltage main transformer relationship in the user, distribution transformer, feeder, 35kV / 110kV main transformer, and 220kV main transformer equipment through topology analysis. S122. Using the 220kV main transformer as the root node, find the lower-level 35kV / 110kV main transformer through the relationship between the high-voltage and low-voltage main transformers. Treat the 220kV and 35kV / 110kV main transformers as nodes of the graph and the connection relationship as edges, and construct the first-level power grid topology tree diagram of 220kV main transformer-35kV / 110kV main transformer.

[0043] In this embodiment, the first-level power grid topology tree diagram of the 220kV main transformer-35kV / 110kV main transformer refers to a hierarchical diagram that takes the 220kV main transformer as the root node and connects to the lower-level 35kV or 110kV main transformers through the relationship between high-voltage and low-voltage main transformers, forming a hierarchical diagram representing the high-voltage power transmission structure.

[0044] S123. Locate the feeders below the 35kV / 110kV main transformer by the relationship between the line and the bus and the main transformer bus topology. Treat the feeders and the 35kV / 110kV main transformer equipment as nodes of the graph and the connection relationship as edges, and construct the second-level power grid topology tree diagram of the 35kV / 110kV main transformer-feeder.

[0045] In this embodiment, the second-layer power grid topology tree diagram of the 35kV / 110kV main transformer-feeder refers to the organizational structure of the medium-voltage power distribution network based on the relationship between the line and the bus and the topology relationship between the main transformer and the bus, with the 35kV or 110kV main transformer and its subordinate feeders as nodes and edges.

[0046] S124. Locate the distribution transformers below the feeder through the medium-voltage line-transformer relationship. Treat the distribution transformers and feeder equipment as nodes in the graph and the connection relationship as edges to construct a third-level power grid topology tree diagram of feeder-distribution transformer.

[0047] In this embodiment, the third-level power grid topology tree diagram of feeder-distribution transformer refers to the identification and connection of feeders and the distribution transformers they serve using the medium-voltage line-transformer relationship, depicting the specific layout of the conversion from medium-voltage power transmission to low-voltage power distribution.

[0048] S125. Find the users below the distribution transformer through the low-voltage user-transformer relationship, regard users and distribution transformer equipment as nodes of the graph, and the connection relationship as edges, and construct the fourth-level power grid topology tree diagram of distribution transformer-user.

[0049] In this embodiment, the fourth-level power grid topology tree diagram of distribution transformer-user refers to determining the users supplied by each distribution transformer based on the relationship between low-voltage transformer and user, constructing a detailed connection diagram from the distribution transformer directly to the final electricity customer, reflecting the actual situation of end-point power distribution.

[0050] S126. Integrate the first-level power grid topology tree diagram, the second-level power grid topology tree diagram, the third-level power grid topology tree diagram, and the fourth-level power grid topology tree diagram to construct a multi-level power grid topology tree diagram with user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationships.

[0051] Specifically, taking the 220kV main transformer as the root node, the lower-level 35kV / 110kV main transformers are found through the relationship between high-voltage and low-voltage main transformers. The 220kV and 35kV / 110kV main transformers are considered as nodes in a graph, and the connections between them are considered as edges, thus constructing the first-level power grid topology tree diagram of the 220kV main transformer-35kV / 110kV main transformer. Let a certain 220kV main transformer be 220kV main transformer A, and the set of lower-level 35kV / 110kV main transformers be denoted as . ,in For the first There are 35kV / 110kV main transformers, and a total of 220kV main transformer A below it. One 35kV / 110kV main transformer; By identifying the feeders below the 35kV / 110kV main transformer through the relationships between lines and busbars, and the main transformer busbar topology, and considering the feeders and 35kV / 110kV main transformer equipment as nodes in a graph, and their connections as edges, a second-level power grid topology tree diagram of the 35kV / 110kV main transformer-feeder is constructed. 35kV / 110kV main transformers The lower layer feeder set is ,in For the first 35kV / 110kV main transformers The lower level feeder line, number 35kV / 110kV main transformers The lower level has a total of One feeder line; By identifying the distribution transformers below the feeder line through the medium-voltage line-transformer relationship, and treating the distribution transformers and feeder equipment as nodes in a graph, with their connections as edges, a third-level power grid topology tree diagram of feeder-distribution transformer is constructed. Let the first... feeder The lower-level distribution transformer set is ,in For the first feeder The lower level The first distribution change, the first feeder The lower level has a total of One variant; By identifying the users below the distribution transformer through the low-voltage transformer-user relationship, and treating users and distribution transformer equipment as nodes in a graph, with the connections between them as edges, a fourth-level power grid topology tree graph of distribution transformer-user is constructed. Let the... Individual distribution change The lower-level user set is ,in For the first Individual distribution change The lower level The user, the first Individual distribution change The lower level has a total of One user; Based on the above layer-by-layer construction, the devices such as users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers are ultimately regarded as nodes in the graph, and the connection relationships between them are regarded as edges. With the 220kV main transformer as the root node and users as leaf nodes, a multi-level power grid topology tree diagram with user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationship is constructed.

[0052] S130. Using the power grid topology tree diagram and the initial data, calculate the load aggregation value and load aggregation deviation rate of each layer of nodes, and label whether the next layer of nodes participates in aggregation.

[0053] In this embodiment, the load aggregation value of each node level refers to the hierarchical load aggregation calculation based on user load, performed on each level (i.e., distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers) using the power grid topology tree diagram and initial data. Specifically, starting from the lowest level (distribution transformer-user), the load values ​​of all participating lower-level nodes are aggregated (e.g., for the distribution transformer level, it is the user load; for the feeder level, it is the distribution transformer load aggregation value), and so on until the highest level (220kV main transformer). Thus, the load aggregation value of each node level represents the sum of the loads of all lower-level nodes covered by that node level.

[0054] Load aggregation deviation rate is an indicator that measures the difference between the actual load and the aggregated load value at each node. It is calculated as follows: for each node, subtract its aggregated load value from its actual load value, then divide by the absolute value of the actual load value plus the absolute value of the aggregated load value. This ratio reflects potential errors or inaccuracies in the load aggregation process, helping to identify which parts of the load forecast or data may have significant deviations, facilitating further analysis and optimization. A smaller deviation rate indicates that the aggregated load value is closer to the actual load value, and the load aggregation process is more accurate; conversely, a larger deviation rate may indicate data problems or the need to adjust the load aggregation algorithm.

[0055] In one embodiment, step S130 described above may include steps S131 to S132.

[0056] S131. Using the power grid topology tree diagram and the initial data, load aggregation is performed level by level based on user load for four levels: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer. The switching position data is used to tag the nodes of the next level with whether they participate in aggregation. The user load of all participating nodes in the next level is summarized as the load aggregation value of the node at this level. The distribution transformer load aggregation value is the sum of the user load of all participating nodes, the feeder load aggregation value is the sum of the distribution transformer load aggregation values ​​of all participating nodes, and so on down to the 220kV main transformer load aggregation value. S132. For the four levels of distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, the load aggregation deviation rate of each node is calculated by subtracting the load aggregation value from the actual load value of each node and dividing by the absolute value of the actual load value of that node plus the absolute value of the load aggregation value.

