CN110334932B - Power grid node importance degree evaluation method, computer equipment and storage medium - Google Patents
Power grid node importance degree evaluation method, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110334932B CN110334932B CN201910565287.5A CN201910565287A CN110334932B CN 110334932 B CN110334932 B CN 110334932B CN 201910565287 A CN201910565287 A CN 201910565287A CN 110334932 B CN110334932 B CN 110334932B
- Authority
- CN
- China
- Prior art keywords
- power grid
- grid node
- node information
- data
- obtaining
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 91
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 73
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000007621 cluster analysis Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 135
- 238000005259 measurement Methods 0.000 claims description 33
- 210000000349 chromosome Anatomy 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012216 screening Methods 0.000 claims description 14
- 230000014509 gene expression Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 239000002096 quantum dot Substances 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 5
- 238000013210 evaluation model Methods 0.000 abstract description 17
- 230000008901 benefit Effects 0.000 abstract description 7
- 238000004422 calculation algorithm Methods 0.000 description 13
- 239000002243 precursor Substances 0.000 description 10
- 238000005457 optimization Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Complex Calculations (AREA)
Abstract
The invention provides a power grid node importance degree evaluation method, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining power grid node information according to the power grid data information; preprocessing the power grid node information to obtain training data; performing clustering analysis processing on the training data to obtain clustering data; obtaining a membership function according to the clustering data; initializing the rule parameters of the membership function to obtain initialized rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters, performing cluster analysis processing on the power grid node information, and constructing the membership function to construct a power grid node importance evaluation model, thereby obtaining the power grid node evaluation value function, namely forming a multi-rule power grid node importance evaluation model to realize comprehensive evaluation of the power grid node importance, effectively preventing power grid cascading faults, guaranteeing safe and stable operation of a power grid, and ensuring the economic benefit of a power grid enterprise.
Description
Technical Field
The invention relates to the technical field of energy system application, in particular to a power grid node importance degree evaluation method, computer equipment and a storage medium.
Background
The power grid structure of China is huge and complex, the occurrence rate of power failure accidents is increased by a large-scale internet power system, and the large-scale power failure accidents seriously endanger the safe and stable operation of the power grid, thus seriously affecting the national economic safety and social safety of China. The main causes of the power failure accident can be summarized into three aspects: firstly, internal faults of a power grid system, such as element equipment faults, overload, communication system faults, system protection faults and the like; secondly, human factors such as misoperation of operators, artificial deliberate destruction and the like; and thirdly, natural factors, such as natural disasters, including earthquakes, typhoons, floods, ice disasters and the like. The large-scale power failure accident is usually caused by that an important node in a power grid is out of operation due to a power failure fault source, so that a cascading fault is caused. Therefore, in order to improve the overall safe operation of the power grid system, the evaluation of the importance of the power grid nodes is of great practical significance in terms of the requirements of prevention before occurrence of an accident and quick recovery after occurrence of the accident.
At present, the domestic and foreign research on the power grid network is mainly related research based on a complex network theory, namely, the power grid network topology structure based on the complex network is constructed by combining the characteristics of a power grid system, and the main characteristics of the power grid network topology structure comprise the following points: firstly, only a high-voltage transmission network is considered, and main wiring of a distribution network, a power plant and a transformer substation is not considered; secondly, generators, power transformation and intermediate electrical connection points in the power grid are abstracted into undifferentiated nodes, and earth zero points are not considered; thirdly, the power transmission line and the transformer branch are abstracted to be sides without right and direction, and the difference between the voltage level and the characteristic parameters of the power transmission line is not considered; fourthly, the transmission lines on the same tower are combined, the parallel capacitor branches are not counted, namely, the importance of the power grid nodes is researched from the aspects of network topology structure, dynamics property and the like. For the evaluation method of the importance of the power grid node, an betweenness method, a node deletion method, a shortest path method, a network aggregation method, a factor analysis method and the like are generally adopted. However, the above methods are often single in evaluation index, and have certain limitations in addressing specific problems. The modern power system has a complex structure, and the single index evaluation result is one-sided, so that the importance of each node in the power grid cannot be effectively evaluated.
Disclosure of Invention
Based on this, it is necessary to provide a power grid node importance degree evaluation method, a computer device, and a storage medium, which can realize accurate evaluation of the importance degree of a power grid node and provide guarantee for safe and stable operation of a power grid.
In one embodiment, a method for evaluating importance of a power grid node is provided, which includes: obtaining power grid node information according to the power grid data information; preprocessing the power grid node information to obtain training data; performing clustering analysis processing on the training data to obtain clustering data; obtaining a membership function according to the clustering data; initializing the rule parameters of the membership function to obtain initialized rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters.
In one embodiment, the step of obtaining the grid node information according to the grid data information includes: obtaining a power grid topological structure according to the power grid data information; and obtaining power grid node information according to the power grid topological structure.
