CN111313403B - Markov random field-based network topology identification method for low-voltage power distribution system - Google Patents
Markov random field-based network topology identification method for low-voltage power distribution system Download PDFInfo
- Publication number
- CN111313403B CN111313403B CN202010119754.4A CN202010119754A CN111313403B CN 111313403 B CN111313403 B CN 111313403B CN 202010119754 A CN202010119754 A CN 202010119754A CN 111313403 B CN111313403 B CN 111313403B
- Authority
- CN
- China
- Prior art keywords
- node
- voltage
- distribution system
- power distribution
- data
- 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
- 238000009826 distribution Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005290 field theory Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
Abstract
The application discloses a network topology identification method of a low-voltage distribution system based on a Markov random field, which comprises the steps of (1) firstly acquiring voltage time sequence data of a user intelligent ammeter and TTU (time to unit) voltage time sequence data of a distribution transformer, and carrying out preprocessing such as noise reduction, feature extraction and the like on the acquired data; (2) After data preprocessing, modeling a power distribution system network structure by using a Markov random field, and establishing joint probability distribution for describing the correlation between nodes in a power distribution network; (3) The application utilizes known data such as historical ammeter voltage data and the like to develop and identify the low-voltage distribution network structure, does not need newly-added equipment, reduces investment and has higher identification accuracy.
Description
Technical Field
The application relates to the technical field of power distribution of power systems, in particular to a method for identifying a low-voltage distribution network topology by using a Markov random field based on historical data of a user intelligent ammeter.
Background
At present, the domestic and foreign medium-high voltage power distribution systems are provided with complete power distribution management systems, and a series of data such as a power distribution network topological structure, an operation state, a load state and the like are acquired through a data acquisition and monitoring control system and a geographic information system, so that state evaluation is realized; and various distribution network analysis and decision algorithms are established based on the method, including a random optimization scheduling method of the distribution network for processing the load and the uncertainty of renewable energy sources in the distribution network, a reconstruction method of the distribution network for aiming at fault recovery or three-phase imbalance management, and the like.
In contrast, low voltage power distribution systems face limited information environments, lack of efficient system modeling and state assessment methods, and difficulty in deploying power distribution system power flow calculations and other power distribution management advanced functions. In particular, the topology modeling of the low-voltage power distribution system is a foundation for establishing the optimal power flow of the low-voltage power distribution system, and is also a foundation for solving a series of problems such as three-phase imbalance, network loss, renewable energy source consumption, electric vehicle charging load acceptance, user electricity reliability improvement and the like of the low-voltage power distribution system. Therefore, identifying the topology of the distribution network is a prerequisite for achieving visualization and management of the low voltage distribution system. Considering that the operation data which can be obtained in the low-voltage power distribution system is very limited, how to effectively utilize the intelligent ammeter data and the distribution transformer operation data to realize the topology identification of the power distribution system, and the establishment of a basic operation model of the power distribution system is the primary aim of developing the low-voltage power distribution system at present.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above-mentioned problems associated with the conventional markov random field-based network topology identification method for a low voltage power distribution system.
Therefore, the application aims to provide a network topology identification method of a low-voltage distribution system based on a Markov random field, which utilizes known data such as historical ammeter voltage data and the like to develop and identify a low-voltage distribution network structure, does not need newly-added equipment, reduces investment and has higher identification accuracy.