[0057] In this embodiment, based on the aforementioned multi-level power grid topology tree diagram of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationship, as well as power data and switch position data, let the first... feeder The lower level Individual distribution change In time The actual load value is Distribution transformer The lower level has a total of The user, the first individual users In time The actual load value is Whether or not to participate in the aggregation tag If participating in the aggregation is represented by 1, and not participating in the aggregation is represented by 0, then the distribution change... In time load convergence value for Individual participants gather users in time The actual load values ​​are summarized and calculated using the following formula: ; No. Individual distribution change In time Load convergence deviation rate Its actual load value Subtract load convergence value Divide by the absolute value of the actual load of the node Add the absolute value of the load convergence value The calculation formula is as follows: ; Based on the above results, let the first... 35kV / 110kV main transformers The lower level feeder In time The actual load value is feeder The lower level has a total of The first distribution change, the first Individual distribution change In time The load convergence value Whether or not to participate in the aggregation tag If participating in the convergence is represented by 1, and not participating in the convergence is represented by 0, then the feeder... In time load convergence value for Individual participants converge and distribute changes in time. The sum of load aggregation values ​​is calculated using the following formula: ; No. feeder In time Load convergence deviation rate Its actual load value Subtract load convergence value Divide by the absolute value of the actual load of the node Add the absolute value of the load convergence value The calculation formula is as follows: ; Based on the above results, let the first layer of a certain 220kV main transformer A be... 35kV / 110kV main transformers In time The actual load value is 35kV / 110kV main transformer The lower level has a total of feeder line, number feeder In time The load convergence value Whether or not to participate in the aggregation tag If participation in aggregation is 1, and non-participation is 0, then the 35kV / 110kV main transformer... In time load convergence value for The participating convergence feeder in time The sum of load aggregation values ​​is calculated using the following formula: .

[0058] No. 35kV / 110kV main transformers In time Load convergence deviation rate Its actual load value Subtract load convergence value Divide by the absolute value of the actual load of the node Add the absolute value of the load convergence value The calculation formula is as follows: ; Based on the above results, suppose a certain 220kV main transformer A is in time The actual load value is The 220kV main transformer A has a total of The first 35kV / 110kV main transformer, 35kV / 110kV main transformers In time The load convergence value Whether or not to participate in the aggregation tag If participation in the aggregation is 1 and non-participation is 0, then the 220kV main transformer A will be in time. load convergence value for Each participating unit converges the 35kV / 110kV main transformer in time. The sum of load aggregation values ​​is calculated using the following formula: ; 220kV main transformer A in time Load convergence deviation rate Its actual load value Subtract load convergence value Divide by the absolute value of the actual load of the node Add the absolute value of the load convergence value The calculation formula is as follows: .

[0059] S140. Based on the upper and lower limit thresholds of the load convergence deviation rate index, determine whether the deviation rate of the 220kV main transformer is normal.

[0060] In this embodiment, the deviation rate of the 220kV main transformer is determined to be normal based on the upper and lower limit thresholds of the load convergence deviation rate index. If the deviation rate of the 220kV main transformer is greater than the upper limit threshold, the deviation rate of the 220kV main transformer is high. If the deviation rate of the 220kV main transformer is less than the lower limit threshold, the deviation rate of the 220kV main transformer is low. Otherwise, the deviation rate of the 220kV main transformer is normal.

[0061] If the deviation rate of the 220kV main transformer is high or low, then the deviation rate of the 220kV main transformer is abnormal, that is, the load aggregation from the user to the main transformer is abnormal; otherwise, the load aggregation from the user to the main transformer is normal.

[0062] S150. If the deviation rate of the 220kV main transformer is abnormal, for the 220kV main transformer with abnormal deviation rate, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the label, each device node at the lower level is labeled with a deviation tag, and a deviation transaction dataset is constructed with time period as the transaction unit. The FP_Growth association rule algorithm is used to mine the frequently associated itemsets with the abnormal deviation rate of the main transformer as the target.

[0063] In this embodiment, frequently associated itemsets refer to combinations of device node deviation labels that frequently appear together, mined from the deviation transaction dataset using association rule algorithms such as FP_Growth. These combinations reflect which device nodes tend to have high, low, or normal deviation rates simultaneously within a specific time period, especially patterns related to abnormal deviation rates of the 220kV main transformer. Frequently associated itemsets help identify potential problems or patterns in the system, providing a basis for subsequent analysis and optimization.

[0064] In one embodiment, step S150 described above may include steps S151 to S153.

[0065] S151. For 220kV main transformers with abnormal main transformer deviation rates, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the tags, each lower-level equipment node is tagged with a deviation tag indicating high deviation rate, low deviation rate, normal deviation rate, or not participating in aggregation.

[0066] Assuming that 220kV main transformer A is the 220kV main transformer with an abnormal deviation rate at the current time, based on the above results, let the deviation label set of 220kV main transformer A be... ;in For the 220kV main transformer A deviation label; Assuming there are a total of [number] units below the 220kV main transformer A The 35kV / 110kV main transformer, according to the first 35kV / 110kV main transformer load convergence deviation rate Indicator threshold settings and whether to participate in aggregation labels The upper and lower limits of the load convergence deviation rate index for 35kV / 110kV main transformers are respectively... and , to the next layer Each 35kV / 110kV main transformer is labeled with a deviation tag indicating high deviation rate, low deviation rate, normal deviation rate, or not included in the aggregation. Let the set of deviation tags for the 35kV / 110kV main transformer be [formula missing]. ;in 35kV / 110kV main transformer Deviation label; Assume the first 35kV / 110kV main transformers The lower level has a total of One feeder, based on the feeder load convergence deviation rate Indicator threshold settings and whether to participate in aggregation labels The upper and lower limits of the feeder load convergence deviation rate index are respectively and , to the next layer Each feeder is labeled with a deviation tag indicating high deviation rate, low deviation rate, normal deviation rate, or not participating in the convergence. Let the set of feeder deviation tags be . ;in For feeder Deviation label; Assume the first feeder The lower level has a total of Each distribution transformer, based on the distribution transformer load convergence deviation rate Indicator threshold settings and whether to participate in aggregation labels The upper and lower limits of the distribution transformer load convergence deviation rate index are respectively and , to the next layer Each distribution transformer is labeled with a deviation tag indicating high deviation rate, low deviation rate, normal deviation rate, or not participating in the aggregation. Let the set of distribution transformer deviation tags be . ;in For distribution transformer Deviation label.

[0067] S152. Obtain historical data on the current time period of abnormal main transformer deviation rate, and construct a deviation transaction dataset with high deviation rate, low deviation rate and no participation in the aggregation label of equipment node using time period as the transaction unit.

[0068] In this embodiment, the deviation transaction dataset refers to a data set constructed based on data from a historical period, where each element (called a transaction) represents a device node status record within a time period. Specifically, it contains deviation labels for each device node in different time periods (such as high deviation rate, low deviation rate, normal deviation rate, not participating in aggregation). These labels are set based on the upper and lower limits of the load aggregation deviation rate index and whether each lower-level device node participates in load aggregation. This dataset is organized by time, enabling the tracking of device node status changes and facilitating the discovery of correlations between device nodes.

[0069] Based on the above results, if the 220kV main transformer A is at the current time For 220kV main transformers with abnormal deviation rates, exclude equipment nodes with normal deviation rates, and construct a deviation transaction dataset consisting of four layers: 220kV main transformer - 35kV / 110kV main transformer - feeder - distribution transformer, with high deviation rates, low deviation rates, and no aggregation labels.

[0070] Let the set of deviation events that satisfy either high or low deviation rate at the current time be denoted as . ={ ;in For the 220kV main transformer A at the current time of Deviation label; Assume that at the current time, the 35kV / 110kV main transformer has A set of deviation transactions that meet the criteria of high deviation rate, low deviation rate, and not participating in the aggregation is: ; in 35kV / 110kV main transformer At the current time of Deviation label; Let the current time be the... 35kV / 110kV main transformers The lower feeder has A set of deviation transactions that meet the criteria of high deviation rate, low deviation rate, and not participating in the aggregation is: ; in 35kV / 110kV main transformer Lower layer feeder At the current time of Deviation label; Let the current time be the... feeder The lower-level distribution transformer has A set of deviation transactions that meet the criteria of high deviation rate, low deviation rate, and not participating in the aggregation is: ; in For feeder Lower-level distribution transformer At the current time of Deviation label; Based on the above results, the deviation transaction set of the 220kV main transformer A with the current time deviation rate anomaly is constructed as follows: .

[0071] Obtain historical data for a period of time for the 220kV main transformer A that shows an abnormal transformer deviation rate at the current time. Let the time point before the current time be... The deviation labels for the 220kV main transformer A history do not exclude labels with normal deviation rates. Similarly, the deviation labels for the 35kV / 110kV main transformers, feeders, and distribution transformers history exclude labels with normal deviation rates. The final deviation transaction dataset is constructed similarly to the above. ; in For time points Deviation transaction set, deviation transaction dataset Total This is a matter.

[0072] S153. Using the FP_Growth association rule algorithm, set a minimum support threshold, and mine frequent association itemsets based on the deviation transaction dataset with the current time main variable deviation rate anomaly as the target.

[0073] In summary, step S150 aims to conduct an in-depth analysis of the abnormal deviation rate of the 220kV main transformer, and use association rule algorithms to discover key factors or patterns that may affect the main transformer deviation rate, thereby providing decision support for power grid operation and maintenance. This includes assigning corresponding deviation labels to each device node at the lower level (S151), constructing a deviation transaction dataset reflecting the changes of these deviation labels over time (S152), and finally using data mining techniques to find frequently associated itemsets related to the abnormal main transformer deviation rate (S153).

[0074] Specifically, traverse the deviation transaction dataset Set the minimum support level to The FP_Growth association rule algorithm is used to mine frequently associated itemsets.

[0075] Filter out transactions containing the current time. Let the frequently associated itemset of the 220kV main transformer with the consistent deviation rate be denoted as . ,in For the first A set of frequently associated itemsets.

[0076] S160. Calculate the confidence level of the associated frequent itemset of the 220kV main transformer deviation rate anomaly, and take the lowest topology layer in the power grid topology tree diagram corresponding to the associated frequent itemset with the highest confidence level as the problem topology layer of the main cause of the 220kV main transformer deviation rate anomaly.

[0077] In this embodiment, the problem topology layer refers to the specific level that causes the abnormal deviation rate of the main transformer by analyzing the associated frequent itemsets related to the abnormal deviation rate of the 220kV main transformer and determining the level based on the confidence of these itemsets.

[0078] In one embodiment, step S160 described above may include steps S161 to S163.

[0079] S161. Traverse the associated frequent itemsets of the 220kV main transformer deviation rate anomaly, calculate the confidence level of the 220kV main transformer deviation rate anomaly derived from the lower-level associated frequent itemsets of the 220kV main transformer, and use it as the confidence level of each associated frequent itemset of the 220kV main transformer deviation rate anomaly.

[0080] Specifically, the frequently associated itemsets of the aforementioned 220kV main transformer deviation rate anomaly were obtained. Calculate frequently associated itemsets Number of transactions and associated frequent itemsets Excluding transactions with abnormal deviation rates of 220kV main transformers Then frequent itemsets are associated The frequent itemsets associated with the lower level of the 220kV main transformer give the anomaly confidence level of the deviation rate of the 220kV main transformer. for ; Traverse the frequently associated itemsets of the above-mentioned 220kV main transformer deviation rate anomalies The confidence level of the frequently associated itemset of the 220kV main transformer deviation rate anomaly is: .

[0081] S162. Select the frequently associated itemset with the highest confidence level as the frequently associated itemset that is the main cause of the abnormal main transformer load convergence deviation rate.

[0082] Take the confidence level of the associated frequent itemset of the 220kV main transformer deviation rate anomaly The maximum value, abbreviated as Obtain the maximum confidence level Corresponding frequent itemsets , which is the frequently associated itemset that is the main cause of the abnormal load convergence deviation rate of the main transformer.

[0083] S163. According to the hierarchy of the power grid topology tree diagram, the lowest level topology in the set of frequently associated terms of the main causes of the abnormal deviation rate of the 220kV main transformer is taken as the problem topology layer of the main causes of the abnormal deviation rate of the 220kV main transformer.

[0084] If the abnormal deviation rate of the 220kV main transformer is due to the frequent itemset of the main causes If a distribution transformer layer exists, then the distribution transformer layer serves as the problem topology layer for the main cause of the abnormal deviation rate of the 220kV main transformer; if the main cause of the abnormal deviation rate of the 220kV main transformer is a frequently associated itemset... If there is no distribution transformer layer but a feeder layer, then the feeder layer is the problem topology layer for the main cause of the 220kV main transformer deviation rate anomaly; if the main cause of the 220kV main transformer deviation rate anomaly is a frequently associated itemset... If there is no distribution transformer layer and feeder layer but there is a 35kV / 110kV main transformer layer, then the 35kV / 110kV main transformer layer is the problem topology layer that is the main cause of the abnormal deviation rate of the 220kV main transformer; if the frequent itemset of the main cause of the abnormal deviation rate of the 220kV main transformer... Without a distribution transformer layer, feeder layer, and 35kV / 110kV main transformer layer, the 220kV main transformer layer becomes the problem topology layer primarily responsible for the abnormal deviation rate of the 220kV main transformer. Assuming the problem topology layer primarily responsible for the abnormal deviation rate of the 220kV main transformer involves frequently associated itemsets... The set of device nodes is .

[0085] Step S161 involves calculating the confidence level of each associated frequent itemset, where the confidence level refers to the ability of the lower-level associated frequent itemset (i.e., the state combination of lower-level equipment nodes) to predict or explain the 220kV main transformer deviation rate anomaly. The higher the confidence level, the stronger the association between the frequent itemset and the main transformer deviation rate anomaly.

[0086] Step S162 involves selecting the most confident item from all calculated frequent itemsets as the primary cause of the abnormal deviation rate of the 220kV main transformer. This means that this specific frequent itemset is most likely to contain the key factors or patterns that cause the abnormal deviation rate of the main transformer.

[0087] Step S163 identifies the lowest-level topological location in the selected set of frequently associated items based on the power grid's topology (usually represented as a tree diagram). Here, "lowest level" refers to the level directly associated with the specific equipment or node causing the deviation rate anomaly, which could be a power grid component such as a transformer, circuit breaker, or capacitor bank. Therefore, the problem topology layer refers to the lowest level containing the main causes of the 220kV main transformer deviation rate anomaly; it helps to locate and understand which specific parts of the power grid's operation or state changes have a significant impact on the main transformer deviation rate.

[0088] In summary, the problem topology layer, determined through in-depth analysis and confidence assessment of association rules, ultimately points to a specific level within the power grid topology. This level is considered the root cause of the abnormal deviation rate of the 220kV main transformer. This process helps to accurately identify the fault source and guide corresponding maintenance and improvement measures.

[0089] S170. Prune or add branches to the next layer of the problem topology layer to correct the convergence of user load to the main transformer.

[0090] In one embodiment, step S170 described above may include steps S171 to S172.

[0091] S171. Based on the problem topology layer, perform pruning or branching operations on the next layer of equipment nodes according to the deviation label or load contribution degree, and recalculate the load convergence deviation rate and change significance at each level.

[0092] In this embodiment, the significance of change refers to a quantitative indicator of the degree of influence of pruning or branching operations on the load convergence deviation rate of the 220kV main transformer.

[0093] Specifically, according to the descending order of the deviation labels or load contribution of the equipment nodes in the next layer of the problem topology layer, the equipment nodes in the next layer of the problem topology layer are traversed, pruned, or added. The load is then re-aggregated step by step from the next layer of the problem topology layer to the 220kV main transformer. The main transformer load aggregation deviation rate after pruning or adding and the significance of the change in the main transformer deviation rate before and after pruning or adding are calculated. The significance of the change in the main transformer deviation rate is defined as the absolute value of the difference between the main transformer load aggregation deviation rate before pruning or adding and the main transformer load aggregation deviation rate after pruning or adding, divided by the absolute value of the main transformer load aggregation deviation rate before pruning or adding.

[0094] Load contribution is defined as the ratio of the aggregated load value of the equipment node to the aggregated load value of the 220kV main transformer; if the abnormal deviation rate of the 220kV main transformer is labeled as high deviation rate and the next layer below the problem topology layer is not the user layer, then the problem topology layer will be... The next-level device nodes are sorted in descending order of load contribution, according to the following order: not participating in aggregation, high deviation rate, low deviation rate, and normal deviation rate. If the 220kV main transformer has an abnormal deviation rate, the label is low deviation rate and the next level after the problem topology layer is not the user layer, then the problem topology layer is... The next-level device nodes are sorted in descending order of load contribution, following the order of low deviation rate, not participating in aggregation, high deviation rate, and normal deviation rate. If the 220kV main transformer has an abnormal deviation rate, the label is either high or low deviation rate, and the next level after the problem topology layer is the user layer, then the problem topology layer... The next layer of device nodes are sorted in descending order of load contribution. The sorted problem topology layer. The next layer of device nodes is ,in For the problem topology layer Next level One device node; The problem topology layers are arranged in the above order. The next layer of equipment nodes is traversed, pruned, or added. If the 220kV main transformer has a high deviation rate and the problem is in the topology layer... A high deviation rate indicates a problem topology layer The next layer of equipment nodes is traversed and branches are added; if the deviation rate of the 220kV main transformer is low and the problem topology layer is... A low deviation rate indicates a good understanding of the problem's topology layer. The next layer of device nodes is traversed and pruned; if the 220kV main transformer has a high deviation rate and the problem is in the topology layer... If it does not participate in the convergence, then the problem topology layer... Branching is performed. Assume the problem topology layer... Next-level device node Perform traversal pruning or branch addition, and calculate the main transformer load convergence deviation rate after pruning or branch addition. and the significance of the change in the principal variable deviation rate before and after pruning or branching. The significance of the change in the main transformer deviation rate is defined as the main transformer load convergence deviation rate before pruning or branching. Subtract the main transformer load convergence deviation rate after pruning or branching The absolute value of the difference is then divided by the main transformer load convergence deviation rate before pruning or branching. Absolute value; Significance of change in main variable deviation rate The calculation formula is as follows: ; Following the above sorting order, the problem topology layer is calculated first. Next-level device node Corresponding main transformer load convergence deviation rate after pruning or branching Significance of change in main variable deviation rate .

[0095] S172. If the load aggregation deviation rate of the 220kV main transformer after pruning or adding branches is normal and the change significance exceeds the threshold, then output the corrected step-by-step load aggregation result; otherwise, continue to adjust until the optimal node is found or the node that minimizes the absolute value of the deviation rate and maximizes the change significance is selected as the optimization scheme and the result is output.

[0096] Specifically, if the 220kV main transformer load aggregation deviation rate after pruning or adding branches is normal and the change significance exceeds the threshold, then the next-level equipment node in the problem topology layer that meets the conditions is found, and the step-by-step load aggregation correction result based on user load (distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer) is output; otherwise, the pruning or adding operation is repeated according to the problem topology layer, sorting the next-level equipment nodes by deviation label or load contribution, and the step-by-step load aggregation deviation rate and change significance are recalculated until a satisfactory result is found. If the conditions are met, the equipment node in the next layer of the problem topology layer is selected, and the result of the step-by-step load aggregation of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on user load is corrected. If the conditions are not met, the equipment node in the next layer of the problem topology layer is selected according to the principle of the smallest absolute value of the main transformer load aggregation deviation rate after pruning or adding branches and the largest significant change in the main transformer deviation rate. The corrected result of the step-by-step load aggregation of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on user load is output.

[0097] If the main transformer load convergence deviation rate is after pruning or adding branches Within normal range And the significance of the change in the main variable deviation rate Greater than the threshold If the condition is not met, then find the next-level device node in the problem topology layer that meets the condition, and output the step-by-step load aggregation correction result based on user load: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer. Otherwise, continue to step C1 until the next-level device node in the problem topology layer that meets the condition is found, and output the step-by-step load aggregation correction result based on user load: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer. If the condition cannot be met, then calculate the main transformer load aggregation deviation rate after pruning or adding branches. Minimum absolute value, significant change in main transformer deviation rate The system prioritizes the top-ranked problem topology layer and selects the next-level device node. It then outputs the step-by-step load aggregation correction results based on user load, from distribution transformer to feeder to 35kV / 110kV main transformer to 220kV main transformer.

[0098] For example, as shown in Table 1, load aggregation data samples for 220kV main transformer A from August 1, 2025 to August 3, 2025 are obtained. The corresponding topology, user ledger, distribution transformer ledger, line ledger, and main transformer ledger are obtained from systems such as PMS (Equipment Asset Management), marketing system, and D5000 system; power measurement data of main transformers and lines are obtained from the D5000 system, with a sampling interval of 15 minutes, and main grid switch position data is also obtained; power measurement data of distribution transformers and users are obtained from the power consumption acquisition system, with a sampling interval of 15 minutes; and distribution network switch position data are obtained from the distribution network automation system.

[0099] In this embodiment, the next level below the 220kV main transformer A consists of two 35kV main transformers and two 110kV main transformers. The next level below the 35kV / 110kV main transformers has a total of 30 feeders, the next level below the feeders has 950 distribution transformers, and the next level below the distribution transformers has 23,822 users. A schematic diagram of the multi-level power grid topology tree of the 220kV main transformer A constructed using the above method is shown below. Figure 2 As shown.

[0100] Table 1. Equipment statistics involved in the multi-level power grid topology tree diagram.

[0101] In this implementation, the above method is used to calculate the tiered load aggregation and load aggregation deviation rate based on user load, from the distribution transformer to the feeder, then to the 35kV / 110kV main transformer, and finally to the 220kV main transformer. Some examples of the results are shown in Table 2 below.

[0102] Table 2. Examples of partial results from the calculation of load convergence and load convergence deviation rate.

[0103] In this embodiment, the upper limit threshold The lower limit threshold is 10%. The load convergence deviation rate of the 220kV main transformer A is -22.1%, which is -5%, indicating that the deviation rate of the 220kV main transformer A is low.

[0104] In this embodiment, the upper limit threshold for the load convergence deviation rate of 35kV / 110kV main transformers, feeders, and distribution transformers is set. , , All are taken as 10%, upper limit threshold , , All values ​​are set to -5%. Deviation transaction dataset. Some data examples are shown in Table 3 below: Table 3. Sample data from the deviation transaction dataset

[0105] Set minimum support Assuming a deviation rate of 10%, the FP_Growth association rule algorithm was used to mine frequent itemsets with the objective of low deviation rate of 220kV main transformer A as follows: {{220kV main transformer A: low deviation rate, 110kV main transformer b2: low deviation rate}, {220kV main transformer A: low deviation rate, 110kV main transformer b2: low deviation rate, feeder c2,6: low deviation rate}, {220kV main transformer A: low deviation rate, 110kV main transformer b2: low deviation rate, feeder c2,6: low deviation rate, distribution transformer d6,23: low deviation rate}}.

[0106] In this embodiment, the problem topology layer for which the abnormal deviation rate of the 220kV main transformer was obtained using the above method is feeder c2,6.

[0107] In this embodiment, the upper limit threshold of the 220kV main transformer load convergence deviation rate index is... , Thresholds for the significance of changes in the main variable deviation rate are set at 10% and -5% respectively. With a value of 0.05, the feeder c2,6 of the problematic topology layer, which is the main cause of the abnormal deviation rate of the 220kV main transformer A, was adjusted using the above method. The deviation rate of the 220kV main transformer A became 6.7%, and the significance of the change in the main transformer deviation rate was 1.3. The result of the step-by-step load convergence correction based on user load is output: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer.

[0108] The method described in this embodiment is used to achieve accurate load aggregation from users to the 220kV main transformer. Its core lies in employing a multi-level tree diagram for deviation source tracing analysis. By applying the FP-Growth association rule algorithm for deviation source tracing analysis, this embodiment can quickly and accurately identify the specific sources of load aggregation deviations. This method significantly reduces the time required to troubleshoot abnormal load aggregation problems and improves work efficiency.

[0109] A multi-level tree diagram constructed based on the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, combined with deviation source analysis technology, can effectively identify and correct load deviations at each level. This multi-level approach significantly improves the accuracy of load aggregation and ensures data consistency and reliability.

[0110] This embodiment introduces a mechanism that allows for dynamic adjustment of the load aggregation label setting at each level based on the results of deviation source analysis, without requiring the reconstruction of the entire calculation model. Compared to traditional fixed-mode aggregation methods, this approach offers greater flexibility and real-time accuracy, ensuring the immediate updating and precision of the main transformer load aggregation results.

[0111] This embodiment is not only clear in principle and easy to understand, but also simple to implement. It can effectively help professionals quickly locate the cause of load aggregation deviation and achieve accurate load aggregation from the user to the 220kV main transformer. Due to its intuitive operation process and good performance, this invention has shown broad prospects and great potential in practical applications.

[0112] The aforementioned user-to-transformer load aggregation method based on a multi-level tree diagram constructs a power grid topology tree diagram with multi-level relationships between users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers. It uses initial data to calculate the load aggregation value and deviation rate of each level node, marks the aggregation participation status of each level, and determines the operating status of the 220kV main transformer based on the load aggregation deviation rate threshold. For cases of abnormal deviations, the FP_Growth algorithm is used to mine frequently associated itemsets to identify the main causes of the deviations, thereby optimizing and adjusting the problematic topology layer to achieve accurate load aggregation from users to main transformers. This method effectively integrates hierarchical topology information, supports refined load analysis and forecasting, improves the operating performance of the distribution network and the accuracy of main transformer load aggregation, reduces the uncertainty caused by multi-level metering errors, and enhances the system's adaptability to dynamic load environments.

[0113] Figure 3 This is a schematic block diagram of a user-to-main transformer load aggregation system 300 based on a multi-level tree diagram, provided in an embodiment of the present invention. Figure 3As shown, corresponding to the above-described user-to-transformer load aggregation method based on a multi-level tree diagram, the present invention also provides a user-to-transformer load aggregation system 300 based on a multi-level tree diagram. This user-to-transformer load aggregation system 300 based on a multi-level tree diagram includes units for executing the above-described user-to-transformer load aggregation method based on a multi-level tree diagram, and the system can be configured in a server. Specifically, please refer to... Figure 3 The user-to-main transformer load aggregation system 300 based on a multi-level tree diagram includes a data acquisition unit 301, a tree diagram construction unit 302, a calculation unit 303, a judgment unit 304, a mining unit 305, a topology layer construction unit 306, and an adjustment unit 307.

