Power distribution network data topology restoration method and device, electronic equipment and storage medium

Abstract

The application provides a power distribution network data topology restoration method and device, electronic equipment and storage medium, and relates to the technical field of power systems. The method comprises the following steps: a first participating device acquires a plurality of data flow information between each service involved in a first business domain of a power distribution network in a preset time period; address information of each service is extracted from the plurality of data flow information, and based on the address information of each service, a plurality of nodes and initial node attributes of each node are determined; a plurality of communication links are determined based on the plurality of data flow information, a plurality of edges between the plurality of nodes are determined based on the plurality of communication links, and initial edge attributes of each edge are determined based on the plurality of data flow information under each communication link, so as to obtain an initial data topology graph of the first business domain; global node attributes and global edge attributes sent by a central coordination device are received, and the initial data topology graph is updated based on the global node attributes and the global edge attributes, so as to obtain a global data topology graph of the first business domain.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, and particularly relates to a power distribution network data topology restoration method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the development of smart grid technology and new power system services, the topology structure of the power distribution network is increasingly complex, and the corresponding network topology description and expression play an increasingly important role in power distribution network service management, data analysis, security risk monitoring and identification. However, the network topology in the related art has the problem of low accuracy, which cannot reflect the actual operation of the power distribution network. SUMMARY

[0003] The embodiments of the present application provide a power distribution network data topology restoration method and device, an electronic device and a storage medium to solve the problem of low accuracy of the power distribution network topology.

[0004] In a first aspect, the embodiments of the present application provide a power distribution network data topology restoration method applied to a first participating device, which comprises: acquiring a plurality of data flow information between each service involved in a first service domain of a power distribution network in a preset time period; the first service domain is a service domain to which the first participating device belongs; extracting address information of each service from the plurality of data flow information, and determining a plurality of nodes and an initial node attribute of each node based on the address information of each service; wherein each service is a node, and the initial node attribute includes address information of the service; determining a plurality of communication links based on the plurality of data flow information, determining a plurality of edges between the plurality of nodes based on the plurality of communication links, and determining an initial edge attribute of each edge based on a plurality of data flow information under each communication link to obtain an initial data topology graph of the first service domain; sending the initial node attribute and the initial edge attribute to a central coordination device; wherein the central coordination device is configured to perform cross-domain aggregation processing on the initial node attribute and the initial edge attribute of each service domain based on a federated learning framework to obtain a global node attribute of each node and a global edge attribute of each edge; receiving the global node attribute and the global edge attribute sent by the central coordination device, and updating the initial data topology graph based on the global node attribute and the global edge attribute to obtain a global data topology graph of the first service domain.

[0005] In some embodiments, the determining the plurality of communication links based on the plurality of data flow information comprises: determining a plurality of first communication links according to source address information and destination address information in the plurality of data flow information; determining a stability index value of each of the first communication links based on data flow information under each of the first communication links; and determining the plurality of communication links from the plurality of first communication links based on the stability index values.

[0006] In some embodiments, the stability index value comprises a flow quantity standard deviation and an average flow of the first communication link; and the determining the plurality of communication links from the plurality of first communication links based on the stability index values comprises: determining a plurality of first communication links with a flow quantity standard deviation less than or equal to a first threshold value and an average flow greater than or equal to a second threshold value as the plurality of communication links.

[0007] In some embodiments, the determining the initial edge attribute of each edge based on the plurality of data flow information under each of the communication links comprises: for each of the communication links, determining a flow attribute of each of the plurality of data flows under the communication link based on the plurality of data flow information under the communication link; the flow attribute comprises a timestamp, a flow size and / or a flow intensity of the data flow; merging the attributes of the data flows with overlapping timestamps under the communication link to obtain the flow attribute of each of the plurality of independent data flows under the communication link; and determining the flow attribute of each of the plurality of independent data flows under the communication link as the initial edge attribute of the edge corresponding to the communication link.

[0008] In a second aspect, an embodiment of the present application provides a power distribution network data topology restoration method applied to a central coordination device, the method comprising: receiving initial node attributes of each node and initial edge attributes of each edge in an initial data topology graph of each business domain of a power distribution network sent by a plurality of first participating devices; wherein the initial data topology graph is constructed by the first participating device based on data flow information between each service involved in the business domain to which the first participating device belongs; performing cross-domain aggregation processing on the initial node attributes and the initial edge attributes in each of the business domains respectively based on a federated learning framework to obtain global node attributes of each node and global edge attributes of each edge in each of the business domains; and sending the global node attributes of each node and the global edge attributes of each edge in each of the business domains to the first participating device of the corresponding business domain, so that each of the first participating devices updates the initial data topology graph based on the global node attributes and the global edge attributes to obtain a global data topology graph of the corresponding business domain.

[0009] In a third aspect, an embodiment of the present application provides a power distribution network data topology restoration device deployed in a first participating device, the device comprising: a first obtaining module configured to obtain a plurality of data flow information between each service involved in a first service domain of a power distribution network in a preset time period; the first service domain is a service domain to which the first participating device belongs; a first determining module configured to extract address information of the each service from the plurality of data flow information, and determine a plurality of nodes and an initial node attribute of each of the nodes based on the address information of the each service; wherein each of the services is a node, and the initial node attribute comprises address information of the service; a second determining module configured to determine a plurality of communication links based on the plurality of data flow information, determine a plurality of edges between the plurality of nodes based on the plurality of communication links, and determine an initial edge attribute of each of the edges based on the plurality of data flow information under each of the communication links, to obtain an initial data topology graph of the first service domain; a first sending module configured to send the initial node attribute and the initial edge attribute to a central coordination device; wherein the central coordination device is configured to perform cross-domain aggregation processing on the initial node attribute and the initial edge attribute of each service domain based on a federated learning framework, to obtain a global node attribute of each of the nodes and a global edge attribute of each of the edges; and a first receiving module configured to receive the global node attribute and the global edge attribute sent by the central coordination device, and update the initial data topology graph based on the global node attribute and the global edge attribute, to obtain a global data topology graph of the first service domain.

[0010] In a fourth aspect, an embodiment of the present application provides a power distribution network data topology restoration device deployed in a central coordination device, the device comprising: a second receiving module configured to receive initial node attributes of each node and initial edge attributes of each edge in an initial data topology graph of each service domain of a power distribution network sent by a plurality of first participating devices; wherein the initial data topology graph is constructed by a first participating device based on data flow information between each service involved in a service domain to which the first participating device belongs; an aggregation module configured to perform cross-domain aggregation processing on the initial node attribute and the initial edge attribute of each service domain based on a federated learning framework, to obtain a global node attribute of each node and a global edge attribute of each edge in each service domain; and a second sending module configured to send the global node attribute of each node and the global edge attribute of each edge in each service domain to a first participating device of a corresponding service domain, so that each first participating device updates the initial data topology graph based on the global node attribute and the global edge attribute, to obtain a global data topology graph of the corresponding service domain.

[0011] In a fifth aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory storing a computer program, wherein the processor implements the power distribution network data topology restoration method described above when executing the program.

[0012] In a sixth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium having stored thereon a computer program, the computer program being executed by a processor to implement the power distribution network data topology restoration method described above.

[0013] In a seventh aspect, an embodiment of the present application provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the power distribution network data topology restoration method described above.

[0014] The power distribution network data topology restoration method, device, electronic equipment and storage medium provided by the embodiments of the present application are as follows: a first participating device acquires a plurality of data flow information between each service involved in a first business domain of a power distribution network in a preset time period; address information of each service is extracted from the plurality of data flow information, and based on the address information of each service, a plurality of nodes and an initial node attribute of each node are determined; a plurality of communication links are determined based on the plurality of data flow information, a plurality of edges between the plurality of nodes are determined based on the plurality of communication links, and an initial edge attribute of each edge is determined based on the plurality of data flow information under each communication link, to obtain an initial data topology graph of the first business domain; a global node attribute and a global edge attribute sent by a central coordination device are received, and the initial data topology graph is updated based on the global node attribute and the global edge attribute to obtain a global data topology graph of the first business domain. The data topology restoration is performed by the data flow information between the systems in the domain, the actual business operation of each system can be reflected based on the business flow information, and high-precision intra-domain topology restoration is achieved. In addition, the topology data of different business domains is aggregated across domains through a federated learning framework, which can improve the security and privacy of the data and achieve comprehensive and accurate restoration of the power distribution network data. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0016] Figure 1 One of the flowcharts of the power distribution network data topology restoration method provided by the embodiments of the present application;

[0017] Figure 2 The second flowchart of the power distribution network data topology restoration method provided by the embodiments of the present application;

[0018] Figure 3 One of the structural diagrams of the power distribution network data topology restoration device provided by the embodiments of the present application;

[0019] Figure 4 Figure 2 is a structural schematic diagram of a power distribution network data topology restoration device provided by an embodiment of the present application.

[0020] Figure 5 Figure 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be described below in conjunction with the accompanying drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0022] It should be noted that, with the development of smart grid technology and new power system services, the topology structure of the power distribution network is increasingly complex, and the corresponding network topology description and expression play an increasingly important role in power distribution network service management, data analysis, security risk monitoring and identification, etc. However, relying on network topology cannot meet the actual needs of the above applications, and it is also necessary to establish accurate data topology to fully and detailedly show the connection relationship between nodes, network traffic, service flow direction, etc. to assist the efficient development of new intelligent power distribution network management and security applications.

[0023] With the expansion of the scale of the power distribution network and the dramatic increase in the amount of data, traditional centralized data processing methods cannot efficiently cope with the real-time processing needs of large-scale data. Secondly, data privacy and security issues are increasingly prominent, and centralized data processing mode is easy to cause privacy leakage.

[0024] To solve the above problems, the present application provides a power distribution network data topology restoration method, device, electronic equipment and storage medium.

[0025] Figure 1 Figure 1 is a flowchart of a power distribution network data topology restoration method provided by an embodiment of the present application. It should be noted that the power distribution network data topology restoration method of the present application is applied to a first participating device. As shown in Figure 1, the method can include the following steps. Figure 1

[0026] Step 101: Obtain a plurality of data flow information between each service involved in a first service domain of the power distribution network in a preset time period; the first service domain is the service domain to which the first participating device belongs.

[0027] The preset time period can be a continuous time period containing the current time and the time before the current time, and the length of the preset time period can be determined based on actual needs, such as 1 hour.​

[0028] In some embodiments, the correspondence between the first service domain and the first participating device for topology restoration of the power grid data of the first service domain can be determined in advance. That is, the power grid can include multiple service domains, and the data topology restoration corresponding to each service domain is performed by different devices.

[0029] The service domain refers to different services supported in the power grid, such as electric vehicle service, distributed photovoltaic service, virtual battery service, etc. Each service is counted as a service domain, and each service involves different application services. The services involved in the first service domain refer to multiple application services involved in the operation of the first service. The multiple data flow information refers to the data flow information of the service interaction between the services in the first service domain.

[0030] In some embodiments, each data flow information includes the relevant information of a data flow, such as the source service address information, the target service address information, the start time, the end time, the byte size of each data packet, the protocol type, the service identifier, etc. of each data flow information. The source service address information and the target service address information can include IP address information and port number, and can also include MAC address information.

[0031] In some embodiments, the multiple data flow information can be obtained through API interface, network scanning tool, etc. The obtained data can be preprocessed to obtain the multiple data flow information. The preprocessing can include: timestamp standardization processing, which uniformly converts the timestamps in the data flow information into international standard time format to eliminate the problem of inconsistent time formats between different systems; data cleaning, which eliminates irrelevant information and noise data, and data that does not conform to the format specification; and abnormal value detection, which applies statistical analysis methods such as Z-score to identify and process abnormal values in the data.

[0032] Step 102, address information of each service is extracted from the multiple data flow information, and based on the address information of each service, multiple nodes and initial node attributes of each node are determined; each service is a node, and the initial node attribute includes the address information of the service.

[0033] In some embodiments, the address information of each service can include IP address information, port number, MAC address information, etc. Since the service address information contained in the data flow information between different services can be different, some data flow information between services includes IP address information and port number, and some data flow information between services also includes MAC address information. Therefore, when extracting the address information of each service from multiple data flow information, the IP address information, port number, and MAC address information in each data flow information can be extracted to obtain the extracted address information of each service.

[0034] Since each pair of IP address information and port number can locate a service, based on the address information of each service, when determining multiple nodes, each pair of different IP address information and port number can be taken as a node based on the extracted address information. The communication nodes with the same IP address information but different port numbers are regarded as different nodes.

[0035] In some embodiments, the address information of the service corresponding to each node can be directly determined as the initial node attribute of each node. The data flow information can also include service identification, name, and other information. The service identification and name of each node can also be taken as the initial node attribute.

[0036] In step 103, multiple communication links are determined based on the multiple data flow information, multiple edges between multiple nodes are determined based on the multiple communication links, and initial edge attributes of each edge are determined based on the multiple data flow information under each communication link to obtain an initial data topology graph of the first service domain.

[0037] Among them, the communication link is used to represent the channel of data interaction between services. Each communication link can be represented based on the source service address information and the destination service address information in the data flow information. Different source service address information and destination service address information pairs are taken as different communication links.

[0038] In some embodiments, in order to ensure the effectiveness of the communication link, the implementation process of determining the multiple communication links based on the multiple data flow information can include: determining multiple first communication links according to the source service address information and the destination service address information in the multiple data flow information; determining a stability index value of each first communication link based on the data flow information under each first communication link; and determining the multiple communication links from the multiple first communication links based on the stability index value.

[0039] As an example, based on the source service address information and the destination service address information in each data flow information, a { (source service IP address information, port number), (destination service IP address information, port number)} communication pair can be determined, and thus a plurality of different { (source service IP address information, port number), (destination service IP address information, port number)} communication pairs can be obtained, each communication pair representing a first communication link, and the same communication pair representing the same first communication link. The data flow information under each first communication link refers to the data flow information whose source service address information and destination service address information are consistent with the communication pair corresponding to the first communication link.

[0040] The stability index value of the first communication link is used to represent the stability of the first communication link, which can be the average flow of the first communication link in a preset time period, or the flow quantity standard deviation of the first communication link in the preset time period.

[0041] In some embodiments, the stability index value of the first communication link includes the flow quantity standard deviation and the average flow of the first communication link; and determining the plurality of communication links from the plurality of first communication links based on the stability index value includes: determining the plurality of first communication links with the flow quantity standard deviation less than or equal to a first threshold value and the average flow greater than or equal to a second threshold value as the plurality of communication links.

[0042] The implementation process of determining the average flow of each first communication link based on the data flow information under each first communication link can include: for each first communication link, determining the flow size of each data flow under the first communication link based on the data flow information under the first communication link, and determining the total flow size under the first communication link; dividing the total flow size by the length of the preset time period to obtain the average flow of the first communication link, as shown in the following formula (1).

[0043] (1);

[0044] wherein, is the average flow of the i th first communication link; is the length of the preset time period; is the number of data flows under the i th first communication link; is the flow size of the j th data flow under the i th first communication link. The flow size of each data flow can be the sum of the sizes of all data packets contained in the data flow.

[0045] The implementation process of determining the flow quantity standard deviation of each first communication link based on the data flow information under each first communication link can include: for each first communication link, determining the quantity of data flows at each observation time point under the first communication link and determining the flow quantity average of the first communication link based on the data flow information under the first communication link; and determining the flow quantity standard deviation of the first communication link according to the quantity of data flows at each observation time point and the flow quantity average, as shown in the following formula (2).

[0046] (2);

[0047] wherein, is the flow quantity standard deviation of the i-th first communication link; is the quantity of data flows of the i-th first communication link at the j-th observation time point; and N is the number of observation time points in a preset time period. is the quantity of data flows of the i-th first communication link at the q-th observation time point.

[0048] In some embodiments, the implementation process of determining a plurality of edges between a plurality of nodes based on a plurality of communication links includes: for each communication link, determining a first node corresponding to the source service address information of the communication link, determining a second node corresponding to the destination service address information of the communication link, and establishing an edge from the first node to the second node. That is, each communication link represents an edge.

[0049] It should be noted that the initial data topology graph of the first service domain includes the plurality of nodes and the plurality of edges between the nodes determined in the above steps, and the initial node attribute of each node and the initial edge attribute of each edge.