In one embodiment, the step of preprocessing the power grid node information to obtain a training data set comprises the steps of obtaining an importance measurement index value of the power grid node information according to the power grid node information; and screening the power grid node information according to the importance measurement index value to obtain the training data.
In one embodiment, the step of screening the grid node information according to the importance measure index value to obtain the training number includes: arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; and obtaining the training data according to the first power grid node information and the second power grid node information.
In one embodiment, the step of performing cluster analysis on the training data to obtain cluster data includes: and performing clustering analysis processing on the training data based on a quantum evolution algorithm to obtain clustering data.
In one embodiment, the step of obtaining a membership function according to the clustering data includes: and substituting the clustering data into a Gaussian function to obtain a membership function.
In one embodiment, the step of obtaining the power grid node evaluation value function according to the membership function and the initialized rule parameter includes: updating and optimizing the initialized rule parameters to obtain updated rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters.
In one embodiment, a grid node importance evaluation apparatus is provided, the apparatus comprising: the device comprises a power grid node information acquisition module, a preprocessing module, a cluster analysis module, a membership function acquisition module, an initialization module and an evaluation value function acquisition module.
The power grid node information acquisition module is used for acquiring power grid node information according to the power grid data information; the preprocessing module is used for preprocessing the power grid node information to obtain training data; the clustering analysis module is used for carrying out clustering analysis processing on the training data to obtain clustering data; the membership function obtaining module is used for obtaining a membership function according to the clustering data; the initialization module is used for initializing the rule parameters of the membership function to obtain initialized rule parameters; and the evaluation value function acquisition module is used for acquiring a power grid node evaluation value function according to the membership function and the initialized rule parameters.
In one embodiment, a computer device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any of the above embodiments when executing the computer program.
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 method of any of the above embodiments.
According to the power grid node importance evaluation method, the power grid node information is subjected to clustering analysis and processing, a membership function is constructed, a power grid node importance evaluation model is constructed, the power grid node evaluation function is obtained by initializing the rule parameters of the membership function, and the multi-rule power grid node importance evaluation model is formed, so that the comprehensive evaluation of the power grid node importance is realized, the power grid cascading failure is effectively prevented, the safe and stable operation of the power grid is guaranteed, and the economic benefit of a power grid enterprise is guaranteed.
Drawings
Fig. 1 is a schematic flow chart of a power grid node importance degree evaluation method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a power grid node importance degree evaluation apparatus according to an embodiment of the present invention;
fig. 3 is an internal structural diagram of a computer device in one embodiment of the present invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
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. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Before describing in detail embodiments that are in accordance with the present invention, it should be observed that the embodiments reside primarily in combinations of steps and apparatus components related to a grid node importance assessment method, apparatus, computer device, and storage medium. Accordingly, the apparatus components and method steps have been represented where appropriate by conventional symbols in the drawings, showing only those details that are pertinent to understanding the embodiments of the present invention so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.
In this document, relational terms such as left and right, top and bottom, front and back, first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
For example, a method for evaluating importance of a grid node is provided, which includes: obtaining power grid node information according to the power grid data information; preprocessing the power grid node information to obtain training data; performing clustering analysis processing on the training data to obtain clustering data; obtaining a membership function according to the clustering data; initializing the rule parameters of the membership function to obtain initialized rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters.
According to the power grid node importance evaluation method, the power grid node information is subjected to clustering analysis and processing, a membership function is constructed, a power grid node importance evaluation model is constructed, the power grid node evaluation function is obtained by initializing the rule parameters of the membership function, and the multi-rule power grid node importance evaluation model is formed, so that the comprehensive evaluation of the power grid node importance is realized, the power grid cascading failure is effectively prevented, the safe and stable operation of the power grid is guaranteed, and the economic benefit of a power grid enterprise is guaranteed.
In one embodiment, please refer to fig. 1, which provides a method for evaluating importance of grid nodes, including:
and step 110, obtaining power grid node information according to the power grid data information.
Specifically, the grid data information is grid data of a certain area, for example, western grid data information of the united states. A transformer or a transformer substation is regarded as a node, a supply line between electric power is regarded as an edge, and data of a regional power grid is abstracted into a undirected network. In this way, the information of each grid node may be obtained according to the grid data information, and in an embodiment, the step of obtaining the grid node information according to the grid data information further includes obtaining the grid data information. In one embodiment, the grid node information comprises a grid node importance measure index value.
And 120, preprocessing the power grid node information to obtain training data.
Specifically, the grid node information is preprocessed, namely the grid node information is screened, grid node data with reference values are selected as training data, and data without reference values or with uncertain reference values are removed, so that the accuracy of grid node importance evaluation is improved.
And step 130, performing clustering analysis processing on the training data to obtain clustering data.
