An energy management collaborative control method and system suitable for a medium and low voltage distribution network

Abstract

The application provides an energy management collaborative control method and system suitable for a medium and low voltage distribution network, comprising the following steps: constructing a medium and low voltage intelligent distribution network system with multi-element power user resource access; obtaining measurement data of each network node and device by using real-time measurement and artificial intelligence estimation technology; cleaning the measurement data by using a micro-grid group collaborative control device, and correcting and optimizing the measurement data estimated by the artificial intelligence; judging the state of each network topology and device in the medium and low voltage intelligent distribution network system by using the micro-grid group collaborative control device through all the measurement data; and reconstructing the structure and composition of the micro-grid and micro-grid group in the medium and low voltage intelligent distribution network system in real time based on the state of each network topology and device by using the micro-grid group collaborative control device. The application realizes the collaborative control of the distribution network on the basis of a small number of intelligent terminal configurations based on real-time measurement and artificial intelligence estimation technology, and effectively reduces the frequency of human intervention.

Description

Technical Field

[0001] This invention belongs to the field of medium and low voltage smart distribution network and energy management technology, specifically relating to an energy management collaborative control method and system suitable for medium and low voltage distribution networks. Background Technology

[0002] Currently, the existing power distribution network is facing enormous challenges from various aspects, such as customized and diversified electricity demand, large-scale access of distributed power sources, and complex power flow coordination and control. In the face of the disorderly development of distributed energy, distributed energy storage, and electric vehicles with high penetration rates, higher requirements need to be placed on the means of ensuring power quality and power supply reliability of medium and low voltage smart distribution networks.

[0003] These problems are difficult to solve effectively using conventional switching, traditional measurement, and energy management control methods. There is also a high frequency of human intervention, which cannot effectively guarantee the safe and stable operation of the distribution network. Summary of the Invention

[0004] In view of this, the present invention aims to solve the problem of high frequency of human intervention in the existing methods of ensuring power quality and power supply reliability of medium and low voltage smart distribution networks by using conventional switching, traditional measurement and energy management control methods.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides an energy management collaborative control method suitable for medium and low voltage distribution networks, comprising the following steps:

[0007] Construct a medium- and low-voltage smart distribution network system with access to diverse power user resources. In the smart distribution network system, the primary equipment of the smart distribution network topology and key network nodes in each region are embedded with microgrid group collaborative control devices.

[0008] Based on neural networks, the system measures the operational data of key nodes and devices in real time through smart terminals, and uses artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices.

[0009] The real-time measurement data is cleaned using a microgrid group collaborative control device. Based on the complementary characteristics of the data of various power user groups in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes, the measurement data estimated by artificial intelligence is corrected. Then, all the corrected measurement data is optimized to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device.

[0010] The status of each network topology and equipment in a medium- and low-voltage smart distribution network system is determined by using a microgrid group collaborative control device based on all measurement data.

[0011] By utilizing a microgrid group collaborative control device, the structure and composition of microgrids and microgrid groups in medium and low voltage smart distribution network systems can be reconstructed in real time based on the network topology and the status of each device.

[0012] Furthermore, the real-time measurement data is cleaned using a microgrid group collaborative control device, specifically including:

[0013] Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the data.

[0014] For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data. Otherwise, the data is determined to be abnormal and further processing is performed.

[0015] Perform historical data similarity identification on abnormal data to find similar historical data;

[0016] If found, the status of abnormal data is determined based on similar historical data, and then included in the usage;

[0017] If not found, determine whether the abnormal data sliding window duration meets the set conditions. If yes, it is determined to be correct measurement data; otherwise, determine the abnormality or change of operating condition of the real-time measurement equipment based on the spatiotemporal coupling relationship of electrical attributes. If the related measurement data is abnormal, the real-time measurement equipment is determined to be abnormal and the corresponding measurement value is discarded. If the related measurement data is normal, the real-time measurement equipment is determined to be in a change of operating condition and the corresponding measurement value is included in the usage.

[0018] Furthermore, the measurement data estimated by artificial intelligence is corrected using a microgrid group collaborative control device, specifically including:

[0019] For measurement data estimated by artificial intelligence, predictions are made based on the characteristics of stored historical measurement data;

[0020] The measurement data estimated by artificial intelligence is corrected based on the predicted measurement values;

[0021] Determine whether the corrected measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step.

[0022] The zero-drift data of the calibrated measurement data is discarded to obtain the final calibrated measurement data.

[0023] Furthermore, the structure and composition of microgrids and microgrid groups in low-voltage smart distribution network systems are reconstructed in real time using microgrid group collaborative control devices, specifically including:

[0024] The microgrid group collaborative control device adopts a hierarchical and zonal approach to reconstruct the energy flow path of the microgrid in real time in two stages. The hierarchical and zonal approach specifies the real-time reconstruction sequence of the microgrid and microgrid group in the medium and low voltage smart distribution network system for the microgrid group collaborative control device, and the real-time reconstruction targets of the microgrid group collaborative control device are specified in the two stages.

[0025] Furthermore, when using microgrid group collaborative control devices for real-time reconfiguration, the first stage specifically involves:

[0026] Based on the principle of minimizing power outages and considering the constraints of power quality, transformer and line overload, a collaborative approach for medium and low voltage smart distribution networks is adopted. The first phase of reconfiguration is completed by controlling the medium and low voltage smart distribution network through multi-state smart soft switches at key nodes.

[0027] During the reconfiguration process, the same-layer power grid is prioritized. If the reconfiguration time of the same-layer power grid exceeds the threshold, the hierarchical power grid reconfiguration will be initiated. If the hierarchical power grid reconfiguration fails, an alarm message will be uploaded.

[0028] Furthermore, when using microgrid group collaborative control devices for real-time reconfiguration, the second stage specifically involves:

[0029] With the goal of achieving the shortest energy flow path, and considering constraints including at least the shortest energy path, lowest network loss, best power quality, minimum voltage drop, and no overload of transformers and lines, we reconstruct self-balancing, self-regulating, and self-controlling microgrids and microgrid clusters.

[0030] Furthermore, the microgrid group collaborative control device utilizes clustering algorithms to comprehensively consider multiple angles and dimensions of various power user groups in the medium and low voltage smart distribution network system, and optimizes the energy flow path of the microgrid and microgrid group in real time to achieve optimal energy flow within the microgrid and microgrid group.

[0031] Secondly, the present invention provides an energy management collaborative control system suitable for medium and low voltage distribution networks, comprising:

[0032] The smart distribution network unit is used to store the medium and low voltage smart distribution network system that has been constructed and has access to multiple power user resources. The primary equipment of the smart distribution network topology and key network nodes in each area of ​​the smart distribution network system are all embedded with microgrid group collaborative control devices.

[0033] The data measurement unit is used to measure the operational data of key nodes and devices in real time through smart terminals based on neural networks, and to use artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices.

[0034] The data processing unit is used to clean the real-time measurement data using the microgrid group collaborative control device, and correct the measurement data estimated by artificial intelligence based on the complementary characteristics of the data of each power user group in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes. Then, it optimizes all the corrected measurement data to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device.

[0035] The status judgment unit is used to determine the status of each network topology and equipment in the medium and low voltage smart distribution network system by using the microgrid group collaborative control device through all measurement data;

[0036] The network reconfiguration unit is used to reconfigure the structure and composition of microgrids and microgrid groups in the medium and low voltage smart distribution network system in real time based on the network topology and the status of each network and device, using the microgrid group collaborative control device.

[0037] Furthermore, in the data processing unit, the real-time measurement data is cleaned using a microgrid group collaborative control device, specifically including:

[0038] Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the data.

[0039] For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data. Otherwise, the data is determined to be abnormal and further processing is performed.

[0040] Perform historical data similarity identification on abnormal data to find similar historical data;

[0041] If found, the status of abnormal data is determined based on similar historical data, and then included in the usage;

[0042] If not found, determine whether the abnormal data sliding window duration meets the set conditions. If yes, it is determined to be correct measurement data; otherwise, determine the abnormality or change of operating condition of the real-time measurement equipment based on the spatiotemporal coupling relationship of electrical attributes. If the related measurement data is abnormal, the real-time measurement equipment is determined to be abnormal and the corresponding measurement value is discarded. If the related measurement data is normal, the real-time measurement equipment is determined to be in a change of operating condition and the corresponding measurement value is included in the usage.

[0043] Furthermore, in the data processing unit, the measurement data estimated by artificial intelligence is corrected using a microgrid group collaborative control device, specifically including:

[0044] For measurement data estimated by artificial intelligence, predictions are made based on the characteristics of stored historical measurement data;

[0045] The measurement data estimated by artificial intelligence is corrected based on the predicted measurement values;

[0046] Determine whether the corrected measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step.

[0047] The zero-drift data of the calibrated measurement data is discarded to obtain the final calibrated measurement data.

[0048] In summary, this invention provides a collaborative control method and system for energy management in medium- and low-voltage distribution networks. The method includes constructing a medium- and low-voltage smart distribution network system with access to diverse power user resources; obtaining measurement data for each network node and device using real-time measurement and artificial intelligence estimation techniques; cleaning the measurement data using a microgrid group collaborative control device and correcting and optimizing the measurement data estimated by artificial intelligence to obtain all the measurement data for the nodes and devices required to finally implement the microgrid group collaborative control device; using the microgrid group collaborative control device to determine the state of each network topology and device in the medium- and low-voltage smart distribution network system based on all the measurement data; and using the microgrid group collaborative control device to reconstruct the structure and composition of the microgrids and microgrid groups in the medium- and low-voltage smart distribution network system in real time based on the state of each network topology and device. This invention, based on real-time measurement and artificial intelligence estimation techniques, achieves collaborative control of the distribution network with a relatively small number of intelligent terminals, effectively reducing the frequency of human intervention. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 A flowchart illustrating an energy management collaborative control method applicable to medium and low voltage power distribution networks, provided as an embodiment of the present invention;

[0051] Figure 2 This is a typical network topology diagram of a medium- and low-voltage smart distribution network provided in an embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of centralized and distributed control networks provided in an embodiment of the present invention;

[0053] Figure 4 A data cleaning flowchart provided for embodiments of the present invention;

[0054] Figure 5 A data correction flowchart provided for embodiments of the present invention;

[0055] Figure 6 A flowchart of energy flow path reconfiguration provided for an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0057] Please see Figure 1 This embodiment provides an energy management collaborative control method suitable for medium and low voltage distribution networks, including the following steps:

[0058] S1: Construct a medium- and low-voltage smart distribution network system with access to diverse power user resources. In the smart distribution network system, the primary equipment of the smart distribution network topology and key network nodes in each region are embedded with microgrid group collaborative control devices.

[0059] It should be noted that the medium and low voltage smart distribution network system is based on a distributed "source-grid-load-storage" microgrid constructed from diverse power user resources such as distributed photovoltaic, distributed wind power, distributed energy storage, electric vehicles, and adjustable flexible loads.

[0060] Microgrids are connected through AC tie lines or flexible multi-state smart soft switches to build a self-balancing, self-regulating, and self-controlling microgrid group that is cooperative, interactive, and mutually complementary within the region. With the interaction of "source-grid-load-storage" as the core, a flexible aggregated smart distribution network with "strong uncertainty-interactive coupling" is constructed.

[0061] Microgrids and microgrid clusters are equipped with microgrid cluster collaborative control devices. These devices are configured in a hierarchical manner, with each device embedded in the existing smart distribution network topology and primary equipment of key network nodes within its controlled area.

[0062] The smart distribution network is built on the "cloud-edge collaboration" to construct a power Internet of Things with information interconnection as the core, realizes the coordinated cooperation of multi-level microgrid group control devices, and builds a highly integrated smart distribution network system of "microgrid-Internet of Things-social user group". Figure 2 This is a typical network topology diagram of the constructed medium- and low-voltage smart distribution network. Figure 3 This is a network diagram illustrating centralized and distributed control.

[0063] S2: Based on neural networks, it measures the operational data of key nodes and devices in real time through smart terminals, and uses artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices.

[0064] S3: The microgrid group collaborative control device is used to clean the real-time measurement data. Based on the complementary characteristics of the data of each power user group in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes, the measurement data estimated by artificial intelligence is corrected. Then, all the corrected measurement data is optimized to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device.

[0065] It should be noted that the microgrid group collaborative control device uses data cleaning technology as its core to identify the rationality of real-time measurement data (comparing data size with the sliding window time period, with continuous sliding window time less than a threshold), eliminating abnormal and unreasonable data, and completing the initial data screening. The specific process of data cleaning includes:

[0066] S211: Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the usage;

[0067] S212: For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data for use; otherwise, the data is determined to be abnormal and further processing is performed.

[0068] S213: Perform historical data similarity identification on abnormal data to find similar historical data;

[0069] S214: If found, the abnormal data status is determined based on similar historical data and included in the usage;

[0070] S215: If not found, determine if the abnormal data sliding window duration meets the set conditions. If yes, it is considered correct measurement data; otherwise, based on the spatiotemporal coupling relationship of electrical attributes, determine the abnormality or change in operating condition of the real-time measurement equipment. If the associated measurement data is abnormal, the real-time measurement equipment is considered abnormal, and the corresponding measurement value is discarded. If the associated measurement data is normal, the real-time measurement equipment is considered to have changed operating conditions, and the corresponding measurement value is included in the usage. Flowchart as follows: Figure 4 As shown.

[0071] The AI ​​estimation and acquisition technology for the “source-grid-load-storage” power user group is based on a combination of grey relational analysis and digital twin methods. It selects similar data from real-time measurement data and historically stored measurement data of the power user group. The microgrid group collaborative control device further filters the data through data cleaning technology to complete the AI ​​estimation and acquisition of measurement data of missing equipment and network nodes.

[0072] The microgrid group collaborative control device considers the complementary characteristics of the "source-grid-load-storage" power user group data and the spatiotemporal coupling relationship of their electrical attributes. It applies artificial intelligence methods such as convolutional neural networks to predict and correct AI-estimated measurement data, making the AI-estimated measurement data closer to the actual characteristics of equipment and nodes. The specific process of data correction in the microgrid group collaborative control device includes:

[0073] S221: Make predictions based on the characteristics of stored historical measurement data, using measurement data estimated by artificial intelligence;

[0074] S222: Correct the measurement data estimated by artificial intelligence based on the predicted measurement values;

[0075] S223: Determine whether the calibrated measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step.

[0076] S224: Discard the zero drift of the calibrated measurement data to obtain the final calibrated measurement data.

[0077] The data correction process is as follows Figure 5 As shown.

[0078] Considering the uncertainties such as diverse data sources, varied transmission methods, and data drift, the microgrid group collaborative control device adopts a high-precision dynamic estimation method of Kalman filtering with pseudo-measurement adaptive interpolation to optimize the corrected data, and finally realizes the acquisition of all the node and equipment measurement data required by the microgrid group collaborative control device.

[0079] S4: Using the microgrid group collaborative control device, the status of each network topology and device in the medium and low voltage smart distribution network system is determined by all measurement data.

[0080] It should be noted that the microgrid and microgrid group coordination control device determines the status of the medium and low voltage smart distribution network and equipment by real-time collected measurement data and artificial intelligence estimation of the collected measurement data. The uncertainty of the status of the medium and low voltage smart distribution network and equipment restricts the energy flow path of the medium and low voltage smart distribution network. The microgrid and microgrid group coordination control device reconstructs the structure and composition of the microgrid and microgrid group in real time based on the uncertainty of the status of the medium and low voltage smart distribution network and distributed photovoltaic, distributed wind power, distributed energy storage, electric vehicles and other equipment.

[0081] S5: Utilizing a microgrid group collaborative control device, the structure and composition of microgrids and microgrid groups in the medium and low voltage smart distribution network system are reconstructed in real time based on the network topology and equipment status.

[0082] It should be noted that the microgrid group coordination control device adopts a hierarchical and partitioned approach for reconfiguration based on equipment status and changes in the medium and low voltage power distribution network architecture (line fault tripping, manual operation withdrawal, etc.). The reconfiguration is divided into two stages: real-time reconfiguration of the energy flow path of the microgrid in the event of faults, poor power quality, and severe network losses.

[0083] In the process of reconstructing the medium and low voltage smart distribution network, the first stage takes the principle of shortest power outage (shortest path to provide power first) as the principle. Considering the basic constraints of power quality and transformer and line overload, the method of medium and low voltage smart distribution network coordination is adopted. The first stage of reconstruction is completed quickly by controlling the medium and low voltage smart distribution network through multi-state smart soft switching of key nodes.

[0084] During the reconfiguration process, the same-layer power grid is prioritized. If the reconfiguration time of the same-layer power grid exceeds the threshold, the hierarchical power grid reconfiguration will be initiated. If the hierarchical power grid reconfiguration fails, an alarm message will be uploaded.

[0085] The second phase of the reconfiguration process considers constraints such as the shortest energy path, the lowest network loss, the best power quality, the lowest voltage drop, and no overload of transformers and lines, with the goal of achieving the shortest energy flow path and reconfiguring "self-balancing, self-regulating, and self-controlling" microgrids and microgrid clusters.

[0086] The microgrid group coordination control device is based on the spatiotemporal characteristics of adjustable devices such as distributed energy storage, electric vehicles, and adjustable flexible loads, which are collected in real time and virtually. The device uses clustering algorithms to analyze the daily load curves of user groups such as distributed energy storage, electric vehicles, and adjustable flexible loads. It comprehensively considers multiple perspectives and dimensions such as adjustable costs and electricity user willingness to optimize the energy flow path of the microgrid and microgrid group in real time to achieve the optimal energy flow within the microgrid and microgrid group. The optimal energy flow reconfiguration must be executed after the operator confirms the command. Figure 6 Flowchart for refactoring energy flow paths.

[0087] This invention provides an energy management collaborative control method suitable for medium and low voltage distribution networks. Based on real-time measurement and artificial intelligence estimation technology, this method realizes automatic power flow control according to the real-time and virtual acquisition of the status of medium and low voltage distribution network equipment, reduces human intervention, and ensures the safe and stable operation of the new energy distribution network system.

[0088] The above is a detailed description of an embodiment of the energy management collaborative control method applicable to medium and low voltage distribution networks according to the present invention. The following will provide a detailed description of an embodiment of the energy management collaborative control system applicable to medium and low voltage distribution networks according to the present invention.

[0089] This embodiment provides an energy management collaborative control system suitable for medium and low voltage distribution networks, including:

[0090] The smart distribution network unit is used to store the medium and low voltage smart distribution network system that has been constructed and has access to multiple power user resources. The primary equipment of the smart distribution network topology and key network nodes in each area of ​​the smart distribution network system are all embedded with microgrid group collaborative control devices.

[0091] The data measurement unit is used to measure the operational data of key nodes and devices in real time through smart terminals based on neural networks, and to use artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices.

[0092] The data processing unit is used to clean the real-time measurement data using the microgrid group collaborative control device, and correct the measurement data estimated by artificial intelligence based on the complementary characteristics of the data of each power user group in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes. Then, it optimizes all the corrected measurement data to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device.

[0093] The status judgment unit is used to determine the status of each network topology and equipment in the medium and low voltage smart distribution network system by using the microgrid group collaborative control device through all measurement data;

[0094] The network reconfiguration unit is used to reconfigure the structure and composition of microgrids and microgrid groups in the medium and low voltage smart distribution network system in real time based on the network topology and the status of each network and device, using the microgrid group collaborative control device.

[0095] Furthermore, in the data processing unit, the real-time measurement data is cleaned using a microgrid group collaborative control device, specifically including:

[0096] Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the data.

[0097] For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data. Otherwise, the data is determined to be abnormal and further processing is performed.

[0098] Perform historical data similarity identification on abnormal data to find similar historical data;

[0099] If found, the status of abnormal data is determined based on similar historical data, and then included in the usage;

[0100] If not found, determine whether the abnormal data sliding window duration meets the set conditions. If yes, it is determined to be correct measurement data; otherwise, determine the abnormality or change of operating condition of the real-time measurement equipment based on the spatiotemporal coupling relationship of electrical attributes. If the related measurement data is abnormal, the real-time measurement equipment is determined to be abnormal and the corresponding measurement value is discarded. If the related measurement data is normal, the real-time measurement equipment is determined to be in a change of operating condition and the corresponding measurement value is included in the usage.

[0101] Furthermore, in the data processing unit, the measurement data estimated by artificial intelligence is corrected using a microgrid group collaborative control device, specifically including:

[0102] For measurement data estimated by artificial intelligence, predictions are made based on the characteristics of stored historical measurement data;

[0103] The measurement data estimated by artificial intelligence is corrected based on the predicted measurement values;

[0104] Determine whether the corrected measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step.

[0105] The zero-drift data of the calibrated measurement data is discarded to obtain the final calibrated measurement data.

[0106] It should be noted that the cooperative control system in this embodiment is used to implement the cooperative control method of the aforementioned embodiment. The specific settings of each unit are based on the complete implementation of the method, and will not be repeated here.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A collaborative control method for energy management applicable to medium and low voltage distribution networks, characterized in that, Includes the following steps: A medium- and low-voltage smart distribution network system with access to diverse power user resources is constructed. In this smart distribution network system, the primary equipment of the smart distribution network topology and key network nodes in each region are embedded with microgrid group collaborative control devices. Based on neural networks, the system measures the operational data of key nodes and devices in real time through smart terminals, and uses artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices. The microgrid group collaborative control device is used to clean the real-time measurement data. Based on the complementary characteristics of the data of each power user group in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes, the measurement data estimated by artificial intelligence is corrected. Then, all the corrected measurement data is optimized to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device. The microgrid group collaborative control device uses all the measurement data to determine the status of each network topology and device in the medium and low voltage smart distribution network system. Using the microgrid group collaborative control device, the structure and composition of the microgrids and microgrid groups in the medium and low voltage smart distribution network system can be reconstructed in real time based on the network topology and the status of each device; The real-time reconstruction of the structure and composition of microgrids and microgrid groups in the medium- and low-voltage smart distribution network system using the microgrid group collaborative control device specifically includes: The microgrid group collaborative control device adopts a hierarchical and partitioned approach to reconstruct the energy flow path of the microgrid in real time in two stages. The hierarchical and partitioned approach specifies the real-time reconstruction sequence of the microgrid and microgrid group in the medium and low voltage smart distribution network system. The two stages respectively specify the real-time reconstruction target of the microgrid group collaborative control device. When using the microgrid group collaborative control device for real-time reconfiguration, the first stage specifically includes: Based on the principle of minimizing power outages and considering the constraints of power quality, transformer and line overload, a collaborative approach for medium and low voltage smart distribution networks is adopted. The first phase of reconfiguration is completed by controlling the medium and low voltage smart distribution network through multi-state smart soft switches at key nodes. During the reconfiguration process, the same-layer power grid is prioritized. If the reconfiguration time of the same-layer power grid exceeds the threshold, the hierarchical power grid reconfiguration will be initiated. If the hierarchical power grid reconfiguration fails, an alarm message will be uploaded. When using the microgrid group collaborative control device for real-time reconfiguration, the second stage specifically involves: With the goal of achieving the shortest energy flow path, and considering constraints including at least the shortest energy path, lowest network loss, best power quality, minimum voltage drop, and no overload of transformers and lines, we reconstruct self-balancing, self-regulating, and self-controlling microgrids and microgrid clusters.

2. The energy management collaborative control method for medium and low voltage distribution networks according to claim 1, characterized in that, The microgrid group collaborative control device is used to perform data cleaning on real-time measurement data, specifically including: Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the data. For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data for use; otherwise, the data is determined to be abnormal and further processing is performed. Perform historical data similarity identification on abnormal data to find similar historical data; If found, the abnormal data status is determined based on the similar historical data and included in the usage; If not found, determine whether the abnormal data sliding window duration meets the set conditions. If yes, it is determined to be correct measurement data; otherwise, determine the abnormality or change of operating condition of the real-time measurement equipment based on the spatiotemporal coupling relationship of electrical attributes. If the related measurement data is abnormal, the real-time measurement equipment is determined to be abnormal and the corresponding measurement value is discarded. If the related measurement data is normal, the real-time measurement equipment is determined to be in a change of operating condition and the corresponding measurement value is included in the usage.

3. The energy management collaborative control method for medium and low voltage distribution networks according to claim 1, characterized in that, The microgrid group collaborative control device is used to correct the measurement data estimated by artificial intelligence, specifically including: For measurement data estimated by artificial intelligence, predictions are made based on the characteristics of stored historical measurement data; The measurement data estimated by the artificial intelligence is corrected based on the predicted measurement values; Determine whether the corrected measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step. The zero-drift data of the calibrated measurement data is discarded to obtain the final calibrated measurement data.

4. The energy management collaborative control method for medium and low voltage distribution networks according to claim 1, characterized in that, The microgrid group collaborative control device uses a clustering algorithm to comprehensively consider multiple angles and dimensions of each power user group in the medium and low voltage smart distribution network system, and optimizes the energy flow path of the microgrid and microgrid group in real time to achieve the optimal energy flow within the microgrid and microgrid group.

5. An energy management collaborative control system suitable for medium and low voltage distribution networks, characterized in that, include: The intelligent distribution network unit is used to store the constructed medium- and low-voltage intelligent distribution network system with access to multiple power user resources. The primary equipment of the intelligent distribution network topology and key network nodes in each area of ​​the intelligent distribution network system are all embedded with microgrid group collaborative control devices. The data measurement unit is used to measure the operational data of key nodes and devices in real time through smart terminals based on neural networks, and to use artificial intelligence estimation technology to supplement the measurement data of the remaining network nodes and devices. The data processing unit is used to clean the real-time measurement data using the microgrid group collaborative control device, and correct the measurement data estimated by artificial intelligence based on the complementary characteristics of the data of each power user group in the smart distribution network system and the spatiotemporal coupling relationship of their electrical attributes. Then, it optimizes all the corrected measurement data to obtain all the measurement data of the nodes and equipment required to finally realize the microgrid group collaborative control device. The status judgment unit is used to determine the status of each network topology and device in the medium and low voltage smart distribution network system by using the microgrid group collaborative control device through all the measurement data; The network reconfiguration unit is used to reconfigure the structure and composition of the microgrids and microgrid groups in the medium and low voltage smart distribution network system in real time based on the network topology and the status of each network and device using the microgrid group collaborative control device. The real-time reconstruction of the structure and composition of microgrids and microgrid groups in the medium- and low-voltage smart distribution network system using the microgrid group collaborative control device specifically includes: The microgrid group collaborative control device adopts a hierarchical and partitioned approach to reconstruct the energy flow path of the microgrid in real time in two stages. The hierarchical and partitioned approach specifies the real-time reconstruction sequence of the microgrid and microgrid group in the medium and low voltage smart distribution network system by the microgrid group collaborative control device, and the two stages specify the real-time reconstruction targets of the microgrid group collaborative control device. When using the microgrid group collaborative control device for real-time reconfiguration, the first stage specifically includes: Based on the principle of minimizing power outages and considering the constraints of power quality, transformer and line overload, a collaborative approach for medium and low voltage smart distribution networks is adopted. The first phase of reconfiguration is completed by controlling the medium and low voltage smart distribution network through multi-state smart soft switches at key nodes. During the reconfiguration process, the same-layer power grid is prioritized. If the reconfiguration time of the same-layer power grid exceeds the threshold, the hierarchical power grid reconfiguration will be initiated. If the hierarchical power grid reconfiguration fails, an alarm message will be uploaded. When using the microgrid group collaborative control device for real-time reconfiguration, the second stage specifically involves: With the goal of achieving the shortest energy flow path, and considering constraints including at least the shortest energy path, lowest network loss, best power quality, minimum voltage drop, and no overload of transformers and lines, we reconstruct self-balancing, self-regulating, and self-controlling microgrids and microgrid clusters.

6. The energy management collaborative control system for medium and low voltage distribution networks according to claim 5, characterized in that, In the data processing unit, the microgrid group collaborative control device is used to perform data cleaning on the real-time measurement data, specifically including: Data with null values ​​in real-time measurement data will be treated as abnormal data and will not be included in the data. For the remaining real-time measurement data, calculate the mean of the data within the sliding window range, and determine whether the difference between the real-time measurement data and the mean meets the set conditions. If so, the real-time measurement data is determined to be correct and included in the data for use; otherwise, the data is determined to be abnormal and further processing is performed. Perform historical data similarity identification on abnormal data to find similar historical data; If found, the abnormal data status is determined based on the similar historical data and included in the usage; If not found, determine whether the abnormal data sliding window duration meets the set conditions. If yes, it is determined to be correct measurement data; otherwise, determine the abnormality or change of operating condition of the real-time measurement equipment based on the spatiotemporal coupling relationship of electrical attributes. If the related measurement data is abnormal, the real-time measurement equipment is determined to be abnormal and the corresponding measurement value is discarded. If the related measurement data is normal, the real-time measurement equipment is determined to be in a change of operating condition and the corresponding measurement value is included in the usage.

7. The energy management collaborative control system for medium and low voltage distribution networks according to claim 5, characterized in that, In the data processing unit, the microgrid group collaborative control device is used to correct the measurement data estimated by artificial intelligence, specifically including: For measurement data estimated by artificial intelligence, predictions are made based on the characteristics of stored historical measurement data; The measurement data estimated by the artificial intelligence is corrected based on the predicted measurement values; Determine whether the corrected measurement data conforms to the corresponding measurement data characteristics. If so, proceed to the next step. The zero-drift data of the calibrated measurement data is discarded to obtain the final calibrated measurement data.

Images