[0050] In some embodiments, the extraction of address information of each service from a plurality of data flow information in step 102 and the determination of a plurality of nodes based on the address information of each service, and the determination of a plurality of communication links based on a plurality of data flow information in step 103, can be implemented by a preset topology semantic model. The topology semantic model is used to traverse and extract data from a plurality of data flow information, obtain address information of each service, determine a plurality of nodes based on the address information, and output a node set. The topology semantic model is also used to determine a plurality of communication pairs based on the extracted source service address information and port number and destination service address information and port number, and determine a plurality of communication links based on the stability index value of each communication pair.

[0051] In some embodiments, the implementation process of determining the initial edge attribute of each edge based on a plurality of data flow information under each communication link can include the following steps.

[0052] In step S1, for each communication link, based on the information of multiple data streams under the communication link, the flow attribute of each data stream under the communication link is determined; the flow attribute includes the timestamp, the traffic size and / or the flow intensity of the data stream.

[0053] The timestamp of the data stream can be the start time and the end time of the data stream. The traffic size of the data stream can be the sum of the byte number of each data packet in the data stream. The flow intensity of the data stream can be the ratio of the traffic size of the data stream to the time delay of the data stream.

[0054] In some embodiments, the flow attribute of each data stream can further include the protocol type, the number of flows, etc.

[0055] In step S2, the attributes of the data streams with time overlap under the communication link are merged to obtain the flow attribute of the multiple independent data streams under the communication link.

[0056] In some embodiments, the timestamp of each data stream under the communication link can be compared with the timestamp of other data streams under the communication link in sequence to determine the multiple data streams with time overlap under the communication link. For example, taking data stream Di and data stream Dj as an example, if , the data stream Di and the data stream Dj have time overlap; is the start time of the data stream Di, is the end time of the data stream Dj, is the start time of the data stream Dj, is the end time of the data stream Di.

[0057] The process of merging the attributes of the data stream Di and the data stream Dj includes: merging the data stream Di and the data stream Dj into one data stream; integrating the timestamp of the data stream Di and the data stream Dj to obtain the timestamp of the merged data stream ; adding the traffic size of the data stream Di and the data stream Dj to obtain the traffic size of the merged data stream; determining the flow intensity of the merged data stream as the ratio of the traffic size of the merged data stream to the time length corresponding to the timestamp of the merged data stream; integrating the protocol types of the data stream Di and the data stream Dj, if the protocol types of the two data streams are the same, the protocol type of the merged data stream remains unchanged, if the protocol types of the two data streams are different, the protocol types of the two data streams are both listed in the protocol type of the merged data stream, that is, the protocol type of the data stream Di is A and the protocol type of the data stream Dj is B, then the protocol type of the merged data stream is A and B.

[0058] The independent data stream includes the data stream obtained after merging and the data stream in the plurality of data stream information under the communication link which does not overlap in time with other data streams, that is, the independent data stream obtained after merging refers to the data stream which does not overlap in time. If the data stream D1 overlaps in time with the data stream D2, the data stream D1 overlaps in time with the data stream D3, and the data stream D3 overlaps in time with the data stream D4, the data streams D1, D2, D3 and D4 can be merged to obtain a merged data stream and the stream attribute of the merged data stream.

[0059] In step S3, the stream attribute of the plurality of independent data streams under the communication link is determined as the initial edge attribute of the edge corresponding to the communication link.

[0060] In some embodiments, the edge attribute of each edge can be initialized, and the initialized edge attribute of each edge is an empty list. For each edge corresponding to a communication link, the timestamp of each data stream under the communication link is compared with the timestamp of other data streams under the communication link. If the data stream does not overlap in time with other data streams, the stream attribute of the data stream is written into the corresponding edge attribute list. If the data stream overlaps in time with other data streams, the stream attribute of the data stream and the data stream which overlaps in time with the data stream are merged, and the stream attribute of the merged data stream is written into the corresponding edge attribute list. Finally, the obtained edge attribute list is the initial edge attribute of the corresponding edge.

[0061] In some embodiments, the initial edge attribute can include the stream attribute of the plurality of independent data streams, and each independent data stream can be distinguished by a data stream identifier.

[0062] In step 104, the initial node attribute and the initial edge attribute are sent to the central coordination device. The central coordination device is configured to aggregate the initial node attribute and the initial edge attribute of each business domain based on the federated learning framework to obtain the global node attribute of each node and the global edge attribute of each edge.

[0063] In order to improve the privacy security of the original data between different participating devices, the embodiments of the present application introduce the federated learning framework. The central coordination device performs cross-domain topology splicing based on the initial node attribute and the initial edge attribute of each business domain, and sends the global node attribute of each node and the global edge attribute of each edge obtained to the first participating device. The first participating device updates the initial data topology based on the global node attribute and the global edge attribute to obtain the global data topology of the first business domain, so as to improve the accuracy and comprehensiveness of data topology restoration.

[0064] In some embodiments, the central coordination device can compare the IP address information and port numbers of nodes between different service domains based on the initial node attributes of different nodes in each service domain, determine a plurality of shared node groups, each of which includes a plurality of shared nodes, a shared node being a node existing in a plurality of service domains, i.e., a node with consistent IP address information and port numbers between different service domains, such as node 1 in service domain A and node 2 in service domain B, both of which have consistent IP address information and port numbers; for each shared node group, take the union of the initial node attributes of the plurality of shared nodes in the shared node group, and take the union result as the global node attribute of each shared node in the shared node group; for other nodes that are not shared nodes, since these nodes do not exist across domains, there is no need to aggregate the node attributes of these nodes across domains, and the initial node attributes of these nodes are directly taken as the global node attributes.

[0065] In some embodiments, the central coordination device can compare the communication links corresponding to each edge between different service domains based on the initial edge attributes of different edges in each service domain, determine a plurality of shared edge groups, each of which includes a plurality of shared edges, a shared edge being an edge existing in a plurality of service domains, i.e., an edge with consistent source service address information and destination service address information between different service domains, such as edge 1 from node 1 to node 2 in service domain A and edge 2 from node 3 to node 4 in service domain B, both of which have consistent IP address information and port numbers; for each shared edge group, take the union of the initial edge attributes of the plurality of shared edges in the shared edge group, and perform time-overlapping attribute merging on the union result to obtain the merged edge attributes as the global edge attributes of each shared edge in the shared edge group; for other edges that are not shared edges, since these edges do not exist across domains, there is no need to aggregate the edge attributes of these edges across domains, and the initial edge attributes of these edges are directly taken as the global edge attributes.

[0066] Step 105, receiving the global node attributes and global edge attributes sent by the central coordination device, and updating the initial data topology graph based on the global node attributes and global edge attributes to obtain a global data topology graph of the first service domain.

[0067] That is, the first participating device replaces the initial node attribute of each node in the initial data topology graph of the first service domain with a global node attribute, and replaces the initial edge attribute of each edge with a global edge attribute, to obtain an updated global data topology graph of the first service domain. The global data topology graph of the first service domain not only can reflect the node connection and service flow situation under the service domain, but also can reflect the service interaction relationship between cross-regions, so that the global data topology graph of the first service domain can better reflect the actual service running situation of each system, and improve the accuracy and comprehensiveness of topology restoration.

[0068] According to the power distribution network data topology restoration method provided in the embodiments of the present application, the first participating device obtains a plurality of data flow information between each service involved in the first service domain of the power distribution network in a preset time period; address information of each service is extracted from the plurality of data flow information, and based on the address information of each service, a plurality of nodes and an initial node attribute of each node are determined; a plurality of communication links are determined based on the plurality of data flow information, a plurality of edges between the plurality of nodes are determined based on the plurality of communication links, and an initial edge attribute of each edge is determined based on the plurality of data flow information under each communication link, to obtain an initial data topology graph of the first service domain; global node attributes and global edge attributes sent by the central coordination device are received, and the initial data topology graph is updated based on the global node attributes and the global edge attributes, to obtain a global data topology graph of the first service domain. According to the present application, the data topology restoration is performed based on the data flow information between the systems in the domain, the actual service running situation of each system can be reflected based on the service flow information, and high-precision intra-domain topology restoration is achieved. In addition, the topology data of different service domains is aggregated across domains based on the federated learning framework, the security and privacy of the data can be improved, and the power distribution network data is restored comprehensively and accurately.

[0069] In order to achieve the above-mentioned embodiments, the embodiments of the present application also provide a power distribution network data topology restoration method applied to a central coordination device.

[0070] Figure 2 A flowchart of the power distribution network data topology restoration method provided in the embodiments of the present application is shown in FIG. 2. It should be noted that the power distribution network data topology restoration method provided in the embodiments of the present application is applied to a central coordination device. As shown in FIG. 2, the method can include the following steps. Figure 2

[0071] In step 201, the initial node attribute of each node in the initial data topology graph of each service domain of the power distribution network sent by a plurality of first participating devices, and the initial edge attribute of each edge are received; wherein the initial data topology graph is constructed by the first participating device based on the data flow information between each service involved in the service domain to which the first participating device belongs.

[0072] ​That is, the power distribution network data topology restoration architecture of the embodiment of the present application comprises a plurality of first participating devices and a central coordinating device, each first participating device is configured to restore the data topology in its own business domain, and the central coordinating device is configured to aggregate the node attributes and edge attributes across domains.

[0073] In some embodiments, after each first participating device restores the initial data topology of its own region, it sends the initial node attributes of each node and the initial edge attributes of each edge in the initial data topology to the central coordinating device, and the central coordinating device receives the initial node attributes and the initial edge attributes of each business domain sent by each first participating device.

[0074] In step 202, based on the federated learning framework, the initial node attributes and the initial edge attributes in each business domain are aggregated across domains to obtain the global node attributes of each node and the global edge attributes of each edge in each business domain.

[0075] It can be understood that there may be overlapping services in different business domains, which constitute connections between different business domains. The nodes corresponding to these overlapping services usually have common characteristics, and the data flow between the overlapping services also has overlaps. The edges corresponding to these overlapping data flows also usually have common characteristics. Therefore, in order to make the node attributes and edge attributes more complete while ensuring data isolation between different participating devices, the central coordinating device can aggregate the node attributes and edge attributes across domains based on the federated learning framework to obtain the global node attributes of each node and the global edge attributes of each edge in each business domain.

[0076] The global node attributes refer to the complete node attributes obtained by the central coordinating device by aggregating the initial node attributes across domains, and the global edge attributes refer to the complete edge attributes obtained by the central coordinating device by aggregating the initial edge attributes across domains.

[0077] In some embodiments, the central coordination device can compare IP address information and port numbers of nodes between different service domains based on initial node attributes of different nodes in each service domain, determine a plurality of shared node groups, each shared node group including a plurality of shared nodes, a shared node being a node existing in a plurality of service domains, i.e., a node with consistent IP address information and port numbers between different service domains, such as node 1 in service domain A and node 2 in service domain B, both of which have consistent IP address information and port numbers, so node 1 in service domain A and node 2 in service domain B are shared nodes; for each shared node group, take the union of initial node attributes of the plurality of shared nodes in the shared node group, and take the union result as the global node attribute of each shared node in the shared node group; for other nodes that are not shared nodes, since these nodes do not exist across domains, there is no need to aggregate node attributes of these nodes across domains, and the initial node attributes of these nodes are directly taken as global node attributes, finally obtaining global node attributes of each node in each service domain.

[0078] In some embodiments, the central coordination device can compare communication links corresponding to each edge between different service domains based on initial edge attributes of different edges in each service domain, determine a plurality of shared edge groups, each shared edge group including a plurality of shared edges, a shared edge being an edge existing in a plurality of service domains, i.e., an edge with consistent source service address information and destination service address information between different service domains, such as edge 1 from node 1 to node 2 in service domain A and edge 2 from node 3 to node 4 in service domain B, if the IP address information and port numbers of node 1 and node 3 are consistent, and the IP address information and port numbers of node 2 and node 4 are also consistent, then edge 1 in service domain A and edge 2 in service domain B are shared edges; for each shared edge group, take the union of initial edge attributes of the plurality of shared edges in the shared edge group, and perform time overlap attribute merging on the union result to obtain merged edge attributes as the global edge attribute of each shared edge in the shared edge group; for other edges that are not shared edges, since these edges do not exist across domains, there is no need to aggregate edge attributes of these edges across domains, and the initial edge attributes of these edges are directly taken as global edge attributes, finally obtaining global edge attributes of each edge in each service domain.

[0079] Step 203, sending the global node attributes of each node and the global edge attributes of each edge in each service domain to the first participating device of the corresponding service domain, so that each first participating device updates the initial data topology graph based on the global node attributes and the global edge attributes, and obtains the global data topology graph of the corresponding service domain.

[0080] As an example, the global node attributes of each node and the global edge attributes of each edge in the service domain A are sent to the first participating device corresponding to the service domain A, and the first participating device corresponding to the service domain A updates the initial data topology graph of the service domain A based on the received global node attributes and global edge attributes, to obtain the global data topology graph of the service domain A.

[0081] According to the power distribution network data topology restoration method provided in the embodiments of the present application, the central coordination device receives the initial node attributes of each node and the initial edge attributes of each edge in the initial data topology graph of each service domain of the power distribution network sent by the plurality of first participating devices; based on a federated learning framework, the initial node attributes and the initial edge attributes in each service domain are respectively subjected to cross-domain aggregation processing, to obtain the global node attributes of each node and the global edge attributes of each edge in each service domain; the global node attributes of each node and the global edge attributes of each edge in each service domain are sent to the first participating device corresponding to the service domain, so that each first participating device updates the initial data topology graph based on the global node attributes and the global edge attributes, to obtain the global data topology graph of the corresponding service domain. According to the present application, the data topology restoration is performed based on the data flow information between the systems in the domain, the actual service operation of each system can be reflected based on the service flow information, and high-precision intra-domain topology restoration is achieved. In addition, the topology data of different service domains is subjected to cross-domain aggregation based on the federated learning framework, the security and privacy of the data can be improved, and the power distribution network data is comprehensively and accurately restored.

[0082] The power distribution network data topology restoration device provided in the embodiments of the present application is described below, and the power distribution network data topology restoration device described below can be correspondingly referred to the power distribution network data topology restoration method described above.

[0083] Figure 3 Fig. 1 shows a structure diagram of the power distribution network data topology restoration device provided in the embodiments of the present application. It should be noted that the power distribution network data topology restoration device in the embodiments of the present application is deployed in the first participating device. As shown in the figure, the device comprises a first acquisition module 310, a first determination module 320, a second determination module 330, a first sending module 340 and a first receiving module 350. Figure 3

[0084] The first acquisition module 310 is configured to acquire a plurality of data flow information between each service involved in the first service domain of the power distribution network in a preset time period; the first service domain is the service domain to which the first participating device belongs;

[0085] The first determination module 320 is configured to extract the address information of each service from the plurality of data flow information, and determine a plurality of nodes and the initial node attributes of each node based on the address information of each service; wherein each service is a node, and the initial node attributes comprise the address information of the service.The second determination module 330 is configured to determine a plurality of edges and the initial edge attributes of each edge based on the plurality of data flow information; wherein each edge is between two nodes, and the initial edge attributes comprise the address information of the two nodes.

[0086] A second determining module 330 is configured to determine a plurality of communication links based on the plurality of data flow information, determine a plurality of edges between the plurality of nodes based on the plurality of communication links, and determine an initial edge attribute of each edge based on the plurality of data flow information under each communication link, thereby obtaining an initial data topology graph of the first service domain;

[0087] A first sending module 340 is configured to send the initial node attributes and initial edge attributes to a central coordination device. The central coordination device is configured to perform cross-domain aggregation processing on the initial node attributes and initial edge attributes of each business domain based on a federated learning framework to obtain global node attributes for each node and global edge attributes for each edge.

[0088] The first receiving module 350 is configured to receive global node attributes and global edge attributes sent by the central coordination device, and update the initial data topology graph based on the global node attributes and global edge attributes to obtain a global data topology graph of the first service domain.

[0089] In some embodiments, the second determination module 330 is specifically used to: determine multiple first communication links based on the source service address information and destination service address information in multiple data flow information; determine the stability index value of each first communication link based on the data flow information under each first communication link; and determine multiple communication links from the multiple first communication links based on the stability index value.

[0090] In some embodiments, the stability index value includes the standard deviation of the number of flows and the average flow of the first communication link; the second determination module 330 is also used to: determine multiple first communication links whose standard deviation of the number of flows is less than or equal to the first threshold and whose average flow is greater than or equal to the second threshold as multiple communication links.

[0091] In some embodiments, the second determination module 330 is also used to: for each communication link, based on multiple data flow information under the communication link, determine the flow attributes of each of the multiple data flows under the communication link; the flow attributes include the timestamp, traffic size and / or flow intensity of the data flow; merge the attributes of the data flows that overlap in time under the communication link to obtain the flow attributes of multiple independent data flows under the communication link; determine the flow attributes of the multiple independent data flows under the communication link as the initial edge attributes of the corresponding edge of the communication link.

[0092] Figure 4 This is the second structural diagram of the distribution network data topology restoration device provided by the embodiment of the present invention. It should be noted that the distribution network data topology original device of the embodiment of the present invention is deployed in the central coordination device. Figure 4 As shown, the device includes: a second receiving module 410, an aggregation module 420 and a second sending module 430.

[0093] The second receiving module 410 is configured to receive initial node attributes of each node in an initial data topology graph of each service domain of the power distribution network and initial edge attributes of each edge sent by the plurality of first participating devices, wherein the initial data topology graph is constructed by the first participating devices based on data flow information among services involved in the service domain to which the first participating device belongs.

[0094] The aggregation module 420 is configured to perform cross-domain aggregation processing on the initial node attributes and the initial edge attributes of each service domain respectively based on a federated learning framework, to obtain global node attributes of each node and global edge attributes of each edge in each service domain.

[0095] The second sending module 430 is configured to send the global node attributes of each node and the global edge attributes of each edge in each service domain to the first participating device of the corresponding service domain, so that each first participating device updates the initial data topology graph based on the global node attributes and the global edge attributes to obtain a global data topology graph of the corresponding service domain.

[0096] Figure 5 An example of an entity structure diagram of an electronic device is shown in FIG. 1. Figure 5As shown, the electronic device can include a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 complete mutual communication through the communication bus 540. The processor 510 can invoke the computer program in the memory 530 to execute the steps of the power distribution network data topology restoration method provided by each of the above embodiments, including: obtaining a plurality of data flow information between each service involved in a first business domain of a power distribution network in a preset time period; the first business domain is the business domain to which the first participating device belongs; extracting address information of each service from the plurality of data flow information, and determining a plurality of nodes and an initial node attribute of each node based on the address information of each service; wherein each service is a node, and the initial node attribute includes address information of the service; determining a plurality of communication links based on the plurality of data flow information, determining a plurality of edges between the plurality of nodes based on the plurality of communication links, and determining an initial edge attribute of each edge based on a plurality of data flow information under each communication link, to obtain an initial data topology graph of the first business domain; sending the initial node attribute and the initial edge attribute to a central coordination device; wherein the central coordination device is configured to perform cross-domain aggregation processing on the initial node attribute and the initial edge attribute of each business domain based on a federated learning framework, to obtain a global node attribute of each node and a global edge attribute of each edge; receiving the global node attribute and the global edge attribute sent by the central coordination device, and updating the initial data topology graph based on the global node attribute and the global edge attribute, to obtain a global data topology graph of the first business domain. And / or,

[0097] The steps of the power distribution network data topology restoration method provided by each of the above embodiments include: receiving initial node attributes of each node and initial edge attributes of each edge in an initial data topology graph of each business domain of a power distribution network sent by a plurality of first participating devices; wherein the initial data topology graph is constructed by a first participating device based on data flow information between each service involved in the business domain to which the first participating device belongs; based on a federated learning framework, respectively performing cross-domain aggregation processing on the initial node attribute and the initial edge attribute in each business domain to obtain a global node attribute of each node and a global edge attribute of each edge in each business domain; sending the global node attribute of each node and the global edge attribute of each edge in each business domain to the first participating device of the corresponding business domain, so that each first participating device updates the initial data topology graph based on the global node attribute and the global edge attribute to obtain a global data topology graph of the corresponding business domain.

[0098] In addition, the logic instructions in the memory 530 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0099] In another aspect, the embodiments of the present application also provide a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the steps of the power distribution network data topology restoration method provided by the above-mentioned embodiments.

[0100] In another aspect, the embodiments of the present application also provide a processor readable storage medium, which stores a computer program, and the computer program is used to make the processor execute the steps of the power distribution network data topology restoration method provided by the above-mentioned embodiments.

[0101] The processor readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to a magnetic storage (such as a floppy disk, a hard disk, a magnetic tape, a magneto-optical disk (MO), etc.), an optical storage (such as a CD, a DVD, a BD, a HVD, etc.), and a semiconductor memory (such as a ROM, an EPROM, an EEPROM, a NAND FLASH, a solid state disk (SSD)), etc.

[0102] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0103] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0104] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for restoring a power distribution grid data topology, characterized in that, The method applied to a first participating device comprises: obtaining a plurality of data flow information between each service involved in a first service domain of a power distribution network in a preset time period; the first service domain is a service domain to which the first participating device belongs; extracting address information of each service from the plurality of data flow information, and determining a plurality of nodes and initial node attributes of each node based on the address information of each service; each service is a node, and the initial node attributes include address information of the service; determining a plurality of communication links based on the plurality of data flow information, determining a plurality of edges between the plurality of nodes based on the plurality of communication links, and determining initial edge attributes of each edge based on the plurality of data flow information under each communication link to obtain an initial data topology graph of the first service domain; sending the initial node attributes and the initial edge attributes to a central coordination device; the central coordination device is configured to perform cross-domain aggregation processing on the initial node attributes and the initial edge attributes of each service domain based on a federated learning framework to obtain global node attributes of each node and global edge attributes of each edge; receiving the global node attributes and the global edge attributes sent by the central coordination device, and updating the initial data topology graph based on the global node attributes and the global edge attributes to obtain a global data topology graph of the first service domain.

2. The method of claim 1, wherein, The method comprises: determining a plurality of first communication links according to source service address information and destination service address information in the plurality of data flow information; determining a stability index value of each first communication link based on data flow information under each first communication link; determining the plurality of communication links from the plurality of first communication links based on the stability index value.

3. The method of claim 2, wherein, The stability index value includes a flow quantity standard deviation and an average flow of the first communication link; the plurality of communication links are determined from the plurality of first communication links based on the stability index value, which comprises: determining a plurality of first communication links with a flow quantity standard deviation less than or equal to a first threshold value and an average flow greater than or equal to a second threshold value as the plurality of communication links.

4. The method according to any one of claims 1 to 3, characterized in that, The method comprises: for each communication link, determining flow attributes of a plurality of data flows under the communication link based on the plurality of data flow information under the communication link; the flow attributes include a timestamp, a flow size and / or a flow intensity of the data flow; performing attribute merging on data flows with overlapping time under the communication link to obtain flow attributes of a plurality of independent data flows under the communication link; determining the flow attributes of the plurality of independent data flows under the communication link as initial edge attributes of an edge corresponding to the communication link.

5. A method for restoring a data topology of a power distribution network, characterized in that, The method applied to a central coordination device comprises: receiving initial node attributes of each node and initial edge attributes of each edge in an initial data topology graph of each service domain of a power distribution network sent by a plurality of first participating devices; Based on the federated learning framework, the initial node attribute and the initial edge attribute in each business domain are respectively processed by cross-domain aggregation to obtain the global node attribute of each node and the global edge attribute of each edge in each business domain; The global node attribute and the global edge attribute of each node in each business domain are sent to the first participating device of the corresponding business domain, so that each first participating device updates the initial data topology graph based on the global node attribute and the global edge attribute to obtain the global data topology graph of the corresponding business domain; Wherein, the initial data topology graph is constructed by the first participating device in the following way: Obtain a plurality of data flow information between each service involved in the first business domain of the power distribution network in a preset time period; the first business domain is the business domain to which the first participating device belongs; From the plurality of data flow information, the address information of each service is extracted, and based on the address information of each service, a plurality of nodes and the initial node attribute of each node are determined; wherein each service is a node, and the initial node attribute includes the address information of the service; Based on the plurality of data flow information, a plurality of communication links are determined, a plurality of edges between the plurality of nodes are determined based on the plurality of communication links, and the initial edge attribute of each edge is determined based on the plurality of data flow information under each communication link, to obtain the initial data topology graph of the first business domain.

6. A power distribution network data topology restoration apparatus, characterized by, Deployed in the first participating device, the device comprises: The first acquisition module is used to acquire a plurality of data flow information between each service involved in the first business domain of the power distribution network in a preset time period; the first business domain is the business domain to which the first participating device belongs; The first determination module is used to extract the address information of each service from the plurality of data flow information, and determine a plurality of nodes and the initial node attribute of each node based on the address information of each service; wherein each service is a node, and the initial node attribute includes the address information of the service; The second determination module is used to determine a plurality of communication links based on the plurality of data flow information, determine a plurality of edges between the plurality of nodes based on the plurality of communication links, and determine the initial edge attribute of each edge based on the plurality of data flow information under each communication link, to obtain the initial data topology graph of the first business domain; The first sending module is used to send the initial node attribute and the initial edge attribute to the central coordination device; wherein the central coordination device is used to process the initial node attribute and the initial edge attribute of each business domain by cross-domain aggregation based on the federated learning framework, to obtain the global node attribute of each node and the global edge attribute of each edge; The first receiving module is used to receive the global node attribute and the global edge attribute sent by the central coordination device, and update the initial data topology graph based on the global node attribute and the global edge attribute to obtain the global data topology graph of the first business domain.

7. A power distribution network data topology restoration apparatus, characterized by, Deployed in the central coordination device, the device comprises: The second receiving module is configured to receive initial node attributes of each node in an initial data topology graph of each service domain of the power distribution network and initial edge attributes of each edge sent by the plurality of first participating devices. The aggregation module is configured to perform cross-domain aggregation processing on the initial node attributes and the initial edge attributes of the service domains based on a federated learning framework, to obtain global node attributes of each node and global edge attributes of each edge in each service domain. The second sending module is configured to send the global node attributes of each node and the global edge attributes of each edge in each service domain to the first participating device of the corresponding service domain, so that each first participating device updates the initial data topology graph based on the global node attributes and the global edge attributes, to obtain a global data topology graph of the corresponding service domain. The initial data topology graph is constructed by the first participating device in the following manner: obtain a plurality of data flow information between each service involved in a first service domain of the power distribution network in a preset time period; the first service domain is a service domain to which the first participating device belongs; extract address information of the services from the plurality of data flow information, and determine a plurality of nodes and initial node attributes of each node based on the address information of the services; each service is a node, and the initial node attributes include address information of the services; determine a plurality of communication links based on the plurality of data flow information, determine a plurality of edges between the plurality of nodes based on the plurality of communication links, and determine initial edge attributes of each edge based on the plurality of data flow information under each communication link, to obtain an initial data topology graph of the first service domain.

8. An electronic device comprising a processor and a memory having a computer program stored therein, characterized in that, The processor executes the computer program to implement the power distribution network data topology restoration method in any one of claims 1 to 5. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the power distribution network data topology restoration method in any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the power distribution network data topology restoration method in any one of claims 1 to 5.

Images