CN109949178B - Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine - Google Patents
Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine Download PDFInfo
- Publication number
- CN109949178B CN109949178B CN201910131792.9A CN201910131792A CN109949178B CN 109949178 B CN109949178 B CN 109949178B CN 201910131792 A CN201910131792 A CN 201910131792A CN 109949178 B CN109949178 B CN 109949178B
- Authority
- CN
- China
- Prior art keywords
- power
- node
- vector machine
- current
- transformer
- 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
Links
Images
Classifications
-
- 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
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a method for judging and complementing a power failure event of a medium-voltage distribution network based on a support vector machine, and belongs to the technical field of operation of power distribution networks. The method comprises 4 links, namely construction of a distribution network model, construction of a vector machine, solution analysis of the vector machine, judgment and combination of fault types. The method for judging the power failure event of the medium-voltage distribution network based on the support vector machine determines the final power failure node and type of the power failure event, complements the power failure event of the medium-voltage distribution network, which is missed, misinformation and lie in the statistics of the power failure event of the medium-voltage distribution network, and improves the statistical accuracy of the power supply reliability of the distribution network.
Description
Technical Field
The invention belongs to the technical field of operation of power distribution networks, and particularly relates to a method for judging and complementing a power failure event of a medium-voltage distribution network based on a support vector machine.
Background
The current power distribution network has large scale, wide coverage, severe equipment operation environment, uneven quality of the acquisition device, missing report of partial terminals on power failure event, and less than 70% of the integrity rate of power failure user data pushed to the power quality system. Some electric power companies can even lie due to examination pressure. However, through the tracking analysis of the leakage report of the medium-voltage power failure event, the functional problem of the device is found to be most prominent, and the device accounts for about 80 percent, for example, the terminal protocol is not updated in time, and the defects or faults such as battery antenna aging, SIM card damage and the like are caused by operation in a severe environment, so that uploading power failure event can not be acquired. Although the device cannot upload the power-off and power-on events, most event points and adjacent event points can acquire load operation data signals such as voltage, current and the like, can help to discriminate the actual power failure occurrence condition of a user, and can be used as a breakthrough point for event completion.
Aiming at the problems, the technical proposal in the prior art is that based on the systems such as an electricity consumption information acquisition system, a marketing system, a 95598 system, a PMS system, a distribution network operation and maintenance management platform and the like, the comprehensive integration of service system data is carried out, an intelligent complement module (short complement module) for medium-voltage power failure event is developed, and the medium-voltage power failure event is analyzed and complemented and then is uploaded to an on-line monitoring system for the electric energy quality of the national network. The module mainly aims at integrating data of each service system and analyzing and completing power failure events in the initial stage of construction, but the power failure event completion rule is only based on simple logic rules and engineering experience, such as certain power failure in the upstream and downstream of a line, the power failure of 70% of users of a certain line is considered as full-line power failure, and the like, and the experience completion method has high dependence on the topology archive information of the power grid, and the accuracy and intelligence of completion still need to be further improved.
Aiming at the problem, the invention researches a power failure event completion method of a medium voltage distribution network based on a support vector machine.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a method for judging and complementing a power failure event of a medium-voltage distribution network based on a support vector machine, which is used for determining a final power failure node, avoiding missing report, false report and lie report of power failure event statistics of a medium-voltage and low-voltage distribution network and improving the statistical accuracy of power supply reliability.
In order to solve the technical problems, the invention provides a method for judging a power failure event of a press-fit network based on a support vector machine, which is characterized by comprising the following steps:
s1, acquiring a power grid model structure of a medium-voltage distribution network, and dividing the distribution network node type according to equipment at a distribution network node;
s2, establishing a vector machine corresponding to the node type at each distribution network node, wherein the input of each vector machine is the measuring point power flow data at each node, and the output of each vector machine is whether a power failure event occurs at each node;
s3, judging whether a power failure event occurs at each node by using a trained vector machine at each distribution network node according to the measuring point power flow data at each node;
and S4, merging the judging results of whether the power is cut off or not of all the distribution network nodes step by step upwards according to the power grid model structure, and determining the final power cut node.
Further, the distribution network node types include: the transformer node, the outlet cabinet node, the ring main unit node, the special transformer node and the public transformer node.
Further, the five distribution network node types are specifically described as follows:
1) The transformer node, the root node of the secondary side outgoing line of the 110/10kV transformer, is defined as a transformer node and is marked as node type A;
2) The outlet cabinet node is defined as the outlet cabinet node at the root node of each outlet in the outlet cabinet of the power distribution room and is marked as node type B;
3) The ring main unit nodes are defined as ring main unit nodes and are marked as node type C;
4) The special transformer node, the 10/380V special transformer, is defined as a special transformer node and is marked as a node type D;
5) The public transformer of 10/380V is defined as public transformer node, which is marked as node type E.
Further, each node type establishes a corresponding vector machine, and the selection of measuring points of various vector machines and the types of tide data collected by the measuring points are respectively as follows:
1) Vector machine A: the measuring points are as follows: under the transformer, each outgoing line cabinet randomly selects a branch outgoing line, and the head end of each outgoing line selects a special or public variable measuring point;
initially input tidal current data: day 96 point measurement data of each measurement point ： Maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
2) Vector machine B: measuring points: selecting a special or public variable measuring point for each of the outlet head, the outlet tail and the outlet, and selecting a special or public variable measuring point for each of 2 outlets adjacent to the outlet;
initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
3) Vector machine C: measuring points: selecting a special or public variable measuring point before and after the judging point;
initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
4) Vector machine D: measuring points: the method comprises the steps that all private transformer node boxes of private transformer users are measuring points, and in addition, 1 private or public variable measuring point is selected to be adjacent to the private transformer node;
initially input tidal current data: the current day 96-point measurement data of the private transformer node of the private transformer user of the box transformer point are as follows: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; selecting average voltage, current and power by a special transformer user adjacent to the measuring point;
5) Vector machine E: the measuring points are as follows: a single public variable measuring point is adjacent to a special variable or public variable measuring point selected 1;
initially input tidal current data: 96-point measurement data of the box transformer point on the same day; maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; average voltage, current and power are selected from the adjacent measuring points.
Further, before the initial input data is input into the vector machine, data normalization processing and data dimension reduction processing are respectively carried out on the initial input data.
Further, the power outage types corresponding to the distribution network nodes are respectively as follows: the transformer node corresponds to the power outage type A, the outlet cabinet node corresponds to the power outage type B, the ring main unit node corresponds to the power outage type C, the special-change node corresponds to the power outage type D, and the public-change node corresponds to the power outage type E.
Further, the inclusion relationship of the event type is a power failure type
Or->
Correspondingly, the invention provides a method for supplementing a power failure event of a medium voltage distribution network based on a support vector machine, which is characterized by comprising the following steps:
collecting a power failure event of a fault point in a medium-voltage distribution network;
determining a final power failure node by adopting the power failure event judging method;
comparing the collected fault points with the determined power failure nodes, and completing the power failure event according to the comparison result.
Compared with the prior art, the invention has the following beneficial effects: according to the method for judging the power failure event of the medium-voltage distribution network based on the support vector machine, the node power flow operation data is utilized to analyze, the final power failure node is determined, the problems of missing acquisition and incorrect acquisition of the power failure event of the medium-voltage distribution network are solved, missing report, incorrect report and lie report of power failure event statistics are avoided, and the statistical accuracy of power supply reliability is improved.
Drawings
FIG. 1 is a flow chart of the medium voltage distribution network blackout event completion based on a support vector machine;
FIG. 2 is a business framework diagram between a completion module and an associated system in accordance with the present invention;
FIG. 3 is a schematic diagram of a node and power outage type according to the present invention;
FIG. 4 is a diagram of the dimension reduction result of the class E vector machine in the example of the present invention;
FIG. 5 is a diagram of a process for optimizing parameters of a class E vector machine in accordance with an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
The invention discloses a method for judging a power failure event of a medium-voltage distribution network based on a support vector machine. Referring to fig. 1, the method comprises the following steps:
step S1, a power grid model structure of a medium-voltage distribution network is obtained, and the distribution network node type is divided according to equipment at a distribution network node.
And integrating distribution network topology data, public transformer account data and private transformer account data in the power consumption information acquisition system in the PMS to construct a power grid model structure of the medium-voltage distribution network.
The construction of the power grid model is derived from data interaction with other systems, a service framework diagram among the systems is shown in fig. 2, and roles of the systems are described as follows:
1) And the electricity consumption information acquisition system comprises: providing a line and private public transformer area user file; the terminal is powered off originally, the load information such as user voltage, current, power and the like, and the business expansion and installation flow information.
2) PMS (engineering production management system): providing a line and public transformer equipment foundation ledger, a power grid topology model, and providing 10kV feeder line occurrence switch state information and feeder line current.
3) 95598: and providing information such as a plan, fault power failure, fault emergency repair processing results and the like which are released outwards.
4) Fibre channel monitoring: concentrator power down information, i.e., a station blackout event, is provided for fiber optic communications.
5) The power quality system comprises: the special transformer basic account information comes from marketing, the public transformer basic account information comes from a PMS system, and the electric energy quality implementation corresponds to marketing and PMS file account; the medium-voltage user power failure event receives a power failure event automatically pushed by the power utilization information acquisition system, and the power failure property and the reason are judged and selected manually; and (5) counting power supply reliability indexes.
As shown in figure 3, the abstract circuit model of the medium-voltage distribution network has a 110/10kV transformer as a starting point, a plurality of outgoing lines are arranged in the network, each outgoing line is divided into a plurality of sections, and then the section branch lines are connected with a plurality of public transformers or private transformers. The back branch is connected with equipment such as an outlet cabinet, a ring main unit, a public transformer, a special transformer and the like. The invention divides different node types for different devices according to different influence surfaces of the devices during faults. The fault range of different node types is different, and the key position of the extraction equipment is abstracted into circuit nodes. Dividing distribution network nodes into five types, namely transformer nodes, outlet cabinet nodes, ring main unit nodes, private transformer nodes and public transformer nodes; the specific description is as follows:
1) The transformer node, the root node of the secondary side outgoing line of the 110/10kV transformer, is defined as a transformer node and is marked as node type A;
2) The outlet cabinet node is defined as the outlet cabinet node at the root node of each outlet in the outlet cabinet of the power distribution room and is marked as node type B;
3) The ring main unit nodes are defined as ring main unit nodes and are marked as node type C;
4) The special transformer node, the 10/380V special transformer, is defined as a special transformer node and is marked as a node type D;
5) The public transformer of 10/380V is defined as public transformer node, which is marked as node type E.
And S2, establishing a vector machine corresponding to the node type at each distribution network node, wherein the input of each vector machine is the measuring point power flow data at each node, and the output of each vector machine is whether a power failure event occurs at each node.
According to faults at 5 node types in the distribution network, corresponding 5 power failure types are achieved, and the corresponding relation is described as follows:
1) The power failure type A corresponds to power failure at a node of a transformer substation, namely, the whole radiation area of the medium-voltage transformer is completely powered off due to the failure of transformer equipment or the power failure of an upper stage;
2) The power failure type B corresponds to power failure of a node of the outlet cabinet, namely, the switch of the outlet cabinet at the head end of the line is disconnected, so that the whole line is powered off;
3) The power failure type C corresponds to power failure of a ring main unit node, namely, a certain ring main unit switch in the middle of a line trips, so that a certain section of the line is powered off;
4) The power failure type D is used for power failure of a corresponding special change node, namely power failure of a special change user of a single special change, and power failure of all special changes of a plurality of special change users;
5) And the power failure type E corresponds to power failure of a public transformer node, namely power failure of a public transformer area.
Five types of vector machines, such as corresponding A, B, C, D, E types of vector machines in fig. 1, are respectively built at corresponding nodes according to the five power outage types, and each node type is built with a corresponding vector machine. The node type, the power failure type and the vector machine type of the same node are all corresponding, so the same letter is used for representing. The vector machine is a machine learning method, inputs some data volume, analyzes and judges, and outputs the result as 0 or 1, namely judges whether the node is at the bottom and has or has not had power failure.
The input data of each type of vector machine are different, and the selection of measuring points of various types of vector machines and the types of data collected by the measuring points are respectively as follows:
1) Vector machine A: the measuring points are as follows: under the transformer, each outlet cabinet randomly selects a branch outlet, and the head end of each outlet selects a special or public variable measuring point.
Initially input tidal current data: day 96 point measurement data of each measurement point ： Maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
2) Vector machine B: measuring points: and selecting a special or public variable measuring point for each of the outlet head, the outlet tail and the outlet, and selecting a special or public variable measuring point for each of 2 outlets adjacent to the outlet.
Initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
3) Vector machine C: measuring points: and selecting a special or public variable measuring point before and after the judging point.
Initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
4) Vector machine D: measuring points: all private transformer node boxes for private transformer users (a private transformer user may comprise 1 private transformer or a plurality of private transformers) are measurement points, and in addition, adjacent to the private transformer nodes, 1 private or public variable measurement point is selected.
Initially input tidal current data: the current day 96-point measurement data of the private transformer node of the private transformer user of the box transformer point are as follows: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; and selecting average voltage, current and power by a special transformer user adjacent to the measuring point.
5) Vector machine E: the measuring points are as follows: a single metric point of public transformation, adjacent to the 1-specific or public variable point of selection.
Initially input tidal current data: 96-point measurement data of the box transformer point on the same day; maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; average voltage, current and power are selected from the adjacent measuring points.
And S3, judging whether a power failure event occurs at each node by using a trained vector machine at each distribution network node according to the measuring point power flow data at each node.
The vector machine solving and analyzing method comprises three processes of data normalization processing and data reduction and SVM operation analysis, wherein the three links are required to be processed for vector machine parameter training and vector machine test judgment.
The vector machine parameter training process comprises the following processing steps:
1) For each type of vector machine, initial input data of the vector machine are obtained;
2) Carrying out data normalization processing, namely carrying out [0,1] normalization on each dimension of sample current, voltage and power in a power system, wherein the dimensions of each dimension are different and have large differences, and screening normalization results according to data fluctuation to eliminate the influence of individual outliers on normalization;
3) The data dimension reduction analysis is carried out by adopting a local linear embedding LLE (Locally linear embedding) data dimension reduction method to carry out data dimension reduction on the principle of covering more than 95% of the original information, and a dimension-reduced low-dimension data set is used as training input of a vector machine; as shown in FIG. 4, the bar graph in the figure represents the first 4-dimensional component after dimension reduction, the percentage of the original total information covered by each dimension component, the broken line represents the percentage of the accumulated total information covered by the original, and the 4-dimensional accumulated percentage reaches 99.2%, so that the 4-dimensional data can be obtained by using the class E vector machine and 13-dimensional data.
4) And (3) training parameters of the vector machine, finding out an optimal penalty factor c and a nuclear parameter gamma by using a grid parameter optimizing method, and substituting the optimal penalty factor c and the nuclear parameter gamma into a vector machine model. Fig. 5 shows a training process of penalty factors and kernel parameters of the E-type vector machine, in which the optimal penalty factor c=0.125 and the optimal kernel parameter g=0.5 of the E-type vector machine are shown.
The vector machine test judging process comprises the following processing steps:
1) For each type of vector machine, acquiring initial input data of the vector machine from an electricity consumption information acquisition system;
2) Carrying out data normalization processing, namely carrying out [0,1] normalization on each dimension of sample current, voltage and power in a power system, wherein the dimensions of each dimension are different and have large differences, and screening normalization results according to data fluctuation to eliminate the influence of individual outliers on normalization;
3) Performing data dimension reduction analysis, namely performing data dimension reduction by taking the principle of covering more than 95% of the original information amount as a training input of a vector machine, wherein a low-dimension data set after dimension reduction is used as a training input of the vector machine;
4) Substituting the data subjected to dimension reduction into a vector machine model, performing test judgment, and determining whether power failure occurs to the distribution network node, wherein the power failure is 1, and the power failure is-1.
And S4, merging the judging results of whether the power is cut off or not of all the distribution network nodes step by step upwards according to the power grid model structure, and determining the final power cut node.
The number of failure points of the power failure event is only 1, but a plurality of nodes in the power grid are powered off, whether the power failure of each node is judged, and the next step is to further analyze according to the conditions of each node so as to find out the final failure point, namely, determine the final power failure event.
According to the inclusion relation of the event type influence surfaces, respectively
Or->
D. E, the event is a parallel tail end power failure event, and the power failure events are combined. The specific merging principle is that the preceding event merges the following event, ifIf the event A occurs, the event B, C, D, E definitely occurs, and the final output result is A; or if C occurs, then part of the D or E events will occur, and the result output is still a C event.
And determining a final power failure node according to the finally output power failure event type.
The electricity consumption information acquisition system acquires a power failure event, but the power failure event can be misadopted or missed. The invention also provides a method for supplementing the power failure event of the medium-voltage distribution network based on the support vector machine, which is to correct the mining errors after judgment and supplement the missed mining, and comprises the following specific processes:
the method for acquiring the original power failure event record list in the electricity information acquisition system comprises the following steps:
1) The power failure event sent by each acquisition terminal node, namely all the class D and class E node positions;
2) According to the power outage event sent by each terminal, combining with the power grid topology combination, comprehensively judging the position of a fault point, and forming the final power outage event type of the medium-voltage distribution network;
the method for supplementing the power failure event record table in the electricity consumption information acquisition system comprises the following steps:
1) Comparing the judgment result of the E-type and D-type vector machines with the result of the power failure event sent by each acquisition terminal node, and completing the comparison;
2) And comprehensively determining a final power failure node by using a vector machine, determining a power failure event type, comparing the power failure event type with the result of the original power failure event type in the power consumption information acquisition system, and completing the power failure event type.
Comparing the collected fault point with the determined power failure node, and correcting the mining error or supplementing the missed mining if the mining error or the missed mining occurs. For example, if the collected power outage event is of type B, and if the vector machine is adopted to judge that the power outage event is of type B or type C, the system is judged to collect the wrong power outage event, and the correct power outage event A is collected again; if the collected power failure event is of the type B, and the vector machine is adopted to judge that the power failure event is of the type A, the system is judged to miss the collected power failure event, and the collected power failure event A is supplemented.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (6)
1. A method for judging a power failure event of a medium voltage distribution network based on a support vector machine is characterized by comprising the following steps:
s1, acquiring a power grid model structure of a medium-voltage distribution network, and dividing the distribution network node type according to the equipment type at the distribution network node;
s2, establishing a vector machine of a type corresponding to the node type at each distribution network node, wherein the input of each vector machine is the power flow data of a corresponding measuring point of each node, and the output of each vector machine is whether a power failure event occurs at each node;
s3, judging whether a power failure event occurs at each node by using a trained vector machine at each distribution network node according to the corresponding measuring point power flow data at each node;
s4, merging the judging results of whether power is cut off or not of all the distribution network nodes step by step upwards according to the power grid model structure, and determining a final power cut node;
the distribution network node type comprises: five types of transformer nodes, outlet cabinet nodes, ring main unit nodes, special transformer nodes and public transformer nodes;
each node type is provided with a corresponding vector machine, and the selection of measuring points of various vector machines and the data types collected by the measuring points are respectively as follows:
1) Vector machine A: the measuring points are as follows: randomly selecting a branch outlet from each outlet cabinet under the transformer, and selecting a special or public variable measuring point at the head end of each outlet;
initially input tidal current data: day 96 point measurement data of each measurement point ： Maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
2) Vector machine B: measuring points: selecting a special or public variable measuring point for each of the outlet head, the outlet tail and the outlet, and selecting a special or public variable measuring point for each of 2 outlets adjacent to the outlet;
initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
3) Vector machine C: measuring points: selecting a special or public variable measuring point before and after the judging point;
initially input tidal current data: day 96 point measurement data of each measurement point: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power;
4) Vector machine D: measuring points: the method comprises the steps that all private transformer node boxes of private transformer users are measuring points, and in addition, 1 private or public variable measuring point is selected to be adjacent to the private transformer node;
initially input tidal current data: the current day 96-point measurement data of the private transformer node of the private transformer user of the box transformer point are as follows: maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; selecting average voltage, current and power by a special transformer user adjacent to the measuring point;
5) Vector machine E: the measuring points are as follows: a single public variable measuring point is adjacent to a special variable or public variable measuring point selected 1;
initially input tidal current data: 96-point measurement data of the box transformer point on the same day; maximum voltage, current and power; average voltage, current and power; minimum voltage, current, and power; average voltage, current and power are selected from the adjacent measuring points.
2. The method for judging the power failure event of the medium voltage distribution network based on the support vector machine according to claim 1, wherein the five node types are specifically described as follows:
1) The transformer node, the root node of the secondary side outgoing line of the 110/10kV transformer, is defined as a transformer node and is marked as node type A;
2) The outlet cabinet node is defined as the outlet cabinet node at the root node of each outlet in the outlet cabinet of the power distribution room and is marked as node type B;
3) The ring main unit nodes are defined as ring main unit nodes and are marked as node type C;
4) The private node, 10/380V user private part, is defined as private node and is marked as node type D;
5) The public transformer of 10/380V is defined as public transformer node, which is marked as node type E.
3. The method for judging the power failure event of the press-fit network based on the support vector machine according to claim 1, wherein the initial input data is subjected to data normalization processing and data dimension reduction processing before being input into the vector machine.
4. The method for judging the power outage event of the medium voltage distribution network based on the support vector machine according to claim 1, wherein the power outage types corresponding to the distribution network nodes are respectively as follows: the transformer node corresponds to the power outage type A, the outlet cabinet node corresponds to the power outage type B, the ring main unit node corresponds to the power outage type C, the special-change node corresponds to the power outage type D, and the public-change node corresponds to the power outage type E.
5. The method for judging a power failure event of a press-fit network based on a support vector machine according to claim 4, wherein the inclusion relation of event types is a power failure type
Or->
6. The method for supplementing the power failure event of the medium-voltage distribution network based on the support vector machine is characterized by comprising the following steps of:
collecting a power failure event of a fault point in a medium-voltage distribution network;
determining a final outage node by using the outage event judgment method according to any one of claims 1 to 3;
comparing the collected fault points with the determined power failure nodes, and completing the power failure event according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910131792.9A CN109949178B (en) | 2019-02-22 | 2019-02-22 | Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910131792.9A CN109949178B (en) | 2019-02-22 | 2019-02-22 | Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949178A CN109949178A (en) | 2019-06-28 |
| CN109949178B true CN109949178B (en) | 2023-06-16 |
Family
ID=67007636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910131792.9A Active CN109949178B (en) | 2019-02-22 | 2019-02-22 | Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949178B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909811B (en) * | 2019-11-28 | 2022-10-18 | 国网湖南省电力有限公司 | OCSVM (online charging management system) -based power grid abnormal behavior detection and analysis method and system |
| CN111813825B (en) * | 2020-06-02 | 2023-03-14 | 国网江西省电力有限公司电力科学研究院 | Distribution transformer outlet power failure event missing report automatic detection method and system |
| CN113344364B (en) * | 2021-05-31 | 2022-12-23 | 广东电网有限责任公司佛山供电局 | Power failure plan risk analysis method and device, electronic equipment and storage medium |
| CN113377835A (en) * | 2021-06-09 | 2021-09-10 | 国网河南省电力公司电力科学研究院 | Distribution network line power failure identification method based on long-short term memory deep learning network |
| CN114268110B (en) * | 2022-03-03 | 2022-06-28 | 广东电网有限责任公司梅州供电局 | Method and device for judging reactive compensation switching-on/off state of distribution transformer |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106443436A (en) * | 2016-11-10 | 2017-02-22 | 国电南瑞科技股份有限公司 | Detection method for remote control function of switch by combining loop risk with operation and maintenance assistant decision |
| CN108169621A (en) * | 2017-12-05 | 2018-06-15 | 国电南瑞科技股份有限公司 | Taiwan area power-off event complementing method based on support vector machines |
| CN108364187A (en) * | 2017-12-20 | 2018-08-03 | 国网冀北电力有限公司承德供电公司 | A kind of power failure sensitive users based on power failure sensitivity characteristic determine method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8892375B2 (en) * | 2008-05-09 | 2014-11-18 | Accenture Global Services Limited | Power grid outage and fault condition management |
| CN102930007B (en) * | 2012-10-30 | 2016-01-06 | 广东电网公司 | User in large-area power-cuts emergency processing sends a telegram in reply urgency level sorting technique |
| CN105974265B (en) * | 2016-04-29 | 2018-11-27 | 北京四方继保自动化股份有限公司 | A kind of electric network fault cause diagnosis method based on svm classifier technology |
| CN107292513A (en) * | 2017-06-21 | 2017-10-24 | 国网辽宁省电力有限公司 | A kind of method that power customer management is realized based on svm classifier algorithm |
| CN108734381A (en) * | 2018-04-11 | 2018-11-02 | 国网山东省电力公司 | A kind of outage information collaborative management method, apparatus and system |
| CN109002937A (en) * | 2018-09-07 | 2018-12-14 | 深圳供电局有限公司 | Load Forecasting, device, computer equipment and storage medium |
| CN109035066A (en) * | 2018-09-30 | 2018-12-18 | 国网山西省电力公司阳泉供电公司 | The high breaking route genetic analysis of 10 kilovolts of distributions and administering method based on SVM |
-
2019
- 2019-02-22 CN CN201910131792.9A patent/CN109949178B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106443436A (en) * | 2016-11-10 | 2017-02-22 | 国电南瑞科技股份有限公司 | Detection method for remote control function of switch by combining loop risk with operation and maintenance assistant decision |
| CN108169621A (en) * | 2017-12-05 | 2018-06-15 | 国电南瑞科技股份有限公司 | Taiwan area power-off event complementing method based on support vector machines |
| CN108364187A (en) * | 2017-12-20 | 2018-08-03 | 国网冀北电力有限公司承德供电公司 | A kind of power failure sensitive users based on power failure sensitivity characteristic determine method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949178A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949178B (en) | Method for judging and complementing power failure event of medium-voltage distribution network based on support vector machine | |
| JP5452613B2 (en) | Power grid supply interruption and failure status management | |
| CN110808633B (en) | Distribution automation terminal optimal configuration method for active distribution network | |
| CN105915398B (en) | Rural power grid fault based rapid detection and power restoration system and concentrator detection method thereof | |
| CN108318782B (en) | Power distribution network fault area identification method based on network topology and distribution transformer power failure information | |
| CN109146124B (en) | Power distribution terminal transformation decision method based on time-varying failure rate | |
| CN103683511A (en) | Method and system for processing fault of integrated monitoring platform based on power distribution network | |
| CN104505825A (en) | Power supply safety diagnosis analysis method for high voltage distribution network | |
| CN113328437B (en) | Intelligent power distribution network CPS topology construction method and fault recovery method | |
| CN107871202A (en) | A kind of system adequacy evaluation method of meter and multi-voltage grade | |
| CN110556920A (en) | Distribution automation monitoring method, system, terminal and storage medium | |
| CN109726880B (en) | Power transmission line parameter rationality assessment method and system | |
| CN111639839B (en) | Micro-service-based power grid fault analysis method and system | |
| CN104537161A (en) | Medium voltage distribution network diagnostic analysis method based on power supply safety standards | |
| CN111062825A (en) | Low-voltage fault diagnosis and rapid power restoration method based on mobile App | |
| CN108596450B (en) | Power grid risk early warning method and system | |
| CN106651113A (en) | Dispatcher operation risk evaluation method based on advanced N-1 analysis | |
| CN113793039B (en) | Reliability evaluation method for medium-low voltage distribution network considering multiple types of terminals | |
| CN112256922B (en) | Method and system for quickly identifying faults and power failure | |
| CN114139744A (en) | Abnormal photovoltaic group string branch identification method and device, electronic equipment and storage medium | |
| CN114596171A (en) | Power failure event intelligent analysis method based on multi-source data fusion | |
| CN108229863B (en) | Power supply reliability calculation method for power distribution network | |
| CN112465358A (en) | Voltage quality classification method and device based on support vector machine | |
| CN107622078B (en) | Method for monitoring health state of power consumption information acquisition equipment in real time | |
| CN112258030A (en) | Site selection method and system for intelligent switching station of power distribution network and information data processing terminal |
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 |