In order to solve the technical problems, the application provides the following technical scheme: the method for identifying the network topology of the low-voltage power distribution system based on the Markov random field comprises the following steps:
(1) Acquiring voltage time sequence data of a user intelligent ammeter and TTU voltage time sequence data of a distribution transformer;
(2) Performing first-order difference and box division processing and single-heat coding processing on the voltage data obtained in the step (1);
(3) Modeling a power distribution system network structure by using a Markov random field, and establishing joint probability distribution for describing the correlation between nodes in the power distribution system network structure;
(4) Solving the joint probability distribution by a maximum likelihood estimation method to obtain a correlation matrix among nodes of a network structure of the power distribution system;
(5) And establishing an adjacency matrix of the network structure of the power distribution system according to the node correlation matrix.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: in the step (1), the required number of samples for data acquisition is more than 500 time sections.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: the data preprocessing in the step (2) specifically comprises:
step 2.1: performing first-order forward difference on the voltage data acquired in the step (1) in time sequence, wherein the calculation expression is as follows:
V i _Diff＝V i (t)-V i (t-1)
wherein Vi (t) represents the voltage of the node i at the time t, vi (t-1) represents the voltage of the node i at the time t-1, and the calculated result is stored in Vi_Diff, wherein Vi_Diff represents the voltage forward differential data of the node i;
step 2.2: after the first order difference of step 2.1 is completed, the obtained voltage data vi_diff is subjected to binning processing, and discrete data are converted into integer codes of 0,1,2, … and N, and the binning processing is as follows:
wherein V is max Diff and V min Diff means the maximum and minimum of the voltage of each node in the next time section after the first-order forward difference, respectively, []For rounding the symbol, storing a calculation result in Bin_Vi, wherein Bin_Vi represents Bin data obtained by the voltage forward differential data of the node i;
step 2.3: after the two-step data preprocessing, finally carrying out one-time encoding on the data Bin_Vi, adopting an N-bit state register to encode N states, wherein each state has independent register bits, only one bit is valid at any time, N bits corresponding to the nth state are 1, the other bits are zero, and storing the information of the encoded i node in X i As an input variable to node i.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: in step 2.2, the voltage data is divided into 21 different states between 0 and 20, bin_vi=n, n=0, 1,2, …,20.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: the markov random field modeling of step (3) specifically includes:
step 3.1: defining a distribution system network structure as a four-tuple m= (X, E, Φ, ψ), wherein (X, E) is an undirected random variable image; x is a top point set of the graph, represents nodes in the power distribution system, E is an edge set of the graph, and represents power lines connecting the nodes of the power distribution system; and then respectively establishing potential functions phi and ψ describing the relation between the power distribution system nodes and the connecting lines to quantitatively describe the variable characteristics of the power distribution network nodes and the connecting lines, wherein the potential functions describing the relation between the power distribution system nodes and the connecting lines are respectively defined as follows:
Φ(X s )＝exp{E(X s )}
Ψ(X st )＝exp{E(X s ,X t )}
wherein X is s And X t The random variables representing node X and node s, respectively, X st Representing the random variable corresponding to the edge connecting node s and node t, E being referred to as the energy function, parameterized formThe following is shown:
E(X s )＝V s d s (X s )
d in s Called state features, which are feature functions defined on nodes, taking into account only the current node, b st Called transfer features, which are feature functions defined on edges, V s Is the weight of a node s in the power distribution system, W st Is the weight of the line connecting the nodes s and t;
step 3.2: after modeling of the individual nodes and the connected nodes is completed, a joint probability distribution describing all nodes in the whole power distribution system, namely the correlation of the whole topological network is built as follows:
wherein Z is a partition function, which is a normalization factor, normalization function, which functions to ensure that P (Y) forms a joint probability distribution, defined as the sum of all possible assignments.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: the solving of the joint probability distribution of the network structure of the power distribution system in the step (4) specifically comprises the following steps:
step 4.1: solving the joint probability distribution by using a maximum likelihood estimation method as follows:
where ll (Θ) =log P (Y) is a log-likelihood form of P (Y);
step 4.2 rootAccording to the node correlation probability obtained by the above solution, solving an objective function according to the voltage data obtained in the step (1) by using a gradient descent algorithmObtaining an edge weight parameter W;
step 4.3, weighting parameter W ij st According toSynthesizing to obtain a node correlation matrix K representing the connection relation of each node in the power distribution network, wherein K is the node correlation matrix, and K st Is the element in K, W ij st Is the weight of the line connecting the nodes s, t, e is a natural constant.
As a preferable scheme of the low-voltage distribution system network topology identification method based on the Markov random field, the application comprises the following steps: and (5) connecting the nodes with the largest correlation in the node correlation matrix K, namely setting the element at the position where the largest correlation is positioned as 1, and setting the other elements as 0, and finally obtaining the adjacent matrix of the low-voltage distribution system network structure.
The application has the beneficial effects that: the traditional power distribution network structure identification method needs to know part of power distribution network structures, and the method can directly generate the topological structure of the low-voltage power distribution network according to the known historical voltage data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a flowchart of a method for topology learning of a power distribution network based on markov random fields.
FIG. 2 is a diagram illustrating the single-hot encoding of pre-processed data.
Fig. 3 is a schematic diagram of an algorithm implementation process.
Fig. 4 is an IEEE123 node authentication result.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Further, in describing the embodiments of the present application in detail, the cross-sectional view of the device structure is not partially enlarged to a general scale for convenience of description, and the schematic is only an example, which should not limit the scope of protection of the present application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Example 1
Referring to fig. 1, for a first embodiment of the present application, there is provided a method for identifying a network topology of a low voltage power distribution system based on a markov random field, the method comprising the steps of:
(1) The method comprises the steps of obtaining voltage time sequence data of a user intelligent electric meter and TTU voltage time sequence data of a distribution transformer, wherein the number of required samples for data acquisition is more than 500 time sections, the required data are continuous, no missing value and abnormal value exist, and the obtained data are mainly the existing data uploaded by the electric meter.
(2) And (3) performing first-order difference, box division and independent heat coding on the voltage data obtained in the step (1).
The data preprocessing in the step (2) specifically comprises:
step 2.1: performing first-order forward difference on the voltage data acquired in the step (1) in time sequence, extracting voltage variation characteristics, and reducing the influence of measurement noise, wherein the calculation expression is as follows:
V i _Diff＝V i (t)-V i (t-1)
wherein Vi (t) represents the voltage of the node i at the time t, vi (t-1) represents the voltage of the node i at the time t-1, and the calculated result is stored in Vi_Diff, wherein Vi_Diff represents the voltage forward differential data of the node i;
step 2.2: after the first-order difference in the step 2.1 is completed, the obtained voltage data Vi_Diff is subjected to the binning treatment, so that the iteration speed of the model can be increased after the data is subjected to the binning treatment, and the influence caused by measurement noise is reduced. Based on the problem of retention of the data bit number of the actual ammeter, the numerical value is transformed to a scale similar to the actual ammeter after the binning process. Discrete data is transformed into integer encodings of 0,1,2, …, N during the binning process. The application divides the voltage data into 21 different states between 0 and 20, and the box division processing process is as follows:
wherein V is max Diff and V min Diff means the maximum and minimum of the voltage of each node in the next time section after the first-order forward difference, respectively, []To round the sign, the calculation result is stored in bin_vi, which represents Bin data obtained from the voltage forward differential data of node i, bin_vi=n, n=0, 1,2, …,20.
Step 2.3: after the two-step data preprocessing, the data Bin_Vi is finally subjected to one-hot coding, N states are coded by adopting an N-bit state register, and each state is codedHaving independent register bits, and only one bit being valid at any time, n bits corresponding to the nth state being 1, the other bits being zero, storing the encoded information of the i-node in X i As an input variable to node i.
(3) Modeling the power distribution system network structure by using the Markov random field, and establishing joint probability distribution for describing the correlation between nodes in the power distribution system network structure.
The markov random field modeling of step (3) specifically includes:
step 3.1: defining a distribution system network structure as a four-tuple m= (X, E, Φ, ψ), wherein (X, E) is an undirected random variable image; x is a top point set of the graph, represents nodes in the power distribution system, E is an edge set of the graph, and represents power lines connecting the nodes of the power distribution system; and then respectively establishing potential functions phi and ψ describing the relation between the power distribution system nodes and the connecting lines to quantitatively describe the variable characteristics of the power distribution network nodes and the connecting lines, wherein the potential functions describing the relation between the power distribution system nodes and the connecting lines are respectively defined as follows:
Φ(X s )＝exp{E(X s )}
Ψ(X st )＝exp{E(X s ,X t )}
wherein X is s And X t The random variables representing node X and node s, respectively, X st The random variable, E, representing the edge connecting node s and node t is called the energy function, and the parameterization is as follows:
E(X s )＝V s d s (X s )
d in s Called state features, which are feature functions defined on nodes, taking into account only the current node, b st Called transfer features, which are feature functions defined on edges, V s Is the weight of a node s in the power distribution system, W st Is the weight of the line connecting the nodes s and t;
step 3.2: after modeling of a single node and connected nodes is completed, the joint probability distribution based on a plurality of variables in the Markov random field theory can be decomposed into products of a plurality of potential functions, and then the joint probability distribution capable of describing all nodes in the whole power distribution system, namely the correlation relationship of the whole topological network is established, as follows:
the parameterization form is as follows:
wherein Z is a partition function, which is a normalization factor, normalization function, which functions to ensure that P (Y) forms a joint probability distribution, defined as the sum of all possible assignments.
(4) And solving the joint probability distribution by using a maximum likelihood estimation method to obtain a correlation matrix among the nodes of the network structure of the power distribution system.
The solving of the joint probability distribution of the network structure of the power distribution system in the step (4) specifically comprises the following steps:
step 4.1: solving the joint probability distribution by using a maximum likelihood estimation method as follows:
where ll (Θ) =log P (Y) is a log-likelihood form of P (Y);
step 4.2, according to the node correlation probability obtained by the previous step, using a gradient descent algorithm, and according to the voltage data obtained in the step (1)Solving an objective functionObtaining an edge weight parameter W, wherein the edge weight obtained by calculation is a weight matrix of N-bit single-heat codes among nodes:
step 4.3, weighting parameter W ij st According toSynthesizing to obtain a node correlation matrix K representing the connection relation of each node in the power distribution network, wherein K is the node correlation matrix, and K st Is the element in K, W ij st Is the weight of the line connecting the nodes s, t, e is a natural constant.
(5) And establishing an adjacency matrix of the network structure of the power distribution system according to the node correlation matrix. And connecting the nodes with the largest correlation in the node correlation matrix K, namely setting the position element with the largest correlation as 1 and setting the other position element with the largest correlation as 0, and finally obtaining the adjacent matrix of the network structure of the low-voltage distribution system.
To verify the accuracy of this method we selected the IEEE123 standard node for testing. Firstly, active and reactive data of each node under 500 time sections are randomly generated according to a Monte Carlo method, then voltage time sequences of each node are obtained through power flow calculation, and then the obtained voltage time sequences are calculated by adopting the algorithm, so that a node connection matrix is obtained as shown in figure 4. The connection relation obtained by the method is compared with an IEEE123 standard node, and the accuracy reaches 100%.
It should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application, which is intended to be covered in the scope of the claims of the present application.
Claims (3)
1. A low-voltage distribution system network topology identification method based on a Markov random field is characterized by comprising the following steps of: the method comprises the following steps:
(1) Acquiring voltage time sequence data of a user intelligent ammeter and TTU voltage time sequence data of a distribution transformer;
(2) Performing first-order difference and box division processing and single-heat coding processing on the voltage data obtained in the step (1);
(3) Modeling a power distribution system network structure by using a Markov random field, and establishing joint probability distribution for describing the correlation between nodes in the power distribution system network structure;
(4) Solving the joint probability distribution by a maximum likelihood estimation method to obtain a correlation matrix among nodes of a network structure of the power distribution system;
(5) Establishing an adjacency matrix of a power distribution system network structure according to the node correlation matrix;
the data preprocessing in the step (2) specifically comprises:
step 2.1: performing first-order forward difference on the voltage data acquired in the step (1) in time sequence, wherein the calculation expression is as follows:
Vi_Diff＝Vi(t)-Vi(t-1)
wherein Vi (t) represents the voltage of the node i at the time t, vi (t-1) represents the voltage of the node i at the time t-1, and the calculated result is stored in Vi_Diff, wherein Vi_Diff represents the voltage forward differential data of the node i;
step 2.2: after the first order difference of step 2.1 is completed, the obtained voltage data vi_diff is subjected to binning processing, and discrete data are converted into integer codes of 0,1,2, … and N, and the binning processing is as follows:
wherein, vmax_Diff and Vmin_Diff respectively refer to the maximum value and the minimum value of the voltage of each node in the next time section of the first-order forward difference, [ ] is a rounding symbol, the calculation result is stored in Bin_Vi, and Bin_Vi represents the sub-box data obtained by the voltage forward difference data of the node i;
step 2.3: after the two-step data preprocessing, carrying out single-heat encoding on the data Bin_Vi, and encoding N states by adopting an N-bit state register, wherein each state has independent register bits, only one bit is valid at any time, N bits corresponding to the nth state are 1, other bits are zero, and the information of the encoded i node is stored in Xi to be used as an input variable of a node i;
in step 2.2, the voltage data is divided into 21 different states between 0 and 20, bin_vi=n, n=0, 1,2, …,20;
the markov random field modeling of step (3) specifically includes:
step 3.1: defining a distribution system network structure as a four-tuple m= (X, E, Φ, ψ), wherein (X, E) is an undirected random variable image; x is a top point set of the graph, represents nodes in the power distribution system, E is an edge set of the graph, and represents power lines connecting the nodes of the power distribution system; and then respectively establishing potential functions phi and ψ describing the relation between the power distribution system nodes and the connecting lines to quantitatively describe the variable characteristics of the power distribution network nodes and the connecting lines, wherein the potential functions describing the relation between the power distribution system nodes and the connecting lines are respectively defined as follows:
Φ(X s )＝exp{E(X s )}
Ψ(X st )＝exp{E(X s ，X t )}
wherein X is s And X t The random variables representing node X and node s, respectively, X st The random variable, E, representing the edge connecting node s and node t is called the energy function, and the parameterization is as follows:
s s
E(X s )＝Vd(X s )
d in s Referred to as state features, defined on nodesFeature function, consider only the current node, b st Called transfer features, which are feature functions defined on edges, V s Is the weight of a node s in the power distribution system, W st Is the weight of the line connecting the nodes s and t;
step 3.2: after modeling of the individual nodes and the connected nodes is completed, a joint probability distribution describing all nodes in the whole power distribution system, namely the correlation of the whole topological network is built as follows:
wherein Z is a partition function, which is a normalization factor, normalization function, which functions to ensure that P (Y) forms a joint probability distribution, defined as the sum of all possible assignments.
2. The method for identifying network topology of a markov random field based low voltage power distribution system of claim 1, wherein: in the step (1), the required number of samples for data acquisition is more than 500 time sections.
3. The method for identifying network topology of a markov random field based low voltage power distribution system of claim 1, wherein: the solving of the joint probability distribution of the network structure of the power distribution system in the step (4) specifically comprises the following steps:
step 4.1: solving the joint probability distribution by using a maximum likelihood estimation method as follows:
where ll (Θ) =log P (Y) is a log-likelihood form of P (Y);
step 4.2, according to the node correlation probability obtained by the solution in the previous step, using a gradient descent algorithm to solve an objective function according to the voltage data obtained in the step 1,
obtaining an edge weight parameter W;
step 4.3, weighting parametersAccording to->Synthesizing to obtain a node correlation matrix K representing the connection relation of each node in the power distribution network, wherein K is the node correlation matrix, and K st Is the element in K, ">Is the weight of the line connecting the nodes s and t, and e is a natural constant;
and (5) connecting the nodes with the largest correlation in the node correlation matrix K, namely setting the element at the position where the largest correlation is positioned as 1, and setting the other elements as 0, and finally obtaining the adjacent matrix of the low-voltage distribution system network structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010119754.4A CN111313403B (en) | 2020-02-26 | 2020-02-26 | Markov random field-based network topology identification method for low-voltage power distribution system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010119754.4A CN111313403B (en) | 2020-02-26 | 2020-02-26 | Markov random field-based network topology identification method for low-voltage power distribution system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111313403A CN111313403A (en) | 2020-06-19 |
| CN111313403B true CN111313403B (en) | 2023-11-03 |
Family
ID=71158426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010119754.4A Active CN111313403B (en) | 2020-02-26 | 2020-02-26 | Markov random field-based network topology identification method for low-voltage power distribution system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111313403B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111709587B (en) * | 2020-06-22 | 2022-05-24 | 国网山西省电力公司电力科学研究院 | Power distribution system state probability evaluation method based on probability-time sequence uncertainty |
| CN113809747B (en) * | 2021-11-19 | 2022-02-15 | 长沙理工大学 | Power distribution network topology identification method, electronic equipment and medium |
| CN117169716B (en) * | 2023-09-07 | 2024-02-27 | 江苏省特种设备安全监督检验研究院 | Motor health diagnosis system based on Markov random field algorithm |
| CN116933104B (en) * | 2023-09-19 | 2023-12-01 | 北京前景无忧电子科技股份有限公司 | Topology identification method for low-voltage distribution network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109274095A (en) * | 2018-10-30 | 2019-01-25 | 东北大学秦皇岛分校 | Low-voltage distribution network users topology estimation method and system based on mutual information |
| CN110190600A (en) * | 2019-06-21 | 2019-08-30 | 国网天津市电力公司 | It is a kind of to measure the three-phase distribution net topology discrimination method that neighbour returns based on AMI |
| CN110323740A (en) * | 2019-06-24 | 2019-10-11 | 中国农业大学 | The economical peak load regulation method of meter and photovoltaic power output and air conditioner load dynamic correlation |
| CN110568265A (en) * | 2019-10-17 | 2019-12-13 | 江苏远致能源科技有限公司 | Impedance identification method and system based on low-voltage distribution network |
-
2020
- 2020-02-26 CN CN202010119754.4A patent/CN111313403B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109274095A (en) * | 2018-10-30 | 2019-01-25 | 东北大学秦皇岛分校 | Low-voltage distribution network users topology estimation method and system based on mutual information |
| CN110190600A (en) * | 2019-06-21 | 2019-08-30 | 国网天津市电力公司 | It is a kind of to measure the three-phase distribution net topology discrimination method that neighbour returns based on AMI |
| CN110323740A (en) * | 2019-06-24 | 2019-10-11 | 中国农业大学 | The economical peak load regulation method of meter and photovoltaic power output and air conditioner load dynamic correlation |
| CN110568265A (en) * | 2019-10-17 | 2019-12-13 | 江苏远致能源科技有限公司 | Impedance identification method and system based on low-voltage distribution network |
Non-Patent Citations (2)
| Title |
|---|
| Identification of power disitribution network topology via voltage correlation nanlysis;Saverio Bolognani;《52nd IEEE Conference on Decision and Control》;第1659-1664页 * |
| 陶启放.基于Markov随机场的机器视觉设计及应用.《中国优秀硕士学位论文全文数据库信息科技辑》.2018,(第undefined期),第I138-605页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111313403A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111313403B (en) | Markov random field-based network topology identification method for low-voltage power distribution system | |
| CN109685314B (en) | Non-intrusive load decomposition method and system based on long-term and short-term memory network | |
| CN109002933B (en) | Distribution line route variable relation model optimization method based on Relieff and t-SNE | |
| CN111880044B (en) | Online fault positioning method for distribution network containing distributed power supply | |
| CN111401757B (en) | Multi-region power load time sequence scene modeling method considering time-space correlation | |
| CN113141008B (en) | Data-driven power distribution network distributed new energy consumption capability assessment method | |
| CN111159638A (en) | Power distribution network load missing data recovery method based on approximate low-rank matrix completion | |
| CN110739692B (en) | Power distribution network structure identification method based on probability map model | |
| CN109412161A (en) | A kind of Probabilistic Load calculation method and system | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN112381673A (en) | Park electricity utilization information analysis method and device based on digital twin | |
| CN112803398A (en) | Load prediction method and system based on empirical mode decomposition and deep neural network | |
| CN116843083A (en) | Carbon emission prediction system and method based on hybrid neural network model | |
| CN114330642A (en) | Building power load prediction method for multiple sampling times | |
| CN111199363B (en) | Method for realizing topology recognition by maximum correlation screening algorithm | |
| CN112595918A (en) | Low-voltage meter reading fault detection method and device | |
| CN115936926A (en) | SMOTE-GBDT-based unbalanced electricity stealing data classification method and device, computer equipment and storage medium | |
| CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
| CN111193254A (en) | Residential daily electricity load prediction method and device | |
| CN113158134B (en) | Method, device and storage medium for constructing non-invasive load identification model | |
| CN115600494A (en) | Low-voltage distribution area topology automatic identification method and device | |
| CN116128211A (en) | Wind-light-water combined short-term optimization scheduling method based on wind-light uncertainty prediction scene | |
| CN113515890B (en) | Renewable energy day-ahead scene generation method based on federal learning | |
| CN115564180A (en) | Power network reliability assessment method based on big data analysis | |
| CN114759579A (en) | Power grid active power optimization control system, method and medium based on data driving |
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 |