Specifically, cluster analysis refers to an analysis process that groups a set of physical or abstract objects into a plurality of classes composed of similar objects, i.e., classifying data into different classes or overcharging clusters, so that objects in the same cluster have great similarity, and objects in different clusters have great difference. The cluster analysis can automatically classify from the sample data. Therefore, the training data are subjected to cluster analysis processing, the data with large similarity are classified into one class, namely each cluster of data in the cluster data has large similarity, so that a power grid node importance evaluation model is preliminarily constructed.
And 140, obtaining a membership function according to the clustering data.
Specifically, the membership function is the application basis of fuzzy control, and whether to correctly construct the membership function is one of the keys for good fuzzy control. The degree of membership belongs to the concept in the fuzzy evaluation function: the fuzzy comprehensive evaluation is a very effective multi-factor decision method for comprehensively evaluating things influenced by various factors, and is characterized in that the evaluation result is not absolutely positive or negative, but is represented by a fuzzy set. If there is a number A (x) e [0,1] corresponding to any element x in the domain of interest (scope of study) U, then A is called the fuzzy set on U, and A (x) is called the membership of x to A. When x varies among U, A (x) is a function, called the membership function of A. The closer to 1 the degree of membership A (x) is, the higher the degree to which x belongs to A, and the closer to 0A (x) is, the lower the degree to which x belongs to A. And (3) representing the degree of the x belonging to the A by using a membership function A (x) which takes values in an interval (0, 1). In this embodiment, the membership function is a membership function of the clustered data, and it can be understood that the clustered data includes a plurality of clustered clusters, and the rule corresponding to each clustered data is different, or the function corresponding to each clustered data is different, so that the membership function needs to be constructed, so as to determine the category of the clustered clusters of the data, and to evaluate the importance value of the power grid node by using the corresponding rule.
And 150, initializing the rule parameters of the membership function to obtain initialized rule parameters. Specifically, the rule parameters of the membership function include a parameter of a rule front piece and a parameter of a rule back piece, and the rule parameters of the membership function are initialized, that is, the parameter of the rule front piece and the parameter of the rule back piece are respectively initialized.
And 160, obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters.
Specifically, because the membership function adopts the power grid node importance evaluation value and the rule parameter as input variables, and the suitability is used as output variables, the initialized rule parameter can be obtained by calculation through initializing the rule parameter, that is, the rule parameter can be obtained by calculation, so that the power grid node evaluation value function, that is, the power grid node importance evaluation value function can be obtained according to the membership function and the initialized rule parameter, so as to realize the evaluation of the power grid node importance, prevent the power grid cascade fault, guarantee the safe and stable operation of the power grid, and guarantee the economic benefit of a power grid enterprise. According to the power grid node importance evaluation method, the power grid node information is subjected to clustering analysis and processing, the membership function is constructed, so that a power grid node importance evaluation model is constructed, the power grid node evaluation value function is obtained by initializing the rule parameters of the membership function, and the multi-rule power grid node importance evaluation model is formed, so that the comprehensive evaluation of the power grid node importance is realized, namely the objectivity evaluation of the power grid node information is realized, the method has practical significance, can effectively prevent the power grid cascading failure, guarantees the safe and stable operation of the power grid, and guarantees the economic benefit of a power grid enterprise.
In order to better obtain the grid node information, in one embodiment, the step of obtaining the grid node information according to the grid data information includes: obtaining a power grid topological structure according to the power grid data information; and obtaining power grid node information according to the power grid topological structure. Specifically, the grid data information refers to a transformer or a substation as a node, a supply line between electric powers as an edge, and data of a grid in a certain area is abstracted into a undirected network, that is, each node is dispersed, and the grid data information needs to be constructed into a topology structure based on a complex network, so that each grid data information is associated. Obtaining power grid node information according to the topological structure, namely determining importance measurement indexes of the power grid nodes in the power grid topological structure, wherein the specific importance measurement indexes of the power grid nodes comprise: degree, proximity centrality, betweenness centrality, and core number, where degree represents the number of edges directly connected to a node; proximity centrality refers to the reciprocal of the sum of the distances of a node to all nodes in the network; the betweenness centrality refers to the ratio of the number of paths passing through the node in all shortest paths to the total number of the shortest paths; the number of cores refers to a k-shell index when a k core is decomposed, and is defined as the order of the maximum core where the node is located. These are all the main indicators for evaluating the importance of the grid nodes. Therefore, a power grid topological structure is constructed according to the power grid data information, and the power grid node information is acquired better.
In order to better obtain training data, in one embodiment, the step of preprocessing the power grid node information to obtain a training data set comprises the steps of obtaining an importance measurement index value of the power grid node information according to the power grid node information; and screening the power grid node information according to the importance measurement index value to obtain the training data. Specifically, the importance measurement index value is a main index for importance evaluation of the power grid node. By adopting the importance measurement index value of the power grid node information as the screening standard, the data with the reference value in the power grid node information can be better screened out, namely the training data can be better obtained.