[0114] The data acquisition unit 301 is used to acquire the corresponding topology structure, user ledger, distribution transformer ledger, line ledger, and main transformer ledger of the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, and to acquire the power data and switch position data of all equipment to obtain initial data; the tree diagram construction unit 302 is used to treat users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers as nodes of a graph, and the connection relationship as an edge, with the 220kV main transformer as the root node and users as leaf nodes, to construct a multi-level power grid topology tree diagram of the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer relationship; the calculation unit 303 is used to calculate the load aggregation value and load aggregation deviation rate of each layer of nodes using the power grid topology tree diagram and the initial data, and to label whether the nodes of the next layer participate in aggregation; the judgment unit 304 is used to determine the load aggregation deviation rate based on the load aggregation deviation rate. The system sets upper and lower limit thresholds for the load aggregation deviation rate indicator to determine whether the deviation rate of the 220kV main transformer is normal. A mining unit 305, if the 220kV main transformer deviation rate is abnormal, tags each lower-level device node with a deviation label based on the upper and lower limit thresholds and the label. It then constructs a deviation transaction dataset using time periods as transaction units and uses the FP_Growth association rule algorithm to mine frequently associated itemsets targeting abnormal main transformer deviation rates. A topology layer construction unit 306 calculates the confidence level of the frequently associated itemsets for abnormal 220kV main transformer deviation rates and selects the lowest topology layer in the power grid topology tree corresponding to the frequently associated itemset with the highest confidence level as the problem topology layer for the main cause of the abnormal 220kV main transformer deviation rate. An adjustment unit 307 prunes or adds branches to the next layer of the problem topology layer to correct the load aggregation from users to the main transformer.

[0115] In one embodiment, the tree diagram construction unit 302 is used to obtain the corresponding low-voltage user-transformer relationships, medium-voltage line-transformer relationships, line-bus relationships, main transformer bus topology relationships, and high-voltage main transformer-low-voltage main transformer relationships among users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformer equipment through topology analysis; taking the 220kV main transformer as the root node, the lower-level 35kV / 110kV main transformers are found through the high-voltage and low-voltage main transformer relationships, and the 220kV and 35kV / 110kV main transformers are regarded as nodes of the graph, and the connection relationships are regarded as edges, thus constructing a first-level power grid topology tree diagram of 220kV main transformer-35kV / 110kV main transformer; the feeders below the 35kV / 110kV main transformers are found through the line-bus relationships and main transformer bus topology relationships, and the feeders, 35kV / 110kV main transformers, etc. The 35kV / 110kV main transformer equipment is considered as nodes in the graph, and the connection relationship is considered as edges, constructing a second-level power grid topology tree diagram of the 35kV / 110kV main transformer-feeder. The distribution transformers below the feeder are found through the medium-voltage line-transformer relationship, and the distribution transformers and feeder equipment are considered as nodes in the graph, with connection relationships considered as edges, constructing a third-level power grid topology tree diagram of the feeder-distribution transformer. The users below the distribution transformer are found through the low-voltage customer transformer relationship, and the users and distribution transformer equipment are considered as nodes in the graph, with connection relationships considered as edges, constructing a fourth-level power grid topology tree diagram of the distribution transformer-user. The first, second, third, and fourth-level power grid topology tree diagrams are integrated to construct a multi-level power grid topology tree diagram with relationships between users, distribution transformers, feeders, 35kV / 110kV main transformers, and 220kV main transformers.

[0116] In one embodiment, the calculation unit 303 is used to perform step-by-step load aggregation based on user load for four levels: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, using the power grid topology tree diagram and the initial data. It labels the nodes at the next level with whether they participate in aggregation by using switch opening and closing position data, and summarizes the user load of all participating nodes at the next level as the load aggregation value for this level node. The distribution transformer load aggregation value is the sum of the user loads of all participating nodes, the feeder load aggregation value is the sum of the distribution transformer load aggregation values ​​of all participating nodes, and so on down to the 220kV main transformer load aggregation value. For the four levels of distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, the load aggregation deviation rate for each node is calculated by subtracting the load aggregation value from the actual load value of each node and dividing by the absolute value of the actual load value of that node, plus the absolute value of the load aggregation value.

[0117] In one embodiment, the judgment unit 304 is used to determine whether the deviation rate of the 220kV main transformer is normal based on the upper and lower limit thresholds of the load convergence deviation rate index. If the deviation rate of the 220kV main transformer is greater than the upper limit threshold, the deviation rate of the 220kV main transformer is high; if the deviation rate of the 220kV main transformer is less than the lower limit threshold, the deviation rate of the 220kV main transformer is low; otherwise, the deviation rate of the 220kV main transformer is normal.

[0118] In one embodiment, the mining unit 305 is used to, for the 220kV main transformer with abnormal main transformer deviation rate, according to the upper and lower limit thresholds of the load aggregation deviation rate index and the labels, label each lower-level device node with deviation rate as high, low, normal, or not participating in aggregation; acquire historical data of the main transformer deviation rate abnormality at the current time for a period of time, and construct a deviation transaction dataset with device node deviation rate high, low, and not participating in aggregation labels in time period as transaction unit; and use the FP_Growth association rule algorithm to set a minimum support threshold and mine frequent itemsets with the current main transformer deviation rate abnormality as the target based on the deviation transaction dataset.

[0119] In one embodiment, the topology layer construction unit 306 is used to traverse the associated frequent itemsets of the 220kV main transformer deviation rate anomaly, calculate the confidence level of the 220kV main transformer deviation rate anomaly derived from the lower-level associated frequent itemsets of the 220kV main transformer, and use it as the confidence level of each associated frequent itemset of the 220kV main transformer deviation rate anomaly; take the associated frequent itemset with the highest confidence level as the associated frequent itemset of the main transformer load convergence deviation rate anomaly; and according to the hierarchy of the power grid topology tree diagram, take the lowest-level topology in the associated frequent itemset of the main cause of the 220kV main transformer deviation rate anomaly as the problem topology layer of the main cause of the 220kV main transformer deviation rate anomaly.

[0120] In one embodiment, the adjustment unit 307 is used to perform pruning or branching operations on the next-level equipment nodes according to the problem topology layer, sorted by deviation label or load contribution, and recalculate the step-by-step load aggregation deviation rate and change significance. If the 220kV main transformer load aggregation deviation rate after pruning or branching is normal and the change significance exceeds the threshold, the corrected step-by-step load aggregation result is output. Otherwise, the adjustment continues until the optimal node is found or the node with the smallest absolute value of deviation rate and the largest change significance is selected as the optimization scheme and the result is output.

[0121] In one embodiment, the adjustment unit 307 is used to traverse and prune or add branches to the next layer of equipment nodes in the problem topology layer according to the descending order of the deviation labels or load contribution of the next layer of equipment nodes in the problem topology layer, and recalculate the load convergence of the next layer to the 220kV main transformer based on the next level of the problem topology layer, and calculate the main transformer load convergence deviation rate after pruning or adding branches and the significance of the change in the main transformer deviation rate before and after pruning or adding branches; wherein, the significance of the change in the main transformer deviation rate is defined as the absolute value of the difference between the main transformer load convergence deviation rate before pruning or adding branches and the main transformer load convergence deviation rate after pruning or adding branches, divided by the absolute value of the main transformer load convergence deviation rate before pruning or adding branches.

[0122] In one embodiment, the adjustment unit 307 is configured to, if the pruned or expanded 220kV main transformer load convergence deviation rate is normal and the change significance exceeds a threshold, find the next-level equipment node in the problem topology layer that meets the conditions, and output the step-by-step load convergence correction result based on user load: distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer; otherwise, repeat the pruning or expansion operation based on the problem topology layer, sorting the next-level equipment nodes by deviation label or load contribution, and recalculate the step-by-step load convergence deviation rate and change significance. The process continues until a suitable equipment node in the next layer of the problem topology layer is found that meets the requirements. The corrected load aggregation result based on user load (distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer) is then output. If the requirements are not met, the equipment node in the next layer of the problem topology layer is selected based on the principle of having the smallest absolute value of the main transformer load aggregation deviation rate after pruning or adding branches, and the greatest significance of the change in the main transformer deviation rate. The corrected load aggregation result based on user load (distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer) is then output.

[0123] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned user-to-main transformer load aggregation system 300 and its various units based on a multi-level tree diagram can be referred to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity, these details will not be repeated here.

[0124] The aforementioned user-to-main transformer load aggregation system 300 based on a multi-level tree diagram can be implemented as a computer program, which can be used in, for example... Figure 4 It runs on the computer device shown.

[0125] Please see Figure 4 , Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0126] See Figure 4 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0127] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a user-to-main transformer load aggregation method based on a multi-level tree diagram.

[0128] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0129] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a user-to-main transformer load aggregation method based on a multi-level tree diagram.

[0130] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0131] The processor 502 is used to run a computer program 5032 stored in a memory to implement all the steps of the user-to-main transformer load aggregation method based on a multi-level tree diagram.

[0132] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0133] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0134] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein when executed by a processor, the computer program causes the processor to perform all the steps of the user-to-main transformer load aggregation method based on a multi-level tree diagram.

[0135] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0136] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0137] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each unit is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0138] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the system of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0139] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0140] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for user-to-master variable load aggregation based on a multi-level tree graph, characterized in that, The method comprises the following steps: Obtain the corresponding topology structure of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, user account, distribution transformer account, line account, main transformer account, and obtain the power data and switch position data of all devices to obtain initial data; Treat the user, distribution transformer, feeder, 35kV / 110kV main transformer and 220kV main transformer devices as nodes of a graph, and treat the connection relationship as an edge, take the 220kV main transformer as the root node and the user as the leaf node, and construct a power grid topology tree diagram of the multi-level relationship of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer; Use the power grid topology tree diagram and the initial data to calculate the load convergence value and load convergence deviation rate of each layer of nodes, and mark whether the next layer of nodes participates in convergence with a label; Determine whether the 220kV main transformer deviation rate is normal according to the upper and lower limit threshold settings of the load convergence deviation rate index; If the 220kV main transformer deviation rate is not normal, mark each device node of the lower level with a deviation label according to the load convergence deviation rate index upper and lower limit threshold settings and the label, and construct a deviation transaction dataset with a time period as a transaction unit, use the FP_Growth association rule algorithm to mine the association frequent item set with main transformer deviation rate anomaly as the target; Calculate the confidence of the 220kV main transformer deviation rate anomaly association frequent item set, and take the topology lowest layer in the power grid topology tree diagram corresponding to the association frequent item set with the maximum confidence as the problem topology layer of the 220kV main transformer deviation rate anomaly; Prune or increase the branches of the next layer of the problem topology layer to correct the user to main transformer load convergence.

2. The multi-level tree-based user-to-master variable load aggregation method of claim 1, wherein, The method for constructing a power grid topology tree diagram of a multi-level relationship of user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer comprises the following steps: Obtain the corresponding low-voltage transformer relationship, medium-voltage line transformer relationship, line and bus relationship, main transformer bus topology relationship, and high-voltage main transformer and low-voltage main transformer relationship of the user, distribution transformer, feeder, 35kV / 110kV main transformer and 220kV main transformer devices through topology structure analysis; Take the 220kV main transformer as the root node, find the 35kV / 110kV main transformer of the lower layer through the high-voltage main transformer and low-voltage main transformer relationship, treat the 220kV main transformer and 35kV / 110kV main transformer as nodes of a graph, treat the connection relationship as an edge, and construct a first layer power grid topology tree diagram of 220kV main transformer-35kV / 110kV main transformer; Find the feeder of the lower layer of the 35kV / 110kV main transformer through the line and bus relationship and main transformer bus topology relationship, treat the feeder and 35kV / 110kV main transformer devices as nodes of a graph, treat the connection relationship as an edge, and construct a second layer power grid topology tree diagram of 35kV / 110kV main transformer-feeder; The feeder-layer distribution transformer is found through the medium-voltage line transformer relationship, the distribution transformer, the feeder equipment are regarded as the nodes of the graph, the connection relationship is regarded as the edge, and the third-layer power grid topology tree graph of the feeder-distribution transformer is constructed; The user-layer distribution transformer is found through the low-voltage user transformer relationship, the user, the distribution transformer equipment are regarded as the nodes of the graph, the connection relationship is regarded as the edge, and the fourth-layer power grid topology tree graph of the distribution transformer-user is constructed; The first-layer power grid topology tree graph, the second-layer power grid topology tree graph, the third-layer power grid topology tree graph and the fourth-layer power grid topology tree graph are integrated to construct the power grid topology tree graph of the multi-level relationship of the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer.

3. The multi-level tree-based user-to-master variable load aggregation method of claim 1, wherein, The power grid topology tree graph and the initial data are used to calculate the load convergence value and the load convergence deviation rate of each layer node, and the label of whether the next layer node participates in the convergence is marked, including: The power grid topology tree graph and the initial data are used to perform user load-based step-by-step load convergence on the four levels of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, the next level node is marked with the label of whether to participate in the convergence through the switch opening and closing position data, the user loads of all the next level nodes participating in the convergence are summarized as the load convergence value of the current layer node, the distribution transformer load convergence value is obtained by summarizing the user loads of all the nodes participating in the convergence, the feeder load convergence value is obtained by summarizing the distribution transformer load convergence values of all the nodes participating in the convergence, and the 220kV main transformer load convergence value is calculated by analogy; For the four levels of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, the actual load value of each node is subtracted from the load convergence value, and the absolute value of the load convergence value is added to the absolute value of the actual load value of the node, to obtain the load convergence deviation rate of each node.

4. The multi-level tree-based user-to-master variable load aggregation method of claim 1, wherein, The upper and lower limit threshold values of the load convergence deviation rate index are set to determine whether the 220kV main transformer deviation rate is normal, including: The upper and lower limit threshold values of the load convergence deviation rate index are set to determine whether the 220kV main transformer deviation rate is normal. If the 220kV main transformer deviation rate is greater than the upper limit threshold value, the 220kV main transformer deviation rate is high, if the 220kV main transformer deviation rate is less than the lower limit threshold value, the 220kV main transformer deviation rate is low, otherwise the 220kV main transformer deviation rate is normal.

5. The multi-level tree-based user-to-master variable load aggregation method of claim 1, wherein, If the 220kV main transformer deviation rate is not normal, for the 220kV main transformer with abnormal main transformer deviation rate, each device node of the lower level is marked with a deviation label according to the upper and lower limit threshold values of the load convergence deviation rate index and the label, and a deviation transaction dataset is constructed with a time period as a transaction unit, and the FP_Growth association rule algorithm is used to mine the association frequent item set with the main transformer deviation rate abnormality as the target, including: For the 220kV main transformer with abnormal main transformer deviation rate, each device node of the lower level is marked with a deviation label according to the upper and lower limit threshold values of the load convergence deviation rate index and the label, including the deviation rate high, the deviation rate low, the deviation rate normal and the non-participation in the convergence. Acquire historical data of current time main transformer deviation rate anomaly for a period of time, take time period as transaction unit, construct device node deviation rate high, deviation rate low, and deviation transaction data set of non-participating convergence label; Use FP_Growth association rule algorithm, set minimum support threshold, and mine association frequent item set with current time main transformer deviation rate anomaly as target based on the deviation transaction data set.

6. The multi-level tree map based user-to-master variable load aggregation method of claim 1, wherein, The calculation of the 220kV main transformer deviation rate anomaly association frequent item set confidence, take the confidence maximum association frequent item set corresponding to the topological lowest layer in the power grid topology tree diagram as the problem topology layer of the 220kV main transformer deviation rate anomaly, including: Traverse the 220kV main transformer deviation rate anomaly association frequent item set, calculate the confidence of the 220kV main transformer lower level association frequent item set to deduce the 220kV main transformer deviation rate anomaly, as the confidence of each association frequent item set of the 220kV main transformer deviation rate anomaly; Take the confidence maximum association frequent item set as the main transformer load convergence deviation rate anomaly main reason association frequent item set; According to the level of the power grid topology tree diagram, take the lowest layer topology in the 220kV main transformer deviation rate anomaly main reason association frequent item set as the problem topology layer of the 220kV main transformer deviation rate anomaly main reason.

7. The multi-level tree map based user-to-master variable load aggregation method of claim 1, wherein, The pruning or branch increasing adjustment of the next layer of the problem topology layer, the correction of user to main transformer load convergence, including: According to the problem topology layer, the next layer device node is sorted according to the deviation label or load contribution degree for pruning or branch increasing operation, and the step-by-step load convergence deviation rate and change significance are recalculated; If the 220kV main transformer load convergence deviation rate after pruning or branch increasing is normal and the change significance exceeds the threshold, output the corrected step-by-step load convergence result; otherwise, continue to adjust until the optimal node is found or the node with the minimum absolute value of deviation rate and the maximum change significance is selected as the optimization scheme and the result is output.

8. The multi-level tree-based user-to-master variable load aggregation method of claim 7, wherein, According to the problem topology layer, the next layer device node is sorted according to the deviation label or load contribution degree for pruning or branch increasing operation, and the step-by-step load convergence deviation rate and change significance are recalculated, including: According to the deviation label or load contribution degree descending order of the next layer device node of the problem topology layer, the next layer device node of the problem topology layer is pruned or branched, and the step-by-step load convergence from the next layer to the 220kV main transformer is recalculated, the main transformer load convergence deviation rate after pruning or branch increasing and the main transformer deviation rate change significance before and after pruning or branch increasing are calculated; wherein the main transformer deviation rate change significance is defined as the absolute value of the difference between the main transformer load convergence deviation rate before pruning or branch increasing and the main transformer load convergence deviation rate after pruning or branch increasing, divided by the absolute value of the main transformer load convergence deviation rate before pruning or branch increasing.

9. The multi-level tree-based user-to-master variable load aggregation method of claim 7, wherein, If the 220kV main transformer load convergence deviation rate after pruning or branch increasing is normal and the change significance exceeds the threshold, output the corrected step-by-step load convergence result; otherwise, continue to adjust until the optimal node is found or the node with the minimum absolute value of deviation rate and the maximum change significance is selected as the optimization scheme and the result is output. If the load convergence deviation rate of the 220kV main transformer after pruning or branch increasing is normal and the change significance exceeds the threshold value, the next layer device node of the problem topology layer meeting the condition is found, and the correction result of the load convergence of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on the user load is output. Otherwise, the pruning or branch increasing operation is repeated on the next layer device node of the problem topology layer according to the deviation label or load contribution degree, and the load convergence deviation rate and change significance are recalculated until the next layer device node of the problem topology layer meeting the condition is found, and the correction result of the load convergence of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on the user load is output. If the condition cannot be met, the next layer device node of the problem topology layer is selected according to the principle of the smallest absolute value of the load convergence deviation rate of the main transformer after pruning or branch increasing and the largest change significance of the main transformer deviation rate, and the correction result of the load convergence of the distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer based on the user load is output.

10. A user-to-master variable load aggregation system based on a multi-level tree graph, characterized by, It comprises: a data acquisition unit configured to acquire the corresponding topology structure of the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer, user account, distribution transformer account, line account, main transformer account, and acquire the power data and switch position data of all devices to obtain initial data; a tree diagram construction unit configured to regard the user, distribution transformer, feeder, 35kV / 110kV main transformer, and 220kV main transformer as nodes of a graph, the connection relationship as an edge, take the 220kV main transformer as the root node, and take the user as the leaf node, and construct a power grid topology tree diagram of the multi-level relationship of the user-distribution transformer-feeder-35kV / 110kV main transformer-220kV main transformer; a calculation unit configured to calculate the load convergence value and load convergence deviation rate of each layer node by using the power grid topology tree diagram and the initial data, and mark the next layer node whether to participate in the convergence with a label; a judgment unit configured to judge whether the 220kV main transformer deviation rate is normal according to the upper and lower threshold value setting of the load convergence deviation rate index; a mining unit configured to, if the 220kV main transformer deviation rate is not normal, mark each device node of the lower level with a deviation label according to the load convergence deviation rate index upper and lower threshold value setting and the label, construct a deviation transaction dataset by taking a time period as a transaction unit, and mine the associated frequent item set taking the main transformer deviation rate anomaly as the target by using the FP_Growth association rule algorithm; a topology layer construction unit configured to calculate the confidence of the associated frequent item set of the 220kV main transformer deviation rate anomaly, take the lowest layer of the power grid topology tree diagram corresponding to the associated frequent item set with the largest confidence as the problem topology layer of the main transformer deviation rate anomaly; an adjustment unit configured to adjust the next layer of the problem topology layer by pruning or branch increasing, and correct the load convergence from the user to the main transformer.

Images