CN114417732A - Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon - Google Patents
Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon Download PDFInfo
- Publication number
- CN114417732A CN114417732A CN202210109162.3A CN202210109162A CN114417732A CN 114417732 A CN114417732 A CN 114417732A CN 202210109162 A CN202210109162 A CN 202210109162A CN 114417732 A CN114417732 A CN 114417732A
- Authority
- CN
- China
- Prior art keywords
- node
- distribution network
- fault
- disaster
- power distribution
- 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.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004891 communication Methods 0.000 claims abstract description 58
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 description 10
- 230000008439 repair process Effects 0.000 description 9
- 238000005452 bending Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000011084 recovery Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000004567 concrete Substances 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001600129 Delftia Species 0.000 description 1
- 229910001294 Reinforcing steel Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011150 reinforced concrete Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
Abstract
The invention provides a method and a system for self-adaptive identification of multi-source disaster damage of a power distribution network under strong typhoon, which comprises the following steps: carrying out fault judgment on node communication of the power distribution network under strong typhoon; if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction; if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
Description
Technical Field
The invention belongs to the technical field of distribution network disaster and loss identification, and particularly relates to a multi-source load and loss self-adaptive identification method and system for a distribution network under strong typhoon.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The large-scale power failure caused by frequent typhoon disasters brings great challenges to the toughness of the power distribution network with the characteristics of multiple voltage levels, complex network structure, various equipment types and the like, and greatly hinders the important task of providing power energy for various users. Currently, the research on the fault recovery strategy under the extreme disaster is generally based on fault positioning and fault isolation, and the optimal fault recovery strategy is solved through different optimization algorithms. Therefore, if the topological identification and fault location are carried out on the ultra-short-term power loss load in the high-risk area and the disaster through the disaster modeling and deep learning algorithm, the load can be recovered to the maximum extent in the least time, and casualties and economic losses are reduced.
(1) A method for predicting the large-range power failure probability of a power distribution network under extreme meteorological conditions is provided by Chenying and the like in national key laboratories of a Motor system of Qinghua university, and the method provides a method for modeling the fault probability of the power distribution network, and comprises the following steps: the node power failure probability prediction method based on the power distribution network equipment outage event Bayesian network comprises a power distribution network equipment outage event Bayesian network model under a typhoon disaster and node power failure probability prediction based on the power distribution network equipment outage event Bayesian network. The method overcomes the defect that the dynamic characteristics of the weather are difficult to describe in the original research, and fully describes the cause-and-effect dependence relationship and uncertainty in the power failure event of the power distribution network by using the Bayesian network.
The method is based on data driving only, the time-space correlation of the equipment outage events after disasters is considered, a disaster time Bayesian network model is constructed by utilizing historical disaster damage records and disaster numerical simulation data, and the power failure range and the power failure probability of the power distribution network are rapidly inferred according to the disasters.
(2) A110 kV line tower collapse and disconnection accident assessment method under typhoon storm disasters is proposed by Wangzhenping and other people in national key laboratories of New energy electric power systems of North China electric university. The method comprises the following steps: and (4) analyzing the influence of the typhoon rainstorm model and the typhoon rainstorm on the 110kV wire and the iron tower. Respectively establishing finite element models for different power transmission tower types of the 110kV line, considering the correlation of wind and rain loads, and analyzing the dynamic response of the line and the iron tower under the wind and rain loads; based on the structural reliability theory, the probability expressions of line breakage and tower falling are deduced, the mechanism influence of factors such as different tower types, purposes and wind direction angles on tower falling is researched, the weak link of a power grid is analyzed, and the accident of tower falling and line breakage of a 110kV line under the typhoon rainstorm disaster is evaluated.
The method is based on mechanism analysis only, and based on a structural reliability theory, a component fault probability expression is deduced, and the weak point of the power grid is analyzed.
(3) A real-time routing strategy of an unmanned aerial vehicle for recovering monitoring and checking after a power distribution network disaster is provided by Foucault of Delftia Technische university. The method comprises the steps of recovering and monitoring the power distribution network after disaster and using the unmanned aerial vehicle real-time routing strategy for checking coordination. Through the real-time unmanned aerial vehicle routing strategy that provides, unmanned aerial vehicle can inspect the damage condition to resume after the calamity. In addition, the transmission line may be monitored for potential hazards, and the road infrastructure may be monitored to provide real-time information about traffic conditions so that maintenance personnel may choose the best way to reach the damaged area.
The method combines a data driving and mechanism analysis method, monitors the damage condition through a real-time unmanned aerial vehicle routing strategy, and facilitates post-disaster recovery.
In short, in the method (1), only data-driven prediction is considered, but the quality of the post-disaster recovery strategy of the data-driven power distribution network depends on the quality of prediction data, so that the defect of low prediction precision is easily caused. The method (2) only predicts based on mechanism analysis, and is not suitable for the power distribution network with the characteristics of multiple voltage levels, complex network structure, various equipment types and the like although the dependence on meteorological data and electrical data is small. The method (3) combines the data driving and mechanism analysis methods, but the method is only suitable for the complete and sound communication condition of the communication network, once the communication network is damaged, when the whole system is in a weak communication condition, the monitoring electrical quantity cannot represent a fault, and related faults cannot be timely transmitted back to the dispatching center through the communication network.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a self-adaptive identification method for the multi-source disaster damage of the power distribution network under strong typhoon, and the topological identification and the fault element positioning can be realized under various communication soundness degrees.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
in a first aspect, a method for self-adaptive identification of multi-source disaster damage of a power distribution network under strong typhoon is disclosed, which comprises the following steps:
carrying out fault judgment on node communication of the power distribution network under strong typhoon;
if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction;
if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
Further technical scheme, the topology identification of the multi-source load distribution network specifically comprises:
acquiring the voltage, the current and the load of each node in the power distribution network in real time;
defining a power distribution network node state matrix S, wherein the S is a 1 x n-order matrix, n elements are all 1 before a disaster occurs, and n nodes are all in a normal power supply state; after the disaster happens, updating the value of the load power-off node corresponding to the matrix S to be 0 according to the load power-off condition;
numbering each node in the power distribution network, and defining a node connection relation matrix; and defining a fault matrix F, and carrying out fault positioning and reason analysis.
The further technical scheme is that a fault matrix F is defined, fault location and reason analysis are carried out, and the method comprises the following steps:
when the fault matrix F is assigned:
when the kth node is power-off, the k-1 node and the k +1 node are normal, and the fault of the transformer at the kth node is indicated;
and searching the superior node number of k and the inferior node number of k by using the connection relation matrix, and then obtaining the value positioned at the (k, k) th coordinate in the fault matrix F.
The further technical scheme defines a fault matrix F, performs fault location and reason analysis, and further comprises the following conditions:
the kth node is powered off, the k-1 node is normal, and the k +1 node is powered off;
traversing all lower nodes of the branch where k is located, and if the nodes are all powered off, determining that a disconnection fault occurs between k and k-1;
if the number of the normal lower-level nodes is not 0, the situation that the transformers at k and k +1 simultaneously have faults is shown.
The further technical scheme defines a fault matrix F, performs fault location and reason analysis, and further comprises the following steps:
the kth node is powered off, and the k-1 node and the k +1 node are also powered off;
assuming that the upper node of k-1 fails, the specific analysis needs to jump to the node;
and then, circularly judging the first execution condition and the second execution condition until all nodes corresponding to all fault values in the distribution network node state matrix S are traversed once, and finally reflecting the fault positions and the fault types according to the values in the matrix F.
According to the further technical scheme, the node power loss probability is obtained through disaster damage identification and correction, and the method specifically comprises the following steps:
considering the model of the pole falling and the line breaking, the probability is set as p1And p2And then the independent power loss probability of the multi-element source load single node of the power distribution network is as follows:
p=1-(1-p1)(1-p2)。
according to the further technical scheme, a deep learning network is trained according to weather and disaster historical data, and a deep learning disaster prediction model for inputting weather and outputting disaster is obtained.
According to the further technical scheme, the wind speed in the multi-dimensional original meteorological information is corrected by considering the ground roughness and the relative height, and the method specifically comprises the following steps:
let the reference wind speed measured by a nearby meteorological station be v0Surface roughness of z0Measuring the wind with uniform height h meters; corrected wind speed of the node is v1Surface roughness of z1;
Wind speed variation due to relative altitude variation: setting the relative height between the node and the reference station as delta h, and the wind speed change caused by terrain as delta vh;
Wind speed variation due to variations in ground roughness: let the variation in wind speed due to variation in roughness be Δ vz;
The wind speed v after the node correction1Can be expressed by the following formula:
v1=v0+Δvh+Δvz。
in a second aspect, a self-adaptive identification system for the multi-source disaster damage of a power distribution network under strong typhoon is disclosed, which comprises:
a communication failure determination module configured to: carrying out fault judgment on node communication of the power distribution network under strong typhoon;
a first node power loss probability calculation module configured to: if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction;
a second node power loss probability calculation module configured to: if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
The above one or more technical solutions have the following beneficial effects:
the invention provides a self-adaptive identification and correction method for multi-source load damage of a power distribution network under strong typhoon, which considers the soundness degree of post-disaster communication. When typhoon comes, real-time meteorological data is input, the model can roll and predict the power distribution network disaster damage situation from a period of time to the end of the typhoon, and the model has practical significance for guiding the post-disaster component emergency repair, so that disaster prevention and reduction commanders and power grid dispatching departments can make decision deployment in time, and economic loss and casualties are reduced as far as possible.
According to the method, only topology information and historical meteorological data of the power distribution network need to be provided, a disaster damage model is obtained through deep learning, the multi-source disaster damage condition of the power distribution network from a period of time to the end of typhoon in the future is predicted, and the method has an instructive effect on the aspect of improving the first-aid repair speed of the power distribution network.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
Referring to the attached drawing 1, the embodiment discloses a self-adaptive identification method for the multi-source load damage of a power distribution network under strong typhoon, which can realize topology identification and fault element positioning under various communication soundness degrees, and guides the post-disaster repair work from top to bottom by analyzing fault propagation and power loss mechanisms.
The embodiment firstly provides a power distribution network post-disaster topological structure recognition method under the condition of sound communication
And secondly, considering fault identification under the conditions of strong typhoon and weak communication, correcting the wind speed at the representative weather station based on the ground roughness and the relative height, introducing a deep learning algorithm, obtaining input weather information based on real-time weather information and historical disaster data, outputting a model for predicting the disaster damage, identifying a fault element under the condition of weak communication, and guiding the emergency repair after the disaster.
The deep learning algorithm finally realizes the online input of meteorological data such as real-time wind speed, rainfall intensity and the like measured by a meteorological station in a region where the power distribution network is located through an offline training process, and outputs the load power loss probability of each node of the power distribution network.
Failure mechanism of power distribution network elements under strong typhoon:
a. tower tower
At the moment, the gust wind speed is v;
mass of air column
m=ρSl
Length of air column
l=vt
According to the theorem of momentum
Ft=mv
Wind resistance on the outside of the pole
F=ρSv2
And a point at the bottom of the electric pole close to the ground is regarded as a lever fulcrum, and the point is subjected to the action of bending moment. The magnitude of the bending moment is as follows:
M=FL
in the formula, the moment arm L is h1/2. And (4) is substituted into (5) to obtain the bending moment applied to the electric pole.
The tower stress bending moment is expressed as:
in the formula: k is a cylinder correction coefficient, and k is less than 1, which indicates that the side surface of the cylinder is subjected to smaller wind load than that of the cuboid under the same wind area.
Pole ultimate design moment of flexure M0Determination of (1):
in the formula: a isnIn order to obtain the reinforcement ratio,Rgdesign strength for reinforcing bar tensile, unit kgf/cm2;FgIs the section area of the reinforcing steel bar in cm2;rgThe radius of the circle where the steel bar is located is in cm; rwDesign strength for concrete bending compression resistance, unit kgf/cm2;FsIs the concrete cross section area in cm2。
Formula of rod breaking condition of 10kV distribution network annular reinforced concrete electric pole in strong wind environment
M>M0
In the formula: p1The probability of pole falling of a 10kV pole of a power distribution network in a strong typhoon environment.
b. Line
A power line wind load calculation model:
W=24.4311CSv2DLg
in the formula: w is the wind load (N) of the power line; c is a wind load constant (0.003); v is the gust wind speed (m/s); g is a gravity constant; d is the power line diameter (m); l is the length (m) of the power line; s is a power line shape coefficient, and
in the formula, if v <2.2352, S is 1.
From the average wind speed vmIn relation to (2)
vt=1.29vm+2.5928
Let the maximum wind load that the power line can bear be W0Then, the maximum wind speed v borne by the power line can be obtainedmax:
The wind load caused by the extreme wind speed is considered to belong to an extreme climate event, and the GEV distribution theory is widely applied to the fields of climate analysis and climate change research, so that the wind load data caused by the wind speed is subjected to extreme value distribution fitting by adopting generalized extreme value distribution.
Carrying out probability analysis on the gust wind speed of the power line to construct the GEV distribution of the gust wind speed
In the formula: mu is a position parameter, sigma is a shape parameter,is the tail index. When ξ is 0, F (v)t) Is Gumbel distribution; xi<0, F (v)t) Is a Weibull distribution; xi>0, F (v)t) Is a frechet distribution.
The GEV distribution parameters can be estimated by a maximum likelihood method, and the maximum likelihood function is as follows:
in the formula:and n is the number of sample data. Solving estimated values of GEV parameters by maximum likelihoodAndthe probability density function of the wind speed of the gust is obtained as
Probability calculation model for power line breakage under storm disaster
In the formula: p2Is the probability of line break at time t.
A method for identifying a post-disaster topological structure of a power distribution network comprises the following steps:
the method is characterized in that an automatic electric quantity monitoring and signal sending device is arranged at the outlet end of the low-voltage side of each distribution transformer on a 10kV line, the voltage, the current and the load of each node can be fed back in real time, and the numerical values of the electric quantities can reflect the working conditions of the nodes.
Numbering each node in the power distribution network, defining a node connection relation matrix C, having
In the formula: n is the total number of nodes of the power distribution network, and the matrix C is an n multiplied by n order sparse matrix.
And defining a power distribution network node state matrix S, wherein the S is a 1 x n-order matrix, and n elements are all 1 before a disaster occurs, which indicates that n nodes are in a normal power supply state. After the disaster happens, the load power-off condition is judged according to the numerical value returned by the information acquisition device, the value in the matrix S corresponding to the load power-off node is updated to be 0, and fault location and reason analysis are performed below. And the number of the power-off node is k, k-1 represents an upper node of the power-off node, and k +1 represents a lower node of the power-off node. Defining a fault matrix F:
in the formula: n is the total number of nodes of the power distribution network, and the matrix F is an n multiplied by n order sparse matrix.
And assigning the fault matrix F according to the following three conditions:
the first condition is as follows: when the kth node is power-off, the k-1 node and the k +1 node are normal, and the fault of the transformer at the kth node is indicated;
searching the superior node number of k by using the connection relation matrix C, and ordering
j=k
Then the upper node of k
k-1 ═ i, if and only if Cik=1
Finding the subordinate node of k in the same way
i=k
k +1 ═ i, if and only if Ckj=1
At this time, the value at the (k, k) -th coordinate in F is
Fkk=Sk-1Sk+1
Case two: the kth node is powered off, the k-1 node is normal, and the k +1 node is powered off. Traversing all lower nodes of the branch where k is located, and if the nodes are all powered off, determining that a disconnection fault occurs between k and k-1; if the number of the normal lower-level nodes is not 0, the situation that the transformers at k and k +1 simultaneously have faults is shown.
The method for searching the serial numbers of the upper and lower nodes of k is the same as the above, and when the disconnection fault occurs between k and k-1
Fk-1,k1, if and only if N (S)k+1,Sk+2,…,Sk+e=0)=e
In the formula: n (S)k+1,Sk+2,…,Sk+eAnd e is 0, and represents that all the lower nodes of the branch where k is located lose power, and e is the number of the lower nodes. When the transformers at k and k +1 simultaneously fail
Fk,kWhen N (S) is equal to 1k+1,Sk+2,…,Sk+e=0)>0
Fk+1,k+1When N (S) is equal to 1k+1,Sk+2,…,Sk+e=0)>0
Case three: the kth node is powered off, and the k-1 node and the k +1 node are also powered off. Because the probability of the simultaneous failure of a plurality of transformers is low, the failure of the upper node of the k-1 can be considered, the specific analysis of the node is required to be skipped, and the failure can be ensured
k=k-1
And then circularly judging the first and second execution conditions until nodes corresponding to all the values of the faults (equal to 0) in the matrix S can be traversed once, and finally providing guidance for emergency repair after the disaster according to the fault positions and the fault types reflected by the values in the matrix F.
The method for identifying the disaster damage of the power distribution network under the sound communication comprises the following steps:
the topology identification based on the electrical quantity measurement data under the sound communication condition can locate and judge most faults, but still has some defects. For example, in a unidirectional distribution line, the method can trace back to a source node of a broken line fault, but whether a lower node behind the fault node has a fault or not can not be determined; in addition, even if there is no short circuit, the lower node is not affected by the lodging of the electric pole, and therefore a disaster identification and correction method based on meteorological data and an element failure mechanism needs to be introduced.
Comprehensively considering the model of pole falling and line breaking, and setting the probability as p1And p2Independent power loss probability of multi-source load single node of power distribution network
p=1-(1-p1)(1-p2)
The method for identifying the disaster damage of the power distribution network under the weak communication comprises the following steps: the basic idea of disaster damage assessment under the weak communication condition is as follows: when the strong typhoon destroys the communication equipment on the power distribution network node, the master station cannot accurately obtain the load power loss situation, the element damage situation of three hours in the future is predicted by a sliding time window method in the time range of one week before and after the strong typhoon logs in, the post-disaster element damage prediction data is obtained, finally the data is input into the power distribution network topological structure, and the disaster damage prediction result of the load power loss is obtained by using a topological identification method.
Under the strong wind environment, the actual wind speed of each transformer, tower and wire in the transformer area cannot be measured, and the wind speed obtained from a nearby meteorological site cannot reflect the actual condition of a certain node, so that the actual wind speed of the node needs to be corrected.
Let the reference wind speed measured by a nearby meteorological station be v0Surface roughness of z0The wind measuring uniform height h is 10 meters; corrected wind speed of the node is v1Surface roughness of z1。
Wind speed variation due to relative altitude variation: setting the relative height between the node and the reference station as delta h, and the wind speed change caused by terrain as delta vh:
Δvh=Δsv0
In the formula: A. and B is a terrain parameter.
Wind speed variation due to variations in ground roughness:
let the variation in wind speed due to variation in roughness be Δ vzAnd calculating a formula:
thus, the nodal corrected wind speed v1Can be expressed by the following formula:
v1=v0+Δvh+Δvz
according to weather and disaster loss historical data, a deep learning network is trained to obtain a disaster loss prediction model of input weather and output disaster loss (load power loss probability of each node of a power distribution network), and current weather data is corrected at a weather station, so that the target of identifying a fault element under a weak communication condition is achieved, the independent power loss probability p of a plurality of source loads of the power distribution network at a single node is obtained, and then the emergency repair after disaster is guided.
The meteorological data here means: real-time wind speed and rainfall intensity of a meteorological station where the power distribution network is located. Therefore, under the weak communication condition, the real-time wind speed and rainfall intensity of the meteorological station where the power distribution network is located are input on line through the offline training deep learning network, and the load power loss probability p of each node is output.
In the actual working process: the invention needs to provide basic information of the power distribution network, including topological structure, importance degree of each node load, unit time power failure loss and the like; it is also necessary to provide historical meteorological data including the most gust wind speed, and the specific work content is as follows:
the method comprises the following steps: acquiring and arranging comprehensive data of the electric quantity of the power distribution network and meteorological stations in the region, wherein the meteorological data comprise multidimensional data such as gust wind speed, air pressure, rainfall intensity and the like; the electrical quantities include node voltage, current, and the like.
Firstly, judging the communication condition of the post-disaster power distribution network, executing a step two if the communication is sound, and executing a step three if the communication of the power distribution network is not sound or the post-disaster communication is damaged (the two conditions are called as weak communication conditions).
Step two: under the condition of sound communication, the node disaster damage condition is identified by using the power distribution network post-disaster topological structure identification method, and a power loss node is output;
specifically, robust communication: judging the load power-loss condition of each node according to the electrical quantity measured by each node; if some nodes have no electricity quantity measuring terminal, the load electricity loss condition of the node is judged according to the meteorological data measured by the node and by combining a stress analysis model.
Step three: under the weak communication condition, the method utilizes a deep learning network to predict the post-disaster loss by combining historical meteorological data and a topological structure, and outputs a power loss node;
specifically, the weak communication condition: real-time weather data such as wind speed, rainfall intensity and the like of a weather station where the power distribution network is located are input into the trained deep learning network, and load power loss probability of each node is output.
Step four: and giving the final multi-source load damage condition of the power distribution network in a risk grade early warning schematic diagram form, and guiding the emergency repair after the disaster.
The invention provides a power distribution network element failure mechanism model under strong typhoon, a post-disaster power distribution network topology identification method, a power distribution network multi-source load damage identification method under sound communication and a power distribution network multi-source load damage identification method under weak communication conditions. When typhoon comes, real-time meteorological data is input, the established model (a mechanism model (P1 and a first-stage formula 2) based on stress analysis is utilized in sound communication, and a trained deep learning network is utilized under weak communication conditions) can be used for predicting the power distribution network disaster damage condition from a future period to the end of the typhoon in a rolling mode, and the method has practical significance for guiding the post-disaster element emergency repair, so that disaster prevention and reduction commanders and power distribution network dispatching departments can make decision and deployment in time, and economic loss and casualties are reduced as far as possible.
The invention can not only identify the power distribution network disaster caused by typhoon under the condition of sound communication, but also correct the current meteorological data by utilizing the deep learning model of inputting weather and outputting the disaster under the condition of weak communication, and identify the fault element under the condition of weak communication so as to achieve the disaster identification.
Particularly, the method is a power distribution network disaster damage identification and recovery strategy under the condition of communication incompleteness in extreme disasters, and has strong practicability.
Example two
It is an object of this embodiment to provide a computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the program.
EXAMPLE III
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
Example four
The purpose of this embodiment is to provide distribution network many first sources disaster and damage self-adaptation identification system under strong typhoon, includes:
a communication failure determination module configured to: carrying out fault judgment on node communication of the power distribution network under strong typhoon;
a first node power loss probability calculation module configured to: if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction;
a second node power loss probability calculation module configured to: if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
The method comprises the steps of carrying out correction based on ground roughness and relative height on wind speed at a representative weather station under the conditions of strong typhoon and weak communication, then introducing a deep learning algorithm, obtaining input weather information based on real-time weather information and historical disaster data, outputting a model for predicting the disaster damage, identifying a multi-source load fault element of a power distribution network under the condition of weak communication, and guiding emergency repair after the disaster.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. The self-adaptive identification method for the multi-source disaster damage of the power distribution network under strong typhoon is characterized by comprising the following steps:
carrying out fault judgment on node communication of the power distribution network under strong typhoon;
if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction;
if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
2. The method for self-adaptive identification of the multiple-source disaster and loss of the power distribution network under the strong typhoon as claimed in claim 1, wherein the topology identification of the multiple-source disaster and loss power distribution network specifically comprises:
acquiring the voltage, the current and the load of each node in the power distribution network in real time;
defining a power distribution network node state matrix S, wherein the S is a 1 x n-order matrix, n elements are all 1 before a disaster occurs, and n nodes are all in a normal power supply state; after the disaster happens, updating the value of the load power-off node corresponding to the matrix S to be 0 according to the load power-off condition;
numbering each node in the power distribution network, and defining a node connection relation matrix; and defining a fault matrix F, and carrying out fault positioning and reason analysis.
3. The method for adaptively identifying the multi-source disaster damage of the power distribution network under the strong typhoon as claimed in claim 2, wherein a fault matrix F is defined, and fault location and cause analysis are performed, wherein the fault location and cause analysis comprise the following steps:
when the fault matrix F is assigned:
when the kth node is power-off, the k-1 node and the k +1 node are normal, and the fault of the transformer at the kth node is indicated;
and searching the superior node number of k and the inferior node number of k by using the connection relation matrix, and then obtaining the value positioned at the (k, k) th coordinate in the fault matrix F.
Preferably, a fault matrix F is defined, fault location and cause analysis are performed, and a second case is further included:
the kth node is powered off, the k-1 node is normal, and the k +1 node is powered off;
traversing all lower nodes of the branch where k is located, and if the nodes are all powered off, determining that a disconnection fault occurs between k and k-1;
if the number of the normal lower-level nodes is not 0, the situation that the transformers at k and k +1 simultaneously have faults is shown.
4. The self-adaptive identification method for the multi-source disaster damage of the power distribution network under the strong typhoon as claimed in claim 3, wherein a fault matrix F is defined, fault location and cause analysis are carried out, and the method further comprises the following steps:
the kth node is powered off, and the k-1 node and the k +1 node are also powered off;
assuming that the upper node of k-1 fails, the specific analysis needs to jump to the node;
and then, circularly judging the first execution condition and the second execution condition until all nodes corresponding to all fault values in the distribution network node state matrix S are traversed once, and finally reflecting the fault positions and the fault types according to the values in the matrix F.
5. The method for adaptively identifying the multi-source load and loss of the power distribution network under the strong typhoon as claimed in claim 1, wherein the obtaining of the node power loss probability through disaster and loss identification and correction specifically comprises:
considering the model of the pole falling and the line breaking, the probability is set as p1And p2And then the independent power loss probability of the multi-element source load single node of the power distribution network is as follows:
p=1-(1-p1)(1-p2)。
6. the method according to claim 1, wherein a deep learning network is trained according to weather and disaster historical data to obtain a deep learning disaster prediction model for inputting weather and outputting disaster.
7. The self-adaptive identification method for the multi-source disaster damage of the power distribution network under the strong typhoon as claimed in claim 1, wherein the wind speed in the multi-dimensional original meteorological information is corrected by considering the ground roughness and the relative height, and the method specifically comprises the following steps:
setting the reference wind speed measured by a nearby meteorological station asv0Surface roughness of z0Measuring the wind with uniform height h meters; corrected wind speed of the node is v1Surface roughness of z1;
Wind speed variation due to relative altitude variation: setting the relative height between the node and the reference station as delta h, and the wind speed change caused by terrain as delta vh;
Wind speed variation due to variations in ground roughness: let the variation in wind speed due to variation in roughness be Δ vz;
The wind speed v after the node correction1Can be expressed by the following formula:
v1=v0+Δvh+Δvz。
8. distribution network many sources disaster and damage self-adaptation identification system under strong typhoon, characterized by includes:
a communication failure determination module configured to: carrying out fault judgment on node communication of the power distribution network under strong typhoon;
a first node power loss probability calculation module configured to: if no communication fault exists, carrying out multi-source load distribution network topology identification by utilizing the collected node electrical quantity information of the distribution network to obtain a fault type and a fault position, and then obtaining a node power loss probability through disaster damage identification and correction;
a second node power loss probability calculation module configured to: if communication faults exist, obtaining multi-dimensional original meteorological information and node information, correcting the wind speed in the multi-dimensional original meteorological information by considering the ground roughness and the relative height to obtain a corrected data sequence, inputting the corrected data sequence into a deep learning disaster damage prediction model to obtain the post-disaster situation and the node element damage situation of a certain time in the future, and then obtaining the independent power loss probability of a single node of the multi-element source load of the power distribution network by utilizing topology identification of the power distribution network.
9. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of the preceding claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210109162.3A CN114417732A (en) | 2022-01-28 | 2022-01-28 | Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210109162.3A CN114417732A (en) | 2022-01-28 | 2022-01-28 | Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114417732A true CN114417732A (en) | 2022-04-29 |
Family
ID=81280121
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210109162.3A Pending CN114417732A (en) | 2022-01-28 | 2022-01-28 | Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114417732A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115021415A (en) * | 2022-08-01 | 2022-09-06 | 国网浙江省电力有限公司台州供电公司 | Power system anti-typhoon method and platform based on digital live data |
CN116660680A (en) * | 2023-05-31 | 2023-08-29 | 国家电网有限公司 | Node power line communication-based power outage event studying and judging method |
-
2022
- 2022-01-28 CN CN202210109162.3A patent/CN114417732A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115021415A (en) * | 2022-08-01 | 2022-09-06 | 国网浙江省电力有限公司台州供电公司 | Power system anti-typhoon method and platform based on digital live data |
CN115021415B (en) * | 2022-08-01 | 2022-10-25 | 国网浙江省电力有限公司台州供电公司 | Power system anti-typhoon method and platform based on digital live data |
CN116660680A (en) * | 2023-05-31 | 2023-08-29 | 国家电网有限公司 | Node power line communication-based power outage event studying and judging method |
CN116660680B (en) * | 2023-05-31 | 2024-05-24 | 国家电网有限公司 | Node power line communication-based power outage event studying and judging method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112365100B (en) | Disaster risk comprehensive assessment-based power grid disaster early warning and response method | |
CN114417732A (en) | Self-adaptive identification method and system for multi-source load damage of power distribution network under strong typhoon | |
CN110705873B (en) | Power distribution network running state portrait analysis method | |
CN107862763B (en) | Train safety early warning evaluation model training method, module and monitoring evaluation system | |
CN113759868B (en) | Industrial Ethernet fault prediction method based on neural network | |
CN116451876B (en) | Power distribution network fault prediction and active overhaul system based on artificial intelligence | |
CN104218570A (en) | Method and system for online evaluating overall measuring errors of electric energy measuring device | |
CN111860943A (en) | Power grid fault prediction method and system based on numerical meteorological data and machine learning | |
CN111488896A (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
CN113988655A (en) | Power transmission line running state evaluation method considering multiple meteorological factors | |
CN112116160A (en) | Important power transmission channel disaster monitoring method based on optimized neural network improved cellular automaton | |
CN110412417B (en) | Micro-grid data fault diagnosis method based on intelligent power monitoring instrument | |
CN111126672A (en) | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree | |
CN113987724A (en) | Power grid risk identification method and system based on topology analysis | |
CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
CN105958474B (en) | Dynamic capacity increasing method and system for power transmission line for power grid regulation and control system | |
CN116591768A (en) | Tunnel monitoring method, system and device based on distributed network | |
Kowalski et al. | The comparison of linear models for PM10 and PM2. 5 forecasting | |
CN114266370A (en) | Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium | |
CN115906639A (en) | Line operation fault rate prediction method and device based on line operation working conditions | |
CN112001073B (en) | Reliability analysis and research method for traction power supply system | |
CN114969068A (en) | Method and system for analyzing real-time flow monitoring data of urban pressure pipe network | |
CN111651493B (en) | Full life cycle forward guidance and feedback optimization management method of passenger lifting equipment | |
CN113541211A (en) | Method and system for determining toughness of alternating current-direct current power distribution network | |
CN111857015A (en) | Power transmission and transformation cloud intelligent controller |
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 |