Power distribution network digital deduction method based on big data and deduction system thereof

Abstract

The invention relates to the field of power distribution of power systems, in particular to a power distribution network digital deduction method and system based on big data. The method comprises the following steps: step 1, carrying out topology verification on a power distribution network based on a breadth-first search algorithm; step 2, completing unknown measurement information of the power distribution network based on data flow mapping; and step 3, deducing the state of the power distribution network impacted by the distributed power supply and the multi-element load. A deduction system used by the method comprises a data acquisition module, a data storage module, a calculation module, a display module and a power supply. Wherein the calculation module receives data of the data acquisition module, processes the data, stores the data in the data storage module, transmits a result to the display module, and meanwhile, depends on the power supply module to provide power support. The data acquisition module is used for acquiring operation data of the power distribution network in real time, including parameters of voltage, current, power, frequency and phase angle, and transmitting the data to the data storage module through a sensor and a communication network.

Description

Technical Field

[0001] The present application relates to the field of power distribution of power systems, and specifically to a distribution network digital deduction method and system based on big data. Background Art

[0002] The construction of fine perception capability of distribution network is an important foundation for improving power supply reliability and safety. The construction of new power system requires distribution network to have comprehensive state perception capability. With the advancement of distribution automation, the amount of measurement data accumulated by distribution network has increased, but there are still problems such as limited deployment of measurement devices, inaccurate maintenance of ledger parameters, and difficulty in carrying out state calculation. Considering the complex and changeable operating environment of distribution network, the accuracy of ledger maintenance is difficult to guarantee, and the traditional distribution network state estimation method based on power flow calculation is difficult to apply to the current distribution network measurement system.

[0003] Moreover, with the continuous growth of global energy demand and the digital transformation of power systems, the operation and control of distribution networks have become increasingly complex. The existing distribution network simulation system has deficiencies in computing speed and accuracy, and it is difficult to meet the needs of large-scale data computing. In addition, traditional distribution network simulation methods have limitations in processing real-time data and performing fault prediction, and cannot effectively cope with the complex power system operating environment. For example, in the prior art, the fault diagnosis and state prediction of distribution networks mainly rely on experience and simple mathematical models, which makes it difficult to achieve efficient and accurate simulation and prediction. Therefore, there is an urgent need for a distribution network digital simulation system based on big data and advanced algorithms to improve the operating efficiency and reliability of the distribution network. Summary of the invention

[0004] This application aims to study the digital power grid computing and deduction technology based on artificial intelligence. By carrying out research on distribution network topology verification methods, distribution network key measurement mining and unknown measurement completion methods, and distribution network state deduction under distributed power sources and multi-load impact, it makes up for the shortcomings of traditional methods that are difficult to calculate the distribution network state under limited measurements, improves the transparent perception level of distribution network operation status, and supports the rapid judgment of distribution network power outages, online verification of topological relationship data, positioning of power grid weak points and heavy overload warning, flexible load transfer, active repair and other businesses. Enhance the observable, describable and computable capabilities of the distribution network by digital and intelligent means, meet the requirements of the construction of new power systems for distribution network situation awareness modeling accuracy, computing efficiency and real-time performance, thereby enhancing the resilience of the distribution network, ensuring power supply reliability, and realizing lean management of the distribution network.

[0005] The present invention provides a distribution network digital deduction method and system based on big data. By conducting research on digital power grid calculation and deduction technology, accurate verification of distribution network ledger topology, completion of missing measurement data, and state calculation and deduction are achieved, thereby improving the observability, measurability, and computability of the distribution network operation status.

[0006] The steps of a distribution network digital deduction method based on big data of the present invention are as follows:

[0007] Step 1: Perform topology verification on the distribution network based on a breadth-first search algorithm;

[0008] Step 2: Completing the unknown measurement information of the distribution network based on data flow mapping;

[0009] Step 3: Simulate the distribution network status under the impact of distributed power sources and multiple loads.

[0010] Specifically, the detailed steps of step 1 are:

[0011] Step 1.1, initialize the topological structure of the distribution network, including the definition of nodes and edges;

[0012] Step 1.2, starting from a node in the distribution network, traverse all nodes and edges using the breadth-first search algorithm; during the traversal process, check whether there is a loop. If a loop is found, record the loop information and process it; after the traversal, check whether there are any nodes that have not been traversed. If there are any isolated nodes, record the isolated node information and process it.

[0013] Step 1.3, based on the detected loop and isolated node information, correct the topology structure to ensure the integrity and correctness of the topology structure;

[0014] Step 1.4: During the operation of the distribution network, real-time topology verification is performed periodically or when the topology changes, to ensure that dynamic changes in the topology can be detected and processed in a timely manner.

[0015] Furthermore, in step 1.2, the topology of the distribution network is verified using a breadth-first search algorithm to ensure the integrity and correctness of the topology, including the following steps:

[0016] Power change increment calculation:

[0017] ΔP i =P i -P i-1

[0018] Where ΔPi is the power change increment of node i, Pi is the power of node i, and Pi-1 is the power of node i-1;

[0019] Voltage correlation coefficient calculation:

[0020]

[0021] Wherein, ρij is the voltage correlation coefficient between node i and node j, Vi and Vj are the voltages of node i and node j respectively, and Viˉ and Vjˉ are the mean values ​​of the voltages of node i and node j respectively.

[0022] Detect loops and isolated nodes by traversing nodes and edges: Detect loops and isolated nodes in the topology by traversing all nodes and edges of the distribution network. Select nodes directly connected to the initial node based on the power change increment and current sum.

[0023] Select node = arg max(ΔP i +I i )

[0024] Where Ii is the sum of the currents at node i.

[0025] Specifically, the detailed steps of step 2 are:

[0026] Step 2.1, collect the operation data of the distribution network in real time through the data acquisition module, including the parameters of voltage, current, power, frequency and phase angle.

[0027] Step 2.2, historical data analysis: By analyzing historical operation data, a data flow model is established to predict unknown measurement information.

[0028] Step 2.3, data flow mapping: Use data flow mapping technology to complete the unknown measurement information in the distribution network.

[0029] Step 2.4, multi-source data fusion: Combine multi-source data, such as smart meter data, sensor data, etc., to improve the accuracy of measurement information completion.

[0030] Step 2.5, adaptive completion: Adaptively adjust the data flow model according to the changes in the operating status of the distribution network to ensure the real-time and accuracy of the completion results.

[0031] Step 2.6, result verification: Verify the completed measurement information to ensure its accuracy and reliability.

[0032] Furthermore, in step 2.3, the method for completing the unknown measurement information in the distribution network is:

[0033] P ij =V i V j (G ij cos(θ i -θ j )+Bij sin(θ i -θ j ))

[0034] Q ij =V i V j (G ij sin(θ i -θ j )-B ij cos(θ i -θ j ))

[0035] Among them, Gij and Bij are the real and imaginary parts of the admittance between node i and node j, respectively.

[0036] In the prior art, the methods for completing unknown measurement information of distribution networks mostly use simple interpolation or extrapolation algorithms, which have the problems of low accuracy and poor adaptability. The prior art is difficult to cope with the dynamic changes in the operating status of the distribution network, while the present invention has an adaptive completion function, which can adjust the data flow model in real time according to the changes in the operating status, thereby improving the accuracy and real-time performance of the completion results.

[0037] Specifically, the detailed steps of step 3 are:

[0038] Step 3.1, distributed power generation modeling: Model the distributed power generation, considering the impact of its output characteristics and access location on the distribution network;

[0039] Step 3.2, multi-load modeling: Analyze the impact characteristics of multi-loads, establish a load model, and predict the impact of load changes on the distribution network status;

[0040] Step 3.3, data collection: collect the operation data of the distribution network in real time through the data collection module;

[0041] Step 3.4, state deduction: Based on big data analysis and machine learning algorithms, the operating state of the distribution network is deduced to predict the state of the distribution network under the impact of distributed power sources and multiple loads.

[0042] Furthermore, in step 3.1, the distributed power modeling method is:

[0043] Modeling of distributed generation, considering the impact of its output characteristics and access location on the distribution network;

[0044] ΔP DG =P DG -P base

[0045] ΔQ DG =Q DG -Q base

[0046] Among them, ΔPDG and ΔQDG are the changes in active power and reactive power before and after the distributed power supply is connected, PDG and QDG are the active power and reactive power after the distributed power supply is connected, and Pbase and Qbase are the active power and reactive power before the distributed power supply is connected.

[0047] Further, in step 3.2, the multivariate load impact analysis method is:

[0048] Analyze the impact characteristics of multiple loads, establish load models, and predict the impact of load changes on the state of the distribution network;

[0049] ΔP load =P load -P base

[0050] ΔQ load =Q load -Q base

[0051] Among them, ΔPload and ΔQload are the changes of active power and reactive power before and after the load impact, respectively, Pload and Qload are the active power and reactive power after the load impact, respectively, and Pbase and Qbase are the active power and reactive power before the load impact, respectively.

[0052] Furthermore, in step 3.3, data collection includes parameters of voltage, current, power, frequency and phase angle.

[0053] The deduction system used in the distribution network digital deduction method based on big data of the present invention includes:

[0054] Data acquisition module, data storage module, computing module, display module and power supply; wherein the computing module receives data from the data acquisition module for processing, stores it in the data storage module, and transmits the result to the display module, while relying on the power supply module to provide power support.

[0055] The data acquisition module is used to collect the distribution network operation data in real time, including the parameters of voltage, current, power, frequency and phase angle, and transmit the data to the data storage module through sensors and communication networks;

[0056] The data storage module adopts distributed storage technology to efficiently store and manage the data collected by the data collection module to ensure the integrity and security of the data;

[0057] The computing module, based on big data analysis technology and machine learning algorithm, processes and analyzes the data stored in the data storage module using a breadth-first search algorithm, data flow mapping, and a distributed power supply and multi-load state deduction method to generate an operating state, fault prediction, and optimized scheduling plan for the distribution network;

[0058] The display module displays the results generated by the calculation module through a visual interface, including real-time monitoring charts, historical data trend analysis and fault warning reports.

[0059] Specifically, the data acquisition module has a sensor for transmitting the collected data to the data storage module, and the sensor is connected to the data storage module via a communication network signal.

[0060] The number of the sensors is not limited to one, and the sensor is any one or more of a voltage sensor, a current sensor, a power sensor and a phase angle sensor.

[0061] The present invention conducts research on digital power grid computing and deduction technology. The hardware part studies the digital power grid computing and deduction technology through data acquisition module, data storage module, computing module and display module. The software part of the computing module proposes a distribution network topology verification method based on breadth-first search algorithm, a distribution network unknown measurement information completion method based on data flow mapping, and a distribution network state deduction method taking into account distributed power sources and multi-load impacts. It realizes accurate verification of the distribution network ledger topology, completion of missing measurement data, and state calculation and deduction, improves the observability, measurability and calculability of the distribution network operation state, and has good use and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 It is the overall working flow chart of the present invention.

[0064] Figure 2 It is a specific workflow diagram of step 1 in the present invention.

[0065] Figure 3 It is the specific workflow diagram of step 2 in the present invention.

[0066] Figure 4 It is the specific workflow diagram of step 3 in the present invention.

[0067] Figure 5 It is the technical roadmap of the hardware system of the present invention.

[0068] Figure 6 It is the technical roadmap of the working method system of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the attached embodiment of the present invention Figure 1-6 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Figure 5 It is the technical roadmap of the hardware system of the present invention, showing the relationship and data flow between the data acquisition module, data storage module, computing module and display module. It includes the configuration of various sensors and communication networks, the implementation of distributed storage technology and data management process, the application of big data analysis technology and machine learning algorithms, and the design and function of the visualization interface.

[0071] Figure 6 It is the technical roadmap of the software system of the present invention, which demonstrates the distribution network topology verification based on breadth-first search algorithm, the distribution network unknown measurement information completion method based on data flow mapping, and the distribution network state deduction method of distributed power sources and multi-load impact.

[0072] In the specific implementation process, the data acquisition module collects the operating data of the distribution network in real time through multiple sensors, and transmits the data to the data storage module through the communication network. The data storage module adopts distributed database technology to ensure the integrity and security of the data, and supports the rapid query and retrieval of large-scale data. The calculation module uses machine learning algorithms and big data analysis technology to process and analyze the stored data to generate the operating status, fault prediction and optimization scheduling plan of the distribution network. The display module displays the calculation results through a visual interface, including real-time monitoring charts, historical data trend analysis and fault warning reports, which facilitates users to make decisions and management. It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0073] A distribution network digital deduction method based on big data includes the following steps:

[0074] Step 1: Perform topology verification on the distribution network based on a breadth-first search algorithm;

[0075] Step 2: Completing the unknown measurement information of the distribution network based on data flow mapping;

[0076] Step 3: Simulate the distribution network status under the impact of distributed power sources and multiple loads.

[0077] The detailed steps of step 1 are:

[0078] Step 1.1, initialize the topological structure of the distribution network, including the definition of nodes and edges;

[0079] Step 1.2, starting from a node in the distribution network, traverse all nodes and edges using the breadth-first search algorithm; during the traversal process, check whether there is a loop. If a loop is found, record the loop information and process it; after the traversal, check whether there are any nodes that have not been traversed. If there are any isolated nodes, record the isolated node information and process it.

[0080] Step 1.3, based on the detected loop and isolated node information, correct the topology structure to ensure the integrity and correctness of the topology structure;

[0081] Step 1.4: During the operation of the distribution network, real-time topology verification is performed periodically or when the topology changes, to ensure that dynamic changes in the topology can be detected and processed in a timely manner.

[0082] Furthermore, in step 1.2, the topology of the distribution network is verified using a breadth-first search algorithm to ensure the integrity and correctness of the topology, including the following steps:

[0083] Power change increment calculation:

[0084] ΔP i =P i -P i-1

[0085] Where ΔPi is the power change increment of node i, Pi is the power of node i, and Pi-1 is the power of node i-1;

[0086] Voltage correlation coefficient calculation:

[0087]

[0088] Wherein, ρij is the voltage correlation coefficient between node i and node j, Vi and Vj are the voltages of node i and node j respectively, and Viˉ and Vjˉ are the mean values ​​of the voltages of node i and node j respectively.

[0089] Detect loops and isolated nodes by traversing nodes and edges: Detect loops and isolated nodes in the topology by traversing all nodes and edges of the distribution network. Select nodes directly connected to the initial node based on the power change increment and current sum.

[0090] Select node = arg max(ΔP i +I i )

[0091] Where Ii is the sum of the currents at node i.

[0092] Specifically, the detailed steps of step 2 are:

[0093] Step 2.1, collect the operation data of the distribution network in real time through the data acquisition module, including the parameters of voltage, current, power, frequency and phase angle.

[0094] Step 2.2, historical data analysis: By analyzing historical operation data, a data flow model is established to predict unknown measurement information.

[0095] Step 2.3, data flow mapping: Use data flow mapping technology to complete the unknown measurement information in the distribution network.

[0096] Step 2.4, multi-source data fusion: Combine multi-source data, such as smart meter data, sensor data, etc., to improve the accuracy of measurement information completion.

[0097] Step 2.5, adaptive completion: Adaptively adjust the data flow model according to the changes in the operating status of the distribution network to ensure the real-time and accuracy of the completion results.

[0098] Step 2.6, result verification: Verify the completed measurement information to ensure its accuracy and reliability.

[0099] Furthermore, in step 2.3, the method for completing the unknown measurement information in the distribution network is:

[0100] P ij =V i V j (G ij cos(θ i -θ j )+B ij sin(θ i -θ j ))

[0101] Q ij =V i V j (G ij sin(θ i -θ j )-Bij cos(θ i -θ j ))

[0102] Among them, Gij and Bij are the real and imaginary parts of the admittance between node i and node j, respectively.

[0103] In the prior art, the methods for completing unknown measurement information of distribution networks mostly use simple interpolation or extrapolation algorithms, which have the problems of low accuracy and poor adaptability. The prior art is difficult to cope with the dynamic changes in the operating status of the distribution network, while the present invention has an adaptive completion function, which can adjust the data flow model in real time according to the changes in the operating status, thereby improving the accuracy and real-time performance of the completion results.

[0104] Specifically, the detailed steps of step 3 are:

[0105] Step 3.1, distributed power generation modeling: Model the distributed power generation, considering the impact of its output characteristics and access location on the distribution network;

[0106] Step 3.2, multi-load modeling: Analyze the impact characteristics of multi-loads, establish a load model, and predict the impact of load changes on the distribution network status;

[0107] Step 3.3, data collection: collect the operation data of the distribution network in real time through the data collection module;

[0108] Step 3.4, state deduction: Based on big data analysis and machine learning algorithms, the operating state of the distribution network is deduced to predict the state of the distribution network under the impact of distributed power sources and multiple loads.

[0109] Furthermore, in step 3.1, the distributed power modeling method is:

[0110] Modeling of distributed generation, considering the impact of its output characteristics and access location on the distribution network;

[0111] ΔP DG =P DG -P base

[0112] ΔQ DG =Q DG -Q base

[0113] Among them, ΔPDG and ΔQDG are the changes in active power and reactive power before and after the distributed power supply is connected, PDG and QDG are the active power and reactive power after the distributed power supply is connected, and Pbase and Qbase are the active power and reactive power before the distributed power supply is connected.

[0114] Further, in step 3.2, the multivariate load impact analysis method is:

[0115] Analyze the impact characteristics of multiple loads, establish load models, and predict the impact of load changes on the state of the distribution network;

[0116] ΔP load =P load -P base

[0117] ΔQ load =Q load -Q base

[0118] Among them, ΔPload and ΔQload are the changes of active power and reactive power before and after the load impact, respectively, Pload and Qload are the active power and reactive power after the load impact, respectively, and Pbase and Qbase are the active power and reactive power before the load impact, respectively.

[0119] Furthermore, in step 3.3, data collection includes parameters of voltage, current, power, frequency and phase angle.

[0120] The deduction system used in the distribution network digital deduction method based on big data of the present invention includes:

[0121] Data acquisition module, data storage module, computing module, display module and power supply; wherein the computing module receives data from the data acquisition module for processing, stores it in the data storage module, and transmits the result to the display module, while relying on the power supply module to provide power support.

[0122] The data acquisition module is used to collect the distribution network operation data in real time, including the parameters of voltage, current, power, frequency and phase angle, and transmit the data to the data storage module through sensors and communication networks;

[0123] The data storage module adopts distributed storage technology to efficiently store and manage the data collected by the data collection module to ensure the integrity and security of the data;

[0124] The computing module, based on big data analysis technology and machine learning algorithm, processes and analyzes the data stored in the data storage module using a breadth-first search algorithm, data flow mapping, and a distributed power supply and multi-load state deduction method to generate an operating state, fault prediction, and optimized scheduling plan for the distribution network;

[0125] The display module displays the results generated by the calculation module through a visual interface, including real-time monitoring charts, historical data trend analysis and fault warning reports.

[0126] Specifically, the data acquisition module has a sensor for transmitting the collected data to the data storage module, and the sensor is connected to the data storage module via a communication network signal.

[0127] The number of the sensors is not limited to one, and the sensor is any one or more of a voltage sensor, a current sensor, a power sensor and a phase angle sensor.

[0128] The steps of the distribution network topology verification method based on the breadth-first search algorithm are as follows:

[0129] 1. Initialization: Initialize the topology of the distribution network, including the definition of nodes and edges.

[0130] 2. Breadth-first search: Starting from a node in the distribution network, use the breadth-first search algorithm to traverse all nodes and edges.

[0131] 3. Detect loops: During the traversal process, detect whether there are loops. If a loop is found, record the loop information and handle it.

[0132] 4. Detect isolated nodes: After the traversal is completed, check whether there are any nodes that have not been traversed. If there are isolated nodes, record the isolated node information and process it.

[0133] 5. Topology error correction: Correct the topology structure based on the detected loops and isolated node information to ensure the integrity and correctness of the topology structure.

[0134] 6. Real-time verification: During the operation of the distribution network, real-time topology verification is performed regularly or when the topology changes to ensure that dynamic changes in the topology can be detected and processed in a timely manner.

[0135] The steps of the method for completing unknown measurement information of distribution network based on data flow mapping are as follows:

[0136] 1. Data acquisition: Through the data acquisition module, the operation data of the distribution network is collected in real time, including parameters such as voltage, current, power, frequency, phase angle, etc.

[0137] 2. Historical data analysis: Analyze the collected historical operation data and establish a data flow model.

[0138] 3. Data flow mapping: Use the data flow model to complete the unknown measurement information in the distribution network.

[0139] 4. Multi-source data fusion: Combine multi-source data such as smart meter data and sensor data to improve the accuracy of measurement information completion.

[0140] 5. Adaptive completion: According to the changes in the operating status of the distribution network, the data flow model is adaptively adjusted to ensure the real-time and accuracy of the completion results.

[0141] 6. Result verification: Verify the completed measurement information to ensure its accuracy and reliability.

[0142] The method and steps for deducing the state of the distribution network with distributed power sources and multi-load impacts are as follows:

[0143] 1. Distributed power generation modeling: Model the distributed power generation, considering the impact of its output characteristics and access location on the distribution network.

[0144] 2. Multi-load modeling: Analyze the impact characteristics of multi-loads, establish load models, and predict the impact of load changes on the state of the distribution network.

[0145] 3. Data acquisition: Through the data acquisition module, the operation data of the distribution network is collected in real time, including parameters such as voltage, current, power, frequency, phase angle, etc.

[0146] 4. State deduction: Based on big data analysis and machine learning algorithms, the operating status of the distribution network is deduced to predict the state of the distribution network under the impact of distributed power sources and multiple loads.

[0147] The specific implementation of the present invention will describe in detail a distribution network topology verification method based on a breadth-first search algorithm, a distribution network unknown measurement information completion method based on data flow mapping, and a distribution network state deduction method for distributed power sources and multi-load impacts. The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A distribution network digital deduction method based on big data, characterized by: The steps include: Step 1: Perform topology verification on the distribution network based on a breadth-first search algorithm; Step 2: Completing the unknown measurement information of the distribution network based on data flow mapping; Step 3: Simulate the distribution network status under the impact of distributed power sources and multiple loads.

2. According to a big data-based distribution network digital deduction method according to claim 1, it is characterized by: The detailed steps of step 1 are: Step 1.1, initialize the topological structure of the distribution network, including the definition of nodes and edges; Step 1.2, starting from a node in the distribution network, traverse all nodes and edges using the breadth-first search algorithm; during the traversal process, check whether there is a loop. If a loop is found, record the loop information and process it; after the traversal, check whether there are any nodes that have not been traversed. If there are any isolated nodes, record the isolated node information and process it. Step 1.3, based on the detected loop and isolated node information, correct the topology structure to ensure the integrity and correctness of the topology structure; Step 1.4: During the operation of the distribution network, real-time topology verification is performed periodically or when the topology changes, to ensure that dynamic changes in the topology can be detected and processed in a timely manner.

3. A distribution network digital deduction method based on big data according to claim 2, characterized in that: In step 1.2, the topology of the distribution network is verified using a breadth-first search algorithm to ensure the integrity and correctness of the topology, including the following steps: Power change increment calculation: ΔP i =P i -P i-1 Where ΔPi is the power change increment of node i, Pi is the power of node i, and Pi-1 is the power of node i-1; Voltage correlation coefficient calculation: Wherein, ρij is the voltage correlation coefficient between node i and node j, Vi and Vj are the voltages of node i and node j respectively, and Viˉ and Vjˉ are the mean values ​​of the voltages of node i and node j respectively. Detect loops and isolated nodes by traversing nodes and edges: Detect loops and isolated nodes in the topology by traversing all nodes and edges of the distribution network. Select nodes directly connected to the initial node based on the power change increment and current sum. Select node = arg max(ΔP i +I i ) Where Ii is the sum of the currents at node i.

4. The method for digital deduction of a distribution network based on big data according to claim 1, characterized in that: Specifically, the detailed steps of step 2 are: Step 2.1, collect the operation data of the distribution network in real time through the data acquisition module, including the parameters of voltage, current, power, frequency and phase angle. Step 2.2, historical data analysis: By analyzing historical operation data, a data flow model is established to predict unknown measurement information. Step 2.3, data flow mapping: Use data flow mapping technology to complete the unknown measurement information in the distribution network. Step 2.4, multi-source data fusion: Combine multi-source data, such as smart meter data, sensor data, etc., to improve the accuracy of measurement information completion. Step 2.5, adaptive completion: Adaptively adjust the data flow model according to the changes in the operating status of the distribution network to ensure the real-time and accuracy of the completion results. Step 2.6, result verification: Verify the completed measurement information to ensure its accuracy and reliability.

5. The method for digital deduction of a distribution network based on big data according to claim 4 is characterized in that: The method for completing the unknown measurement information in the distribution network in step 2.3 is: P ij =V i V j (G ij cos(θ i -θ j )+B ij sin(θ i -θ j )) Q ij =V i V j (G ij sin(θ i -θ j )-B ij cos(θ i -θ j )) Among them, Gij and Bij are the real and imaginary parts of the admittance between node i and node j, respectively.

6. The method for digital deduction of a distribution network based on big data according to claim 1, characterized in that: The detailed steps of step 3 are: Step 3.1, distributed power generation modeling: Model the distributed power generation, considering the impact of its output characteristics and access location on the distribution network; Step 3.2, multi-load modeling: Analyze the impact characteristics of multi-loads, establish a load model, and predict the impact of load changes on the distribution network status; Step 3.3, data collection: collect the operation data of the distribution network in real time through the data collection module; Step 3.4, state deduction: Based on big data analysis and machine learning algorithms, the operating state of the distribution network is deduced to predict the state of the distribution network under the impact of distributed power sources and multiple loads.

7. The method for digital deduction of a distribution network based on big data according to claim 6 is characterized in that: In step 3.1, the distributed power modeling method is: Modeling of distributed generation, considering the impact of its output characteristics and access location on the distribution network; ΔP DG =P DG -P base ΔQ DG =Q DG -Q base Among them, ΔPDG and ΔQDG are the changes in active power and reactive power before and after the distributed power supply is connected, PDG and QDG are the active power and reactive power after the distributed power supply is connected, and Pbase and Qbase are the active power and reactive power before the distributed power supply is connected.

8. The method for digital deduction of a distribution network based on big data according to claim 6 is characterized by: In step 3.2, the multivariate load impact analysis method is: Analyze the impact characteristics of multiple loads, establish load models, and predict the impact of load changes on the state of the distribution network; ΔP load =P load -P base ΔQ load =Q load -Q base Among them, ΔPload and ΔQload are the changes of active power and reactive power before and after the load impact, respectively, Pload and Qload are the active power and reactive power after the load impact, respectively, and Pbase and Qbase are the active power and reactive power before the load impact, respectively.

9. The method for digital deduction of a distribution network based on big data according to claim 6, characterized in that: In step 3.3, data acquisition includes parameters of voltage, current, power, frequency and phase angle.

10. The deduction system used by the distribution network digital deduction method based on big data according to claim 1 is characterized in that include: Data acquisition module, data storage module, calculation module, display module and power supply; The computing module receives data from the data acquisition module for processing, stores the data in the data storage module, and transmits the result to the display module, while relying on the power supply module to provide power support; The data acquisition module is used to collect the distribution network operation data in real time, including the parameters of voltage, current, power, frequency and phase angle, and transmit the data to the data storage module through sensors and communication networks; The data storage module adopts distributed storage technology to efficiently store and manage the data collected by the data collection module to ensure the integrity and security of the data; The computing module, based on big data analysis technology and machine learning algorithm, processes and analyzes the data stored in the data storage module using a breadth-first search algorithm, data flow mapping, and a distributed power supply and multi-load state deduction method to generate an operating state, fault prediction, and optimized scheduling plan for the distribution network; The display module displays the results generated by the calculation module through a visual interface, including real-time monitoring charts, historical data trend analysis and fault warning reports.

11. The deduction system used in the distribution network digital deduction method based on big data according to claim 10 is characterized in that include: Specifically, the data acquisition module has a sensor for transmitting the collected data to the data storage module, and the sensor is connected to the data storage module via a communication network signal.

12. The deduction system used in the distribution network digital deduction method based on big data according to claim 10 is characterized in that include: The number of the sensors is not limited to one, and the sensor is any one or more of a voltage sensor, a current sensor, a power sensor and a phase angle sensor.

Images