In one embodiment, the step of screening the grid node information according to the importance measure index value to obtain the training number includes: arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; and obtaining the training data according to the first power grid node information and the second power grid node information. Specifically, the grid node information is arranged according to the size of the importance measurement index value, that is, the grid node information is arranged according to the order of the importance measurement index value from large to small; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information, extracting the arranged power grid node information with the arrangement sequence within a first preset range, marking the power grid node information as an important node, and determining an importance evaluation value of the first power grid node information, wherein in one embodiment, the first preset range is 5%, namely extracting the power grid nodes with the importance measurement indexes of 5% in the firstInformation; extracting the arranged power grid node information with the arrangement sequence being in a second preset range to obtain second power grid node information, namely extracting the arranged power grid node information with the arrangement sequence being in a second preset range at the tail part, marking the power grid node information as an unimportant node, and determining the importance evaluation value of the second power grid node information, wherein in one embodiment, the second preset range is 5%, namely extracting the power grid node information with the importance measurement index being 5% of the rear part; obtaining training data according to the first power grid node information and the second power grid node information, namely, taking the extracted importance measurement index value of each piece of power grid node information as an input variable, taking the importance evaluation value of each piece of power grid node information as an output variable, and constructing the training data, wherein the importance measurement index values comprise: degree u1Proximity centrality u2Central property of medium number u3U number of nuclei4(ii) a The importance evaluation value y, then the training data is { u }1,u2,u3,u4Y }. The power grid node information with evaluation value is screened by extracting the power grid node information of the important node and the power grid node information of the unimportant node, so that the training data with evaluation value is obtained.
In order to better perform cluster analysis on the training data, in one embodiment, the step of performing cluster analysis processing on the training data to obtain cluster data includes: and performing clustering analysis processing on the training data based on a quantum evolution algorithm to obtain clustering data.
Specifically, the quantum evolutionary algorithm is an intelligent optimization method based on quantum computation, the concept and theory of quantum computation are introduced into the evolutionary algorithm, so that qubits encode chromosomes, each dyeing quantum evolutionary algorithm is an intelligent optimization method based on quantum computation, the concept and theory of quantum computation are introduced into the evolutionary algorithm, the qubits encode the chromosomes, each chromosome represents the superposition of all feasible solutions, candidate solutions of problems are obtained through observation operation, and the chromosomes are updated through a quantum gate. The algorithm has strong optimization performance and can effectively solve the premature convergence problem. Based on the quantum evolutionary algorithm, the training data are subjected to clustering analysis, the ratio of the inter-cluster distance to the intra-cluster distance can be maximized, the best clustering number can be obtained, and clustering is realized, namely the training data are better classified.
In an embodiment, the step of performing cluster analysis processing on the training data based on a quantum evolution algorithm to obtain clustered data includes: dividing the training data to obtain the number of clustering clusters; initializing the training data to obtain a chromosome with quantum bits as codes; and acquiring related parameters, updating the chromosomes according to the related parameters, and performing cluster analysis processing on the updated chromosomes to obtain cluster data.
Specifically, the training data is divided to obtain the number of cluster clusters, that is, the training data is divided to obtain R10 clusters, the number of cluster clusters determines the number of fuzzy rules in the evaluation model, and the centroid of a cluster is the cluster center of the cluster.
Specifically, the training data is initialized to obtain the chromosome with the qubits as codes, that is, the selected model training data set is initialized to construct the chromosome with the qubits as the codes. Determining the length of each binary coded bit, initializing the phase angle of each quantum bit of the quantum chromosome to pi/4, calculating the cosine value and the sine value of each phase angle, and taking the square value of the cosine value as the probability. And generating a random number of [0,1] for each qubit of each quantum chromosome, wherein the qubit takes a value of 1 when the random value is greater than the probability value, and takes a value of 0 otherwise. The binary chromosomes are decoded to obtain decoded decimal values.
Acquiring related parameters, and updating the chromosome according to the related parameters; specifically, the related parameters include a cross probability, a mutation probability, and a maximum iteration number Iter. In one embodiment, the cross probability is 0.95, the mutation probability is 0.05, and the maximum number of iterations Iter is 100. Adding a variation angle to the phase angle of each quantum bit of the quantum chromosome according to the states of the chromosome and the quantum bit, so that the phase angle is rotated, and each phase angle of the quantum chromosome is updated; performing a quantum not gate: and (3) enabling the phase angle of the quantum bit of the quantum chromosome part to rotate by pi/2 in the positive direction according to the mutation probability, thereby realizing the updating of the chromosome.
And carrying out clustering analysis processing on the updated chromosome to obtain clustering data. Classifying data sets of the same cluster, calculating cluster centers of the clusters and fitness evaluation values, judging whether the maximum iteration times are reached, if the set maximum iteration times are reached, outputting an optimal solution, namely a chromosome decoding value of an individual with the maximum total fitness evaluation value, returning cluster class numbers of all data, calculating the cluster centers of all clusters, and obtaining cluster data according to the cluster centers of the clusters and the fitness evaluation values. The cluster center of the cluster is expressed as
Wherein, CrIs the cluster center of the r-th cluster,
is the jth data belonging to the r-th class.
The fitness evaluation value expression is as follows:
wherein, fitness (iter) is the fitness evaluation value at iter iteration number, JrIs the total number of data belonging to class r.
In order to better obtain the membership function, in one embodiment, the step of obtaining the membership function according to the clustering data includes: and substituting the clustering data into a Gaussian function to obtain a membership function. Specifically, the membership function is a membership function of the clustering data, and the clustering data is substituted into the gaussian function by taking the gaussian function as the membership function to obtain the membership function, so as to obtain a power grid node importance evaluation model and an applicability ω of an r-th rule corresponding to the power grid node importance evaluation modelrIs shown as：
Wherein, n represents AND, { ξri,σriIs the parameter set of the rule antecedent.
Therefore, the clustering data is substituted into the Gaussian function, so that the membership function can be better obtained.
In an embodiment, the step of initializing the rule parameters of the membership function to obtain initialized rule parameters includes initializing the rule front-part parameters and the rule back-part parameters respectively to obtain initialized rule parameters. Specifically, the rule precursor parameter is the rule precursor parameter set { ξ }ri,σriOf, initialize a rule precursor parameter set, i.e., ξriInput data for the ith dimension of the r-th class center,
is the membership width. The rule back-part parameters include alphariAnd brThen, the rule back-part parameter initialization calculation formula is:
in order to obtain a more accurate evaluation value function of the power grid node, in one embodiment, the step of obtaining the evaluation value function of the power grid node according to the membership function and the initialized rule parameter includes: updating and optimizing the initialized rule parameters to obtain updated rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters. The updated and optimized rule parameters are obtained by optimizing the parameters of the rule back part and the parameters of the rule front part, and the updated and optimized rule parameters are more in line with the actual evaluation standard, so that the accuracy of the evaluation value of the importance of the power grid node is higher, namely the evaluation of the importance of the power grid node is more accurate.
The step of performing update optimization processing on the initialized rule parameters to obtain updated rule parameters is to respectively construct matrices Q, S, a, and d according to the clustering data, where the expressions corresponding to Q, S, a, and d are respectively:
Q＝[α11,α12,...,α14,b1,α21,α22,...,α24,b2,...,α101,...,α104,b10]T (6)
wherein, M is 10 × (4+1) ═ 50, and num is the screened grid node.
Setting the initial value of the matrix Q as a zero matrix, and iterating according to a preset function, wherein the iteration times are the number of the selected training data, so as to obtain the updated and optimized rule back-part parameter alphariAnd br. The expression of the preset function is:
and calculating to obtain a corresponding root mean square error value according to the membership function. Specifically, a root mean square error value of the power grid node importance evaluation model is calculated according to the power grid node importance evaluation model, and the root mean square error value is a standard error.
Judging whether the root mean square error value is smaller than a preset threshold value or not, and if so, judging whether the root mean square error value is larger than a preset threshold valueAnd when the threshold value is reached, updating and optimizing the rule precursor parameters to obtain the updated rule precursor parameters. Outputting a rule precursor parameter when the root mean square error is smaller than a preset threshold, wherein in one embodiment, the preset threshold is epsilon-10-6。
The step of performing update optimization processing on the rule precursor parameters to obtain updated rule precursor parameters includes: and optimizing the rule precursor parameters until the root mean square error is smaller than a preset threshold value, and outputting the corresponding updated rule precursor parameters. In particular, the function f is setnumThe expression is as follows:
wherein the content of the first and second substances,
the importance evaluation value is the output importance evaluation value of the num power grid node importance comprehensive evaluation model;
set up ZξAnd ZσThe matrix is a 10 × 4 matrix, the initial values are all zero matrices, and the ith row and column elements of the matrix are expressed as follows:
updating rule antecedent parameter xi of optimization modelriAnd σriUpdating the optimized xiriAnd σriThe expression of (a) is:
wherein st is a training step length, and an initial value of st is set to 0.1; if the root mean square error RMSE value is increased or decreased in 4 continuous iterations in the training, the size of the st value needs to be corrected; the increase time step st becomes 1.1 times before, and the decrease time step st becomes 0.9 times before.
And obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters.
The updated and optimized rule parameters are obtained by optimizing the parameters of the rule back part and the parameters of the rule front part, and the updated and optimized rule parameters are more in line with the actual evaluation standard, so that the accuracy of the evaluation value of the importance of the power grid node is higher, namely the evaluation of the importance of the power grid node is more accurate.
The following is a complete embodiment, and provides a method for evaluating importance of a grid node, including: obtaining a power grid topological structure according to the power grid data information; obtaining power grid node information according to the power grid topological structure; obtaining an importance measurement index value of the power grid node information according to the power grid node information; arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; obtaining the training data according to the first power grid node information and the second power grid node information; based on a quantum evolutionary algorithm, performing clustering analysis processing on the training data to obtain clustering data; substituting the clustering data into a Gaussian function to obtain a membership function; updating and optimizing the initialized rule parameters to obtain updated rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters.
In one embodiment, referring to fig. 2, a grid node importance evaluation apparatus 20 is provided, which includes: the system comprises a power grid node information acquisition module 210, a preprocessing module 220, a cluster analysis module 230, a membership function acquisition module 240, an initialization module 250 and an evaluation value function acquisition module 260. In one embodiment, the grid node importance evaluation device includes corresponding modules for implementing the steps of the grid node importance evaluation method. In one embodiment, the power grid node importance degree evaluation device is implemented by using the power grid node importance degree evaluation method in any one of the embodiments.
The power grid node information acquisition module is used for acquiring power grid node information according to the power grid data information; the preprocessing module is used for preprocessing the power grid node information to obtain training data; the clustering analysis module is used for carrying out clustering analysis processing on the training data to obtain clustering data; the membership function obtaining module is used for obtaining a membership function according to the clustering data; the initialization module is used for initializing the rule parameters of the membership function to obtain initialized rule parameters; and the evaluation value function acquisition module is used for acquiring a power grid node evaluation value function according to the membership function and the initialized rule parameters.
According to the power grid node importance evaluation device, the power grid node information is subjected to cluster analysis and processing, a membership function is constructed, a power grid node importance evaluation model is constructed, the power grid node evaluation function is obtained by initializing the rule parameters of the membership function, and the multi-rule power grid node importance evaluation model is formed, so that the comprehensive evaluation of the power grid node importance is realized, the power grid cascading failure is effectively prevented, the safe and stable operation of a power grid is guaranteed, and the economic benefit of a power grid enterprise is guaranteed.
In one embodiment, the power grid node information acquisition module includes a power grid topology acquisition submodule and a power grid node information acquisition submodule, and the power grid topology acquisition submodule is used for acquiring a power grid topology according to the power grid data information; and the power grid node information acquisition submodule is used for acquiring power grid node information according to the power grid topological structure.
In one embodiment, the preprocessing module comprises a measurement index value acquisition sub-module and a screening sub-module; the measurement index value acquisition submodule is used for acquiring an importance measurement index value of the power grid node information according to the power grid node information; and the screening submodule screens the power grid node information according to the importance measurement index value to obtain the training data.
In one embodiment, the screening submodule includes an arranging unit and a screening unit; the arrangement unit is used for arranging the power grid node information according to the importance measurement index value to obtain the arranged power grid node information; the screening unit is used for extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; and obtaining the training data according to the first power grid node information and the second power grid node information.
In one embodiment, the cluster analysis module is configured to perform cluster analysis processing on the training data based on a quantum evolutionary algorithm to obtain cluster data.
In one embodiment, the membership function obtaining module is configured to substitute the clustering data into a gaussian function to obtain a membership function.
In one embodiment, the evaluation value function obtaining module includes an update optimization submodule and an evaluation value function obtaining submodule, and the update optimization submodule is configured to perform update optimization processing on the initialized rule parameters to obtain updated rule parameters; and the evaluation value function acquisition submodule is used for acquiring a power grid node evaluation value function according to the membership function and the updated rule parameters.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in FIG. 3. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for grid node importance assessment. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
obtaining power grid node information according to the power grid data information; preprocessing the power grid node information to obtain training data; performing clustering analysis processing on the training data to obtain clustering data; obtaining a membership function according to the clustering data; initializing the rule parameters of the membership function to obtain initialized rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters.
In one embodiment, the processor, when executing the computer program, performs the steps of: obtaining a power grid topological structure according to the power grid data information; and obtaining power grid node information according to the power grid topological structure.
In one embodiment, the processor, when executing the computer program, performs the steps of: obtaining an importance measurement index value of the power grid node information according to the power grid node information; and screening the power grid node information according to the importance measurement index value to obtain the training data.
In one embodiment, the processor, when executing the computer program, performs the steps of: arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; and obtaining the training data according to the first power grid node information and the second power grid node information.
In one embodiment, the processor, when executing the computer program, performs the steps of: and performing clustering analysis processing on the training data based on a quantum evolution algorithm to obtain clustering data.
In one embodiment, the processor, when executing the computer program, performs the steps of: and substituting the clustering data into a Gaussian function to obtain a membership function.
In one embodiment, the processor, when executing the computer program, performs the steps of: updating and optimizing the initialized rule parameters to obtain updated rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters.
In one embodiment, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining power grid node information according to the power grid data information; preprocessing the power grid node information to obtain training data; performing clustering analysis processing on the training data to obtain clustering data; obtaining a membership function according to the clustering data; initializing the rule parameters of the membership function to obtain initialized rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters.
In one embodiment, the computer program when executed by a processor implements the steps of: obtaining a power grid topological structure according to the power grid data information; and obtaining power grid node information according to the power grid topological structure.
In one embodiment, the computer program when executed by a processor implements the steps of: obtaining an importance measurement index value of the power grid node information according to the power grid node information; and screening the power grid node information according to the importance measurement index value to obtain the training data.
In one embodiment, the computer program when executed by a processor implements the steps of: arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information; extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information; extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information; and obtaining the training data according to the first power grid node information and the second power grid node information.
In one embodiment, the computer program when executed by a processor implements the steps of: and performing clustering analysis processing on the training data based on a quantum evolution algorithm to obtain clustering data.
In one embodiment, the computer program when executed by a processor implements the steps of: and substituting the clustering data into a Gaussian function to obtain a membership function.
In one embodiment, the computer program when executed by a processor implements the steps of: updating and optimizing the initialized rule parameters to obtain updated rule parameters; and obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
1. A power grid node importance degree assessment method is characterized by comprising the following steps:
obtaining power grid node information according to the power grid data information;
preprocessing the power grid node information to obtain training data;
performing clustering analysis processing on the training data to obtain clustering data;
obtaining a membership function according to the clustering data;
initializing the rule parameters of the membership function to obtain initialized rule parameters;
obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters;
the clustering analysis processing of the training data to obtain clustering data comprises:
initializing the training data to obtain a chromosome with quantum bits as codes; acquiring related parameters, updating the chromosomes according to the related parameters, and performing cluster analysis processing on the updated chromosomes to obtain cluster data; wherein the related parameters comprise cross probability, mutation probability and maximum iteration number; the method specifically comprises the following steps: adding a variation angle to the phase angle of each qubit of the chromosome according to the states of the chromosome and the qubits to rotate the phase angles and update each phase angle of the quantum chromosome; according to the variation probability, enabling the phase angle of the partial qubits of the chromosome to rotate pi/2 in the positive direction, thereby realizing the updating of the chromosome, and carrying out cluster analysis processing on the updated chromosome to obtain cluster data;
substituting the clustering data into a Gaussian function to obtain a membership function, wherein the membership function formula is as follows:
wherein u isiThe method is characterized in that different importance measurement index values of power grid nodes; xiriInputting data of ith dimension of the r type class center; sigmariIs the membership width;
the step of obtaining a power grid node evaluation value function according to the membership function and the initialized rule parameters comprises the following steps:
updating and optimizing the initialized rule parameters to obtain updated rule parameters;
obtaining a power grid node evaluation value function according to the membership function and the updated rule parameters;
the method specifically comprises the following steps: respectively constructing matrixes Q, S, a and d according to the clustering data, wherein the expressions corresponding to Q, S, a and d are respectively as follows:
Q＝[α11,α12,...,α14,b1,α21,α22,...,α24,b2,...,α101,...,α104,b10]T
wherein, M is 10 × (4+1) ═ 50, and num is the screened power grid node; y isnumEvaluating a function for the power grid node;
setting the initial value of the matrix Q as a zero matrix, and iterating according to a preset function, wherein the iteration times are the number of the selected training data, so as to obtain the updated and optimized rule back-part parameter alphariAnd br；
The expression of the preset function is:
2. the method according to claim 1, wherein the step of obtaining grid node information from grid data information comprises:
obtaining a power grid topological structure according to the power grid data information;
and obtaining power grid node information according to the power grid topological structure.
3. The method for evaluating the importance of the grid node according to claim 1, wherein the step of preprocessing the grid node information to obtain a training data set comprises:
obtaining an importance measurement index value of the power grid node information according to the power grid node information;
and screening the power grid node information according to the importance measurement index value to obtain the training data.
4. The method according to claim 2, wherein the step of screening the grid node information according to the importance measure index value to obtain the training number includes:
arranging the power grid node information according to the size of the importance measurement index value to obtain the arranged power grid node information;
extracting the arranged power grid node information with the arrangement sequence within a first preset range to obtain first power grid node information;
extracting the arranged power grid node information with the arrangement sequence within a second preset range to obtain second power grid node information;
and obtaining the training data according to the first power grid node information and the second power grid node information.
5. An apparatus for assessing importance of a grid node, the apparatus comprising:
the power grid node information acquisition module is used for acquiring power grid node information according to the power grid data information;
the preprocessing module is used for preprocessing the power grid node information to obtain training data;
the cluster analysis module is used for carrying out cluster analysis processing on the training data to obtain cluster data; the clustering analysis processing of the training data to obtain clustering data comprises: initializing the training data to obtain a chromosome with quantum bits as codes; acquiring related parameters, updating the chromosomes according to the related parameters, and performing cluster analysis processing on the updated chromosomes to obtain cluster data; wherein the related parameters comprise cross probability, mutation probability and maximum iteration number;
the membership function obtaining module is used for obtaining a membership function according to the clustering data;
the initialization module is used for initializing the rule parameters of the membership function to obtain initialized rule parameters;
and the evaluation value function acquisition module is used for acquiring a power grid node evaluation value function according to the membership function and the initialized rule parameters.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 4 are implemented when the computer program is executed by the processor.
7. 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 method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910565287.5A CN110334932B (en) | 2019-06-27 | 2019-06-27 | Power grid node importance degree evaluation method, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910565287.5A CN110334932B (en) | 2019-06-27 | 2019-06-27 | Power grid node importance degree evaluation method, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110334932A CN110334932A (en) | 2019-10-15 |
| CN110334932B true CN110334932B (en) | 2021-10-29 |
Family
ID=68143250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910565287.5A Active CN110334932B (en) | 2019-06-27 | 2019-06-27 | Power grid node importance degree evaluation method, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110334932B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112073220B (en) * | 2020-08-14 | 2022-08-16 | 合肥本源量子计算科技有限责任公司 | Method and device for constructing network evaluation model |
| CN114419736B (en) * | 2022-03-10 | 2022-07-15 | 成都西交智汇大数据科技有限公司 | Experiment scoring method, system, equipment and readable storage medium |
| CN115510669A (en) * | 2022-10-11 | 2022-12-23 | 昆明理工大学 | Power transmission line seismic loss assessment method based on GIS fuzzy analysis |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992266A (en) * | 2015-06-15 | 2015-10-21 | 广东电网有限责任公司电力调度控制中心 | Method of determining power grid node importance degree and system thereof |
| US10291029B2 (en) * | 2016-08-18 | 2019-05-14 | General Electric Technology Gmbh | Enhanced island management application for power grid systems |
| CN107016503A (en) * | 2017-03-31 | 2017-08-04 | 国家电网公司 | The real-time stipulations of CIM topology and modification method based on fuzzy reasoning |
| CN109800782A (en) * | 2018-12-11 | 2019-05-24 | 国网甘肃省电力公司金昌供电公司 | A kind of electric network fault detection method and device based on fuzzy knn algorithm |
-
2019
- 2019-06-27 CN CN201910565287.5A patent/CN110334932B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110334932A (en) | 2019-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lei et al. | Data-driven optimal power flow: A physics-informed machine learning approach | |
| CN110334932B (en) | Power grid node importance degree evaluation method, computer equipment and storage medium | |
| CN108764273A (en) | A kind of method, apparatus of data processing, terminal device and storage medium | |
| Yang et al. | Fast economic dispatch in smart grids using deep learning: An active constraint screening approach | |
| Hou et al. | Sparse oblique decision tree for power system security rules extraction and embedding | |
| Zhang et al. | Mapping Koch curves into scale-free small-world networks | |
| CN108197773A (en) | Methods of electric load forecasting, load forecast device and terminal device | |
| CN108733631A (en) | A kind of data assessment method, apparatus, terminal device and storage medium | |
| Donate et al. | Evolutionary optimization of sparsely connected and time-lagged neural networks for time series forecasting | |
| Yin et al. | Data‐driven approach for real‐time distribution network reconfiguration | |
| Qu et al. | False data injection attack detection in power systems based on cyber-physical attack genes | |
| CN106649479A (en) | Probability graph-based transformer state association rule mining method | |
| Sun et al. | Probabilistic load flow calculation based on sparse polynomial chaos expansion | |
| Li et al. | Research on short-term photovoltaic power prediction based on multi-scale similar days and ESN-KELM dual core prediction model | |
| Qiu et al. | Ensemble learning for power systems TTC prediction with wind farms | |
| Xie et al. | Reliability evaluation of bulk power systems using the uniform design technique | |
| Gao et al. | Physics embedded graph convolution neural network for power flow calculation considering uncertain injections and topology | |
| Liu et al. | An integrated scheme for static voltage stability assessment based on correlation detection and random bits forest | |
| Wang et al. | A novel multi-layer stacking ensemble wind power prediction model under Tensorflow deep learning framework considering feature enhancement and data hierarchy processing | |
| Sang et al. | Ensembles of gradient boosting recurrent neural network for time series data prediction | |
| Zhang et al. | Using recurrent neural network for intelligent prediction of water level in reservoirs | |
| Leng et al. | Power system black-start decision making based on back-propagation neural network and genetic algorithm | |
| CN112598188A (en) | Neural network generation method, power prediction method, device and storage medium | |
| CN115564155A (en) | Distributed wind turbine generator power prediction method and related equipment | |
| Zhang et al. | The expressivity and training of deep neural networks: Toward the edge of chaos? |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200922 Address after: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant after: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. Address before: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant before: GUANGZHOU POWER SUPPLY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |