CN114938333B - Power distribution station room end side node access method, device, chip, equipment and medium - Google Patents

Power distribution station room end side node access method, device, chip, equipment and medium Download PDF

Info

Publication number
CN114938333B
CN114938333B CN202210864844.5A CN202210864844A CN114938333B CN 114938333 B CN114938333 B CN 114938333B CN 202210864844 A CN202210864844 A CN 202210864844A CN 114938333 B CN114938333 B CN 114938333B
Authority
CN
China
Prior art keywords
side node
node
end side
nodes
new
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210864844.5A
Other languages
Chinese (zh)
Other versions
CN114938333A (en
Inventor
霍超
苑佳楠
白晖峰
尹志斌
张港红
郑利斌
甄岩
瞿玲
陈文彬
高建
杨双双
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Smartchip Microelectronics Technology Co Ltd
Original Assignee
Beijing Smartchip Microelectronics Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Smartchip Microelectronics Technology Co Ltd filed Critical Beijing Smartchip Microelectronics Technology Co Ltd
Priority to CN202210864844.5A priority Critical patent/CN114938333B/en
Publication of CN114938333A publication Critical patent/CN114938333A/en
Application granted granted Critical
Publication of CN114938333B publication Critical patent/CN114938333B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0806—Configuration setting for initial configuration or provisioning, e.g. plug-and-play
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/12—Discovery or management of network topologies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
    • Y04S40/128—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment involving the use of Internet protocol

Abstract

The disclosure relates to the technical field of wireless communication, in particular to a method, a device, a chip, equipment and a medium for accessing a node at the end side of a power distribution station room, wherein the method for accessing the node at the end side of the power distribution station room comprises the following steps: when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all end side nodes; generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node; realizing dynamic equilibrium networking according to the network topology and the performance parameters of each link forming the network topology; and acquiring the configuration information of the new end-side node based on the network completed by networking, and determining the service type of the new end-side node according to the configuration information of the new end-side node. The technical scheme of the embodiment of the disclosure solves the technical problem that automatic access and intelligent service type sensing cannot be realized at the room side of the power distribution station at present.

Description

Power distribution station room end side node access method, device, chip, equipment and medium
Technical Field
The present disclosure relates to the field of wireless communication technologies, and in particular, to a method, an apparatus, a chip, a device, and a medium for accessing a node at a power distribution station room end.
Background
The distribution station house is positioned at the tail end of a power supply network, bears the transmission and the configuration of electric energy and is a hub of the whole low-voltage distribution network system. With the increasing of the power supply load density in China, the number of power distribution station rooms applied to enterprises, communities and rural areas is larger and larger, the distribution is wider and wider, the number of the existing stock power distribution station rooms is huge, compared with the automation of high-voltage power distribution, the automation level of the existing power distribution network low-voltage power distribution station rooms is lower, a large number of power distribution station rooms are in an unattended supervision environment, and abnormal conditions cannot be discovered and processed in the first time. Therefore, important power equipment and power environment in the power distribution station room are monitored in real time, the collected parameters are analyzed in real time, operation and maintenance personnel can find faults in time and then remove the faults, and it is more and more important to ensure that various power equipment in the power distribution station room can safely and stably operate.
With the construction of a power distribution internet of things, in order to collect power distribution service information such as switches and intelligent electric meters, monitor the states of equipment such as transformers and buses, and perform dynamic loop monitoring such as temperature sensors and smoke intensity sensors, a power distribution station house is constructed by adopting a cloud-side-end structure, and a station house is provided with a platform area intelligent fusion terminal or a station house gateway and other side devices to realize information collection and service unified access. At present, after the devices such as sensors are connected into a power distribution station room system, the devices such as the sensors need to be confirmed and added at the end side nodes in a master station, meanwhile, a gateway of the power distribution station room cannot automatically identify the connected service types, and the master station also needs to perform classification analysis of the service types, protocols and the like, so that automatic connection of the sensors, the devices and the like in the power distribution station room and intelligent perception of the novel gateway of the power distribution station room on new energy connection, electric vehicles and other access services are not realized.
Disclosure of Invention
In order to solve the problems in the related art, embodiments of the present disclosure provide a method, an apparatus, a chip, a device, and a medium for accessing a node on a power distribution station room end side.
In a first aspect, an embodiment of the present disclosure provides a method for accessing a node at a power distribution station room end side, including:
when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all the end side nodes;
generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node;
realizing dynamic balanced networking according to the network topology and performance parameters of each link forming the network topology;
and acquiring the configuration information of the new end-side node based on the network completed by networking, and determining the service type of the new end-side node according to the configuration information of the new end-side node.
According to an embodiment of the present disclosure, the traversing searches for all end-side nodes of the distribution substation room, and establishes connections for all end-side nodes, including:
randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer;
searching a first end side node group adjacent to a gateway node by taking the gateway node as an initial node to obtain an end side node Si which is not connected with the gateway node in the first end side node group;
establishing connection between the mesh joint point and the end side node Si;
continuously searching the remaining end side nodes which are not searched by the gateway node in the first end side node group by taking the end side node Si as a starting node to obtain end side nodes Sj which are not connected with the gateway node and the end side node Si;
establishing a connection between the end side node Si and the end side node Sj;
repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group;
and searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as an initial node, and repeating the steps until all the end side node groups are traversed to complete the establishment of the connection of all the end side nodes.
According to an embodiment of the present disclosure, an end side node S of the first end side node group k The method comprises the following steps:
a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group.
According to the embodiment of the present disclosure, the implementing dynamic equilibrium networking according to the network topology and the performance parameters of each link constituting the network topology includes:
calculating the available bandwidth of the channel of each end-side node;
and the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to realize dynamic equilibrium networking.
According to an embodiment of the present disclosure, the calculating a channel available bandwidth of each end-side node includes:
according to formula B v =B（1-（T 0 /T)) calculates the available bandwidth of the channel of each end-side node, wherein B v The available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time that the channel is busy in a given time.
According to the embodiment of the present disclosure, the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to implement dynamic equalization networking, including:
for the end-side node with small channel available bandwidth, reducing the number of nodes of the link where the node is located;
for the end-side node with large channel available bandwidth, the number of nodes of the link where the node is located is increased.
According to an embodiment of the present disclosure, the configuration information of the new end-side node includes: device identification, device address and/or device key information of the end-side node.
According to an embodiment of the present disclosure, the determining a service type of the new end-side node according to the configuration information of the new end-side node includes:
identifying key features of the new end-side nodes based on an improved long-short term memory artificial neural network (LSTM) algorithm;
determining a traffic type of the new end-side node based on the key features and data items in a feature library.
According to an embodiment of the present disclosure, the identifying key features of the new end-side node based on the improved long-short term memory artificial neural network LSTM algorithm comprises:
identifying key features of the new end-side node based on an LSTM algorithm of a simplified gate structure equation in which a network gate structure signal outputs a signal h from a time t-1 t-1 A recursive weight matrix and a bias matrix.
According to an embodiment of the present disclosure, the simplified gate structure equation is:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 422482DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where m is the dimension of the input vector, fd t To forget the door, md t For memorizing doors, od t For input gates, T t-1 For the last moment of memory state, T t For the current memory state, h t-1 Hidden state at the previous moment, h t For the hidden state at the present moment, pl t Is input at the momentσ and g are activation functions, W fd 、WM md 、W md And W o As a weight matrix, b fd 、b md And b o In order to be a vector of the offset,
Figure 808464DEST_PATH_IMAGE002
for temporary memory state, \ 664is exclusive nor operation.
According to an embodiment of the present disclosure, the determining a traffic type of the new end-side node based on the key feature and a data item in a feature library includes:
comparing the key features with feature parameters of data items in the feature library one by one;
determining the data item with the most same characteristic parameters as the key characteristic as the service type of the new end-side node;
wherein the characteristic parameters include: a physical device identification, a logical node identification, a data object identification, and/or a data attribute identification of an end-side node.
In a second aspect, an embodiment of the present disclosure provides a power distribution station room-side node access apparatus, including:
the searching module is configured to search all end-side nodes of the power distribution station house in a traversing manner and establish connection to all the end-side nodes when a new end-side node is accessed;
the topology generation module is configured to generate a network topology according to the number of the end-side nodes and the connection relation of each end-side node;
the networking module is configured to realize dynamic balanced networking according to the network topology and performance parameters of each link forming the network topology;
and the service type determining module is configured to acquire the configuration information of the new end-side node based on the network completed by networking, and determine the service type of the new end-side node according to the configuration information of the new end-side node.
According to an embodiment of the present disclosure, the traversing searches for all end-side nodes of the distribution substation room, and establishes connections for all end-side nodes, including:
randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer;
searching a first end side node group adjacent to a gateway node by taking the gateway node as an initial node to obtain an end side node S which is not connected with the gateway node in the first end side node group i ；
Establishing the mesh node and the end side node S i The connection between them;
with said end side node S i As the initial node, the remaining end side nodes which are not searched by the gateway node in the first end side node group are continuously searched to obtain the end side nodes which are not searched by the gateway node and the end side node S i Connected end-side node S j ；
Establishing the end side node S i With said end side node S j The connection between them;
repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group;
with an end side node S of said first end side node group k And searching a second end side node group adjacent to the first end side node group in the same way for the starting node, and so on until all end side node groups are traversed to complete the establishment of the connection to all end side nodes.
According to an embodiment of the present disclosure, an end side node S of the first end side node group k The method comprises the following steps:
a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group.
According to the embodiment of the present disclosure, the implementing dynamic equilibrium networking according to the network topology and the performance parameters of each link constituting the network topology includes:
calculating the available bandwidth of the channel of each end-side node;
and the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to realize dynamic equilibrium networking.
According to an embodiment of the present disclosure, the calculating the channel available bandwidth of each end-side node includes:
according to the formula B v =B（1-（T 0 /T)) calculates the available bandwidth of the channel of each end-side node, wherein B v The available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time that the channel is busy in a given time.
According to the embodiment of the present disclosure, the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to implement dynamic balanced networking, including:
for the end-side node with small channel available bandwidth, reducing the number of nodes of the link where the node is located;
for the end-side node with large channel available bandwidth, the number of nodes of the link where the node is located is increased.
According to an embodiment of the present disclosure, the configuration information of the new end-side node includes: device identification, device address and/or device key information of the end-side node.
According to an embodiment of the present disclosure, the determining a service type of the new end-side node according to the configuration information of the new end-side node includes:
identifying key features of the new end-side nodes based on an improved long-short term memory artificial neural network (LSTM) algorithm;
determining a traffic type of the new end-side node based on the key features and data items in a feature library.
According to an embodiment of the present disclosure, the identifying key features of the new end-side node based on the improved long-short term memory artificial neural network LSTM algorithm comprises:
identifying key characteristics of the new end-side node based on an LSTM algorithm of a simplified gate structure equation, wherein in the simplified gate structure equation, a network gate structure signal outputs a signal h from a t-1 moment t-1 Recursive weight momentsAn array and a bias matrix.
According to an embodiment of the present disclosure, the simplified gate structure equation is:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 57042DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where m is the dimension of the input vector, fd t To forget the door, md t For memorizing doors, od t For the input gate, T t-1 For the last moment of memory state, T t For the current memory state, h t-1 Is a hidden state at the previous moment, h t For the hidden state at the present moment, pl t For this moment, input, σ and g are activation functions, W fd 、WM md 、W md And W o As a weight matrix, b fd 、b md And b o In order to be a vector of the offset,
Figure 921093DEST_PATH_IMAGE002
for temporary memory state, it is logical or operation.
According to an embodiment of the present disclosure, the determining a traffic type of the new end-side node based on the key feature and a data item in a feature library includes:
comparing the key features with feature parameters of data items in the feature library one by one;
determining the data item with the most same characteristic parameters as the key characteristic as the service type of the new end-side node;
wherein the characteristic parameters include: a physical device identification, a logical node identification, a data object identification, and/or a data attribute identification of an end-side node.
In a third aspect, the disclosed embodiments provide a chip including the power distribution station room-side node access device according to any one of the second aspects.
In a fourth aspect, the present disclosure provides an electronic device, comprising a memory and a processor, wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of the first aspect.
In a fifth aspect, the disclosed embodiments provide a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method as described in the first aspect.
According to the technical scheme provided by the embodiment of the disclosure, when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all end side nodes; generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node; realizing dynamic equilibrium networking according to the network topology and the performance parameters of each link forming the network topology; the configuration information of the new end-side node is obtained based on the network completed by networking, the service type of the new end-side node is determined according to the configuration information of the new end-side node, automatic access of the distribution station room gateway to end-side equipment is achieved, intelligent perception of the service type of the end-side equipment is achieved, and the management efficiency of the distribution station room is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings.
Fig. 1 shows a power distribution station house system configuration diagram.
Fig. 2 shows a flow chart of a method for power distribution station premises side node access in accordance with an embodiment of the disclosure.
Fig. 3 shows a block diagram of a power distribution station room-side node access apparatus according to an embodiment of the present disclosure.
Fig. 4 shows a block diagram of an electronic device according to an embodiment of the present disclosure.
FIG. 5 shows a schematic block diagram of a computer system suitable for use in implementing methods according to embodiments of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.
It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the present disclosure, if an operation of acquiring user information or user data or an operation of presenting user information or user data to others is involved, the operations are all operations authorized, confirmed by a user, or actively selected by the user.
In the above, after the devices such as the sensors are accessed into the distribution station room system, the master station needs to confirm and add the end-side nodes, and meanwhile, the distribution station room gateway cannot automatically identify the accessed service types, and also needs the master station to perform classification analysis of the service types, protocols and the like, so that automatic access of the sensors, the devices and the like in the distribution station room and intelligent perception of the novel station room gateway on new energy access, electric vehicles and other access services are not realized.
In view of this, the embodiment of the present disclosure provides a method for accessing a node at a power distribution station room end side, including: when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all end side nodes; generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node; realizing dynamic equilibrium networking according to the network topology and the performance parameters of each link forming the network topology; and acquiring the configuration information of the new end-side node based on the network completed by networking, and determining the service type of the new end-side node according to the configuration information of the new end-side node. According to the technical scheme provided by the embodiment of the disclosure, the automatic access of the gateway of the power distribution station room to the end-side equipment and the intelligent perception of the service type of the end-side equipment are realized, and the management efficiency of the power distribution station room is improved.
Fig. 1 shows a block diagram of a distribution station room system. As shown in fig. 1, the distribution station room system includes a master station system, a station room gateway, a transformer area, a dynamic loop monitor, and a video monitor. The master station system can be located at a remote server, receives and processes information of each device through the station house gateway, and issues commands and/or messages to each device through the station house gateway. District, rotating ring control and video monitoring are distolateral equipment in the distribution station room system, each distribution station room system can include a plurality of districts, and each district is including distribution power consumption business module and equipment state module, distribution power consumption business can be including distolateral nodes such as switch, electric energy quality, intelligent ammeter and new forms of energy, equipment state includes distolateral nodes such as cubical switchboard, condenser, transformer and generating line. The moving ring monitoring comprises end side nodes such as temperature and humidity, smoke sensing and air conditioners, and the video monitoring comprises end side nodes such as cameras and robots. And the station house gateway is in communication connection with the end-side node. The main station system forms a cloud in a cloud-edge-end structure of a power distribution station room, the station room gateway forms an edge in the cloud-edge-end structure, and the equipment in the station area, the dynamic ring monitoring and the video monitoring form an end in the cloud-edge-end structure.
Fig. 2 shows a flow diagram of a power distribution station room-side node access method according to an embodiment of the present disclosure. As shown in fig. 1, the access method for the power distribution station room-side node includes the following steps S201 to S204:
in step S201, when a new end-side node is accessed, traversing and searching all end-side nodes of the distribution station room, and establishing connections for all end-side nodes;
in step S202, a network topology is generated according to the number of end-side nodes and the connection relationship of each end-side node;
in step S203, implementing dynamic balanced networking according to the network topology and performance parameters of each link forming the network topology;
in step S204, the configuration information of the new end-side node is obtained based on the network that completes networking, and the service type of the new end-side node is determined according to the configuration information of the new end-side node.
In the embodiment of the disclosure, the method for accessing the end-side node of the power distribution station house can be applied to the station house gateway of the power distribution station house, the station house gateway can be used as a gateway node, automatically accesses the end-side node in each device, completes networking of the gateway node and each end-side node, then acquires configuration information of the new end-side node based on a network completed by networking, and automatically determines the service type of the new end-side node according to the configuration information of the new end-side node.
In an embodiment of the present disclosure, the traversing searches for all end-side nodes of the distribution substation room, and establishes connections for all end-side nodes, where the traversing searches for all end-side nodes include: randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer; searching a first end side node group adjacent to the gateway node by taking the gateway node as a starting node to obtain an end side node Si which is not connected with the gateway node in the first end side node group; establishing connection between the gateway node and the end side node Si; continuously searching the remaining end side nodes which are not searched by the gateway node in the first end side node group by taking the end side node Si as a starting node to obtain end side nodes Sj which are not connected with the gateway node and the end side node Si; establishing a connection between the end side node Si and the end side node Sj; repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group; and searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as an initial node, and repeating the steps until all the end side node groups are traversed to complete the establishment of the connection of all the end side nodes.
Specifically, each time a new end-side Node is accessed, the gateway Node automatically creates an array, which may be a Node array, for example, in which all end-side nodes accessing the gateway Node are recorded. In an embodiment of the present disclosure, the end-side node may be directly connected to the gateway node, or may be connected to the gateway node via another end-side node. After the array is established, the gateway node and each end-side node may be initialized, for example, the values of the gateway node and each end-side node are set to 0, and for any node in the array, the value is 0 when the node is not reached by the search, and the value of the node becomes 1 when the node is reached by the search and the connection between the node and other nodes is completed. The gateway node then randomly groups all end side nodes of the distribution substation room into m groups. Then, the gateway node is used as a starting node to search, the searched object is a first end side node group closest to the gateway node, the first end side node group closest to the gateway node can be determined by calculating the average position of the end side node and the gateway node in each group, or can be determined by other manners, and the determination is not limited here. When the search is started, the value of the gateway node may be set to 1, and when one end-side node in the first end-side node group is searched and it is determined that the end-side node and the gateway node have a connection relationship, the value of the end-side node in the array is set to 1. When an end side node Si not connected to the gateway node in the first end side node group is searched, a connection between the gateway node and the end side node Si is first established, and then the value of the end side node Si in the array is set to 1. Thereafter, the end can be terminatedAnd in the searching process, when determining that the searched end side node is connected with the gateway node or the end side node Si, setting the value of the searched end side node in the array to be 1, and when searching the end side node Sj which is not connected with the gateway node and the end side node Si in the first end side node group, firstly establishing the connection between the end side node Si and the end side node Sj, and then setting the value of the end side node Sj in the array to be 1. And repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group, so that the automatic discovery of the node connection relationship in the first end side node group is completed. And finally, searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as an initial node, and repeating the steps until all end side node groups are traversed to complete the establishment of the connection of all end side nodes. Wherein an end side node S of the first end side node group k The node may be a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group, or may be a node determined in another manner, which is not limited herein.
In the embodiment of the present disclosure, all end-side nodes of the distribution station room are searched in a traversal manner, connections are established for all the end-side nodes, and a network topology is generated according to the number of the end-side nodes and the connection relationship between the end-side nodes. Wherein the network topology may be a star topology, or a tree topology, or other types of topologies. Factors such as reliability, cost, flexible response time and throughput of topology formation can be comprehensively considered during selection, and the selection is not limited herein.
In the embodiment of the present disclosure, after the selected network topology is generated, the selected network topology and the component network can be further selected according to the network topology and the component networkThe performance parameters of each link of the network topology realize dynamic equilibrium networking so as to optimize the network formed by the gateway nodes and the nodes at each end side. In particular, dynamic balanced networking may be achieved by first calculating a channel available bandwidth for each end-side node, and then adjusting the network topology by a gateway node based on the channel available bandwidth for each end-side node. Wherein the channel available bandwidth of each end-side node can be represented by formula B v =B（1-（T 0 /T)) is calculated, B v The available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time the channel is busy in a given time. In a specific embodiment of the present disclosure, the gateway node may readjust the routing connection according to the channel available bandwidth of each end-side node, reduce the number of nodes of the link where the end-side node has a small channel available bandwidth, and increase the number of nodes of the link where the end-side node has a large channel available bandwidth, thereby implementing dynamic balanced networking.
In the embodiment of the present disclosure, after completing the dynamic balanced networking, the gateway node completes the automatic access to the newly added end-side node, and adjusts the network topology according to the newly added end-side node, thereby forming a new networking. Subsequently, the gateway node also needs to automatically identify the traffic type of the newly joined end-side node. Specifically, the gateway node may acquire configuration information of the new end-side node based on the network completed by networking, and determine the service type of the new end-side node according to the configuration information of the new end-side node, where the configuration information of the new end-side node includes: device identification, device address and/or device key information of the end-side node.
In the embodiment of the present disclosure, the determining of the traffic type of the new end-side node according to the configuration information of the new end-side node may be performed by a gateway node, first, identifying key features of the new end-side node based on an improved long-short term memory artificial neural network LSTM algorithm, and then, determining the traffic type of the new end-side node based on the key features and data items in a feature library. In particular, standard LSTThe M algorithm reserves important information by realizing forgetting, memorizing and outputting of the memory unit, ignores the information with lower importance degree, can realize key feature identification of the input service flow and output a key feature set. Setting m as dimension of input vector, n as number of hidden layer unit, and according to hidden state h of last moment t-1 And at this moment input pl t Get the forget gate fd t And memory gate md t And input door od t From h t-1 And pl t Obtaining a temporary memory state
Figure 469886DEST_PATH_IMAGE002
From fd t 、md t 、
Figure 26770DEST_PATH_IMAGE002
And remembering the state T at the last moment t-1 Obtaining the current memory state T t From od t And T t Obtaining the hidden state h at the current moment t The calculation formula of the standard LSTM algorithm can be expressed by the following formula:
fd t = σ（WM fd pl t + W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 762644DEST_PATH_IMAGE003
Figure 695965DEST_PATH_IMAGE001
od t =σ（WM o pl t + W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where σ and g are activation functions, WM fd 、W fd 、WM md 、M md 、WM T 、M T 、WM o 、M o As a weight matrix, b fd 、b md 、b T And b o Is a bias vector.
In the disclosed embodiment, the standard LSTM algorithm described above is modified. In particular, the input weight matrix WM is required to be input in each training process fd 、WM o The updating is carried out, so that the calculation amount is large, and the training time is long. This patent proposes to remove the input weight WM fd 、WM o The LSTM algorithm is improved by simplifying the parameters of the gate structure equation, so that the network gate structure signal of the improved LSTM algorithm outputs a signal h from the t-1 moment t-1 A recursive weight matrix and a bias matrix, so that the number of parameters to be updated by the network in each iteration process is made up of
4（mn+n 2 + n) to 4 (mn + n) 2 + n-2 mn), the computational complexity is reduced on the premise of not losing precision, and the training time of the network is shortened. The specific formula of the improved LSTM is as follows:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 99265DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）。
in the embodiment of the present disclosure, after the key features of the new end-side node are identified based on the improved LSTM algorithm, the service type of the new end-side node may be determined by comparing the key features with the feature parameters of the data items in the feature library one by one. The feature library is a pre-established sequence containing different feature parameters, the feature parameters may include physical device identifiers, logical node identifiers, data object identifiers and/or data attribute identifiers of end-side nodes, and for different end-side device types, the feature library may correspond to different feature parameters and may be dynamically adjusted according to actual conditions.
According to the technical scheme of the embodiment of the disclosure, the identification, connection and service type perception of the end side node are automatically completed at the gateway node, so that the automatic access of the power distribution station house gateway to the end side equipment and the intelligent perception of the service type of the end side equipment are realized, and the management efficiency of the power distribution station house is improved.
Fig. 3 shows a block diagram of a substation room side node access arrangement according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both.
As shown in fig. 3, the access apparatus 300 includes a search module 310, a topology generation module 320, a networking module 330, and a service type determination module 340. Wherein:
the searching module 310 is configured to search all end-side nodes of the distribution station house in a traversal manner and establish connections for all end-side nodes when a new end-side node is accessed;
the topology generating module 320 is configured to generate a network topology according to the number of end-side nodes and the connection relationship of each end-side node;
the networking module 330 is configured to implement dynamic balanced networking according to the network topology and performance parameters of each link constituting the network topology;
the service type determining module 340 is configured to acquire configuration information of the new end-side node based on the network completed by networking, and determine the service type of the new end-side node according to the configuration information of the new end-side node.
In this embodiment of the present disclosure, the traversing searches for all end-side nodes of the distribution substation room, and establishes connections for all end-side nodes, including: randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer; searching a first end side node group adjacent to the gateway node by taking the gateway node as an initial node to obtain an end side node Si which is not connected with the gateway node in the first end side node group; establishing connection between the mesh joint point and the end side node Si; continuously searching the remaining end side nodes which are not searched by the gateway node in the first end side node group by taking the end side node Si as a starting node to obtain end side nodes Sj which are not connected with the gateway node and the end side node Si; establishing a connection between the end side node Si and the end side node Sj; repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group; and searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as an initial node, and repeating the steps until all the end side node groups are traversed to complete the establishment of the connection of all the end side nodes.
Specifically, each time a new end-side Node is accessed, the gateway Node automatically creates an array, which may be a Node array, for example, in which all end-side nodes accessing the gateway Node are recorded. In an embodiment of the present disclosure, the end-side node may be directly connected to the gateway node, or may be connected to the gateway node via another end-side node. After the array is established, the gateway node and each end-side node may be initialized, for example, the values of the gateway node and each end-side node are set to 0, and for any node in the array, the value is 0 when the node is not reached by the search, and the value of the node becomes 1 when the node is reached by the search and the connection between the node and other nodes is completed. The gateway node then randomly groups all end side nodes of the distribution substation room into m groups. Then, the gateway node is used as a starting node to search, the searched object is a first end side node group closest to the gateway node, the first end side node group closest to the gateway node can be determined by calculating the average position of the end side node and the gateway node in each group, or can be determined by other manners, and the determination is not limited here. When the search starts, the value of the gateway node can be set to 1, and each search is performedAnd when one end side node in the first end side node group is reached and the connection relation between the end side node and the gateway node is determined, setting the value of the end side node in the array to be 1. When an end side node Si not connected to the gateway node in the first end side node group is searched, a connection between the gateway node and the end side node Si is first established, and then the value of the end side node Si in the array is set to 1. After that, the remaining end side nodes in the first end side node group that are not searched by the gateway node may be continuously searched by using the end side node Si as a start node, and also in the searching process, when it is determined that a connection has been established between the searched end side node and the gateway node or the end side node Si, the value of the searched end side node in the array is set to 1, and when an end side node Sj in the first end side node group that is not connected to the gateway node and the end side node Si is searched, the connection between the end side node Si and the end side node Sj is firstly established, and then the value of the end side node Sj in the array is set to 1. And repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group, so that the automatic discovery of the node connection relationship in the first end side node group is completed. And finally, searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as a starting node, and repeating the steps until all the end side node groups are traversed to complete the establishment of the connection of all the end side nodes. Wherein an end side node S of the first end side node group k The node may be a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group, or may be a node determined in another manner, which is not limited herein.
In the embodiment of the present disclosure, all end-side nodes of the distribution station room are searched in a traversal manner, connections are established for all the end-side nodes, and a network topology is generated according to the number of the end-side nodes and the connection relationship between the end-side nodes. The network topology may be a star topology, or a tree topology, or other types of topologies. Factors such as reliability, cost, flexible response time and throughput of topology formation can be comprehensively considered during selection, and the selection is not limited herein.
In the embodiment of the present disclosure, after the selected network topology is generated, dynamic balanced networking may be further implemented according to the network topology and performance parameters of each link forming the network topology, so as to optimize a network formed by the gateway node and each end-side node. In particular, dynamic balanced networking may be achieved by first calculating a channel available bandwidth for each end-side node, and then adjusting the network topology by a gateway node based on the channel available bandwidth for each end-side node. Wherein the available bandwidth of the channel of each end-side node can be represented by formula B v =B（1-（T 0 T)) was calculated, B v Is the available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time the channel is busy in a given time. In a specific embodiment of the present disclosure, the gateway node may readjust the routing connection according to the channel available bandwidth of each end-side node, reduce the number of nodes of the link where the end-side node has a small channel available bandwidth, and increase the number of nodes of the link where the end-side node has a large channel available bandwidth, thereby implementing dynamic balanced networking.
In the embodiment of the present disclosure, after completing the dynamic balanced networking, the gateway node completes the automatic access to the newly added end-side node, and adjusts the network topology according to the newly added end-side node, thereby forming a new networking. Subsequently, the gateway node also needs to automatically identify the traffic type of the newly joined end-side node. Specifically, the gateway node may acquire configuration information of the new end-side node based on the network completed by networking, and determine the service type of the new end-side node according to the configuration information of the new end-side node, where the configuration information of the new end-side node includes: device identification, device address and/or device key information of the end-side node.
In the embodiment of the present disclosure, the determining the traffic type of the new end-side node according to the configuration information of the new end-side node may be performed by a gateway node, first, identifying key features of the new end-side node based on an improved long-short term memory artificial neural network LSTM algorithm, and then, determining the traffic type of the new end-side node based on the key features and data items in a feature library. Specifically, the standard LSTM algorithm retains important information by implementing forgetting, memorizing, and outputting of the memory unit, ignores information with a low degree of importance, and can implement key feature identification of the input service flow and output a key feature set. Let m be the dimension of the input vector, n be the number of hidden layer units, according to the hidden state h at the previous moment t-1 And at this moment input pl t Get the forgetting gate fd t Memory gate md t And an input gate od t From h by t-1 And pl t Obtaining a temporary memory state
Figure 561470DEST_PATH_IMAGE002
From fd t 、md t 、
Figure 784641DEST_PATH_IMAGE002
And remembering the state T at the last moment t-1 Obtaining the current memory state T t By od t And T t Obtaining the hidden state h at the current moment t The calculation formula for the standard LSTM algorithm can be expressed as follows:
fd t = σ（WM fd pl t + W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 990494DEST_PATH_IMAGE003
Figure 717142DEST_PATH_IMAGE001
od t =σ（WM o pl t + W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where σ and g are activation functions, WM fd 、W fd 、WM md 、M md 、WM T 、M T 、WM o 、M o As a weight matrix, b fd 、b md 、b T And b o Is a bias vector.
In the disclosed embodiment, the standard LSTM algorithm described above is modified. Specifically, the input weight matrix needs to be updated in each training process, which results in large calculation amount and long training time. The LSTM algorithm is improved by removing input weight and simplifying parameters of a gate structure equation, so that a network gate structure signal of the improved LSTM algorithm outputs a signal h from t-1 moment t-1 The recursive weight matrix and the bias matrix, so that the number of parameters to be updated by the network in each iteration process is reduced, the computational complexity is reduced on the premise of not losing the precision, and the training time of the network is shortened. The specific formula of the improved LSTM is as follows:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 881407DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）。
in the embodiment of the present disclosure, after the key features of the new end-side node are identified based on the improved LSTM algorithm, the service type of the new end-side node may be determined by comparing the key features with the feature parameters of the data items in the feature library one by one. The feature library is a pre-established sequence containing different feature parameters, the feature parameters may include physical device identifiers, logical node identifiers, data object identifiers and/or data attribute identifiers of the end-side nodes, and for different end-side device types, the feature library may correspond to different feature parameters and may be dynamically adjusted according to actual conditions.
According to the technical scheme of the embodiment of the disclosure, the identification, connection and service type perception of the end side node are automatically completed at the gateway node, so that the automatic access of the distribution station room gateway to the end side equipment and the intelligent perception of the service type of the end side equipment are realized, and the management efficiency of the distribution station room is improved. The embodiment of the disclosure further provides a chip, where the chip includes the above power distribution station room end-side node access device, the chip may be any chip that can implement power distribution station room end-side node access, and the device may be implemented as part or all of the chip through software, hardware, or a combination of the two.
The embodiment of the present disclosure further provides a chip, where the chip includes the above power distribution station room end side node access device, and the device may be implemented as part or all of the chip through software, hardware, or a combination of the two.
The present disclosure also discloses an electronic device, and fig. 4 shows a block diagram of the electronic device according to an embodiment of the present disclosure.
As shown in fig. 4, the electronic device includes a memory and a processor, where the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement a power distribution station room-side node access method according to an embodiment of the disclosure.
The access method of the power distribution station room end side node comprises the following steps:
when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all the end side nodes;
generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node;
realizing dynamic equilibrium networking according to the network topology and the performance parameters of each link forming the network topology;
and acquiring the configuration information of the new end-side node based on the network completed by networking, and determining the service type of the new end-side node according to the configuration information of the new end-side node.
According to an embodiment of the present disclosure, the traversing searches for all end-side nodes of the distribution substation room, and establishes connections for all end-side nodes, including:
randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer;
searching a first end side node group adjacent to the gateway node by taking the gateway node as a starting node to obtain an end side node Si which is not connected with the gateway node in the first end side node group;
establishing connection between the gateway node and the end side node Si;
continuously searching the remaining end side nodes which are not searched by the gateway node in the first end side node group by taking the end side node Si as a starting node to obtain end side nodes Sj which are not connected with the gateway node and the end side node Si;
establishing a connection between the end side node Si and the end side node Sj;
repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group;
and searching a second end side node group adjacent to the first end side node group in the same way by taking the end side node Sk in the first end side node group as an initial node, and repeating the steps until all the end side node groups are traversed to complete the establishment of the connection of all the end side nodes.
According to an embodiment of the present disclosure, an end side node S of the first end side node group k The method comprises the following steps:
a last search starting end-side node in the first end-side node group, a last searched end-side node in the first end-side node group, or an end-side node in the first end-side node group that is closest to an end-side node in the second end-side node group.
According to the embodiment of the present disclosure, the implementing dynamic equilibrium networking according to the network topology and the performance parameters of each link constituting the network topology includes:
calculating the available bandwidth of the channel of each end-side node;
and the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to realize dynamic equilibrium networking.
According to an embodiment of the present disclosure, the calculating the channel available bandwidth of each end-side node includes:
according to formula B v =B（1-（T 0 /T)) calculates the available bandwidth of the channel of each end-side node, wherein B v The available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time that the channel is busy in a given time.
According to the embodiment of the present disclosure, the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to implement dynamic equalization networking, including:
for the end-side node with small channel available bandwidth, reducing the number of nodes of the link where the node is located;
for the end-side node with large channel available bandwidth, the number of nodes of the link where the node is located is increased.
According to an embodiment of the present disclosure, the configuration information of the new end-side node includes: device identification, device address and/or device key information of the end-side node.
According to an embodiment of the present disclosure, the determining a service type of the new end-side node according to the configuration information of the new end-side node includes:
identifying key features of the new end-side nodes based on an improved long-short term memory artificial neural network (LSTM) algorithm;
determining a traffic type of the new end-side node based on the key features and data items in a feature library.
According to an embodiment of the present disclosure, the identifying key features of the new end-side node based on the improved long-short term memory artificial neural network LSTM algorithm comprises:
identifying key features of the new end-side node based on an LSTM algorithm of a simplified gate structure equation in which a network gate structure signal outputs a signal h from a time t-1 t-1 A recursive weight matrix and a bias matrix.
According to an embodiment of the present disclosure, the simplified gate structure equation is:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 591874DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）。
according to an embodiment of the present disclosure, the determining a traffic type of the new end-side node based on the key feature and a data item in a feature library includes:
comparing the key features with feature parameters of data items in the feature library one by one;
determining the data item with the most same characteristic parameters as the key characteristic as the service type of the new end-side node;
wherein the characteristic parameters include: a physical device identification, a logical node identification, a data object identification, and/or a data attribute identification of an end-side node.
FIG. 5 shows a schematic block diagram of a computer system suitable for use in implementing a method according to an embodiment of the present disclosure.
As shown in fig. 5, the computer system includes a processing unit that can execute the various methods in the above-described embodiments according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage section into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the computer system are also stored. The processing unit, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
The following components are connected to the I/O interface: an input section including a keyboard, a mouse, and the like; an output section including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section including a hard disk and the like; and a communication section including a network interface card such as a LAN card, a modem, or the like. The communication section performs a communication process via a network such as the internet. The drive is also connected to the I/O interface as needed. A removable medium such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive as needed, so that the computer program read out therefrom is mounted into the storage section as needed. The processing unit can be realized as a CPU, a GPU, a TPU, an FPGA, an NPU and other processing units.
In particular, the above described methods may be implemented as computer software programs according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the above-described method. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or by programmable hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or the computer system in the above embodiments; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims (21)

1. A method for accessing a node at the room end side of a power distribution station is characterized by comprising the following steps:
when a new end side node is accessed, traversing and searching all end side nodes of the power distribution station house, and establishing connection for all end side nodes;
generating a network topology according to the number of the end-side nodes and the connection relation of each end-side node;
realizing dynamic equilibrium networking according to the network topology and the performance parameters of each link forming the network topology;
acquiring configuration information of the new end-side node based on the network completed by networking, and determining the service type of the new end-side node according to the configuration information of the new end-side node;
wherein, the determining the service type of the new end-side node according to the configuration information of the new end-side node includes:
identifying key characteristics of the new end-side nodes by using a long-short term memory artificial neural network (LSTM) algorithm based on a simplified gate structure equation;
determining a traffic type of the new end-side node based on the key features and data items in a feature library;
the simplified door structural equation is as follows:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 315136DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where m is the dimension of the input vector, fd t To forget the door, md t For memorizing the door, od t For input gates, T t-1 For the last moment of memory state, T t For the current memory state, h t-1 Is to be arranged atHidden state at a moment, h t For the hidden state at the present moment, pl t For this moment, input, σ and g are activation functions, W fd 、WM md 、W md And W o As a weight matrix, b fd 、b md And b o In order to be a vector of the offset,
Figure 435539DEST_PATH_IMAGE002
for temporary memory state, \ 664is exclusive nor operation.
2. The method of claim 1, wherein said traversing searches all end-side nodes of said distribution substation building to establish connections to said all end-side nodes, comprising:
randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer;
searching a first end side node group adjacent to a gateway node by taking the gateway node as an initial node to obtain an end side node S which is not connected with the gateway node in the first end side node group i ；
Establishing the mesh node and the end side node S i The connection between them;
with said end side node S i For the initial node, the remaining end side nodes which are not searched by the gateway node in the first end side node group are continuously searched to obtain the end side nodes which are not searched by the gateway node and the end side node S i Connected end-side node S j ；
Establishing the end side node S i With said end side node S j The connection between them;
repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group;
with an end node S in the first end node group k And searching a second end side node group adjacent to the first end side node group in the same way for the starting node, and so on until all end side node groups are traversed to complete the establishment of connection for all end side nodes.
3. The method according to claim 2, characterized in that an end side node S in the first end side node group k The method comprises the following steps:
a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group.
4. The method of claim 1, wherein implementing dynamically balanced networking based on the network topology and performance parameters of the links that make up the network topology comprises:
calculating the available bandwidth of the channel of each end-side node;
and the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to realize dynamic equilibrium networking.
5. The method of claim 4, wherein the calculating the channel available bandwidth of each end-side node comprises:
according to formula B v =B（1-（T 0 /T)) calculates the available bandwidth of the channel of each end-side node, wherein B v Is the available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time that the channel is busy in a given time.
6. The method of claim 4, wherein the gateway node adjusts the network topology according to the channel available bandwidth of each end-side node, and implements dynamic equalization networking, comprising:
for the end-side node with small channel available bandwidth, reducing the number of nodes of the link where the node is located;
for the end-side node with large channel available bandwidth, the number of nodes of the link where the node is located is increased.
7. The method of claim 1, wherein the configuration information of the new end-side node comprises: device identification, device address and/or device key information of the end-side node.
8. The method of claim 1, wherein the simplified gate structure equation based long short term memory artificial neural network (LSTM) algorithm identifies key features of the new end-side nodes, comprising:
in the simplified gate structure equation, a network gate structure signal outputs a signal h from a time t-1 t-1 A recursive weight matrix and a bias matrix.
9. The method of claim 1, wherein the determining the traffic type of the new end-side node based on the key feature and a data item in a feature library comprises:
comparing the key features with feature parameters of data items in the feature library one by one;
determining the data item with the most same characteristic parameters as the key characteristic as the service type of the new end-side node;
wherein the characteristic parameters include: a physical device identification, a logical node identification, a data object identification, and/or a data attribute identification of an end-side node.
10. A power distribution station room end side node access device is characterized by comprising:
the searching module is configured to search all end-side nodes of the power distribution station house in a traversing manner and establish connection for all the end-side nodes when a new end-side node is accessed;
the topology generation module is configured to generate a network topology according to the number of the end-side nodes and the connection relation of each end-side node;
the networking module is configured to realize dynamic balanced networking according to the network topology and performance parameters of each link forming the network topology;
the service type determining module is configured to acquire configuration information of the new end-side node based on a network which is completed by networking, and determine the service type of the new end-side node according to the configuration information of the new end-side node;
wherein, the determining the service type of the new end-side node according to the configuration information of the new end-side node includes:
identifying key features of the new end-side nodes based on a long-short term memory artificial neural network (LSTM) algorithm of a simplified gate structure equation;
determining a traffic type of the new end-side node based on the key features and data items in a feature library;
the simplified gate structural equation is:
fd t = σ（W fd h t-1 +b fd ）
md t =σ（WM md pl t +W md h t-1 +b md ）
Figure 120336DEST_PATH_IMAGE001
od t =σ（W o h t-1 +b o ）
h t = od t ʘg（T t ）；
where m is the dimension of the input vector, fd t To forget the door, md t For memorizing doors, od t For input gates, T t-1 For the last moment of memory state, T t For the current memory state, h t-1 Hidden state at the previous moment, h t For the hidden state at the present moment, pl t For this moment, input, σ and g are activation functions, W fd 、WM md 、W md And W o As a weight matrix, b fd 、b md And b o In order to be a vector of the offset,
Figure 46704DEST_PATH_IMAGE002
for temporary memorizationMemory state, 664NOR operation.
11. The apparatus of claim 10, wherein said traversing searches all end-side nodes of said distribution substation building to establish connections to said all end-side nodes, comprising:
randomly dividing all end side nodes of the power distribution station room into m groups, wherein m is a positive integer;
searching a first end side node group adjacent to a gateway node by taking the gateway node as an initial node to obtain an end side node S which is not connected with the gateway node in the first end side node group i ；
Establishing the mesh node and the end side node S i The connection between them;
with said end side node S i For the initial node, the remaining end side nodes which are not searched by the gateway node in the first end side node group are continuously searched to obtain the end side nodes which are not searched by the gateway node and the end side node S i Connected end-side node S j ；
Establishing the end side node S i With said end side node S j The connection between them;
repeatedly executing the searching and connection establishing operation until no end side node which is not connected with the gateway node and other end side nodes exists in the first end side node group;
with an end side node S of said first end side node group k And searching a second end side node group adjacent to the first end side node group in the same way for the starting node, and so on until all end side node groups are traversed to complete the establishment of connection for all end side nodes.
12. The apparatus of claim 11, wherein an end side node S in the first end side node group k The method comprises the following steps:
a last search start end side node in the first end side node group, a last searched end side node in the first end side node group, or an end side node in the first end side node group that is closest to an end side node in the second end side node group.
13. The apparatus of claim 10, wherein the implementing dynamically balanced networking according to the network topology and performance parameters of each link constituting the network topology comprises:
calculating the available bandwidth of the channel of each end-side node;
and the gateway node adjusts the network topology according to the available bandwidth of the channel of each end-side node, so as to realize dynamic equilibrium networking.
14. The apparatus of claim 13, wherein the calculating of the channel available bandwidth for each end-side node comprises:
according to formula B v =B（1-（T 0 /T)) calculates the available bandwidth of the channel of each end-side node, wherein B v Is the available bandwidth of the channel of each end-side node, B is the total bandwidth of the channel, T is the given time, T 0 The total time the channel is busy in a given time.
15. The apparatus of claim 13, wherein the gateway node adjusts the network topology according to the channel available bandwidth of each end-side node, and implements dynamic equalization networking, comprising:
for the end-side node with small available bandwidth of the channel, the number of nodes of the link where the node is located is reduced;
for the end-side node with large available bandwidth of the channel, the number of nodes of the link where the node is located is increased.
16. The apparatus of claim 10, wherein the configuration information of the new end-side node comprises: device identification, device address and/or device key information of the end-side node.
17. The apparatus of claim 10, wherein the simplified gate structure equation based long short term memory artificial neural network (LSTM) algorithm identifies key features of the new end-side nodes, comprising:
in the simplified gate structure equation, a network gate structure signal outputs a signal h from a time t-1 t-1 A recursive weight matrix and a bias matrix.
18. The apparatus of claim 10, wherein the determining the traffic type of the new end-side node based on the key feature and a data item in a feature library comprises:
comparing the key features with feature parameters of data items in the feature library one by one;
determining the data item with the most same characteristic parameters as the key characteristic as the service type of the new end-side node;
wherein the characteristic parameters include: a physical device identification, a logical node identification, a data object identification, and/or a data attribute identification of an end-side node.
19. A chip, characterized in that,
the chip comprises a substation room side node access device according to any of claims 10-18.
20. An electronic device comprising a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any of claims 1-9.
21. A computer-readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-9.
CN202210864844.5A 2022-07-22 2022-07-22 Power distribution station room end side node access method, device, chip, equipment and medium Active CN114938333B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210864844.5A CN114938333B (en) 2022-07-22 2022-07-22 Power distribution station room end side node access method, device, chip, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210864844.5A CN114938333B (en) 2022-07-22 2022-07-22 Power distribution station room end side node access method, device, chip, equipment and medium

Publications (2)

Publication Number Publication Date
CN114938333A CN114938333A (en) 2022-08-23
CN114938333B true CN114938333B (en) 2022-10-04

Family

ID=82867759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210864844.5A Active CN114938333B (en) 2022-07-22 2022-07-22 Power distribution station room end side node access method, device, chip, equipment and medium

Country Status (1)

Country Link
CN (1) CN114938333B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104050536A (en) * 2014-06-20 2014-09-17 国家电网公司 Topology analysis method for power distribution network crossing voltage grades
CN106877497A (en) * 2017-02-22 2017-06-20 国网辽宁省电力有限公司 A kind of electric power terminal communication access net and optimization method
CN112994246A (en) * 2021-04-02 2021-06-18 河池学院 Power distribution network feeder automation control method suitable for distributed power supply access

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9312728B2 (en) * 2009-08-24 2016-04-12 Access Business Group International Llc Physical and virtual identification in a wireless power network
WO2018017544A1 (en) * 2016-07-18 2018-01-25 Commscope Technologies Llc Systems and methods for high capacity power delivery to remote nodes

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104050536A (en) * 2014-06-20 2014-09-17 国家电网公司 Topology analysis method for power distribution network crossing voltage grades
CN106877497A (en) * 2017-02-22 2017-06-20 国网辽宁省电力有限公司 A kind of electric power terminal communication access net and optimization method
CN112994246A (en) * 2021-04-02 2021-06-18 河池学院 Power distribution network feeder automation control method suitable for distributed power supply access

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"基于深度学习和知识库的配电站监控***";闫勇志;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》;20211231;全文 *

Also Published As

Publication number Publication date
CN114938333A (en) 2022-08-23

Similar Documents

Publication Publication Date Title
CN109214599B (en) Method for predicting link of complex network
WO2021203980A1 (en) Meteorological event prediction method and apparatus, and related device
CN104767682A (en) Routing method and system as well as routing information distributing method and device
CN109697455B (en) Fault diagnosis method and device for distribution network switch equipment
CN108696453B (en) Lightweight SDN service flow notification method and system
CN113341712B (en) Intelligent hierarchical control selection method for unmanned aerial vehicle autonomous control system
CN113037783B (en) Abnormal behavior detection method and system
Li Retracted: Design and implementation of music teaching assistant platform based on Internet of Things
CN111739285A (en) Traffic flow prediction method, device, equipment and computer storage medium
CN114265913A (en) Space-time prediction algorithm based on federal learning on industrial Internet of things edge equipment
CN112149967A (en) Power communication network vulnerability assessment method and system based on complex system theory
CN112367678A (en) Micro base station monitoring method and device and storage medium
CN114938333B (en) Power distribution station room end side node access method, device, chip, equipment and medium
CN111865690B (en) Opportunistic network link prediction method based on network structure and time sequence
Mertens et al. Federated learning through model gossiping in wireless sensor networks
CN113541986B (en) Fault prediction method and device for 5G slice and computing equipment
CN105897463B (en) Multinode power line channel based on low pressure topological network responds generation method
Parihar et al. Flying ad hoc network (fanet): Opportunities, trending applications and simulators
CN110705062A (en) Cabinet energy consumption remote statistical metering method based on 5G
US20230104448A1 (en) Attenuation weight tracking in graph neural networks
Li Network intrusion risk assessment based on big data
CN115426635A (en) Unmanned aerial vehicle communication network inference method and system under unreliable transmission scene
Ibraheem et al. Internal network monitoring with dnn and network tomography for in-vehicle networks
Sun Research on Intelligent Predictive Analysis System Based on Embedded Wireless Communication Network
CN116744305B (en) Communication system based on safety control of 5G data communication process

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant